id
stringlengths 1
5
| prompt
listlengths 1
1
| completion
listlengths 1
1
| Label
stringclasses 3
values |
|---|---|---|---|
410
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pentobarbital versus thiopental in the treatment of refractory intracranial hypertension in patients with traumatic brain injury: a randomized controlled trial\n\n ABSTRACT.INTRODUCTION:\nExperimental research has demonstrated that the level of neuroprotection conferred by the various barbiturates is not equal. Until now no controlled studies have been conducted to compare their effectiveness, even though the Brain Trauma Foundation Guidelines recommend that such studies be undertaken. The objectives of the present study were to assess the effectiveness of pentobarbital and thiopental in terms of controlling refractory intracranial hypertension in patients with severe traumatic brain injury, and to evaluate the adverse effects of treatment.\n\nABSTRACT.METHODS:\nThis was a prospective, randomized, cohort study comparing two treatments: pentobarbital and thiopental. Patients who had suffered a severe traumatic brain injury (Glasgow Coma Scale score after resuscitation ≤ 8 points or neurological deterioration during the first week after trauma) and with refractory intracranial hypertension (intracranial pressure > 20 mmHg) first-tier measures, in accordance with the Brain Trauma Foundation Guidelines.\n\nABSTRACT.RESULTS:\nA total of 44 patients (22 in each group) were included over a 5-year period. There were no statistically significant differences in ' baseline characteristics, except for admission computed cranial tomography characteristics, using the Traumatic Coma Data Bank classification. Uncontrollable intracranial pressure occurred in 11 patients (50%) in the thiopental treatment group and in 18 patients (82%) in the pentobarbital group (P = 0.03). Under logistic regression analysis – undertaken in an effort to adjust for the cranial tomography characteristics, which were unfavourable for pentobarbital – thiopental was more effective than pentobarbital in terms of controlling intracranial pressure (odds ratio = 5.1, 95% confidence interval 1.2 to 21.9; P = 0.027). There were no significant differences between the two groups with respect to the incidence of arterial hypotension or infection.\n\nABSTRACT.CONCLUSIONS:\nThiopental appeared to be more effective than pentobarbital in controlling intracranial hypertension refractory to first-tier measures. These findings should be interpreted with caution because of the imbalance in cranial tomography characteristics and the different dosages employed in the two arms of the study. The incidence of adverse effects was similar in both groups.\n\nABSTRACT.TRIAL REGISTRATION:\n(Trial registration: US Clinical Trials registry NCT00622570.)\n\nBODY.INTRODUCTION:\nHigh dosages of barbiturates are used in patients with severe traumatic brain injury (TBI) who present with refractory intracranial hypertension (ICH) after medical and surgical treatment. This practice is recommended in the Brain Trauma Foundation (BTF) Guidelines, because this is the only second-level measure for which there is class II evidence that it can reduce intracranial pressure (ICP) [1]. Nevertheless, its effect on outcome is unproven [2], mainly because of severe medical complications. Within the family of barbiturates the oxibarbiturates and thiobarbiturates stand out, their primary representatives being pentobarbital and thiopental. Until now no controlled studies have been reported that compare the effectiveness of pentobarbital and thiopental in controlling ICH. At the experimental level, research has demonstrated that mechanisms of action and levels of neuroprotection differ between these agents [3-6]. For this reason, research is needed to compare the effectiveness of these two drugs in terms of controlling refractory ICH in patients with severe TBI. Based on various studies conducted in laboratory animals [3-6], suggesting that the neuroprotective capacity of thiopental is superior, our working hypothesis was that thiopental is more effective than pentobarbital in controlling ICP in patients with severe TBI, with a similar incidence of adverse side effects. In support of our work in the present study, the BTF Guidelines recommend that studies be undertaken to compare the effectiveness of the different barbiturates that are currently used in TBI patients [1].\n\nBODY.MATERIALS AND METHODS:\nWe conducted a prospective, randomized cohort study comparing two treatments: pentobarbital and thiopental. Our primary objective was to compare the effectiveness of these agents in controlling refractory ICH in patients with severe TBI. Secondary objectives were to compare the incidence of secondary effects, especially arterial hypotension, which was defined as the presence of mean arterial pressure (MAP) under 80 mmHg at any point during barbiturate therapy. This study was conducted at Son Dureta University Hospital (Palma de Mallorca, Spain) and was approved by the Ethics Committee of the Balearic Islands on 31 March 2002. It is registered with the US Clinical Trials Registry, with the number NCT00622570. In all cases, the patient's closest relative, legal representative, or guardian gave written informed consent for their inclusion in the study.\n\nBODY.MATERIALS AND METHODS.INCLUSION CRITERIA:\nPatients admitted to our intensive care unit (ICU) between May 2002 and July 2007 with a severe TBI (Glasgow Coma Scale [GCS] score after nonsurgical resuscitation ≤ 8) and presenting with refractory ICH (ICP > 20 mmHg), and who underwent first-level measures in accordance with the BTF Guidelines [7], were included. Refractory ICH was defined as follows: ICP 21 to 29 mmHg for 30 minutes or more, ICP of 30 to 39 mmHg for 15 minutes or more, or ICP greater than 40 mmHg for more than 1 minute, in the absence of external interventions. Included patients were required to be haemodynamically stable at the point of inclusion in the study; haemodynamic stability was defined as systolic blood pressure of 100 mmHg or greater.\n\nBODY.MATERIALS AND METHODS.EXCLUSION CRITERIA:\nWe did not include in the study patients who were younger than 15 or older than 76 years; patients with a GCS score of 3 upon admission and neurological signs of brain death (bilateral arreactive midryasis and loss of brainstem reflexes); and patients who were pregnant, had barbiturate allergy or intolerance, or had a history of severe cardiac ventricular dysfunction with an ejection fraction under 35%.\n\nBODY.MATERIALS AND METHODS.GENERAL THERAPEUTIC PROTOCOL:\nAll patients with severe TBI underwent cranial computed tomography (CT) upon admission and were categorized in accordance with the classification proposed by the Traumatic Coma Data Bank [8]. We also recorded findings of CTs conducted before inclusion of the patients in the study. The CT findings on inclusion were regarded to be the worst of the hospital stay; the prognostic value of such CT findings have been described by other authors [9]. CTs were independently reviewed and categorized by two neurosurgeons (JI and MB) who were unaware of the treatment group to which the patients had been assigned. In cases of disagreement between these investigators, a third investigator reviewed the CT images. All patients' ICP was monitored using an intraparenchymal Camino catheter (Integra Neurosciences, Plainsboro, NJ, USA). The ICP catheter was placed in the frontal region of the hemisphere with more radiological lesions on the CT. The systemic monitoring of these patients included invasive blood pressure, pulse oximetry, and a pulmonary artery thermodilution catheter. The ICP, MAP and cerebral perfusion pressure data were gathered on an hourly basis (one value every full hour) throughout the study using the Care Vue® clinical monitoring system (Phillips, Eindhoven, The Netherlands). The general treatment objectives in patients with severe TBI were to maintain MAP above 80 mmHg, ICP below 20 mmHg, and cerebral perfusion pressure above 60 mmHg. To achieve these objectives, we used liquids and/or vasoactive support with norepinephrine (noradrenaline). In patients with ICP greater than 20 mmHg, initial treatment included elevation of the head of the bed, keeping the neck straight, appropriate sedation, muscular paralysis, ventricular drainage (if the patient had visible ventricles on the CT), 20% mannitol (0.25 to 0.75 mg/kg), 7.5% hypertonic saline (2 ml/kg) and moderate hyperventilation (partial carbon dioxide tension of 30 to 35 mmHg). Neurosurgical interventions were undertaken when necessary to evacuate surgical lesions. This approach can be considered conventional treatment and is included in the BTF Guidelines as first-tier therapy [7]. Patients whose ICP remained high with conventional treatment were included in the study. Before randomization of the patient to a study group, we required that patient to have received maximal medical treatment (first-level measures). In addition, we required a CT to have been conducted within 24 hours before inclusion of the patient in the study; intravenous administration of 0.7 g/kg mannitol 1 hour before randomization; or a plasmatic osmolarity measurement above 320 mOsm/kg, in order to ensure that hyperosmolar therapy had been optimized before inclusion.\n\nBODY.MATERIALS AND METHODS.RANDOMISATION:\nRandomization was based on a computer-generated list that intercollated the two drugs. Allocation was done by the intensive care unit physician who was on duty, once the patient had been found to meet the inclusion criteria and none of the exclusion criteria. Data collection and patient follow up were conducted by the same investigator (JPB).\n\nBODY.MATERIALS AND METHODS.BLINDING OF TREATMENT GROUPS:\nThe study was not blinded because it was difficult for us to mask treatment; thiopental is liophylized for administration and pentobarbital is not.\n\nBODY.MATERIALS AND METHODS.ADMINISTRATION OF BARBITURATES AND MONITORING OF EFFECTS:\nPentobarbital was administered in accordance with the protocol established by Eisenberg and coworkers [10], using a loading dose of 10 mg/kg over 30 minutes followed by a continuous perfusion of 5 mg/kg per hour for 3 hours. This was followed by a maintenance dosage of 1 mg/kg per hour. Thiopental was administered in the form of a 2 mg/kg bolus administered over 20 seconds. If the ICP was not lowered to below 20 mmHg, then the protocol permitted a second bolus of 3 mg/kg, which could be readministered at 5 mg/kg if necessary to reduce persistently elevated ICP. The maintenance dosage was an infusion of thiopental at a rate of 3 mg/kg per hour. In both treatment groups, for cases in which the maintenance dosage did not achieve the reduction in ICP to below the 20 mmHg threshold, the maintenance dosage for both drugs could be increased by 1 mg/kg per hour, while looking for electroencephalographic burst suppression or even the flat pattern, in order to ensure that different doses of the two barbiturates were equipotent. Electroencephalography was conducted daily in a noncontinuous manner (Nicolet; Viasys Healthcare, Verona Road, Madison, WI, USA). Results were analyzed by an experienced neurologist who was blinded to the treatment of the patients. In those patients in whom barbiturate coma did not control ICP, we used decompressive craniotomy and/or external lumbar drainage, in accordance with the Munch criteria, as life-saving measures [11,12].\n\nBODY.MATERIALS AND METHODS.EFFECTIVENESS CRITERIA:\nAdequate response to treatment was defined as a decrease in ICP to below 20 mmHg, and maintenance below this threshold for at least 48 hours. To describe the ICP, we also followed the criteria previously employed by Stocchetti and coworkers [13]; the arithmetic mean of ICP data recorded during every 24-hour period, after filtering to exclude inaccurate readings, was calculated and expressed as 'mean ICP'. Three ICP blocks were considered for further analysis: less than 20 mmHg, 20 to 30 mmHg, and more than 30 mmHg. Uncontrollable ICP was defined as follows: ICP of 21 to 35 mmHg for 4 hours, ICP of 36 to 40 mmHg for 1 hour, or ICP above 41 mmHg for 5 minutes, in the absence of external interventions. We also defined as unresponsive to treatment those cases in which, because of refractory ICP, the patient needed some other treatment (surgery and/or lumbar drainage) and cases in which the patient progressed to brain death. Although it was not a main objective of the study, patients were evaluated 6 months after injury using the Glasgow Outcome Scale [14].\n\nBODY.MATERIALS AND METHODS.WITHDRAWAL OF TREATMENT:\nWhen ICP was controlled (<20 mmHg for 48 hours), we conducted a step-wise reduction in the barbiturate coma in steps that reduced the dosage by 50% every 24 hours until the infusion was suspended. In the event of ICP values rising to the study's inclusion values during the withdrawal of barbiturate treatment, the perfusion dosage was once again increased to achieve control of the patient's ICP.\n\nBODY.MATERIALS AND METHODS.SAMPLE SIZE:\nAccepting an α error of 0.05 and a β error of 0.2 in a bilateral hypothesis contrast, we estimated that 47 patients were needed in each group to detect differences of 30% or greater in the control of ICH. To calculate sample size, we assumed that the therapeutic response rate in the pentobarbital group would be 50%, excluding patients lost to follow up.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nQuantitative variables are expressed as the mean and standard deviation from the mean (SD) in normal distributions, and as median and interquartile range in cases that were not normally distributed. Qualitative variables are expressed as percentages, along with 95% confidence interval (CI). To determine whether variables followed a normal distribution, we used the Shapiro Wilks test. For the comparison of quantitative variables, Student's t-test was used if the variable followed a normal distribution. In other cases, we used the Mann-Whitney U-test. For the comparison of qualitative variables, we used χ2 or Fisher's exact test, as appropriate. Given that the randomization did not create groups that were similar in terms of types of intracranial lesions shown on the CT results, which is a prognostic variable that influences the effectiveness of barbiturate treatment in controlling ICP, we conducted a multivariate analysis using binary logistic regression, so that we would include the prognostic variables with the most plausible association with the dependent variable 'uncontrollable ICP'. These are variables such as age, GCS score at admission, and the worst CT obtained within 24 hours before inclusion of the patient in the study, as well as the type of barbiturate administered. To achieve this multivariate analysis, and given the small number of cases in each of the five groups in Marshall's classification, the CT data were grouped into focal and diffuse lesions. We also included in the model the minimum daily MAP during barbiturate treatment, given that in the second and third days of treatment there were statistically significant differences between the groups in the univariate analysis. The significant variables identified by the 'likelihood ratio' ≤ 0.1 test were used, along with those whose inclusion affected the calculation of the effect of the 'treatment group' variable. Both treatment groups were very similar in terms of other known prognostic variables, such as the presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them, so these were not included in the multivariate analysis. To analyze the variable ICP, which was determined on an hourly basis, we calculated the area under the curve (AUC) at 24, 48 and 72 hours, and also standardized by time [15]. For all comparisons, we considered statistical significance to have been achieved if the two-tailed α error probability was 5% or less (P ≤ 0.05). Statistical analyses were conducted using SPSS version 15 (SPSS Inc., Chicago, IL, USA).\n\nBODY.RESULTS:\nPreliminary results for the first 20 patients have already been published elsewhere [16]. From May 2002 to July 2007, 480 TBI patients were admitted to the intensive care unit of the Son Dureta University Hospital. Of these 480 patients, 71 (14.8%) presented with ICH refractory to first-level measures, of whom 44 were included in the study. The study was concluded prematurely because of the unexpected and slow inclusion rate; this could have modified some uncontrollable environmental factors that may affect results. The reasons for not including the remaining 27 refractory ICH cases were as follows: 13 patients were included in other studies, six were older than 76 years, five were admitted with nonreacting midriatic pupils and with clinical evidence of brain death, two presented with haemodynamic instability at the time of randomization, and one patient was transferred to a different hospital during the first 24 hours of admission, which excluded that patient from follow-up analysis. On average, the barbiturate coma was initiated in the thiopental group at 89 ± 15.5 hours after admission and in the pentobarbital group at 61 ± 14.3 hours after admission (P = 0.33). The baseline characteristics of the 44 patients included in the study, 22 randomized to each group, are presented in Table 1. There were no statistically significant differences with respect to epidemiological data, co-morbidity (data not shown) or lesions associated with TBI, although there were differences in the CT classification. Table 1 Baseline characteristics of patient population Characteristic Thiopental (n = 22) Pentobarbital (n = 22) P Sex (male; n) 19 19 1 Age (years) 26 (20 to 41) 32 (22 to 43) 0.45 ISS 25 (24 to 34) 25 (25 to 38) 0.77 SAPS II 42 (28 to 54) 43 (38 to 46) 0.95 APACHE II 23 (15 to 25) 20 (18 to 26) 0.27 APACHE III 60 (38 to 73) 52 (32 to 76) 0.41 Associated lesion (n) Thoracic injury 7 2 0.13 Abdominal injury 4 1 0.34 Extremities injury 9 5 0.20 Admission CT (n) Diffuse injury without brain swelling 12 4 0.046 Diffuse bilateral brain swelling 6 12 Diffuse unilateral brain swelling with midline shift 1 0 Any mass lesion > 25 ml 3 6 Age, ISS, SAPS II, APACHE II and APACHE III are expressed as median and interquartile range. APACHE, Acute Physiology and Chronic Health Evaluation; admission CT, admission computed tomography (according to the Traumatic Coma Data Bank); ISS, Injury Severity Score; SAPS, Simplified Acute Physiology. The summary of prognostic variables for the 44 patients is shown in Table 2. As in Table 1 the characteristics of the worst CT conducted before inclusion in the study differed between the two groups. Table 2 Prognostic variables of patient population Variable Thiopental (n = 22) Pentobarbital (n = 22) P Admission GCS score 6.5 (3.0 to 7.2) 7 (4.7 to 10.0) 0.38 Out-of-hospital hypoxia (n) 5 7 0.63 Out-of-hospital hypotension (n) 5 4 1 Pupillary reactivity (n) a One reacting 3 5 0.66 Both reacting b 12 14 Pre-enrolment CT (n) Diffuse injury without brain swelling 8 5 0.04 Diffuse bilateral brain swelling 1 8 Diffuse injury unilateral brain swelling with midline shift 5 1 Any mass lesion evacuated 7 5 Nonevacuated mass lesion 1 3 Admission GCS is expressed as median (interquartile range). a Pupillary reactivity at hospital admission. b Miotic pupils were considered as reactive. CT, computed tomography; GCS, Glasgow Coma Scale. \n\nBODY.RESULTS.EFFECTIVENESS CRITERION: CONTROL OF INTRACRANIAL PRESSURE:\nThe distribution of the ICP during the first 3 days of treatment, according to Stocchetti's criteria, is summarized in Table 3. The missing cases during these 3 days were due to brain deaths or to receipt of rescue treatment for uncontrollable ICP. Finally ICP was uncontrollable in 11 cases (50%) in the thiopental group and in 18 patients (82%) in the pentobarbital group (P = 0.03). In nonresponding patients, we chose to place a lumbar drainage in five, in three we opted for surgical treatment, and in three other patients we combined both treatments, drainage and surgery. Surgical decompression was conducted in four patients in the thiopental group and in two of the patients in the pentobarbital group. The number of hyperosmolar treatments administered (manitol and/or hypertonic saline) during the barbiturate coma was similar in both groups: 16.5 (8.0 to 24.2) in the thiopental group and 16.5 (3.0 to 21.5) in the pentobarbital group (P = 0.9). The mean ± SD duration of the barbiturate coma was 156 ± 60 hours for thiopental and 108 ± 100 hours for pentobarbital (P = 0.06). Seven (31.8%) patients presented an ICP rebound with thiopental and six (27.3%) with pentobarbital (P = 0.74) during treatment withdrawal. Table 3 Mean ICP recorded per day during the first 3 days of barbiturate coma Drug Day Mean ICP (n[%]) <20 mmHg 20 to 30 mmHg >30 mmHg Thiopental 1 10 46 11 50 1 5 2 15 71 4 19 2 10 3 12 63 6 32 1 5 Pentobarbital 1 9 41 8 36 5 23 2 8 38 9 43 4 19 3 6 43 8 57 0 0 Mean intracranial pressure (ICP) is the arithmetic mean of ICP data recorded during every 24-hour period, according to Stocchetti's criteria [ 13 ]. Data are presented as number of cases and as a percentage of the total number of cases each day. Figure 1 presents the AUC for ICP above 20 mmHg, standardized over time, as follows. The ICP value of AUC0–24 h was 458.00 mmHg·hour (95% CI = 421.84 to 494.16) in the thiopental group and 550.63 mmHg·hour (95% CI = 411.31 to 689.95) in the pentobarbital group. The AUC0–48 h was 913.18 mmHg·hour (95% CI = 814.08 to 1,012.27) in the thiopental group and 997.27 mmHg·hour (95% CI = 757.10 to 1,237.43) in the pentobarbital group. The AUC0–72 h in the thiopental group was 1,291.69 mmHg·hour (95% CI = 1,172.27 to 1,411.12) and 1,399.73 mmHg·hour (95% CI = 1,291.11 to 1,508.35) in the pentobarbital group. Standardized over time, the AUC per hour in the thiopental group was 23.90 mmHg (95% CI = 22.00 to 25.81) and in the pentobarbital group it was 29.39 mmHg (95% CI = 23.20 to 35.59). Figure 1AUC of ICP data. Presented are areas under the curve (AUCs) of the intracranial pressure (ICP) data, standardized by time, with a base value of 20 mmHg. Both treatment groups were similar in terms of known prognostic variables, such as presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them. Therefore, these were not included in the multivariate analysis. The logistic regression analysis showed that, after adjusting for the worst CT and the type of barbiturate used, thiopental was five times more likely than pentobarbital to control ICP (odds ratio = 5.1, 95% CI = 1.2 to 21.9; P = 0.027). The Hosmer-Lemeshow test indicated that the fit of the model was good (P = 0.799). The association of focal lesions in the pre-inclusion CT with ICP control was 3.6 times higher than that for the diffuse lesions. The relative risk for good control of ICP in the thiopental versus pentobarbital group was 2.26 for patients with focal lesions and 3.52 for those who presented with diffuse lesions. The other variables analyzed did not exhibit a significant relationship to ICP control, and did not modify the effect of the barbiturate treatment, including the third day minimum MAP, which was significantly different between the two treatments (data not shown).\n\nBODY.RESULTS.ADVERSE SIDE EFFECTS DURING THE BARBITURATE COMA:\nThe secondary effects during the barbiturate coma are presented in Table 4. In both groups almost all patients presented with at least one MAP measurement below 80 mmHg. There were no differences between groups with respect to the incidence of infections, Sepsis related Organ-Failure Assessment (SOFA) scores before initiation of treatment, or the maximum SOFA value [17] during the entire period of barbiturate coma. Table 4 Adverse events during barbiturate coma Adverse event Thiopental (n = 22) Pentobarbital (n = 22) P Hypotension a 21 20 1 Respiratory infection b 18 17 1 Urinary infection c 0 2 0.49 Positive blood culture 4 1 0.34 ICP catheter colonization 7 5 0.5 CNS infection (CSF) d 3 0 0.23 SOFA pre e 7 (4.5 to 9.5) 8.0 (5.5 to 9.0) 0.57 SOFA maximum f 11 (10 to 12) 11 (10 to 12) 0.94 a Hypotension is defined as detection of a medium arterial blood pressure below 80 mmHg at any time during barbiturate coma. b Respiratory infection: presence of a positive sputum culture. c Urinary infection: presence of a positive urine culture. d Central nervous system infection (CNS) infection (cerebrospinal fluid [CSF]): infection of the CNS with a positive culture in the CSF. e SOFA pre: value of the Sepsis related Organ-Failure Assessment (SOFA) score before the beginning of the barbiturate coma. f SOFA maximum: maximum value of the SOFA during the barbiturate coma, according the indication by Moreno and coworkers [ 16 ]. A thermodilution catheter was placed in 42 patients to facilitate haemodynamic control. The haemodynamic changes produced during the barbiturate coma are presented in Table 5. Differences of note include the minimum MAP, the pulmonary wedge pressure value, and the maximum norepinephrine dosage on days 2 and 3. Table 5 Systemic changes during barbiturate coma Parameter Pretreatment 1st day 2nd day 3rd day 4rd day Cardiac output (l/minute) a Thiopental 6.8 ± 1.4 6.4 ± 1.5 6.0 ± 1.4 6.7 ± 1.5 6.6 ± 1.8 Pentobarbital 7.4 ± 2.2 7.1 ± 1.9 6.5 ± 2.0 7 ± 1.4 6.1 ± 1.3 Cardiac index (l/minute per m 2 ) Thiopental 3.6 ± 0.6 3.4 ± 0.6 3.1 ± 0.6 3.6 ± 1.6 3.5 ± 0.9 Pentobarbital 3.8 ± 1.2 3.8 ± 0.8 3.4 ± 0.8 3.6 ± 0.7 3.2 ± 0.6 Peripheral venous resistance (dines/m 2 ) Thiopental 1,015 ± 325 1,022 ± 347 1,140 ± 429 1,089 ± 289 1,029 ± 253 Pentobarbital 952 ± 257 893 ± 210 1,003 ± 322 939 ± 261 914 ± 188 Pulmonary artery wedge pressure (mmHg) Thiopental 10.4 ± 4.5 9.6 ± 3.6 10.1 ± 4.1* 10.9 ± 4.6* 11.4 ± 3.5* Pentobarbital 11.6 ± 4.0 11.4 ± 3.1 12.8 ± 3.1 13.2 ± 2.1 13.9 ± 3.1 mBP (mmHg) b Thiopental 92 ± 11 75 ± 7 76 ± 9* 76 ± 6* 76 ± 8 Pentobarbital 94 ± 10 74 ± 1 68 ± 10 70 ± 1 70 ± 10 NAD (μg/kg per minute) c Thiopental 0.18 ± 0.33 0.28 ± 0.27 0.37 ± 0.3* 0.46 ± 0.39 0.56 ± 0.63 Pentobarbital 0.19 ± 0.18 0.55 ± 0.68 0.73 ± 0.69 0.60 ± 0.44 0.96 ± 0.79 P O 2 /Fi O 2 d Thiopental 284 ± 130 300 ± 139 293 ± 132 285 ± 138 254 ± 119 Pentobarbital 317 ± 127 304 ± 116 262 ± 125 211 ± 77 184 ± 92 Haemoglobin Thiopental 10.9 ± 1.6 10.7 ± 1.3 11 ± 1.2 10.8 ± 0.9 10.7 ± 1.4 Pentobarbital 10.6 ± 1.2 10.1 ± 1.0 10.4 ± 1.1 10.5 ± 1.1 10.2 ± 1.2 Temperature (°C) e Thiopental 35.8 ± 0.5 34.6 ± 1.3 34.6 ± 3.4 34.9 ± 1.0 34.9 ± 1.0 Pentobarbital 35.7 ± 1.0 34.6 ± 1.2 34.3 ± 1.3 34.4 ± 1.3 34.2 ± 1.1 a Cardiac output, cardiac index, peripheral venous resistance and pulmonary artery wedge pressure: the values are the mean values over 24 hours. b mBP: minimum value of the medium blood pressure during the day. c NAD: maximum dose of Noradrenaline bitartrate during the day. d P O 2 /Fis O 2 : ratio of partial oxygen tension to inspired fractional oxygen tension at 8:00 am. e Temperature: value of the minimum central temperature. * P < 0.05. \n\nBODY.RESULTS.SIX-MONTH OUTCOMES:\nIn the thiopental group, the neurological outcomes at 6 months (in accordance with Glasgow Outcome Scale score) were as follows: death in nine patients, vegetative state in two, severe disability in two, moderate disability in four and good recovery in four. In the pentobarbital group, the 6-month outcome was death in 16 patients, vegetative state in one, moderate disability in two and good recovery in two. In both groups one case was missing from the 6-month follow up analysis\n\nBODY.DISCUSSION:\nThe results of this study indicate that thiopental is five times more effective than pentobarbital in controlling refractory ICH. However, these findings must be interpreted with caution, given the small sample size and the fact that the study was unable to mask assignment to treatment groups. Barbiturate coma is at present the only therapy for which we have class II evidence, under BTF Guidelines [1], of efficacy in treating refractory ICH. Hence, it is perhaps the case that barbiturate coma is the most used second-level measure, with a usage frequency reported in the literature that varies from 13% to 56% [18,19]. Therefore, it is important to test the effectiveness of the various barbiturates available for controlling ICP refractory to first-level measures.\n\nBODY.DISCUSSION.DIFFERENCES BETWEEN OXIBARBITURATES AND THIOBARBITURATES:\nThe pharmacokinetic characteristics of thiopental and pentobarbital are different because their protein binding, distribution volume and clearance differ [20]. Nevertheless, the mean half life (thiopental 6 to 46 hours and pentobarbital 15 and 48 hours), which is the fundamental pharmacological parameter, differs little between the two agents. It therefore does not appear that these pharmacokinetic differences have clinical repercussions. One difference between these two groups of barbiturates is the presence of active metabolites. Thiopental has five metabolites, of which four are inactive and one (pentobarbital, or pentobarbitone) is active. Therefore, pentobarbital is an active metabolite of thiopental. This fact, along with the great intra-individual and inter-individual variability in the metabolism of these agents (caused by the existence of enzymatic induction phenomena associated with hepatic cytochrome P450), results in a weak correlation between serum concentrations and pharmacological effect. For this reason, monitoring this treatment with electroencephalography is strongly recommended. At the experimental level, various studies have compared these two medications. Hatano and coworkers [21], in a study conducted in a dog model, concluded that thiobarbiturates provoke cerebral vasoconstriction, which could help to redistribute cerebral blood flow toward ischaemic zones. Cole and colleagues [4] demonstrated that thiopental reduced the size of the ischaemic area more than did pentobarbital, even though both drugs achieved electroencephalographic burst suppression patterns. Shibuta [5] observed that thiopental, but not pentobarbital, was capable of limiting the cytotoxic damage caused by nitric oxide. Almaas and coworkers [3] observed that the different barbiturates had different neuroprotective effects with respect to oxygen and glucose deprivation in a model using human neurone cultures. Thiopental exhibited a neuroprotective effect at all the dosages studied, whereas pentobarbital was neuroprotective only at elevated dosages. Finally, in an in vitro study, Smith and colleagues [6] demonstrated that although thiopental provoked 96% inhibition of lipid peroxidation, pentobarbital had almost no effect. These experimental studies demonstrate that not all barbiturates are equal and that their neuroprotective capacity and effectiveness may differ [22]. Therefore, despite the unavoidable methodological limitations of the present study, we believe that our results may have clinical relevance.\n\nBODY.DISCUSSION.SECONDARY EFFECTS OF BARBITURATE COMA:\nThe most frequently detected secondary effect in our study, as might be expected, was arterial hypotension, which occurred in 21 patients in the thiopental group and 20 patients in the pentobarbital group. Although this incidence may be greater than that in previous studies [10], we attribute this to the definition of hypotension used (detection at any time in the barbiturate coma of MAP < 80 mmHg), which did not take the 'time' variable into account. For that reason, we collected data on other variables, such as maximum daily norepinephrine dosage and minimum daily MAP. Nearly all patients were monitored using a pulmonary artery thermodilution catheter, and arterial hypotension episodes were rigorously managed with fluid therapy and vasoactive drugs. We would note that the changes produced by pentobarbital at the cardiac and respiratory level were, in general terms, greater than those produced by thiopental. This is because (as shown in Table 5) cardiac output, cardiac index, and partial oxygen tension/fraction of inspired oxygen ratio exhibited greater changes during treatment with pentobarbital than with thiopental. This observation contrasts with the findings of previous experimental studies [23], in which it appeared that at high doses pentobarbital was safer and better tolerated than thiopental. Other complications (mostly infections) and the incidence of multiple organ dysfunction (identified using maximum SOFA) were similar in the two groups.\n\nBODY.DISCUSSION.LIMITATIONS OF THE STUDY:\nAs previously noted, this study has two important limitations. First, it was not a blinded study because the pentobarbital was not liophylized and thiopental was. Second, the sample size was small, so that small changes in the principal variable studied, namely ICP control, could significantly affect the statistical analysis. The classical view is that ICP response to barbiturates varies from 30% to 50%, and so it is possible that part of the difference found between drugs is due to poor response by the pentobarbital group as a result of any confounding bias. The randomization process is a potent mechanism that tends to eliminate bias by randomly distributing the values of all of the variables to the experimental groups. Nonetheless, the tool is not perfect and the groups frequently exhibit an imbalance in some confounding variable, especially when working with samples that are not very large. For this reason, in this study we used logistic regression analysis to eliminate any possible bias, and separate, independent analyses of the CT data were also conducted by two investigators who did not know the experimental group to which the patients belonged. Another limitation is that the dosages in the two groups were not the same. This leaves the possibility that the reason for the difference between agents that we identified is inadequate pentobarbital dose. Although in the two groups barbiturates were used with the end-point of ICP control, in this type of patient we also employ daily noncontinuous electroencephalographic monitoring. In this way, we believe that – despite different doses – the effect of the two barbiturates can be considered as equipotent because we looked for burst suppression or even the flat electroencephalographic pattern if the ICP was not controlled and the patients remained haemodynamically stable.\n\nBODY.CONCLUSION:\nIn this patient sample, thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-level measures, according to the BTF Guidelines. Nevertheless, these findings should be interpreted with caution because of the imbalance in CT characteristics and the different dosages employed in the two arms of the study. However, the present study is useful as a hypothesis testing exercise and will help to inform the design of future studies. These findings corroborate experimental evidence suggesting that there are differences in the neuroprotective mechanism between the two treatments, and this study may be a first step toward translating evidence from animal models to clinical disease. The incidence of secondary effects during treatment was similar between groups.\n\nBODY.KEY MESSAGES:\n• High doses of barbiturates are used in those patients with severe TBI who present with refractory ICH, and this recommendation is included in the BTF Guidelines. • Until now no controlled studies have been conducted to compare the effectiveness of pentobarbital and thiopental in controlling refractory ICH. Nevertheless, at the experimental level, research has demonstrated that their mechanisms and levels of neuroprotection differ. • Thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-tier measures, although these results should be interpreted with caution because of the imbalance in CT characteristics and other limitations of the study.\n\nBODY.ABBREVIATIONS:\nAUC: area under the curve; BTF: Brain Trauma Foundation; CI: confidence interval; ICH: intracranial hypertension; ICP: intracranial pressure; MAP: mean arterial pressure; SD: standard deviation; SOFA: Sepsis related Organ-Failure Assessment; TBI: traumatic brain injury.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nJPB was responsible for study design, acquisition of data, analysis and interpretation of data, and writing of the manuscript. JALP was responsible for acquisition of data and patient randomization. JH acquired data and conducted patient randomization. JMA acquired data and conducted patient randomization. JMR conducted statistical analyses. GF conducted statistical analyses. MB was responsible for designing the study and reviewing CT findings. JI was responsible for designing the study and reviewing CT findings. JI revised the article critically and gave final approval to the version to be published.\n\n**Question:** Compared to Pentobarbital what was the result of Thiopental on Infection?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
244
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Short-term comparative study of high frequency chest wall oscillation and European airway clearance techniques in patients with cystic fibrosis\n\n ABSTRACT.BACKGROUND:\nHigh frequency chest wall oscillation (HFCWO) is standard treatment for airway clearance in the USA and has recently been introduced in the UK and Europe. There is little published research comparing HFCWO with airway clearance techniques (ACTs) frequently used in the UK and Europe. The aim of this study was to compare the short-term effects of HFCWO with usual ACTs in patients with cystic fibrosis hospitalised with an infective pulmonary exacerbation.\n\nABSTRACT.METHODS:\nA 4-day randomised crossover design was used. Patients received either HFCWO on days 1 and 3 and usual ACTs on days 2 and 4 or vice versa. Wet weight of sputum, spirometry and oxygen saturation were measured. Perceived efficacy, comfort, incidence of urinary leakage and preference were assessed. Data were analysed by mixed model analysis.\n\nABSTRACT.RESULTS:\n29 patients (72% male) of mean (SD) age 29.4 (8.4) years and mean (SD) forced expiratory volume in 1 s (FEV1) percentage predicted (FEV1%) 38 (16.7) completed the study. Significantly more sputum was expectorated during a single treatment session and over a 24 h period (mean difference 4.4 g and 6.9 g, respectively) with usual ACTs than with HFCWO (p<0.001). No statistically significant change in FEV1% or oxygen saturation was observed after either HFCWO or usual ACTs compared with baseline. 17 patients (55%) expressed a preference for their usual ACT.\n\nABSTRACT.CONCLUSIONS:\nDuring both a finite treatment period and over 24 h, less sputum was cleared using HFCWO than usual ACT. HFCWO does not appear to cause any adverse physiological effects and may influence adherence.\n\nBODY.INTRODUCTION:\nThe last four decades have seen improved survival in patients with cystic fibrosis (CF). The latest figures estimate the median life expectancy of individuals with CF born in 2000–3 to be approximately 40 years.1 Respiratory failure is the major cause of morbidity and mortality in those with CF.2 Accumulation of secretions in the CF airway precipitates chronic infection, causing a progressive deterioration in lung function and eventually respiratory failure and death.3 Airway clearance techniques (ACTs) are an essential component of the management of patients with CF and are considered standard care.4 There is a range of ACTs which augment the normal mucus clearance mechanisms of the lung to facilitate expectoration. These techniques generally aim to promote secretion clearance by altering airflow and mucus viscosity. Typically, high frequency chest wall oscillation (HFCWO) produces compression of the chest wall via an inflatable jacket linked to an air pulse generator. The generator delivers an intermittent flow of air into the jacket which rapidly compresses and releases the chest wall at a variety of frequencies. Consequently, an oscillation in airflow within the airways is achieved. HFCWO has been shown to enhance central and peripheral mucus clearance.5 A number of underlying mechanisms have been hypothesised including increased airflow-mucus interaction causing a reduction in viscolelasticity, production of an expiratory airflow bias which promotes a cephalad movement of mucus and the enhancement and stimulation of ciliary activity.6 7 Published short-term evidence has demonstrated increased sputum clearance and improved pulmonary function with HFCWO compared with no treatment.8 This and other studies have also compared HFCWO with alternative ACTs. Some have demonstrated increased sputum clearance with HFCWO compared with postural drainage and percussion (PD&P).9–11 Others found no significant difference in sputum clearance between HFCWO and PD&P,8 12 13 positive expiratory pressure (PEP),8 high frequency oral oscillation13 or intrapulmonary percussive ventilation.14 Furthermore, some of these studies found no differences in efficacy related to pulmonary function between HFCWO and PD&P,8 12 13 PEP,8 15 oscillating positive expiratory pressure (Flutter, manufactured by Axcan Scandipharm Inc, Birmingham, AL, USA)16 and high frequency oral oscillation.13 One study reported an improved outcome in forced expiratory volume in 1 s (FEV1) in the longer term using HFCWO compared with PD&P.17 Few trials have compared HFCWO with alternative ACTs which are commonly used in the UK and Europe by individuals with CF. Phillips et al18 compared HFCWO (using the Hayek Cuirass) with the active cycle of breathing techniques (ACBT) in hospitalised paediatric patients. Significantly more sputum was cleared with the ACBT. The authors concluded that HFCWO was not an effective airway clearance treatment for children with CF. It is difficult to compare this study directly with those above, as the Hayek Cuirass machine has a different operating mode to the inflatable vest system. A series of Cochrane systematic reviews have found that no one ACT is superior in terms of respiratory function and efficacy.19 Of a number of published studies on HFCWO, only two were deemed of sufficient quality to be included in these randomised control trial systematic reviews.8 12 HFCWO is widely used in the USA where it is considered standard care in CF.20 It has recently been introduced to the UK and Europe, where the mainstay of care for airway clearance in CF is the ACBT, autogenic drainage (AD) and other airway clearance regimens using small devices.4 In the USA these techniques and devices tend to be considered adjuncts, with PD&P and HFCWO remaining the most common ACTs.20 While there is a body of evidence which equates HFCWO and PD&P, there is a need for further trials to compare HFCWO with alternative ACTs to provide a more relevant evidence base for HFCWO in the UK and Europe. The aim of the present study was to compare the short-term effects of HFCWO with patients' usual ACTs in those with CF admitted to hospital with an acute exacerbation of pulmonary infection. The hypothesis was that HFCWO was superior to patients' usual ACTs.\n\nBODY.METHODS.STUDY PARTICIPANTS:\nAll patients admitted to hospital who met the entry criteria were invited to participate in the study. The inclusion criteria were a diagnosis of CF (established by genotype or sweat sodium >70 mmol/l or sweat chloride of >60 mmol/l), FEV1 ≥ 20% predicted, age ≥16 years and an infective pulmonary exacerbation as defined by Thornton et al.21 Exclusion criteria were current severe haemoptysis, rib fractures, pregnancy, inability to give consent and those whose usual ACT was HFCWO. Informed written consent was obtained for all patients and the study was approved by Brompton Harefield and National Heart and Lung Institute research ethics committee.\n\nBODY.METHODS.STUDY DESIGN:\nA randomised crossover design was used to compare HFCWO with patients' usual ACTs, which allowed within-patient variability to be controlled. Over four consecutive days, patients received either HFCWO therapy on days 1 and 3 and their normal ACT on days 2 and 4 or vice versa. Allocation to HFCWO or usual ACT on day 1 was determined using a computer-generated randomisation table.\n\nBODY.METHODS.PROTOCOLS:\nPatients performed their usual ACT or received HFCWO two times daily at the same time. Before starting the study, each patient's usual ACT was reviewed by an experienced senior respiratory physiotherapist. In addition, patients were familiarised with HFCWO (The Vest). This involved the patients using The Vest for a trial period the day before the start of the study, during which time they were given the opportunity to experience all three protocol frequencies at a variety of pressures. Each airway clearance treatment session lasted 30 min and was supervised by the same physiotherapist to ensure optimisation and standardisation of usual ACT and HFCWO performance. All nebulised and inhaled medications were taken before each treatment session in accordance with the patients' individual regimens.\n\nBODY.METHODS.HIGH FREQUENCY CHEST WALL OSCILLATION:\nThe following regimen was identified as current best practice following an in-depth review of the literature and discussion with clinical experts in the USA. Using The Vest Airway Clearance System Model 4 (Hill-Rom UK Ltd, Leicestershire, UK), each patient was fitted with an appropriately-sized, full torso, inflatable, disposable vest connected to the air pulse generator via two flexible tubes. Patients remained in an upright sitting position throughout the 30 min treatment session. HFCWO was applied for 8 min at each of three frequencies in sequence (10, 13 and 15 Hz) with each frequency followed by a 2 min rest period. The pulse pressure was set according to individual patient's reported comfort at all three frequency settings. During both the HFCWO and rest periods, patients were instructed to huff or cough as they felt necessary in order to expectorate loosened bronchial secretions.\n\nBODY.METHODS.USUAL ACT:\nUsual ACTs were in accordance with the guidelines of the International Physiotherapy Group for Cystic Fibrosis.22 Patients performed their usual ACT for 30 min, and for patients practising an assisted ACT, the physiotherapist provided percussion. Patients were allowed to perform combined ACTs where this was their usual practice. This reflected current international practice more accurately and recommendations that ACTs be adapted on an individual basis.23\n\nBODY.METHODS.OUTCOME MEASURES:\nThe primary outcome measure was wet weight of sputum expectorated during a treatment session. Patients were instructed to expectorate all sputum into a preweighed pot during and for 30 min following each treatment session. They were also instructed to collect sputum expectorated at all other times during each 24 h period. All sputum collected was weighed immediately following collection on weighing scales with an accuracy of 0.01 g (BL310; Sartorious UK Ltd, Epsom, UK). FEV1 was measured using a hand-held spirometer (2120; Vitalograph Ltd, Buckingham, UK) in accordance with internationally agreed standards.24 Measurements were taken immediately before and after a 30 min period following each treatment session. Data were analysed using Spirotrac IV Version 4.30 software (Vitalograph Ltd). Pulsed arterial oxygen saturation (SpO2) was measured transcutaneously at rest, for 5 min immediately before, 30 min during and 30 min immediately following each session. SpO2 was measured with a fingertip pulse oximeter (Konica-Minolta Pulsox-300i; Stowood Scientific Instruments, Oxford, UK). The data were analysed using Download 2001 Version 2.8.0 software (Stowood Scientific Instruments Ltd). The perceived efficacy and comfort of each ACT and the incidence of urinary leakage during treatment were measured using 10 cm visual analogue scales (VAS). Each day, after the last treatment session, patients completed three 10 cm VAS with reference to the ACT used that day. On the VAS used, 0 represented not at all effective/comfortable or no urinary leakage and 10 represented extremely effective/comfortable or a lot of urinary leakage. On the fourth and final day, participants were also asked to indicate which ACT they would prefer. An independent observer, blind to the daily method of airway clearance used, performed the spirometry, weighed the sputum samples and collected the 10 cm VAS throughout the study.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nA sample size calculation determined the number of patients required to test for superiority of HFCWO. This was based on a difference of 4 g of sputum between the usual ACT and HFCWO during a single treatment session. A square-root of within SEM of 4 g at the 5% significance level would require 24 patients to achieve 90% power. Data are presented as mean (SD), median (IQR) or n (%) as appropriate. Continuous variables were analysed using a mixed-effects linear regression model. This was to allow the results to be adjusted for a number of factors which are inherent to the design of a crossover trial. The order of treatment randomisation and the day and time of treatment were all entered into the model and their effect on the outcomes was tested. For this trial, the results were also adjusted for the method and position of treatment in the ACT session. In these models, patients were entered as random effects since it was not of interest to quantify the differences between individual patients, but it was important to account for the repeated measurements on each patient. The estimates of the fixed effect of ACT versus HFCWO are presented as mean (95% CI). A p value of 0.05 was taken to be statistically significant. All analyses were conducted using Stata 9.2 (StataCorp).\n\nBODY.RESULTS.PARTICIPANTS:\nFifty patients were invited to participate in the study, 20 declined, 29 patients completed the study and 1 patient was withdrawn due to a hypoglycaemic episode. Table 1 shows demographic and baseline characteristics of the patients who completed the study. Table 1 Patient demographics and baseline characteristics (n=29) Age (years) 29.4 (8.4) Male (%) 21 (72%) Height (cm) 171 (9) Weight (kg) 60 (11) BMI (kg/m 2 ) 20.4 (2.6) FEV 1 (l) 1.46 (0.72) FEV 1 % predicted 38 (16.7) SpO 2 (%) 94.3 (2.1) Data are presented as mean (SD) or n (%) as appropriate. BMI, body mass index; FEV 1 , forced expiratory volume in 1 s; SpO 2 , pulsed arterial oxygen saturation. Twenty-nine patients were treated with intravenous antibiotics as part of their medical management. All participants received two treatment sessions on each study day and all treatment sessions were 30 min in duration. The mean (SD) length of stay for patients was 14 (5) days and the mean day of entry to the study was day 8 (3) days.\n\nBODY.RESULTS.USUAL ACT:\nUsual ACTs included the ACBT with modified PD&P (41%; n=12) and with modified PD alone (7%; n=2), AD in sitting (28%; n=8) and with modified PD (7%; n=2), PEP (7%; n=2) and Flutter (10%; n=3).\n\nBODY.RESULTS.SPUTUM WEIGHT:\nThe wet weight of sputum expectorated with usual ACT compared with HFCWO is shown in table 2. The mean weight of sputum expectorated during a single treatment session and over a 24 h period was significantly greater with usual ACT than with HFCWO. The mean difference in wet weight of sputum expectorated during a treatment session was 4.4 g (p<0.001) and the mean difference in wet weight of sputum expectorated over a 24 h period was 6.9 g (p<0.001). These findings were not affected by order, time, day or position of treatment. Table 2 Wet weight of sputum expectorated: HFCWO compared with usual ACT Period of sputum collection Expectorated sputum wet weight (g) Usual ACT HFCWO Mean difference p Value Mean (SD) Median (IQR) Mean (SD) Median (IQR) Single treatment session 9.1 (7.9) 7.2 (3.0–14.2) 4.6 (4.1) 3.4 (1.5–6.7) 4.4 (3.5 to 5.4) <0.001 24 h (excluding treatment) * 22.4 (26.8) 12.9 (4.0–29.9) 24.9 (25.8) 15.3 (3.9–40.1) −1.5 (−4.6 to 1.6) 0.352 24 h (including treatment) 39.8 (36.3) 25.5 (14.0–57.1) 34.3 (30.7) 26.3 (12.1–46.0) 6.9 (3.1 to 10.8) <0.001 Data are presented as mean (SD) or (95% CI) or median (IQR) as appropriate. Data are adjusted for randomisation, day, time and position of treatment using a mixed effects linear regression model. * Of 116 24-h sputum samples collected, two were discarded as they were incomplete. ACT, airway clearance technique; HFCWO, high frequency chest wall oscillation. No statistically significant difference was observed in the amount of sputum expectorated when using HFCWO or usual ACT between treatments in a 24 h period.\n\nBODY.RESULTS.PHYSIOLOGICAL MEASURES:\nFEV1 and SpO2 measured before, during and after usual ACT and HFCWO treatment sessions are shown in table 3. Table 3 Forced expiratory volume in 1 s and pulsed arterial oxygen saturation at baseline, during and after treatment with usual airway clearance technique and HFCWO Usual ACT HFCWO Baseline During treatment 30 min after treatment Baseline During treatment 30 min after treatment FEV 1 % predicted 39.1 (16.9) NA 38.9 (17.1) 38.9 (16.8) NA 39.2 (16.7) SpO 2 (%) 94.4 (2.0) 94.4 (1.9) 93.9 (1.6) 94.5 (1.8) 95.0 (1.7) 94.3 (1.7) Data are presented as mean (SD). ACT, airway clearance technique; FEV 1 , forced expiratory volume in 1 s; HFCWO, high frequency chest wall oscillation; NA, not applicable; SpO 2 , pulsed arterial oxygen saturation. \n\nBODY.RESULTS.COMFORT, EFFICACY AND PREFERENCE:\nThe VAS scores for comfort, efficacy and urinary leakage during usual ACT compared with HFCWO are shown in table 4. No significant differences were observed in VAS scores for comfort or urinary leakage between HFCWO and usual ACT. Patients scored the efficacy of their usual ACT significantly higher than for HFCWO (mean difference 14 mm; p=0.002). This was not affected by the order or day of treatment. Of those patients who completed the study, 17 (55%) expressed a preference for their usual ACT over HFCWO. Preference was not predicted by the amount of sputum expectorated. Table 4 Comfort, efficacy and urinary leakage: HFCWO compared with usual ACT Self reported measure Visual analogue scale score (mm) Usual ACT HFCWO Mean difference p Value Comfort 69 (23) 70 (22) −1 (−9 to 7) 0.784 Efficacy 68 (21) 54 (26) 14 (6 to 23) 0.002 Urinary leakage 0 (1) 0 (1) −0.05 (−0.3 to 0.4) 0.791 Data are presented as mean (SD) or (95% CI) as appropriate. Data are adjusted for randomisation, day of treatment and time of treatment using a mixed effects linear regression model. ACT, airway clearance technique; HFCWO, high frequency chest wall oscillation. \n\nBODY.DISCUSSION:\nThere have been few published comparisons between HFCWO using a vest system with the ACTs of the ACBT and AD. This short-term study, carried out in individuals with CF admitted to hospital with an acute infective pulmonary exacerbation, showed that significantly more sputum was expectorated during a single treatment session and over a 24 h period using the patient's usual ACT than with HFCWO. In addition, slightly less sputum was expectorated at all other times (excluding treatment sessions) on usual ACT days compared with HFCWO, but this trend was not statistically significant. These findings were independent of order, time or day and position of treatment. Neither HFCWO nor any of the usual ACTs were associated with any adverse clinical events. A possible factor contributing to the difference in sputum clearance between HFCWO and usual ACT may have been the number and frequency of forced expiratory manoeuvres (FEMs) and the more gentle expiratory manoeuvres of the AD breath that were performed with the usual ACTs. Some studies have standardised the number of coughs and FEMs that patients performed; however, at the time of designing the protocol, the aim was to compare the regimens as currently practised internationally and the frequency of coughs and FEMs was neither standardised nor counted. In retrospect, it would have been of value to have counted the number of coughs and FEMs undertaken during each regimen, but it had not been anticipated that any differences between HFCWO and usual ACTs may be a consequence of the number of FEMs or AD breaths. Theoretically, during the three 8 min periods of HFCWO, fewer FEMs, coughs or AD breaths would be undertaken than during an equivalent period of the ACBT, AD, PEP or Flutter (all of which inherently include FEMs or AD breaths at regular intervals). This difference was supported by observations of the investigators. However, manual cough counts are subject to observer error. Objective cough monitoring using the Leicester Cough Monitor has only recently been validated and should be considered for use in further studies.25 Components of patient satisfaction include efficacy, comfort and convenience. Some studies have formally evaluated patient satisfaction and compliance. One study reported that 50% of subjects chose HFCWO compared with the Flutter, and efficacy was the most frequently cited reason for this choice.16 A later study reported that HFCWO was not preferred over PD&P and intrapulmonary percussive ventilation; furthermore, there was no significant correlation between treatment preference and sputum weight.14 The current study found that patients perceived the efficacy of HFCWO to be statistically significantly less than that of their usual ACT. However, nearly half (45%) of patients expressed a preference for HFCWO. Preference may have been affected by the novelty of a new treatment and it is unknown whether this would continue in the long term. There is no one recommended protocol for the application of HFCWO in the literature. Published studies describe differing numbers and duration of frequencies, length of treatment and airway clearance. Frequencies of 10, 13 and 15 Hz were chosen as it has been reported that maximum mucus transport occurs between 11 and 15 Hz with a peak at 13 Hz.5 6 In addition, the highest oscillated tidal volume flow (peak airflow) occurred between 10 and15 Hz in patients with CF.26 More recent research recommends an individual \"tuning\" method to identify optimum treatment frequencies. These have been shown to vary among individuals and the oscillation waveform,27 but it is unknown whether \"tuning\" increases efficacy. It is possible that a practice effect could have occurred as all patients were new to HFCWO. However, the protocol used in this study did not require the patient to perform any newly learnt physical technique. In addition, the statistical analysis ensured data were adjusted for day of treatment and found no effect. Alternatively, patients' familiarity with their usual ACT may also have had an effect on outcomes. This study was powered to detect a difference of 4 g of sputum expectorated during a single treatment session. Other studies have been based on a difference of 3–3.5 g, which is generally accepted as a clinically important difference.28 29 Wet weight sputum was felt to be an appropriate primary outcome measure in this short-term study in an acute environment. Previous work has found wet weight to be proportional to dry weight sputum.28 30 Emerging non-invasive means of measuring airway clearance may be more sensitive indicators in the future (eg, lung clearance index and electrical impedance tomography). Considering the cost benefit of HFCWO compared with other ACTs and the differing healthcare systems in the USA and the UK, it is unlikely that HFCWO will become the first choice ACT for most individuals in the UK. Further work needs to be undertaken to identify the place of HFCWO in Europe. Patient preference for a treatment regimen may positively influence adherence to treatment in the short term, and nearly half the patients who participated in this study preferred HFCWO to their usual ACT. HFCWO is a safe treatment that facilitates airway clearance in CF but, when compared with patients' usual ACTs, HFCWO led to the clearance of significantly less sputum during a single treatment session and over a 24 h period.\n\n**Question:** Compared to Usual airway clearance techniques what was the result of High frequency chest wall oscillation on FEV1%?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
468
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Comparison of intravenous immunoglobulin and plasma exchange in treatment of mechanically ventilated children with Guillain Barré syndrome: a randomized study\n\n ABSTRACT.INTRODUCTION:\nRespiratory failure is a life threatening complication of Guillain Barré syndrome (GBS). There is no consensus on the specific treatment for this subset of children with GBS.\n\nABSTRACT.METHODS:\nThis was a prospective randomized study to compare the outcome of intravenous immunoglobulin (IVIG) and plasma exchange (PE) treatment in children with GBS requiring mechanical ventilation. Forty-one children with GBS requiring endotracheal mechanical ventilation (MV) within 14 days from disease onset were included. The ages of the children ranged from 49 to 143 months. Randomly, 20 children received a five-day course of IVIG (0.4 g/kg/day) and 21 children received a five-day course of one volume PE daily. Lumbar puncture (LP) was performed in 36 patients (18 in each group).\n\nABSTRACT.RESULTS:\nBoth groups had comparable age (p = 0.764), weight (p = 0.764), duration of illness prior to MV (p = 0.854), preceding diarrhea (p = 0.751), cranial nerve involvement (p = 0.756), muscle power using Medical Research Council (MRC) sum score (p = 0.266) and cerebrospinal fluid (CSF) protein (p = 0.606). Children in the PE group had a shorter period of MV (median 11 days, IQR 11.0 to 13.0) compared to IVIG group (median 13 days, IQR 11.3 to 14.5) with p = 0.037. Those in the PE group had a tendency for a shorter Pediatric Intensive Care Unit (PICU) stay (p = 0.094). A total of 20/21 (95.2%) and 18/20 (90%) children in the PE and IVIG groups respectively could walk unaided within four weeks after PICU discharge (p = 0.606). There was a negative correlation between CSF protein and duration of mechanical ventilation in the PE group (p = 0.037), but not in the IVIG group (p = 0.132).\n\nABSTRACT.CONCLUSIONS:\nIn children with GBS requiring MV, PE is superior to IVIG regarding the duration of MV but not PICU stay or the short term neurological outcome. The negative correlation between CSF protein values and duration of MV in PE group requires further evaluation of its clinical usefulness.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicaltrials.gov Identifier NCT01306578\n\nBODY.INTRODUCTION:\nGuillain-Barré syndrome (GBS) is, currently, the most common cause of acute flaccid paralysis following the worldwide decline in incidence of poliomyelitis. Incidence varies according to age, geographic areas and diagnostic criteria used for inclusion. Annual incidence in western countries varies from 1.1 to 1.8/100,000 population per year [1-5] with a considerably lower annual incidence of 0.66/100,000 population per year in each of Taiwan [6] and China [7]. GBS usually follows infection by a number of bacterial and viral agents with Campylobacter jejuni representing the most common preceding infection [8-11]. The syndrome is also reported to rarely temporally follow vaccination with measles vaccine [12,13], tetanus toxoid [14], rabies vaccine [15], oral polio vaccine [16], polysaccharide meningococcal vaccine [17], measles-rubella vaccine [18], flu vaccine [19] and hepatitis B vaccine [19]. Since the publishing of the first report of the condition by Guillain, Barré, and Strohl in 1916, GBS has remained a clinically-diagnosed disorder. The condition is a polyneuropathy involving mainly motor but sometimes also sensory and autonomic nerves. It starts with rapidly progressive bilateral and relatively symmetric weakness in the lower limbs with diminished or absent deep tendon reflexes. Paralysis follows an ascending pattern involving trunk, upper limb and, finally, bulbar muscles. There can be numbness, parathesia and muscle pain and tenderness. Labile blood pressure with postural hypotension and labile heart rate with episodes of bradycardia up to asystole rarely occur denoting autonomic neuropathy. van Doorn et al. categorize diagnostic features of the condition into features required for diagnosis, including progressive weakness in both arms and legs, and areflexia or hyporeflexia, and features that strongly support the diagnosis, including progression of symptoms to a nadir over days to four weeks, relative symmetry of symptoms, mild sensory symptoms or signs, cranial nerve involvement, autonomic dysfunction, pain, a high concentration of protein in CSF without increase in cells and typical electro-diagnostic features [20]. A common, yet not an early, feature of GBS is increased cerebrospinal fluid (CSF) protein (> 45 mg/dL) without CSF pleocytosis (< 10 cells/mm3), often referred to as cytoalbuminous dissociation [21]. Electromyography may be used to confirm the diagnosis in the small subset of patients where the diagnosis is not straightforward. It is also useful to sub-classify patients into motor axonal neuropathy and acute inflammatory demyelinating polyneuropathy [22]. A recent study conducted in Egypt on children with GBS found that acute inflammatory demyelinating polyneuropathy, was the most common type (76%) while, acute motor axonal neuropathy, acute motor sensory axonal neuropathy and unclassified forms represented 8% each [23]. Respiratory failure is one of the most serious complications of GBS. It affects 15% of children with the condition [24]. The ability to predict the occurrence of respiratory failure and need for mechanical ventilation (MV) among patients with GBS has long been a target for neurologists and intensivists alike. Some bedside indicators of the likelihood of requiring MV are rapid disease progression, bulbar dysfunction, bilateral facial weakness, or dysautonomia, inability to stand, inability to lift the elbows or head, elevated liver enzymes and abnormal pulmonary function test [25-27]. Electrophysiological evidence of demyelination was also suggested to predict the need for endotracheal MV [28]. Treatment of GBS is a multidisciplinary effort. The general care of the child with muscle weakness includes regular monitoring of pulmonary and cardiovascular function for possible involvement of respiratory muscles and autonomic neuropathy respectively, prevention of infection and deep vein thrombosis, pain management, early physiotherapy, early rehabilitation once muscle power improvement starts and psychosocial support for the affected children and their families [20]. Specific treatment of severely affected children comprises intravenous immunoglobulin (IVIG) or plasma exchange (PE). Performed on more than 200 patients each, two large trials in the mid-1980s confirmed the beneficial role of PE in treatment of patients with GBS compared to the conventional treatment of the time [29,30]. The routine use of IVIG as the first line of treatment in GBS followed the publication of a randomized controlled trial (RCT) in 1992 showing a similar, if not a superior, effect of IVIG compared to PE [31]. A recent systematic review of heterogeneous study populations showed there was no evidence for a better outcome with either of the two modalities of treatment. There is also no evidence of a beneficial effect of adding corticosteroids to the treatment [32]. The objective of this study is to compare PE and IVIG as a first line treatment for children with severe GBS requiring MV regarding the duration of MV, PICU stay and short term neurological outcome.\n\nBODY.MATERIALS AND METHODS:\nChildren with GBS admitted to the Pediatric Intensive Care Unit (PICU) at Mansoura University Children Hospital, Mansoura, Egypt, with the need for MV were prospectively enrolled in the study. Cases were diagnosed to have GBS according to clinical criteria by van Doorn et al. [20]. Patients were eligible for inclusion if they required MV based on the indications listed below, and if the duration of muscle weakness did not exceed 14 days on enrollment. Children were not eligible for inclusion if they had muscle weakness for longer than 14 days before requiring MV and if IVIG or PE was started prior to enrollment. All patients were ventilated using endotracheal MV. Children were intubated if they were unable to protect their airway, had increased work of breathing (WOB), had PaO2 less than 70 mmHg in room air requiring increasing FiO2, or showed CO2 retention. When children were able to trigger spontaneous breathing, they were changed to a pressure-support spontaneous ventilation mode with continuous positive airway pressure of 5 cm H2O. Pressure support was gradually weaned to 10 cm H2O. If secretions were manageable and airway reflexes intact, a daily spontaneous breathing trial (SBT) was performed using a T-piece for two hours. Patients were extubated if SBT was successful. An SBT was deemed successful if there was no diaphoresis, increased WOB or apnea, tachycardia (defined by increase in the heart rate of 40 bpm or more) and if SpO2, pH, PaO2 and PaCO2 remained close to pre-SBT values. The decisions to initiate, wean and terminate MV were made independently by the attending consultant in accordance with and in strict adherence to the unit guidelines as above. Over a period of three years, from January 2007 to December 2009, 44 children were admitted with GBS requiring MV; 41 children fulfilled inclusion criteria and were randomized to receive either IVIG (20 children) or PE (21 children) for initial treatment. Randomization was done by computer-generated random tables. IVIG was administered in a dose of 0.4 g/kg/day for five days. Patients in the PE group received a daily one-volume PE for five consecutive days. The sample size yields a study power of 86.9%. On admission, the muscle power was recorded using the Medical Research Council (MRC) sum score [33]. Lumbar puncture (LP) was performed in the second week of illness in 36 out of the 41 children (18 in each group). LP was performed at the discretion of the attending consultant. The primary outcome measure was the duration of mechanical ventilation and secondary outcome measures were length of PICU stay and ability to walk unaided within four weeks of PICU discharge. Institutional research ethics committee approval was granted and an informed consent was obtained from legal guardians of children included in the study. Statistical analysis was performed using Statistical Package for the Social Sciences, Version 17 (SPSS, Inc., Chicago, IL, USA). p-value was considered significant if less than .05.\n\nBODY.RESULTS:\nChildren in the two treatment groups were comparable as regards base line characteristics, such as age, weight, duration of illness prior to requiring mechanical ventilation, presence or absence of preceding diarrhea, cranial nerve affection, severity of muscle weakness on PICU admission and CSF protein when available (Table 1). Table 1 Comparison of IVIG and PE groups regarding base line variables IVIG group ( n = 20) PE group ( n = 21) p- value Age (months) 106.0 ± 22.8 (74.3 to 113.5) 96.0 ± 32.8 (65.5 to 135.0) 0.764 1 Weight (kg) 32.5 ± 7.0 (23.0 to 34.8) 29.0 ± 10.1 (20.0 to 41.5) 0.764 1 DOI (days) 9.0 ± 2.7 (7.0 to 12.0) 9.0 ± 2.8 (6.5 to 11.5) 0.854 1 Diarrhea (%) Yes 13 (65%) 12 (57.1%) 0.751 2 No 7 (35%) 9 (42.9%) Cranial nerve affection (%) Yes 8 (40%) 10 (47.6%) 0.756 2 No 12 (60%) 11 (52.4%) MRC sum score 12.0 ± 4.8 (8.5 to 15.5) 12.0 ± 5.9 (4.0 to 12.0) 0.266 1 CSF protein (mg/dL) 152.1 ± 55.7 (88.3 to 173.6) 148.4 ± 43.0 (117.5 to 166.5) 0.606 1 IVIG, intravenous immunoglobulin; PE, plasma exchange; DOI, Duration of illness prior to requiring mechanical ventilation; MRC, Medical Research Council score. Data presented as median ± SD (interquartile range) 1 Mann Whitney test 2 Chi square test. There was a statistically insignificant better outcome in the PE group compared to the IVIG group. Favorable outcome was defined as the child's ability to walk independently for 10 meters (Grade 2 on GBS disability score) [34] within four weeks from PICU discharge. The post discharge management and physiotherapy were standardized for children in the two groups. In the IVIG group, favorable outcome was observed in 90% (18/20) of children compared to 95.2% (20/21) in the PE group (Table 2). Table 2 Comparison of PICU stay and duration of mechanical ventilation in the IVIG and PE groups PICU stay (days) Mechanical ventilation (Days) Favorable outcome (%) Yes No IVIG group 16.5 ± 2.1 (15.3 to 18.8) 13.0 ± 2.1 (11.3 to 14.5) 18 (90%) 2 (10%) PE group 15.0 ± 2.6 (13.0 to 17.0) 11.0 ± 1.5 (11.0 to 13.0) 20 (95.2%) 1 (4.8%) p- value .094 1 0.037 1 0.606 2 IVIG, intravenous immunoglobulin; PE, plasma exchange. Data presented as median ± SD (interquartile range) 1 Mann Whitney test 2 Chi square test. Children receiving PE had a significantly shorter period of mechanical ventilation compared to those receiving IVIG. The hospital stay was shorter in the PE group without statistical significance (Table 2). For all patients, there was a statistically significant negative correlation between CSF protein and duration of mechanical ventilation (p = .024). Examining the treatment groups separately, the significant negative correlation remained for the PE group (p-value = 0.037) and not for the IVIG group (p-value 0.132) (Table 3). Table 3 Correlation between CSF protein and duration of mechanical ventilation All patients IVIG group PE group CSF protein (mg/dL) 149.3 ± 49.0 (110.5 to 169.0) 152.1 ± 55.7 (88.3 to 173.6) 148.4 ± 43.0 (117.5 to 166.5) Mechanical ventilation (days) 12.0 ± 1.9 (11.0 to 13.0) 13.0 ± 2.1 (11.3 to 14.5) 11.0 ± 1.5 (11.0 to 13.0) p -value 0.024 1 0.132 1 0.037 1 CSF, cerebrospinal fluid; IVIG, intravenous immunoglobulin; PE, plasma exchange. Data presented as median ± SD (interquartile range) 1 Pearson test. There was no significant side effect attributable to any of the treatment modalities in any of the studied patients.\n\nBODY.DISCUSSION:\nRespiratory failure among children with GBS is a serious complication requiring intensive supportive treatment in addition to the specific treatment. The two treatment groups had no significant complications attributable to treatment intervention apart from minor hypotension episodes responding to fluid boluses in the PE group. This confirms the safety of both IVIG and PE for treating children with GBS. The results of this study suggest that PE is more useful than IVIG as a specific treatment for the subset of children with severe rapidly progressive GBS requiring MV. PE is believed to act by removal of circulating autoantibodies [35,36], while IVIG, among other mechanisms, is thought to work through blocking antibody production both in vivo [37] and in vitro [38,39]. Removal of autoantibodies, by PE, creates a concentration gradient between the lowered blood level and the extravascular space forcing antibody movement from the extra to the intra vascular space to be removed during the subsequent session [40]. Specific anti-ganglioside antibody levels were recently found to be associated with disease severity [41]. Children with severe, rapidly progressive GBS, as those included in this study, most likely have an intense autoantibody production with a high percentage of these antibodies already bound to nerves on development of respiratory failure. This might provide an explanation of why this subset of patients preferentially benefit from removal of already bound antibodies, PE, in comparison to blocking antibody production, IVIG. The clinical usefulness of this relatively small difference in the duration of mechanical ventilation between PE and IVIG groups waits to be confirmed in a larger, probably multi-center, study. CSF protein was elevated in all patients (Table 3) with no statistically significant difference between the two treatment groups (Table 1). On post hoc analysis, there was, however, a negative correlation between CSF protein level and duration of MV in PE but not IVIG group. This finding supports the above explanation of a shorter duration of MV in the PE group especially in view of a RCT showing CSF filtration to be at least as effective as PE for treatment of GBS [42] and the suggestion of a blood-CSF barrier dysfunction in adults and children with GBS [43]. PE group had a tendency for a shorter PICU stay, p = 0.094 with a comparable ability of children to walk unaided within four weeks from PICU discharge (Table 2). So, despite a shorter duration of MV, there was no difference between PE and IVIG groups regarding PICU stay or short term neurological outcome. To our knowledge, this is the first randomized controlled study comparing PE and IVIG for treatment of children with rapidly progressive GBS requiring MV. An RCT conducted in adults with GBS showed no difference in the duration of MV in PE, IVIG and combined treatment groups [44]. This difference can be accounted for by differences in the age and PE protocol used. It would have been more informative to perform an electrophysiological study for the study children to confirm homogeneity of the study population. It would also add to the understanding of these results to study kinetics of autoantibodies in future research with a similar design.\n\nBODY.CONCLUSIONS:\nRapidly progressive GBS necessitating MV in children responds favorably to both IVIG and PE, with PE being superior in regard to the duration of MV but not PICU stay or short term neurological outcome. The finding of a negative correlation between CSF protein values and duration of MV in the PE group might serve as a basis for future research aiming at a better understanding of autoantibody kinetics during treatment of GBS.\n\nBODY.KEY MESSAGES:\n• Children with GBS requiring MV respond favorably to both IVIG and PE. • Using a weaning and extubation protocol, children receiving PE had a shorter duration of MV.\n\nBODY.ABBREVIATIONS:\nCSF: cerebrospinal fluid; DOI: duration of Illness; GBS: Guillain-Barré syndrome; IVIG: intravenous immunoglobulin; LP: lumbar puncture; MRC: Medical Research Council; MV: mechanical ventilation; PE: plasma exchange; PICU: pediatric intensive care unit; SBT: spontaneous breathing trial; WOB: work of breathing.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nMAE formulated the research idea, designed the plan, performed statistical analysis and proofread the draft. AME co-designed the plan and supervised the plasma exchange making sure of uniformity of the procedure in all studied subjects and proofread the draft. AMA followed up patients on PICU, made sure the plan was followed, and helped MAE in performing statistical analysis. ME followed up patients on PICU, drafted the manuscript, and designed statistical methodology. AAA co-formulated the research idea, co-designed the plan, followed up patients on PICU, and generated and was responsible for the random assignment of the groups. HME followed up patients on PICU, co-drafted the manuscript with ME and made sure PICU management of patients complied with the unit guidelines. All authors read and approved the final manuscript.\n\nBODY.AUTHORS' INFORMATION:\nHME is one of the founding members and the current president of the ESPIC (Egyptian Society of Pediatric Intensive Care). MAE is a member of the Board of Directors of WFPICCS (World Federation of Pediatric Intensive Care Societies) and the ambassador of WFPICCS in Egypt. An abstract of this article has been presented by MAE as an oral presentation at the 6th World Congress of Pediatric Intensive Care, Sydney, 2011.\n\n**Question:** Compared to intravenous immunoglobulin (IVIG) what was the result of plasma exchange (PE) on side effects?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
214
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: A heart failure self-management program for patients of all literacy levels: A randomized, controlled trial [ISRCTN11535170]\n\n ABSTRACT.BACKGROUND:\nSelf-management programs for patients with heart failure can reduce hospitalizations and mortality. However, no programs have analyzed their usefulness for patients with low literacy. We compared the efficacy of a heart failure self-management program designed for patients with low literacy versus usual care.\n\nABSTRACT.METHODS:\nWe performed a 12-month randomized controlled trial. From November 2001 to April 2003, we enrolled participants aged 30–80, who had heart failure and took furosemide. Intervention patients received education on self-care emphasizing daily weight measurement, diuretic dose self-adjustment, and symptom recognition and response. Picture-based educational materials, a digital scale, and scheduled telephone follow-up were provided to reinforce adherence. Control patients received a generic heart failure brochure and usual care. Primary outcomes were combined hospitalization or death, and heart failure-related quality of life.\n\nABSTRACT.RESULTS:\n123 patients (64 control, 59 intervention) participated; 41% had inadequate literacy. Patients in the intervention group had a lower rate of hospitalization or death (crude incidence rate ratio (IRR) = 0.69; CI 0.4, 1.2; adjusted IRR = 0.53; CI 0.32, 0.89). This difference was larger for patients with low literacy (IRR = 0.39; CI 0.16, 0.91) than for higher literacy (IRR = 0.56; CI 0.3, 1.04), but the interaction was not statistically significant. At 12 months, more patients in the intervention group reported monitoring weights daily (79% vs. 29%, p < 0.0001). After adjusting for baseline demographic and treatment differences, we found no difference in heart failure-related quality of life at 12 months (difference = -2; CI -5, +9).\n\nABSTRACT.CONCLUSION:\nA primary care-based heart failure self-management program designed for patients with low literacy reduces the risk of hospitalizations or death.\n\nBODY.BACKGROUND:\nLimited literacy skills are common among adults in the United States [1]. Low literacy is associated with increased risk of hospitalization and worse control of chronic diseases [1-4]. Heart failure is a common chronic illness requiring multiple medications and significant self-care. Heart failure is the leading cause of hospitalization in the Medicare population [5]. The complexity of care for heart failure puts people with low literacy at considerable risk for adverse outcomes including hospitalization, worse quality of life, and mortality. Heart failure disease-management interventions appear effective in reducing rehospitalizations and improving quality of life [6]. Most randomized clinical trials of heart failure disease management completed over the last 10 years have enrolled patients during, or shortly after, hospitalization and reported the outcome of readmission [6]. Although the designs of these programs vary, several have tested education and support to enhance patient self-management as the main component of the intervention [7-10]. The content of self-management education usually includes teaching to understand medications, reduce salt intake, monitor daily weights, and recognize symptoms. Most programs include structured follow-up either by home visit, phone, or mail. Only a few, uncontrolled studies specifically ask patients to self-adjust their diuretics [11,12]. Heart failure self-management programs may be particularly effective for vulnerable populations, such as those with poor literacy [13,14]. However, to our knowledge, no previous studies have explicitly examined the role of self-management programs in a low literacy population. A recently published study and accompanying editorial suggested that such self-management support may be most effective among vulnerable populations [13,14]. Low literacy may represent a vulnerability for which we should design our programs. Disease management for patients with low literacy may require refined approaches to foster self-management skills. We developed a heart failure self-management program for use by patients with a variety of literacy levels [15]. We performed a randomized controlled trial comparing our self-management program to usual care among outpatients to test if the program could reduce hospitalizations and improve heart failure-related quality of life.\n\nBODY.METHODS.STUDY DESIGN:\nWe conducted a randomized controlled trial in the University of North Carolina (UNC) General Internal Medicine Practice, which serves a wide socioeconomic range of patients. The practice, staffed by over 20 attending faculty and 70 medical residents, cares for over 500 patients with heart failure.\n\nBODY.METHODS.STUDY PARTICIPANTS:\nTo be eligible, patients had to have a clinical diagnosis of heart failure confirmed by their primary provider through a direct interview, and one of the following: 1) chest x-ray findings consistent with heart failure, 2) ejection fraction <40% by any method, or 3) a history of peripheral edema. They also had to have New York Heart Association class II-IV symptoms within the last 3 months. Patients were excluded if they had moderate to severe dementia (based on the treating physician's clinical judgment), terminal illness with life expectancy less than 6 months, severe hearing impairment, blindness, current substance abuse, a serum creatinine >4 mg/dl or on dialysis, a requirement of supplemental oxygen at home, lacked a telephone, or were scheduled to undergo cardiac surgery or awaiting heart transplant. We did not exclude patients on the basis of literacy skill because we felt patients of all literacy levels would benefit from this intervention. Patients who read well often prefer information presented in an easy-to-read format [16]. We accepted referrals from the cardiology clinic if patients met eligibility criteria. This study was approved by the Institutional Review Board of the UNC School of Medicine, and all participants gave informed consent prior to enrollment. For participants who could not adequately read the informed consent document, the research assistant read and explained it to them. They were asked to sign a short form indicating that the informed consent document was reviewed and they agreed to participate. When the short form was used, a witness was asked to attest to the adequacy of the consent process.\n\nBODY.METHODS.PROCEDURES:\nParticipants were recruited between November 2001 and April 2003 from the General Internal Medicine and Cardiology Practices at UNC Hospitals. A trained research assistant screened all patients age 30–80 for use of furosemide. If the patient was on furosemide, their physician was queried about the presence of heart failure. If the patient met eligibility criteria and consented to participate, baseline data were collected. We then randomized patients by concealed allocation based on a random number generator to receive the intervention or usual care. All patients were followed for one year. All data were collected in the General Internal Medicine Practice.\n\nBODY.METHODS.INTERVENTION:\nThe intervention was delivered in the General Internal Medicine Practice. The educational materials and disease management intervention were previously described in detail, and the intervention is summarized here [15]. The intervention began with a 1-hour educational session with a clinical pharmacist or health educator during a regular clinic visit. Patients were given an educational booklet designed for low literacy patients (written below the 6th grade level and extensively pre-tested in focus groups and a pilot study [15]) and a digital scale. The educator and patient reviewed the booklet together, including management scenarios. As part of the educational session, patients were taught to identify signs of heart failure exacerbation, perform daily weight assessment, and adjust their diuretic dose. Because this intervention was aimed at patients with low literacy, the health educator used pedagogic strategies felt to improve comprehension for patients with low literacy [17]. For example, the educator had the patient teach back the information [18], engaged the patient in filling out the notebook, and used brainstorming to help the patient incorporate self-management into their lives. The educator, patient, and primary care physician collaborated to establish the patient's \"good weight\" (i.e., where the patient's heart failure was stable) and baseline diuretic dose. The educator then filled in the management plan in the patient's notebook to help the patient better manage weight fluctuations and self-adjust the diuretic dose based on weight (Figure 1). The general plan involved doubling the dosage if weight went up and halving it if weight went down. The program coordinator then made scheduled follow-up phone calls (days 3, 7, 14, 21, 28, 56) and monthly during months 3–6. The follow-up phone calls, each lasting 5–15 minutes, were designed to reinforce the educational session and provide motivation for the patients. Again, the program coordinator had the patient describe their self-management practices and offered feedback to improve them. Patients experiencing worsening symptoms were scheduled acute visits with their physician. We did not provide specialized nursing assessment, care or medication advice beyond diuretic dosing. If the patient's doctor determined that the good weight had changed, the program coordinator would revise the care plan with the patient. Patients enrolled in the control group received a general heart failure education pamphlet written at approximately the 7th grade level, and continued with usual care from their primary physician. The only contacts between the research team and the control patients were at enrollment and data collection.\n\nBODY.METHODS.MEASURES:\nWe assessed outcomes at 6 and 12 months through in-person interviews and review of the medical record. To be sensitive to low literacy, all interviews were conducted verbally by a trained research assistant. If patients were unable to come to clinic for the interview, it was conducted by phone. The research assistant was not blinded to the patient's study group. Primary outcomes were death or all-cause readmission and heart failure-related quality of life at the end of 12 months. Data on hospitalization dates were obtained from the patient and confirmed by medical chart review. All admissions, regardless of hospital or cause, were counted. For exploratory analyses, we classified reason for admission as cardiac or non-cardiac. Cardiac admissions included those primarily for heart failure (e.g., shortness of breath and edema relieved by diuresis) and other cardiac causes such as chest pain, arrhythmias, or syncope. Cause of admission was determined by chart review by one of the authors (D.D.) who was blinded to treatment allocation. Heart failure-related quality of life was assessed using a modified version of the Minnesota Living with Heart Failure Questionnaire (MLHF). The MLHF is a 21 question instrument with a 6-point Likert scale response option and scores ranging from 0 to 105 [19]. In pilot testing of the MLHF, we found that low literacy patients had trouble answering questions with the standard 6-point Likert scale [15], so we changed the response scale to 4 points, using a visual display with stars to represent increasing severity. The 4-point Likert scale was scored as 0, 1, 3, and 5 to approximate standard scores on the MLHF. Secondary measures included heart failure self-efficacy, knowledge, and behaviors. Self-efficacy was measured with an 8 item scale developed for the behaviors needed in this trial as suggested by self-efficacy scale developers [20]. Respondents used a 4-point Likert scale yielding a total score from 0–24. We assessed heart failure knowledge using a knowledge test previously developed for this population [15], Heart failure self-management behavior was assessed by asking patients how often they weighed themselves. We used patient self-report and the medical chart to measure age, gender, race, insurance status, income, years of education, medication use, years with heart failure, and the presence of co-morbidities. We measured literacy using the Short Test of Functional Health Literacy in Adults (S-TOFHLA) [21], a well-validated scale that correlates well with other measures of reading ability [22]. Patients who scored in the inadequate literacy range on the S-TOFHLA were considered to have \"low literacy.\" The cut-point for inadequate literacy is roughly analogous to the 4th grade reading level.\n\nBODY.METHODS.SAMPLE SIZE:\nSample size was based on pilot study results showing a 9-point improvement in MLHF scores over 3-months with the intervention [15]. Detecting a 9-point difference between intervention and control group with 80% power and alpha set at 0.05 required 70 patients per group. We aimed to enroll 150 patients to account for possible attrition, but stopped at 127 because funding ended. We did not power this study to detect differences in hospitalization, but studies with even smaller numbers of patients have shown a difference for that outcome [7].\n\nBODY.METHODS.STATISTICAL METHODS:\nPatients who did not return any phone calls and did not return for follow-up assessment did not have outcome data for analysis. Patients who withdrew from the study were censored at the time of withdrawal; any data collected prior to withdrawal were included in the analysis. Baseline differences between groups were assessed using t-tests for continuous outcomes and chi-squared tests for categorical outcomes. For MLHF, heart failure self-efficacy and heart failure knowledge, we used two-sample t-tests. Non-parametric tests were also performed for all comparisons, but results did not differ from the parametric tests. Because of the small sample size and the unequal distribution of baseline characteristics, we adjusted for baseline differences using linear regression. Analyses of self-reported outcomes, such as MLHF, excluded patients who died or withdrew from the study before 6 or 12 month data was collected. For hospitalization or death, we used negative binomial regression and censored patients at the time of death or withdrawal from the study. Based on the likelihood ratio test, negative binomial regression was a better fit for the data than a Poisson regression. Additionally, the Vuong test confirmed that a zero-inflated model was inappropriate [23]. Because of uneven distribution of baseline characteristics, we performed analysis of covariance with negative binomial regression to control for baseline differences [24]. We identified the following variables that could contribute to hospitalization or death based on previous studies: age, race, gender, literacy level, hypertension, diabetes, creatinine, MLHF score, use of β-blockers, angiotensin converting enzyme (ACE) inhibitors or angiotensin receptor blockers (ARBs), use of digoxin, and presence of systolic dysfunction [7,25]. Variables were not included in the model if the relationship between the variable and the study group or outcome had a p value greater than 0.3. We started with a model including the following items to arrive at the best point estimate: age, gender, hypertension, creatinine, MLHF, use of β-blockers, and use of ACE inhibitors or ARBs. We then eliminated variables from the model if p > 0.30, and if the point estimate remained within 10% of the initial estimate. We prespecified a subgroup analysis in patients with low literacy to analyze if the intervention had a similar effect. The same analysis described above was repeated for the subgroups of patients with low literacy and those with higher literacy. The initial multivariate model for the subgroups analysis included: age, gender, hypertension, MLHF, use of β-blockers, and use of ACE inhibitors or ARBs.\n\nBODY.METHODS.ROLE OF THE FUNDING SOURCE:\nThe funding sources had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; or preparation, review, or approval of the manuscript.\n\nBODY.RESULTS.PATIENTS:\nWe screened 919 patients on furosemide between November 2001 and April 2003. 127 met eligibility criteria and agreed to participate (Figure 2). Of those not enrolled, 407 did not have heart failure according to their physician, 367 did not meet eligibility criteria and 27 declined to participate. Of those randomized to the control group, 1 never returned after the first visit, 1 withdrew during the study and 4 died during the study. Follow-up was completed for all of the remaining participants (98%) (Figure 3). Of those randomized to the intervention group, 3 never returned after the first visit, 4 withdrew during the study and 3 died during the study. Follow-up was completed for all of the remaining participants (93%). At baseline, most characteristics were similar between the two groups (Table 1). However, the control group had more participants with hypertension, fewer with diabetes, and fewer men. Of heart failure related characteristics, the control group had more participants with systolic dysfunction, and taking β-blockers. The intervention group had more participants taking ACE inhibitors or ARBs, and digoxin. Regardless of these differences, none were statistically significant. The control group did have statistically significantly higher baseline MLHF scores representing worse symptoms at baseline.\n\nBODY.RESULTS.HOSPITALIZATION OR DEATH:\nThere were 68 hospitalizations (65) or deaths (3) in the intervention group and 111 (107 hospitalizations, 4 deaths) in the control group. The crude all-cause hospital admission or death incidence rate ratio (IRR) was 0.69 (95% CI 0.40, 1.19). After adjusting for age, gender, use of ACE inhibitor or ARB, use of a β-blocker, presence of hypertension, and baseline MLHF, intervention patients were less likely to have the outcome (IRR = 0.53; 95% CI 0.32, 0.89). 61% of patients in the control group had at least one hospitalization or died, and 42% of patients in the intervention group had at least 1 hospitalization or died (p = 0.13).\n\nBODY.RESULTS.CARDIAC HOSPITALIZATION:\n39% of patients in the control group and 34% of patients in the intervention group had at least one hospitalization for cardiac causes (p = 0.55). The unadjusted IRR was 0.79 (95% CI 0.42, 1.5). After adjusting for baseline differences, the IRR was 0.85 (95% CI 0.44, 1.7).\n\nBODY.RESULTS.HEART FAILURE-RELATED QUALITY OF LIFE:\nIn unadjusted analysis, the control group, on average, improved 5 points on the MLHF and the intervention group improved by 1 point. The difference was not statistically significant (3.5 points, 95% CI 11, -4, p = 0.36). After adjusting for baseline differences between the groups, the difference was 2 points (95% CI 9, -5, p = 0.59) suggesting no effect on heart failure-related quality of life.\n\nBODY.RESULTS.OTHER OUTCOMES.KNOWLEDGE:\nHeart failure related knowledge improved more in the intervention group than in the control group. Mean difference in score improvement was 12 percentage points (95% CI 6, 18; p < 0.001).\n\nBODY.RESULTS.OTHER OUTCOMES.SELF-EFFICACY:\nHeart failure self-efficacy improved more in the intervention group than in the control group. Mean difference in score improvement was 2 points (95% CI 0.7, 3.1; p = 0.0026).\n\nBODY.RESULTS.OTHER OUTCOMES.SELF-CARE BEHAVIOR:\nSignificantly more patients in the intervention group than in the control group reported daily weight measurement at 12 months (79% vs. 29%, p < 0.001).\n\nBODY.RESULTS.SUBGROUP ANALYSES ACCORDING TO LITERACY:\nTwenty-four patients in each group had inadequate literacy based on the S-TOFHLA (Table 2). Among these patients, there was no difference in quality of life score in unadjusted and adjusted analyses (difference = -1.6; 95% CI -15, 12); p = 0.81). For the combined outcome of hospitalization or death, the unadjusted IRR was 0.77 (95% CI 0.30, 1.94). After adjusting for baseline differences, the IRR was 0.39 (95% CI 0.16, 0.91). Seventy-five patients had marginal or adequate literacy based on the S-TOFHLA. We found no difference in quality of life score in unadjusted and adjusted analyses (difference = -4.2; 95% CI -14, 6; p = 0.40). Among patients in the higher literacy group, the unadjusted IRR for hospitalization or death was 0.65 (95% CI 0.33, 1.3). After adjusting for baseline differences, the IRR was 0.56 (95% CI 0.30, 1.04). We did not find a statistically significant effect modification between literacy and the intervention.\n\nBODY.DISCUSSION:\nA heart failure self-management program designed for patients with low literacy reduced the rate of the combined endpoint of hospitalization or death. The prespecified subgroup analyses suggest that patients with low literacy benefited as much from the intervention as the patients with higher literacy. The success of our intervention reflects the goals of our program. We designed an easy-to-read and use educational booklet and self-management plan, and focused on overcoming barriers to learning self-management [15]. Our intervention was founded on teaching self-management. We focused on helping patients understand signs and symptoms of worsening heart failure and perform self-adjustment of diuretics based on weight fluctuation. Many care providers would not attempt to teach patients, particularly those with low literacy, how to self-adjust their diuretic medication. We found that, with careful teaching, many patients incorporated this strategy into their daily routine successfully, as demonstrated by improved self-care behaviors. Teaching self-adjustment of diuretics, rather than the conventional teaching to call the care provider if weight fluctuates, empowers patients to take more control over their illness. Self-adjustment of diuretic dose is a prominent aspect of the self-management training we provided to the intervention patients. Other programs to improve patient self-management have not been explicit in teaching patients to self-adjust their diuretic dose based on weight fluctuation. Although our outcomes are comparable to others', using this approach puts more control into the hands of the patient. Furthermore, our intervention appears effective among patients with low literacy skills, a group often overlooked for empowering interventions. Our study adds to the growing literature on disease management programs for patients with heart failure [6], particularly those that focus on self-management training [7-10]. Studies focusing on self-management training have demonstrated comparable improvements in hospitalization rates to more comprehensive programs that aim to improve the quality of pharmaceutical prescribing, provide home visits, and take place in specialized cardiology clinics [6]. Such comprehensive programs have also been shown to reduce mortality, but self-management programs have not [6]. We did not detect any difference in heart failure related quality of life which was the outcome we powered our study to detect. Other self-management studies that have found improved quality of life have enrolled patients during a heart failure hospitalization [8,9]; however, we enrolled patients in the outpatient setting while they were clinically stable. Improving quality of life for stable outpatients may be more difficult for this type of intervention. We have previously reported that patients with diabetes and low literacy benefited more from a disease management intervention than those with higher literacy skills [26]. A similar result in two different chronic diseases substantiates the claim that appropriately designed disease management programs may have greater effect for low literacy or vulnerable populations, who are most at risk for adverse outcomes with usual care. This finding is particularly important in light of the recent study by DeBusk and colleagues that did not find a reduction in hospitalization with a well-designed comprehensive intervention [13]. The authors and an accompanying editorial [14] suggested that the failure to detect improvement may have occurred because the patients studied were less at-risk than in other studies. They called for more research to determine better ways of targeting disease management. We believe that low literacy is an important marker for vulnerability to adverse outcomes, and that disease management programs targeted to patients with low literacy may be an effective way of focusing resources on those most able to benefit. If patients with low literacy are to be preferentially recruited for such programs, innovative outreach and screening efforts will likely be required, as patients with low literacy may face particular barriers to accessing such care. This study should be interpreted in light of its limitations. Research assistants were not blind to group assignment during the assessment of self-reported outcomes. As such, patients in the intervention may have been more likely to inflate their responses in an effort to please the interviewer. This effect would tend to inflate patient responses to the subjective assessments of heart failure-related quality of life, self-efficacy, and self-care behaviors. The MLHF questionnaire was modified from its original form to make it easier for patients with low literacy to respond. This change in the scale may have changed its ability to detect important changes in heart failure related quality of life. Because the groups' mean scores were almost identical, we do not feel this limitation changed our results. In a similar vein, most questionnaires are not validated in low literacy populations, raising questions as to their ability to perform to the same standards. Our sample size was small, which did not allow for an even distribution of baseline variables among the groups. We controlled for baseline differences between groups in our analysis. While it is controversial whether or not to control for baseline differences in randomized controlled trials, some analysts have argued that doing so improves the power without introducing bias [24]. A larger, multi-site study would offer better control of confounders, better generalizability, and more power to determine differences in effect according to literacy. We did not collect data on the resources needed to implement this type of intervention in usual settings, and such a study and cost-effectiveness analysis would be helpful for most interventions of this type. We used health educators, not nurses or physicians, to deliver the intervention. By using less highly trained individuals to deliver the intervention, we enabled nurses and physicians to perform clinical tasks more commensurate with their training. Other studies that have performed global cost estimates have found that the savings from reductions in hospitalizations exceed the cost of the intervention [6].\n\nBODY.CONCLUSION:\nIn conclusion, our heart failure self-management program, designed for patients of all literacy levels, appears to reduce rates of hospitalization and death. Patients with low literacy, and other vulnerable patients, may stand to benefit most from these programs. Further research into the design, implementation, and dissemination of disease management programs for low literacy patients will be crucial for meeting the health care needs of the growing population of patients with chronic illness.\n\nBODY.COMPETING INTERESTS:\nDrs. DeWalt and Pignone have received honoraria and grants from Pfizer, Inc., Dr. Rothman has received grants from Pfizer, Inc., and Dr. Sueta is in their speakers bureau.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nDD conceived of the study, participated in its design and coordination, performed statistical analyses, interpretation of the data, and drafted the manuscript. RM, MB conceived of the study and participated in its coordination. MK, KC coordinated the study, and collected the data, RR, CS participated in study design and interpretation of the data. MP conceived of the study, participated in its design and coordination, and interpretation of the data. All authors reviewed the manuscript for important intellectual content and gave final approval.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here:\n\n**Question:** Compared to Standard information about self-care what was the result of Follow-up and thorough education on self-care on Hospitalization or death?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
364
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Placebo what was the result of Budesonide/formoterol pMDI 320/9 μg on Sputum score improvement?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
215
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: A heart failure self-management program for patients of all literacy levels: A randomized, controlled trial [ISRCTN11535170]\n\n ABSTRACT.BACKGROUND:\nSelf-management programs for patients with heart failure can reduce hospitalizations and mortality. However, no programs have analyzed their usefulness for patients with low literacy. We compared the efficacy of a heart failure self-management program designed for patients with low literacy versus usual care.\n\nABSTRACT.METHODS:\nWe performed a 12-month randomized controlled trial. From November 2001 to April 2003, we enrolled participants aged 30–80, who had heart failure and took furosemide. Intervention patients received education on self-care emphasizing daily weight measurement, diuretic dose self-adjustment, and symptom recognition and response. Picture-based educational materials, a digital scale, and scheduled telephone follow-up were provided to reinforce adherence. Control patients received a generic heart failure brochure and usual care. Primary outcomes were combined hospitalization or death, and heart failure-related quality of life.\n\nABSTRACT.RESULTS:\n123 patients (64 control, 59 intervention) participated; 41% had inadequate literacy. Patients in the intervention group had a lower rate of hospitalization or death (crude incidence rate ratio (IRR) = 0.69; CI 0.4, 1.2; adjusted IRR = 0.53; CI 0.32, 0.89). This difference was larger for patients with low literacy (IRR = 0.39; CI 0.16, 0.91) than for higher literacy (IRR = 0.56; CI 0.3, 1.04), but the interaction was not statistically significant. At 12 months, more patients in the intervention group reported monitoring weights daily (79% vs. 29%, p < 0.0001). After adjusting for baseline demographic and treatment differences, we found no difference in heart failure-related quality of life at 12 months (difference = -2; CI -5, +9).\n\nABSTRACT.CONCLUSION:\nA primary care-based heart failure self-management program designed for patients with low literacy reduces the risk of hospitalizations or death.\n\nBODY.BACKGROUND:\nLimited literacy skills are common among adults in the United States [1]. Low literacy is associated with increased risk of hospitalization and worse control of chronic diseases [1-4]. Heart failure is a common chronic illness requiring multiple medications and significant self-care. Heart failure is the leading cause of hospitalization in the Medicare population [5]. The complexity of care for heart failure puts people with low literacy at considerable risk for adverse outcomes including hospitalization, worse quality of life, and mortality. Heart failure disease-management interventions appear effective in reducing rehospitalizations and improving quality of life [6]. Most randomized clinical trials of heart failure disease management completed over the last 10 years have enrolled patients during, or shortly after, hospitalization and reported the outcome of readmission [6]. Although the designs of these programs vary, several have tested education and support to enhance patient self-management as the main component of the intervention [7-10]. The content of self-management education usually includes teaching to understand medications, reduce salt intake, monitor daily weights, and recognize symptoms. Most programs include structured follow-up either by home visit, phone, or mail. Only a few, uncontrolled studies specifically ask patients to self-adjust their diuretics [11,12]. Heart failure self-management programs may be particularly effective for vulnerable populations, such as those with poor literacy [13,14]. However, to our knowledge, no previous studies have explicitly examined the role of self-management programs in a low literacy population. A recently published study and accompanying editorial suggested that such self-management support may be most effective among vulnerable populations [13,14]. Low literacy may represent a vulnerability for which we should design our programs. Disease management for patients with low literacy may require refined approaches to foster self-management skills. We developed a heart failure self-management program for use by patients with a variety of literacy levels [15]. We performed a randomized controlled trial comparing our self-management program to usual care among outpatients to test if the program could reduce hospitalizations and improve heart failure-related quality of life.\n\nBODY.METHODS.STUDY DESIGN:\nWe conducted a randomized controlled trial in the University of North Carolina (UNC) General Internal Medicine Practice, which serves a wide socioeconomic range of patients. The practice, staffed by over 20 attending faculty and 70 medical residents, cares for over 500 patients with heart failure.\n\nBODY.METHODS.STUDY PARTICIPANTS:\nTo be eligible, patients had to have a clinical diagnosis of heart failure confirmed by their primary provider through a direct interview, and one of the following: 1) chest x-ray findings consistent with heart failure, 2) ejection fraction <40% by any method, or 3) a history of peripheral edema. They also had to have New York Heart Association class II-IV symptoms within the last 3 months. Patients were excluded if they had moderate to severe dementia (based on the treating physician's clinical judgment), terminal illness with life expectancy less than 6 months, severe hearing impairment, blindness, current substance abuse, a serum creatinine >4 mg/dl or on dialysis, a requirement of supplemental oxygen at home, lacked a telephone, or were scheduled to undergo cardiac surgery or awaiting heart transplant. We did not exclude patients on the basis of literacy skill because we felt patients of all literacy levels would benefit from this intervention. Patients who read well often prefer information presented in an easy-to-read format [16]. We accepted referrals from the cardiology clinic if patients met eligibility criteria. This study was approved by the Institutional Review Board of the UNC School of Medicine, and all participants gave informed consent prior to enrollment. For participants who could not adequately read the informed consent document, the research assistant read and explained it to them. They were asked to sign a short form indicating that the informed consent document was reviewed and they agreed to participate. When the short form was used, a witness was asked to attest to the adequacy of the consent process.\n\nBODY.METHODS.PROCEDURES:\nParticipants were recruited between November 2001 and April 2003 from the General Internal Medicine and Cardiology Practices at UNC Hospitals. A trained research assistant screened all patients age 30–80 for use of furosemide. If the patient was on furosemide, their physician was queried about the presence of heart failure. If the patient met eligibility criteria and consented to participate, baseline data were collected. We then randomized patients by concealed allocation based on a random number generator to receive the intervention or usual care. All patients were followed for one year. All data were collected in the General Internal Medicine Practice.\n\nBODY.METHODS.INTERVENTION:\nThe intervention was delivered in the General Internal Medicine Practice. The educational materials and disease management intervention were previously described in detail, and the intervention is summarized here [15]. The intervention began with a 1-hour educational session with a clinical pharmacist or health educator during a regular clinic visit. Patients were given an educational booklet designed for low literacy patients (written below the 6th grade level and extensively pre-tested in focus groups and a pilot study [15]) and a digital scale. The educator and patient reviewed the booklet together, including management scenarios. As part of the educational session, patients were taught to identify signs of heart failure exacerbation, perform daily weight assessment, and adjust their diuretic dose. Because this intervention was aimed at patients with low literacy, the health educator used pedagogic strategies felt to improve comprehension for patients with low literacy [17]. For example, the educator had the patient teach back the information [18], engaged the patient in filling out the notebook, and used brainstorming to help the patient incorporate self-management into their lives. The educator, patient, and primary care physician collaborated to establish the patient's \"good weight\" (i.e., where the patient's heart failure was stable) and baseline diuretic dose. The educator then filled in the management plan in the patient's notebook to help the patient better manage weight fluctuations and self-adjust the diuretic dose based on weight (Figure 1). The general plan involved doubling the dosage if weight went up and halving it if weight went down. The program coordinator then made scheduled follow-up phone calls (days 3, 7, 14, 21, 28, 56) and monthly during months 3–6. The follow-up phone calls, each lasting 5–15 minutes, were designed to reinforce the educational session and provide motivation for the patients. Again, the program coordinator had the patient describe their self-management practices and offered feedback to improve them. Patients experiencing worsening symptoms were scheduled acute visits with their physician. We did not provide specialized nursing assessment, care or medication advice beyond diuretic dosing. If the patient's doctor determined that the good weight had changed, the program coordinator would revise the care plan with the patient. Patients enrolled in the control group received a general heart failure education pamphlet written at approximately the 7th grade level, and continued with usual care from their primary physician. The only contacts between the research team and the control patients were at enrollment and data collection.\n\nBODY.METHODS.MEASURES:\nWe assessed outcomes at 6 and 12 months through in-person interviews and review of the medical record. To be sensitive to low literacy, all interviews were conducted verbally by a trained research assistant. If patients were unable to come to clinic for the interview, it was conducted by phone. The research assistant was not blinded to the patient's study group. Primary outcomes were death or all-cause readmission and heart failure-related quality of life at the end of 12 months. Data on hospitalization dates were obtained from the patient and confirmed by medical chart review. All admissions, regardless of hospital or cause, were counted. For exploratory analyses, we classified reason for admission as cardiac or non-cardiac. Cardiac admissions included those primarily for heart failure (e.g., shortness of breath and edema relieved by diuresis) and other cardiac causes such as chest pain, arrhythmias, or syncope. Cause of admission was determined by chart review by one of the authors (D.D.) who was blinded to treatment allocation. Heart failure-related quality of life was assessed using a modified version of the Minnesota Living with Heart Failure Questionnaire (MLHF). The MLHF is a 21 question instrument with a 6-point Likert scale response option and scores ranging from 0 to 105 [19]. In pilot testing of the MLHF, we found that low literacy patients had trouble answering questions with the standard 6-point Likert scale [15], so we changed the response scale to 4 points, using a visual display with stars to represent increasing severity. The 4-point Likert scale was scored as 0, 1, 3, and 5 to approximate standard scores on the MLHF. Secondary measures included heart failure self-efficacy, knowledge, and behaviors. Self-efficacy was measured with an 8 item scale developed for the behaviors needed in this trial as suggested by self-efficacy scale developers [20]. Respondents used a 4-point Likert scale yielding a total score from 0–24. We assessed heart failure knowledge using a knowledge test previously developed for this population [15], Heart failure self-management behavior was assessed by asking patients how often they weighed themselves. We used patient self-report and the medical chart to measure age, gender, race, insurance status, income, years of education, medication use, years with heart failure, and the presence of co-morbidities. We measured literacy using the Short Test of Functional Health Literacy in Adults (S-TOFHLA) [21], a well-validated scale that correlates well with other measures of reading ability [22]. Patients who scored in the inadequate literacy range on the S-TOFHLA were considered to have \"low literacy.\" The cut-point for inadequate literacy is roughly analogous to the 4th grade reading level.\n\nBODY.METHODS.SAMPLE SIZE:\nSample size was based on pilot study results showing a 9-point improvement in MLHF scores over 3-months with the intervention [15]. Detecting a 9-point difference between intervention and control group with 80% power and alpha set at 0.05 required 70 patients per group. We aimed to enroll 150 patients to account for possible attrition, but stopped at 127 because funding ended. We did not power this study to detect differences in hospitalization, but studies with even smaller numbers of patients have shown a difference for that outcome [7].\n\nBODY.METHODS.STATISTICAL METHODS:\nPatients who did not return any phone calls and did not return for follow-up assessment did not have outcome data for analysis. Patients who withdrew from the study were censored at the time of withdrawal; any data collected prior to withdrawal were included in the analysis. Baseline differences between groups were assessed using t-tests for continuous outcomes and chi-squared tests for categorical outcomes. For MLHF, heart failure self-efficacy and heart failure knowledge, we used two-sample t-tests. Non-parametric tests were also performed for all comparisons, but results did not differ from the parametric tests. Because of the small sample size and the unequal distribution of baseline characteristics, we adjusted for baseline differences using linear regression. Analyses of self-reported outcomes, such as MLHF, excluded patients who died or withdrew from the study before 6 or 12 month data was collected. For hospitalization or death, we used negative binomial regression and censored patients at the time of death or withdrawal from the study. Based on the likelihood ratio test, negative binomial regression was a better fit for the data than a Poisson regression. Additionally, the Vuong test confirmed that a zero-inflated model was inappropriate [23]. Because of uneven distribution of baseline characteristics, we performed analysis of covariance with negative binomial regression to control for baseline differences [24]. We identified the following variables that could contribute to hospitalization or death based on previous studies: age, race, gender, literacy level, hypertension, diabetes, creatinine, MLHF score, use of β-blockers, angiotensin converting enzyme (ACE) inhibitors or angiotensin receptor blockers (ARBs), use of digoxin, and presence of systolic dysfunction [7,25]. Variables were not included in the model if the relationship between the variable and the study group or outcome had a p value greater than 0.3. We started with a model including the following items to arrive at the best point estimate: age, gender, hypertension, creatinine, MLHF, use of β-blockers, and use of ACE inhibitors or ARBs. We then eliminated variables from the model if p > 0.30, and if the point estimate remained within 10% of the initial estimate. We prespecified a subgroup analysis in patients with low literacy to analyze if the intervention had a similar effect. The same analysis described above was repeated for the subgroups of patients with low literacy and those with higher literacy. The initial multivariate model for the subgroups analysis included: age, gender, hypertension, MLHF, use of β-blockers, and use of ACE inhibitors or ARBs.\n\nBODY.METHODS.ROLE OF THE FUNDING SOURCE:\nThe funding sources had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; or preparation, review, or approval of the manuscript.\n\nBODY.RESULTS.PATIENTS:\nWe screened 919 patients on furosemide between November 2001 and April 2003. 127 met eligibility criteria and agreed to participate (Figure 2). Of those not enrolled, 407 did not have heart failure according to their physician, 367 did not meet eligibility criteria and 27 declined to participate. Of those randomized to the control group, 1 never returned after the first visit, 1 withdrew during the study and 4 died during the study. Follow-up was completed for all of the remaining participants (98%) (Figure 3). Of those randomized to the intervention group, 3 never returned after the first visit, 4 withdrew during the study and 3 died during the study. Follow-up was completed for all of the remaining participants (93%). At baseline, most characteristics were similar between the two groups (Table 1). However, the control group had more participants with hypertension, fewer with diabetes, and fewer men. Of heart failure related characteristics, the control group had more participants with systolic dysfunction, and taking β-blockers. The intervention group had more participants taking ACE inhibitors or ARBs, and digoxin. Regardless of these differences, none were statistically significant. The control group did have statistically significantly higher baseline MLHF scores representing worse symptoms at baseline.\n\nBODY.RESULTS.HOSPITALIZATION OR DEATH:\nThere were 68 hospitalizations (65) or deaths (3) in the intervention group and 111 (107 hospitalizations, 4 deaths) in the control group. The crude all-cause hospital admission or death incidence rate ratio (IRR) was 0.69 (95% CI 0.40, 1.19). After adjusting for age, gender, use of ACE inhibitor or ARB, use of a β-blocker, presence of hypertension, and baseline MLHF, intervention patients were less likely to have the outcome (IRR = 0.53; 95% CI 0.32, 0.89). 61% of patients in the control group had at least one hospitalization or died, and 42% of patients in the intervention group had at least 1 hospitalization or died (p = 0.13).\n\nBODY.RESULTS.CARDIAC HOSPITALIZATION:\n39% of patients in the control group and 34% of patients in the intervention group had at least one hospitalization for cardiac causes (p = 0.55). The unadjusted IRR was 0.79 (95% CI 0.42, 1.5). After adjusting for baseline differences, the IRR was 0.85 (95% CI 0.44, 1.7).\n\nBODY.RESULTS.HEART FAILURE-RELATED QUALITY OF LIFE:\nIn unadjusted analysis, the control group, on average, improved 5 points on the MLHF and the intervention group improved by 1 point. The difference was not statistically significant (3.5 points, 95% CI 11, -4, p = 0.36). After adjusting for baseline differences between the groups, the difference was 2 points (95% CI 9, -5, p = 0.59) suggesting no effect on heart failure-related quality of life.\n\nBODY.RESULTS.OTHER OUTCOMES.KNOWLEDGE:\nHeart failure related knowledge improved more in the intervention group than in the control group. Mean difference in score improvement was 12 percentage points (95% CI 6, 18; p < 0.001).\n\nBODY.RESULTS.OTHER OUTCOMES.SELF-EFFICACY:\nHeart failure self-efficacy improved more in the intervention group than in the control group. Mean difference in score improvement was 2 points (95% CI 0.7, 3.1; p = 0.0026).\n\nBODY.RESULTS.OTHER OUTCOMES.SELF-CARE BEHAVIOR:\nSignificantly more patients in the intervention group than in the control group reported daily weight measurement at 12 months (79% vs. 29%, p < 0.001).\n\nBODY.RESULTS.SUBGROUP ANALYSES ACCORDING TO LITERACY:\nTwenty-four patients in each group had inadequate literacy based on the S-TOFHLA (Table 2). Among these patients, there was no difference in quality of life score in unadjusted and adjusted analyses (difference = -1.6; 95% CI -15, 12); p = 0.81). For the combined outcome of hospitalization or death, the unadjusted IRR was 0.77 (95% CI 0.30, 1.94). After adjusting for baseline differences, the IRR was 0.39 (95% CI 0.16, 0.91). Seventy-five patients had marginal or adequate literacy based on the S-TOFHLA. We found no difference in quality of life score in unadjusted and adjusted analyses (difference = -4.2; 95% CI -14, 6; p = 0.40). Among patients in the higher literacy group, the unadjusted IRR for hospitalization or death was 0.65 (95% CI 0.33, 1.3). After adjusting for baseline differences, the IRR was 0.56 (95% CI 0.30, 1.04). We did not find a statistically significant effect modification between literacy and the intervention.\n\nBODY.DISCUSSION:\nA heart failure self-management program designed for patients with low literacy reduced the rate of the combined endpoint of hospitalization or death. The prespecified subgroup analyses suggest that patients with low literacy benefited as much from the intervention as the patients with higher literacy. The success of our intervention reflects the goals of our program. We designed an easy-to-read and use educational booklet and self-management plan, and focused on overcoming barriers to learning self-management [15]. Our intervention was founded on teaching self-management. We focused on helping patients understand signs and symptoms of worsening heart failure and perform self-adjustment of diuretics based on weight fluctuation. Many care providers would not attempt to teach patients, particularly those with low literacy, how to self-adjust their diuretic medication. We found that, with careful teaching, many patients incorporated this strategy into their daily routine successfully, as demonstrated by improved self-care behaviors. Teaching self-adjustment of diuretics, rather than the conventional teaching to call the care provider if weight fluctuates, empowers patients to take more control over their illness. Self-adjustment of diuretic dose is a prominent aspect of the self-management training we provided to the intervention patients. Other programs to improve patient self-management have not been explicit in teaching patients to self-adjust their diuretic dose based on weight fluctuation. Although our outcomes are comparable to others', using this approach puts more control into the hands of the patient. Furthermore, our intervention appears effective among patients with low literacy skills, a group often overlooked for empowering interventions. Our study adds to the growing literature on disease management programs for patients with heart failure [6], particularly those that focus on self-management training [7-10]. Studies focusing on self-management training have demonstrated comparable improvements in hospitalization rates to more comprehensive programs that aim to improve the quality of pharmaceutical prescribing, provide home visits, and take place in specialized cardiology clinics [6]. Such comprehensive programs have also been shown to reduce mortality, but self-management programs have not [6]. We did not detect any difference in heart failure related quality of life which was the outcome we powered our study to detect. Other self-management studies that have found improved quality of life have enrolled patients during a heart failure hospitalization [8,9]; however, we enrolled patients in the outpatient setting while they were clinically stable. Improving quality of life for stable outpatients may be more difficult for this type of intervention. We have previously reported that patients with diabetes and low literacy benefited more from a disease management intervention than those with higher literacy skills [26]. A similar result in two different chronic diseases substantiates the claim that appropriately designed disease management programs may have greater effect for low literacy or vulnerable populations, who are most at risk for adverse outcomes with usual care. This finding is particularly important in light of the recent study by DeBusk and colleagues that did not find a reduction in hospitalization with a well-designed comprehensive intervention [13]. The authors and an accompanying editorial [14] suggested that the failure to detect improvement may have occurred because the patients studied were less at-risk than in other studies. They called for more research to determine better ways of targeting disease management. We believe that low literacy is an important marker for vulnerability to adverse outcomes, and that disease management programs targeted to patients with low literacy may be an effective way of focusing resources on those most able to benefit. If patients with low literacy are to be preferentially recruited for such programs, innovative outreach and screening efforts will likely be required, as patients with low literacy may face particular barriers to accessing such care. This study should be interpreted in light of its limitations. Research assistants were not blind to group assignment during the assessment of self-reported outcomes. As such, patients in the intervention may have been more likely to inflate their responses in an effort to please the interviewer. This effect would tend to inflate patient responses to the subjective assessments of heart failure-related quality of life, self-efficacy, and self-care behaviors. The MLHF questionnaire was modified from its original form to make it easier for patients with low literacy to respond. This change in the scale may have changed its ability to detect important changes in heart failure related quality of life. Because the groups' mean scores were almost identical, we do not feel this limitation changed our results. In a similar vein, most questionnaires are not validated in low literacy populations, raising questions as to their ability to perform to the same standards. Our sample size was small, which did not allow for an even distribution of baseline variables among the groups. We controlled for baseline differences between groups in our analysis. While it is controversial whether or not to control for baseline differences in randomized controlled trials, some analysts have argued that doing so improves the power without introducing bias [24]. A larger, multi-site study would offer better control of confounders, better generalizability, and more power to determine differences in effect according to literacy. We did not collect data on the resources needed to implement this type of intervention in usual settings, and such a study and cost-effectiveness analysis would be helpful for most interventions of this type. We used health educators, not nurses or physicians, to deliver the intervention. By using less highly trained individuals to deliver the intervention, we enabled nurses and physicians to perform clinical tasks more commensurate with their training. Other studies that have performed global cost estimates have found that the savings from reductions in hospitalizations exceed the cost of the intervention [6].\n\nBODY.CONCLUSION:\nIn conclusion, our heart failure self-management program, designed for patients of all literacy levels, appears to reduce rates of hospitalization and death. Patients with low literacy, and other vulnerable patients, may stand to benefit most from these programs. Further research into the design, implementation, and dissemination of disease management programs for low literacy patients will be crucial for meeting the health care needs of the growing population of patients with chronic illness.\n\nBODY.COMPETING INTERESTS:\nDrs. DeWalt and Pignone have received honoraria and grants from Pfizer, Inc., Dr. Rothman has received grants from Pfizer, Inc., and Dr. Sueta is in their speakers bureau.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nDD conceived of the study, participated in its design and coordination, performed statistical analyses, interpretation of the data, and drafted the manuscript. RM, MB conceived of the study and participated in its coordination. MK, KC coordinated the study, and collected the data, RR, CS participated in study design and interpretation of the data. MP conceived of the study, participated in its design and coordination, and interpretation of the data. All authors reviewed the manuscript for important intellectual content and gave final approval.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here:\n\n**Question:** Compared to Standard information about self-care what was the result of Follow-up and thorough education on self-care on Daily weight monitoring at the end of treatment?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
382
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Placebo what was the result of Budesonide/formoterol pMDI 160/9 μg on Incidence of pneumonia?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
317
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Formoterol DPI 9 μg what was the result of Budesonide/formoterol pMDI 320/9 μg on 1-hour post-dose FEV1 improvements?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
445
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Effects of high volume saline enemas vs no enema during labour – The N-Ma Randomised Controlled Trial [ISRCTN43153145]\n\n ABSTRACT.BACKGROUND:\nEnemas are used during labour in obstetric settings with the belief that they reduce puerperal and neonatal infections, shorten labour duration, and make delivery cleaner for attending personnel. However, a systematic review of the literature found insufficient evidence to support the use of enemas. The objective of this RCT was to address an identified knowledge gap by determining the effect of routine enemas used during the first stage of labour on puerperal and neonatal infection rates.\n\nABSTRACT.METHODS:\nDesign: RCT (randomised controlled trial; randomized clinical trial). Outcomes: Clinical diagnosis of maternal or neonatal infections, labour duration, delivery types, episiotomy rates, and prescription of antibiotics Setting: Tertiary care referral hospital at the Javeriana University (Bogotá, Colombia) that attended 3170 births during study period with a caesarean section rate of 26%. Participants: 443 women admitted for delivery to the obstetrics service (February 1997 to February 1998) and followed for a month after delivery. Inclusion criteria were women with: low risk pregnancy and expected to remain in Bogotá during follow up; gestational age ≥ 36 weeks; no pelvic or systemic bacterial infection; intact membranes; cervix dilatation ≤7 cm. Intervention: 1 litre saline enema, versus no enema, allocated following a block random allocation sequence and using sealed opaque envelopes.\n\nABSTRACT.RESULTS:\nAllocation provided balanced groups and 86% of the participants were followed up for one month. The overall infection rate for newborns was 21%, and 18% for women. We found no significant differences in puerperal or neonatal infection rates (Puerperal infection: 41/190 [22%] with enema v 26/182 [14%] without enema; RR 0.66 CI 95%: 0.43 to 1.03; neonatal infection 38/191 [20%] with enema v 40/179 [22%] without enema; RR 1.12, 95% CI 95% 0.76 to 1.66), and median labour time was similar between groups (515 min. with enema v 585 min. without enema; P = 0.24). Enemas didn't significantly change episiorraphy dehiscence rates (21/182 [12%] with enema v 32/190 [17%] without enema; P = 0.30).\n\nABSTRACT.CONCLUSION:\nThis RCT found no evidence to support routine use of enemas during labour. Although these results cannot rule out a small clinical effect, it seems unlikely that enemas will improve maternal and neonatal outcomes and provide an overall benefit.\n\nBODY.BACKGROUND:\nEnemas are frequently used in obstetric settings because they are thought to reduce the risk of puerperal and neonatal infections, shorten the duration of labour and make delivery cleaner for attending personnel [1,2]. However, the use of enemas is controversial and there is little evidence of their effectiveness. Enemas are upsetting and humiliating for women in labour and increase the workload in labour wards. Enemas cause watery stools and could theoretically increase contamination and infection rates[3,4]. A systematic review of the literature found one trial with 222 women, which found no difference in puerperal or neonatal infections. However, it only followed women while they remained hospitalized; this time may be too short to identify outcomes that could be affected by enemas. The review concluded that there was insufficient evidence to recommend the use of enemas during labour and called for additional RCTs [5]. The main objective of this RCT was to find out if the use of high volume enemas during the first stage of labour modified neonatal and puerperal infectious rates. The null hypothesis stated that proportion of infections was similar for the intervention and control groups. The secondary objectives were to establish if there was an effect on specific neonatal or puerperal infectious rates, and other clinically relevant outcomes such as neonatal infections, maternal pelvic inflammatory disease or suture dehiscence, and antibiotic prescriptions. The protocol for this study was presented and debated at two meetings of the Latin American Clinical Epidemiology Network: Latinclen I in April 1995 in Colombia; and the Latinclen III in September 1997 in Dominican Republic.\n\nBODY.METHODS:\nThe RCT was conducted at the obstetric service of the Hospital Universitario San Ignacio, a tertiary care referral centre in Bogota, Colombia. Women attending the admission unit of the obstetrics' clinic for delivery were invited to participate. In accordance with the protocol, the examining intern or resident would invite all eligible women to participate in the study. Recruitment rates varied greatly among different interns and residents. Because of the frequent rotation of interns and residents through the admission unit, interns and residents attended standardised monthly training sessions on how to enrol patients on the study. Inclusion criteria included: absence of life threatening events at admission interview (such as placental abruptio, prolapsed cord, or eclampsia); gestational age ≥36 weeks based on the best available estimation such as a reliable last menstrual period date or an appropriate ultrasound; projected permanence in Bogota during the month following delivery; and willingness to participate expressed in a written informed consent. There was no age restriction for participants. However, for women under 18 years of age, an adult witness – most frequently a next of kin, was also asked to participate in the informed consent process. Exclusion criteria included: a clinical diagnosis of any systemic or gynaecological bacterial infection; use of systemic antibiotics during the week prior to admission; rupture of amniotic membranes or uncertainty of their integrity; or a cervical dilatation >7 cm. The trial protocol was approved by the Institutional Review Board of the Medical School of the Javeriana University and by the staff of the Clinical Epidemiology and Biostatistics Unit. Women willing to participate were offered a range of additional services during follow-up. These services were designed to improve outcome detection and adherence to the study. All women received a booklet that addressed questions frequently raised by women during labour and puerperium (30 days following delivery), and informed on early signs for maternal and neonatal infections[6]. The development of the booklet involved semi-structured interviews carried out by a trained nurse who would elicit the issues that worried women during the first day, first week and first month after delivery. The team that designed the booklet included graphic designers and a social communications specialist. The booklet was tested and printed prior to the beginning of the RCT. Participants were offered two programmed health care visits where their concerns could be discussed with a professional nurse. During the visits, the nurse examined the mother and the baby and assessed outcomes. Systematic telephone reminders for these visits were scheduled before the 1st and 4th week after delivery. Women received instructions on how to access a 24-hour paging service which allowed them to contact a health care provider to address any concerns, seek support, inform about problems, or get advice on issues such as emergency medical attention. This allowed retrieving relevant information of visits to other healthcare providers and contacting them to collect data. The local branch of La Leche League International, a volunteer organization delivering support and education on breastfeeding, offered regular free educational sessions for participants. All participants were offered subsidised screening for neonatal hypothyroidism; when this RCT was done, screening for thyroid disease was not mandatory nor covered by health maintenance organisations in Colombia.\n\nBODY.METHODS.ASSIGNMENT AND FOLLOW-UP PROCEDURES:\nRandomisation was done in blocks of 2 (20%), 4 (60%) and 6 (20%) using Ralloc® allocation software. Once the participant had completed the informed consent process, an opaque envelope with sequential numbering and instructions was opened. Women randomised to the intervention group received a 1 litre Travad® 2.5% sodium chloride solution enemas applied by a nurse assistant prior to been taken to the labour wards, where participants in both groups would thereafter receive the same care. During the first and third week after delivery, reminders to attend scheduled appointments at the outpatient primary care clinic were delivered by phone and mail. We used a standardised telephone survey to assess if participants had used any other health services or been diagnosed with any particular condition. Newborns were screened for hypothyroidism during the first scheduled visit when the mother agreed to it. Results for the screening tests were scheduled to be delivered at the second visit, but these were also couriered with an explanatory note if the appointment was missed. The screening scheme covered confirmation diagnostic tests, when necessary. The primary outcomes were the diagnosis of infections in newborns or women during the month following delivery. A neonatal outcome was positive if during the first month of life the child was prescribed systemic antibiotics. A neonatal outcome was also positive when the child was diagnosed with any of the following clinical conditions: ocular infection (purulent drainage in the eye after the sixth day of delivery), umbilical infection (foul smell with periumbilical erythema), skin infection (cellulitis or impetigo), lower or upper respiratory tract infection, intestinal infection, meningitis or sepsis. A puerperal outcome was positive when, during the first month after delivery, a health care provider diagnosed the women with any of the following: dehiscence of the episiorraphy suture, purulent effusion from the episiorraphy, urinary tract infection, pelvic inflammatory disease, or vulvovaginitis. The primary outcome of the study was an aggregated maternal and neonatal infection rate: either the mother or the newborn had an infectious outcome (combined infection rate) . A team member visited participating women and newborns in hospital on a daily basis. Throughout the trial, trained research assistants using standardised questionnaires, registered data from telephone calls, hospitalisations, follow-up visits, and any communications with the participants, their families, or their health care providers.\n\nBODY.METHODS.MASKING:\nMasking the use of enemas was unfeasible. However, we made efforts to conceal the intervention by not separating documents with information on the allocation from those outcome data collection, by training the team's supporting clinical team (professional nurse, family medicine residents, family medicine staff, and consulting dermatologist) to avoid enquiring in ways that would unmask the allocation. Health care providers in other settings, such as physicians at emergency wards, paediatricians and medics at outpatient clinics were unaware of the allocation and frequently of the specific objectives of the study. Except for the intervention, participants received the same health care, and data retrievers would remain unaware of individual allocations. Interventions remained coded for the analysis and the code was broken once the analysis was completed. Input between data at recruitment and allocation was done weeks before the collection of data on outcomes at follow up.\n\nBODY.METHODS.SAMPLE SIZE DETERMINATION:\nWe were unable to find reliable data on the incidence of baseline infection rates for puerperal women or newborns so we did a pilot study to have base data that would allow a good estimate of frequencies for sample size calculations. The pilot study, which included the first 44 participants of the control group, estimated the combined infection rate of puerperal women and newborns at 46 percent [7]. Using 5% significance and a 80% power, a sample of 394 participants distributed in two parallel groups was estimated to be required to detect a relative difference of 25% in combined infection rates of women and newborns, following the formulas provided by Duppont and Plummer[8]. Assuming 4% of the participants would be lost to follow-up, an estimated total sample of 410 women was required.\n\nBODY.METHODS.DATA MANAGEMENT AND ANALYSIS:\nThe database created in Epi-Info v 6.04 b was fed using double data entry and transferred to Stata 5.0© using Stata Transfer 4.0©. A Shapiro-Wilk test was used to determine if the distribution of continuous variables was normal. Non-normal distributions were transformed using a log transformation, and if the distribution was persistently non-normal, a Mann-Whitney test was used to compare groups. Bivariate analyses were done using the chi-square test or Fisher's exact test. Power calculations were done using specialized software developed at the Clinical Epidemiology Unit at the Javeriana University[9].\n\nBODY.RESULTS:\nDuring the twelve months recruitment period (Feb 1997–Feb 1998) 3170 women were admitted for delivery to the obstetric service. The caesarean section rate in the obstetrics service was 26% at the time. Of the 460 women interviewed for recruitment, 16 were non-eligible and 1 declined to participate. We randomised 443 women (see Figure 1), among which we had 12 protocol violations; 4 in the enema group and 8 in the control group. Nevertheless, these women were offered the care and benefits that all other participants had. Protocol violations included admission with ruptured amniotic membranes (5 women in the control group), infection at admission (1 in the control group, 2 in the enema group). Five women didn't fulfil inclusion criteria but were randomised (2 in the control group and 3 in the enema group). The analysis for the remaining women was done by group of allocation. Women who delivered by caesarean section were considered in the analysis. Data were not available to include in an 'intention to treat' analysis the 12 women excluded because of violations to the selection criteria (protocol violations). Follow up was completed by 87% of the participating women and 86% of newborns. Direct examination by a team member at one month follow up was carried out in 20% of women and 19% of newborns (P = 0.51 and P = 0.98 respectively, with similar distribution between groups); standardised telephone interviews with participants and healthcare providers allowed to assess outcomes from the remaining participants. Baseline characteristics were similar in both groups, suggesting that randomisation provided well-balanced and comparable groups (Table 1 [see additional file 2]). Labour duration times and other maternal outcomes were obtained from women's records after delivery and are presented in Table 2 [see Additional file 2]. Neonatal baseline data obtained shortly after delivery from newborns' records are summarised in Table 3 [see Additional file 2]. We found no statistically significant differences between groups for labour duration, delivery types, episiotomy rates, or prescription of antibiotics. Caesarean sections were done in 12% of women with no significant differences in rates between groups. No significant differences were found in the distribution between groups for newborns' \"Ballard\" score, birth weight, diagnosis of neonatal apnoea, or the administration of ocular and umbilical prophylaxis. Five newborns allocated to the control group and none in the treatment group developed respiratory tract infections, but this difference had no statistical significance. Two out of the five newborns who developed lower respiratory tract infections were delivered by caesarean section. The three newborns with omphalitis belonged to the intervention group, but again this difference was not statistically significant. Similarly, no significant differences were found for ophthalmic infection rates, skin infections, intestinal infections or the need for systemic antibiotics (Table 4 [see Additional file 2]). No statistically significant differences were found for any of the assessed outcomes in puerperal women. Pelvic infections affected 4% of women: one was diagnosed with myometrytis; five with endometritis; three had vulvovaginitis; and six had infected episiorraphy sutures. The frequency and severity of perineal tear was similar in the intervention and control group. No significant differences were found in the rates of suture dehiscence among the 372 women who had epysiorraphy (Table 5 [see Additional file 2]). Breast pain complaints were not categorised as an infectious outcome and affected 31% of women, with 79% of them suffering breast engorgement or nipple cracking and no significant difference between groups (P = 0.75). Summarised outcomes are provided in Table 6 [see Additional file 2]. Overall, one in five newborns had an infectious outcome, and rates were not statistically significant between groups. No significant differences were found for aggregated maternal infections, although the study may have been underpowered to rule out such differences; We found an 8% absolute risk difference and a broad, skewed confidence interval (see Table 6 [see Additional file 2]). The aggregated outcome of \"neonatal or puerperal infection\" during the 30-day follow-up was higher in the control group than in the intervention group. However, the 6% difference in absolute risk can be due to chance (P = 0.23). Infections affecting both child and mother in the same family were not significantly different (6/183 [3%] with enema v 5/191 [3%] with no enema; P = 0.39). We planned to assess the effect of enemas' on labour duration using multiple linear regression to adjust for parity. However the normality test of the variable was rejected and a Boxcox transformation (with a range between -2 and 2) did not provide an appropriate model. The residuals analysed through a robust regression had a non-normal distribution, so a non-parametric quintile regression was done, finding no significant differences of labour duration within study groups after adjusting for parity (P = 0.07).\n\nBODY.RESULTS.PARTICIPANT FLOW AND FOLLOW-UP:\nDescribed in Figure 1 [see Additional file 1].\n\nBODY.DISCUSSION:\nPuerperal and neonatal infections, although seldom life threatening, were very frequent in this study. Ophthalmic infections were the most frequent infections amongst newborns. Breast engorgement and nipple cracking were the most frequent maternal complaints during puerperium. Episiorraphy dehiscence was the most frequent infectious outcome in women. We were impressed by how frequent these outcomes were, and it is likely that these problems are being missed in studies with a shorter follow up, such as those that only follow women during hospitalization. It also suggests that the follow up strategy probably had a good sensitivity. High volume enemas used during the first stage of labour did not have a significant effect in the incidence of puerperal or neonatal infections, or labour duration. This RCT found no significant differences in puerperal or neonatal infection rates with enemas. No statistically significant effects were found when analysing women or newborns separately or when their outcomes were aggregated to analyse them as mother-newborn dyads. The RCT had a power in excess of 80% to find differences as big as 25% in the aggregated infection rates for women and newborns. However, the study may have been underpowered to detect differences for individual outcomes. This RCT had an estimated power of 56% to find differences in neonatal infections, and 61% power to detect puerperal infections. A higher rate of operative vaginal deliveries was found in the enema group, although it did not reach statistical significance. It is worth mentioning this, because operative vaginal deliveries may have an effect in puerperal infection rates. The use of an aggregated outcome helped to reduce sample size but it would have been ideal to have a sample size large enough to establish effects in newborns and puerperal women separately. Despite being practical, aggregating results has important limitations: if the maternal and neonatal outcomes have significantly different magnitudes or point out in different directions, aggregation will cancelled out or underestimate the differences. We didn't have resources to collect information to assess if the population of women admitted to the trial represented all eligible women. However, participation in the trial was apparently determined by the commitment of recruiters, not the participants' risk. The RCT did not evaluate women's preferences or known adverse effects of enemas, such as pain, discomfort, embarrassment, or diarrhoea. Since just one-fifth of the participants were personally examined by trained research assistants at the one-month assessment, measurements of these outcomes may have been imprecise and could potentially disguise existing differences, accounting for the lack of differences (risk of Type II error). Nevertheless, significant misrepresentations of outcomes grave enough as to require hospitalisation, dedicated care, or urgent consultations are unlikely with the follow up strategy we endorsed. Overall, participants and their families were helpful and willing to provide information; and we went to great efforts to use more than one information source and verify abnormal results in both women and neonates.\n\nBODY.CONCLUSION:\nPuerperal and neonatal infections had high incidence rates. Severe infections, such as myometritis and omphaylitis, were unusual. In this study enemas didn't significantly modify puerperal or neonatal infection rates. A dramatically larger study would be necessary to determine the effects, if any, of enemas on specific outcomes including life-threatening complications. Enemas cause discomfort, increase workload for health carers and marginally increase the cost of health care. At this time there is no good evidence supporting the routine use of enemas. It seems unlikely that the effect of enemas on the incidence of specific outcomes is large enough to outweigh the inconvenience or adverse effects associated to the routine use of enemas during labour. The data from this study combined from additional RCTs may help better understand the particular effects of enemas, guide policies and elucidate the role of enemas during labour.\n\nBODY.COMPETING INTERESTS:\nThe author(s) declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nLuis Gabriel Cuervo led the conception and design of the RCT, coordinated its implementation and development, data recollection, analysis and interpretation of data, and leads the writing of this manuscript. María del Pilar Bernal trained research assistants, collected and input data, helped with the day to day management, participated in the writing of this article, and has reviewed its different versions. Natalia Mendoza contributed to the development of data capturing templates, trained research assistants, collected and input data, and participated in the original writing of this article and has reviewed its different versions.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: \n\nBODY.SUPPLEMENTARY MATERIAL:\nAdditional File 1Participant flow and follow-up.Click here for file Additional File 2Characteristics of participants at admission. Maternal postpartum outcomes. Neonatal baseline data. Neonatal infectious outcomes. Maternal infectious outcomes. Grouped infectious outcomes.Click here for file\n\n**Question:** Compared to no enema what was the result of 1 litre saline enema on Episiorraphy dehiscence rates?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
248
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Short-term comparative study of high frequency chest wall oscillation and European airway clearance techniques in patients with cystic fibrosis\n\n ABSTRACT.BACKGROUND:\nHigh frequency chest wall oscillation (HFCWO) is standard treatment for airway clearance in the USA and has recently been introduced in the UK and Europe. There is little published research comparing HFCWO with airway clearance techniques (ACTs) frequently used in the UK and Europe. The aim of this study was to compare the short-term effects of HFCWO with usual ACTs in patients with cystic fibrosis hospitalised with an infective pulmonary exacerbation.\n\nABSTRACT.METHODS:\nA 4-day randomised crossover design was used. Patients received either HFCWO on days 1 and 3 and usual ACTs on days 2 and 4 or vice versa. Wet weight of sputum, spirometry and oxygen saturation were measured. Perceived efficacy, comfort, incidence of urinary leakage and preference were assessed. Data were analysed by mixed model analysis.\n\nABSTRACT.RESULTS:\n29 patients (72% male) of mean (SD) age 29.4 (8.4) years and mean (SD) forced expiratory volume in 1 s (FEV1) percentage predicted (FEV1%) 38 (16.7) completed the study. Significantly more sputum was expectorated during a single treatment session and over a 24 h period (mean difference 4.4 g and 6.9 g, respectively) with usual ACTs than with HFCWO (p<0.001). No statistically significant change in FEV1% or oxygen saturation was observed after either HFCWO or usual ACTs compared with baseline. 17 patients (55%) expressed a preference for their usual ACT.\n\nABSTRACT.CONCLUSIONS:\nDuring both a finite treatment period and over 24 h, less sputum was cleared using HFCWO than usual ACT. HFCWO does not appear to cause any adverse physiological effects and may influence adherence.\n\nBODY.INTRODUCTION:\nThe last four decades have seen improved survival in patients with cystic fibrosis (CF). The latest figures estimate the median life expectancy of individuals with CF born in 2000–3 to be approximately 40 years.1 Respiratory failure is the major cause of morbidity and mortality in those with CF.2 Accumulation of secretions in the CF airway precipitates chronic infection, causing a progressive deterioration in lung function and eventually respiratory failure and death.3 Airway clearance techniques (ACTs) are an essential component of the management of patients with CF and are considered standard care.4 There is a range of ACTs which augment the normal mucus clearance mechanisms of the lung to facilitate expectoration. These techniques generally aim to promote secretion clearance by altering airflow and mucus viscosity. Typically, high frequency chest wall oscillation (HFCWO) produces compression of the chest wall via an inflatable jacket linked to an air pulse generator. The generator delivers an intermittent flow of air into the jacket which rapidly compresses and releases the chest wall at a variety of frequencies. Consequently, an oscillation in airflow within the airways is achieved. HFCWO has been shown to enhance central and peripheral mucus clearance.5 A number of underlying mechanisms have been hypothesised including increased airflow-mucus interaction causing a reduction in viscolelasticity, production of an expiratory airflow bias which promotes a cephalad movement of mucus and the enhancement and stimulation of ciliary activity.6 7 Published short-term evidence has demonstrated increased sputum clearance and improved pulmonary function with HFCWO compared with no treatment.8 This and other studies have also compared HFCWO with alternative ACTs. Some have demonstrated increased sputum clearance with HFCWO compared with postural drainage and percussion (PD&P).9–11 Others found no significant difference in sputum clearance between HFCWO and PD&P,8 12 13 positive expiratory pressure (PEP),8 high frequency oral oscillation13 or intrapulmonary percussive ventilation.14 Furthermore, some of these studies found no differences in efficacy related to pulmonary function between HFCWO and PD&P,8 12 13 PEP,8 15 oscillating positive expiratory pressure (Flutter, manufactured by Axcan Scandipharm Inc, Birmingham, AL, USA)16 and high frequency oral oscillation.13 One study reported an improved outcome in forced expiratory volume in 1 s (FEV1) in the longer term using HFCWO compared with PD&P.17 Few trials have compared HFCWO with alternative ACTs which are commonly used in the UK and Europe by individuals with CF. Phillips et al18 compared HFCWO (using the Hayek Cuirass) with the active cycle of breathing techniques (ACBT) in hospitalised paediatric patients. Significantly more sputum was cleared with the ACBT. The authors concluded that HFCWO was not an effective airway clearance treatment for children with CF. It is difficult to compare this study directly with those above, as the Hayek Cuirass machine has a different operating mode to the inflatable vest system. A series of Cochrane systematic reviews have found that no one ACT is superior in terms of respiratory function and efficacy.19 Of a number of published studies on HFCWO, only two were deemed of sufficient quality to be included in these randomised control trial systematic reviews.8 12 HFCWO is widely used in the USA where it is considered standard care in CF.20 It has recently been introduced to the UK and Europe, where the mainstay of care for airway clearance in CF is the ACBT, autogenic drainage (AD) and other airway clearance regimens using small devices.4 In the USA these techniques and devices tend to be considered adjuncts, with PD&P and HFCWO remaining the most common ACTs.20 While there is a body of evidence which equates HFCWO and PD&P, there is a need for further trials to compare HFCWO with alternative ACTs to provide a more relevant evidence base for HFCWO in the UK and Europe. The aim of the present study was to compare the short-term effects of HFCWO with patients' usual ACTs in those with CF admitted to hospital with an acute exacerbation of pulmonary infection. The hypothesis was that HFCWO was superior to patients' usual ACTs.\n\nBODY.METHODS.STUDY PARTICIPANTS:\nAll patients admitted to hospital who met the entry criteria were invited to participate in the study. The inclusion criteria were a diagnosis of CF (established by genotype or sweat sodium >70 mmol/l or sweat chloride of >60 mmol/l), FEV1 ≥ 20% predicted, age ≥16 years and an infective pulmonary exacerbation as defined by Thornton et al.21 Exclusion criteria were current severe haemoptysis, rib fractures, pregnancy, inability to give consent and those whose usual ACT was HFCWO. Informed written consent was obtained for all patients and the study was approved by Brompton Harefield and National Heart and Lung Institute research ethics committee.\n\nBODY.METHODS.STUDY DESIGN:\nA randomised crossover design was used to compare HFCWO with patients' usual ACTs, which allowed within-patient variability to be controlled. Over four consecutive days, patients received either HFCWO therapy on days 1 and 3 and their normal ACT on days 2 and 4 or vice versa. Allocation to HFCWO or usual ACT on day 1 was determined using a computer-generated randomisation table.\n\nBODY.METHODS.PROTOCOLS:\nPatients performed their usual ACT or received HFCWO two times daily at the same time. Before starting the study, each patient's usual ACT was reviewed by an experienced senior respiratory physiotherapist. In addition, patients were familiarised with HFCWO (The Vest). This involved the patients using The Vest for a trial period the day before the start of the study, during which time they were given the opportunity to experience all three protocol frequencies at a variety of pressures. Each airway clearance treatment session lasted 30 min and was supervised by the same physiotherapist to ensure optimisation and standardisation of usual ACT and HFCWO performance. All nebulised and inhaled medications were taken before each treatment session in accordance with the patients' individual regimens.\n\nBODY.METHODS.HIGH FREQUENCY CHEST WALL OSCILLATION:\nThe following regimen was identified as current best practice following an in-depth review of the literature and discussion with clinical experts in the USA. Using The Vest Airway Clearance System Model 4 (Hill-Rom UK Ltd, Leicestershire, UK), each patient was fitted with an appropriately-sized, full torso, inflatable, disposable vest connected to the air pulse generator via two flexible tubes. Patients remained in an upright sitting position throughout the 30 min treatment session. HFCWO was applied for 8 min at each of three frequencies in sequence (10, 13 and 15 Hz) with each frequency followed by a 2 min rest period. The pulse pressure was set according to individual patient's reported comfort at all three frequency settings. During both the HFCWO and rest periods, patients were instructed to huff or cough as they felt necessary in order to expectorate loosened bronchial secretions.\n\nBODY.METHODS.USUAL ACT:\nUsual ACTs were in accordance with the guidelines of the International Physiotherapy Group for Cystic Fibrosis.22 Patients performed their usual ACT for 30 min, and for patients practising an assisted ACT, the physiotherapist provided percussion. Patients were allowed to perform combined ACTs where this was their usual practice. This reflected current international practice more accurately and recommendations that ACTs be adapted on an individual basis.23\n\nBODY.METHODS.OUTCOME MEASURES:\nThe primary outcome measure was wet weight of sputum expectorated during a treatment session. Patients were instructed to expectorate all sputum into a preweighed pot during and for 30 min following each treatment session. They were also instructed to collect sputum expectorated at all other times during each 24 h period. All sputum collected was weighed immediately following collection on weighing scales with an accuracy of 0.01 g (BL310; Sartorious UK Ltd, Epsom, UK). FEV1 was measured using a hand-held spirometer (2120; Vitalograph Ltd, Buckingham, UK) in accordance with internationally agreed standards.24 Measurements were taken immediately before and after a 30 min period following each treatment session. Data were analysed using Spirotrac IV Version 4.30 software (Vitalograph Ltd). Pulsed arterial oxygen saturation (SpO2) was measured transcutaneously at rest, for 5 min immediately before, 30 min during and 30 min immediately following each session. SpO2 was measured with a fingertip pulse oximeter (Konica-Minolta Pulsox-300i; Stowood Scientific Instruments, Oxford, UK). The data were analysed using Download 2001 Version 2.8.0 software (Stowood Scientific Instruments Ltd). The perceived efficacy and comfort of each ACT and the incidence of urinary leakage during treatment were measured using 10 cm visual analogue scales (VAS). Each day, after the last treatment session, patients completed three 10 cm VAS with reference to the ACT used that day. On the VAS used, 0 represented not at all effective/comfortable or no urinary leakage and 10 represented extremely effective/comfortable or a lot of urinary leakage. On the fourth and final day, participants were also asked to indicate which ACT they would prefer. An independent observer, blind to the daily method of airway clearance used, performed the spirometry, weighed the sputum samples and collected the 10 cm VAS throughout the study.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nA sample size calculation determined the number of patients required to test for superiority of HFCWO. This was based on a difference of 4 g of sputum between the usual ACT and HFCWO during a single treatment session. A square-root of within SEM of 4 g at the 5% significance level would require 24 patients to achieve 90% power. Data are presented as mean (SD), median (IQR) or n (%) as appropriate. Continuous variables were analysed using a mixed-effects linear regression model. This was to allow the results to be adjusted for a number of factors which are inherent to the design of a crossover trial. The order of treatment randomisation and the day and time of treatment were all entered into the model and their effect on the outcomes was tested. For this trial, the results were also adjusted for the method and position of treatment in the ACT session. In these models, patients were entered as random effects since it was not of interest to quantify the differences between individual patients, but it was important to account for the repeated measurements on each patient. The estimates of the fixed effect of ACT versus HFCWO are presented as mean (95% CI). A p value of 0.05 was taken to be statistically significant. All analyses were conducted using Stata 9.2 (StataCorp).\n\nBODY.RESULTS.PARTICIPANTS:\nFifty patients were invited to participate in the study, 20 declined, 29 patients completed the study and 1 patient was withdrawn due to a hypoglycaemic episode. Table 1 shows demographic and baseline characteristics of the patients who completed the study. Table 1 Patient demographics and baseline characteristics (n=29) Age (years) 29.4 (8.4) Male (%) 21 (72%) Height (cm) 171 (9) Weight (kg) 60 (11) BMI (kg/m 2 ) 20.4 (2.6) FEV 1 (l) 1.46 (0.72) FEV 1 % predicted 38 (16.7) SpO 2 (%) 94.3 (2.1) Data are presented as mean (SD) or n (%) as appropriate. BMI, body mass index; FEV 1 , forced expiratory volume in 1 s; SpO 2 , pulsed arterial oxygen saturation. Twenty-nine patients were treated with intravenous antibiotics as part of their medical management. All participants received two treatment sessions on each study day and all treatment sessions were 30 min in duration. The mean (SD) length of stay for patients was 14 (5) days and the mean day of entry to the study was day 8 (3) days.\n\nBODY.RESULTS.USUAL ACT:\nUsual ACTs included the ACBT with modified PD&P (41%; n=12) and with modified PD alone (7%; n=2), AD in sitting (28%; n=8) and with modified PD (7%; n=2), PEP (7%; n=2) and Flutter (10%; n=3).\n\nBODY.RESULTS.SPUTUM WEIGHT:\nThe wet weight of sputum expectorated with usual ACT compared with HFCWO is shown in table 2. The mean weight of sputum expectorated during a single treatment session and over a 24 h period was significantly greater with usual ACT than with HFCWO. The mean difference in wet weight of sputum expectorated during a treatment session was 4.4 g (p<0.001) and the mean difference in wet weight of sputum expectorated over a 24 h period was 6.9 g (p<0.001). These findings were not affected by order, time, day or position of treatment. Table 2 Wet weight of sputum expectorated: HFCWO compared with usual ACT Period of sputum collection Expectorated sputum wet weight (g) Usual ACT HFCWO Mean difference p Value Mean (SD) Median (IQR) Mean (SD) Median (IQR) Single treatment session 9.1 (7.9) 7.2 (3.0–14.2) 4.6 (4.1) 3.4 (1.5–6.7) 4.4 (3.5 to 5.4) <0.001 24 h (excluding treatment) * 22.4 (26.8) 12.9 (4.0–29.9) 24.9 (25.8) 15.3 (3.9–40.1) −1.5 (−4.6 to 1.6) 0.352 24 h (including treatment) 39.8 (36.3) 25.5 (14.0–57.1) 34.3 (30.7) 26.3 (12.1–46.0) 6.9 (3.1 to 10.8) <0.001 Data are presented as mean (SD) or (95% CI) or median (IQR) as appropriate. Data are adjusted for randomisation, day, time and position of treatment using a mixed effects linear regression model. * Of 116 24-h sputum samples collected, two were discarded as they were incomplete. ACT, airway clearance technique; HFCWO, high frequency chest wall oscillation. No statistically significant difference was observed in the amount of sputum expectorated when using HFCWO or usual ACT between treatments in a 24 h period.\n\nBODY.RESULTS.PHYSIOLOGICAL MEASURES:\nFEV1 and SpO2 measured before, during and after usual ACT and HFCWO treatment sessions are shown in table 3. Table 3 Forced expiratory volume in 1 s and pulsed arterial oxygen saturation at baseline, during and after treatment with usual airway clearance technique and HFCWO Usual ACT HFCWO Baseline During treatment 30 min after treatment Baseline During treatment 30 min after treatment FEV 1 % predicted 39.1 (16.9) NA 38.9 (17.1) 38.9 (16.8) NA 39.2 (16.7) SpO 2 (%) 94.4 (2.0) 94.4 (1.9) 93.9 (1.6) 94.5 (1.8) 95.0 (1.7) 94.3 (1.7) Data are presented as mean (SD). ACT, airway clearance technique; FEV 1 , forced expiratory volume in 1 s; HFCWO, high frequency chest wall oscillation; NA, not applicable; SpO 2 , pulsed arterial oxygen saturation. \n\nBODY.RESULTS.COMFORT, EFFICACY AND PREFERENCE:\nThe VAS scores for comfort, efficacy and urinary leakage during usual ACT compared with HFCWO are shown in table 4. No significant differences were observed in VAS scores for comfort or urinary leakage between HFCWO and usual ACT. Patients scored the efficacy of their usual ACT significantly higher than for HFCWO (mean difference 14 mm; p=0.002). This was not affected by the order or day of treatment. Of those patients who completed the study, 17 (55%) expressed a preference for their usual ACT over HFCWO. Preference was not predicted by the amount of sputum expectorated. Table 4 Comfort, efficacy and urinary leakage: HFCWO compared with usual ACT Self reported measure Visual analogue scale score (mm) Usual ACT HFCWO Mean difference p Value Comfort 69 (23) 70 (22) −1 (−9 to 7) 0.784 Efficacy 68 (21) 54 (26) 14 (6 to 23) 0.002 Urinary leakage 0 (1) 0 (1) −0.05 (−0.3 to 0.4) 0.791 Data are presented as mean (SD) or (95% CI) as appropriate. Data are adjusted for randomisation, day of treatment and time of treatment using a mixed effects linear regression model. ACT, airway clearance technique; HFCWO, high frequency chest wall oscillation. \n\nBODY.DISCUSSION:\nThere have been few published comparisons between HFCWO using a vest system with the ACTs of the ACBT and AD. This short-term study, carried out in individuals with CF admitted to hospital with an acute infective pulmonary exacerbation, showed that significantly more sputum was expectorated during a single treatment session and over a 24 h period using the patient's usual ACT than with HFCWO. In addition, slightly less sputum was expectorated at all other times (excluding treatment sessions) on usual ACT days compared with HFCWO, but this trend was not statistically significant. These findings were independent of order, time or day and position of treatment. Neither HFCWO nor any of the usual ACTs were associated with any adverse clinical events. A possible factor contributing to the difference in sputum clearance between HFCWO and usual ACT may have been the number and frequency of forced expiratory manoeuvres (FEMs) and the more gentle expiratory manoeuvres of the AD breath that were performed with the usual ACTs. Some studies have standardised the number of coughs and FEMs that patients performed; however, at the time of designing the protocol, the aim was to compare the regimens as currently practised internationally and the frequency of coughs and FEMs was neither standardised nor counted. In retrospect, it would have been of value to have counted the number of coughs and FEMs undertaken during each regimen, but it had not been anticipated that any differences between HFCWO and usual ACTs may be a consequence of the number of FEMs or AD breaths. Theoretically, during the three 8 min periods of HFCWO, fewer FEMs, coughs or AD breaths would be undertaken than during an equivalent period of the ACBT, AD, PEP or Flutter (all of which inherently include FEMs or AD breaths at regular intervals). This difference was supported by observations of the investigators. However, manual cough counts are subject to observer error. Objective cough monitoring using the Leicester Cough Monitor has only recently been validated and should be considered for use in further studies.25 Components of patient satisfaction include efficacy, comfort and convenience. Some studies have formally evaluated patient satisfaction and compliance. One study reported that 50% of subjects chose HFCWO compared with the Flutter, and efficacy was the most frequently cited reason for this choice.16 A later study reported that HFCWO was not preferred over PD&P and intrapulmonary percussive ventilation; furthermore, there was no significant correlation between treatment preference and sputum weight.14 The current study found that patients perceived the efficacy of HFCWO to be statistically significantly less than that of their usual ACT. However, nearly half (45%) of patients expressed a preference for HFCWO. Preference may have been affected by the novelty of a new treatment and it is unknown whether this would continue in the long term. There is no one recommended protocol for the application of HFCWO in the literature. Published studies describe differing numbers and duration of frequencies, length of treatment and airway clearance. Frequencies of 10, 13 and 15 Hz were chosen as it has been reported that maximum mucus transport occurs between 11 and 15 Hz with a peak at 13 Hz.5 6 In addition, the highest oscillated tidal volume flow (peak airflow) occurred between 10 and15 Hz in patients with CF.26 More recent research recommends an individual \"tuning\" method to identify optimum treatment frequencies. These have been shown to vary among individuals and the oscillation waveform,27 but it is unknown whether \"tuning\" increases efficacy. It is possible that a practice effect could have occurred as all patients were new to HFCWO. However, the protocol used in this study did not require the patient to perform any newly learnt physical technique. In addition, the statistical analysis ensured data were adjusted for day of treatment and found no effect. Alternatively, patients' familiarity with their usual ACT may also have had an effect on outcomes. This study was powered to detect a difference of 4 g of sputum expectorated during a single treatment session. Other studies have been based on a difference of 3–3.5 g, which is generally accepted as a clinically important difference.28 29 Wet weight sputum was felt to be an appropriate primary outcome measure in this short-term study in an acute environment. Previous work has found wet weight to be proportional to dry weight sputum.28 30 Emerging non-invasive means of measuring airway clearance may be more sensitive indicators in the future (eg, lung clearance index and electrical impedance tomography). Considering the cost benefit of HFCWO compared with other ACTs and the differing healthcare systems in the USA and the UK, it is unlikely that HFCWO will become the first choice ACT for most individuals in the UK. Further work needs to be undertaken to identify the place of HFCWO in Europe. Patient preference for a treatment regimen may positively influence adherence to treatment in the short term, and nearly half the patients who participated in this study preferred HFCWO to their usual ACT. HFCWO is a safe treatment that facilitates airway clearance in CF but, when compared with patients' usual ACTs, HFCWO led to the clearance of significantly less sputum during a single treatment session and over a 24 h period.\n\n**Question:** Compared to Usual airway clearance techniques what was the result of High frequency chest wall oscillation on Visual analogue scale scores for comfort?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
263
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Randomized Clinical Trial of Laparoscopic Versus Open Repair of the Perforated Peptic Ulcer: The LAMA Trial\n\n ABSTRACT.BACKGROUND:\nLaparoscopic surgery has become popular during the last decade, mainly because it is associated with fewer postoperative complications than the conventional open approach. It remains unclear, however, if this benefit is observed after laparoscopic correction of perforated peptic ulcer (PPU). The goal of the present study was to evaluate whether laparoscopic closure of a PPU is as safe as conventional open correction.\n\nABSTRACT.METHODS:\nThe study was based on a randomized controlled trial in which nine medical centers from the Netherlands participated. A total of 109 patients with symptoms of PPU and evidence of air under the diaphragm were scheduled to receive a PPU repair. After exclusion of 8 patients during the operation, outcomes were analyzed for laparotomy (n = 49) and for the laparoscopic procedure (n = 52).\n\nABSTRACT.RESULTS:\nOperating time in the laparoscopy group was significantly longer than in the open group (75 min versus 50 min). Differences regarding postoperative dosage of opiates and the visual analog scale (VAS) for pain scoring system were in favor of the laparoscopic procedure. The VAS score on postoperative days 1, 3, and 7 was significant lower (P < 0.05) in the laparoscopic group. Complications were equally distributed. Hospital stay was also comparable: 6.5 days in the laparoscopic group versus 8.0 days in the open group (P = 0.235).\n\nABSTRACT.CONCLUSIONS:\nLaparoscopic repair of PPU is a safe procedure compared with open repair. The results considering postoperative pain favor the laparoscopic procedure.\n\nBODY.INTRODUCTION:\nThe incidence of perforated peptic ulcer (PPU) has declined over the past several years because of the introduction of anti-ulcer medication and Helicobacter eradication therapy [1, 2]. Nevertheless the incidence and mortality of PPU is 5–10%. The mortality will increase up to 50% if the perforation exists for more than 24 h [3, 4]. There are several options for treatment of PPU, but the preferred treatment is surgery by upper abdominal laparotomy [5, 6]. Mouret et al. published the first results of laparoscopic repair in 1990 [7]. He concluded that it was a good method that probably reduced postoperative wound problems and adhesions. After the success of laparoscopic cholecystectomy and other laparoscopic procedures, it was thought that patients would have less pain and a shorter hospital stay after laparoscopic correction of PPU [8, 9]. Various studies have shown that laparoscopic suturing of the perforation is feasible, but there is still no proof of real benefits of laparoscopic correction [3, 6, 10–12]. Therefore we performed a multicenter randomized trial comparing open correction of PPU with laparoscopic repair.\n\nBODY.METHODS.PARTICIPANTS:\nPatients with symptoms of the clinical diagnosis of PPU were included in nine medical centers in the Netherlands participating in the LAMA (LAparoscopische MAagperforatie) trial between March 1999 and July 2005. Eligible patients were informed of the two surgical approaches and were invited to participate in the study. Exclusion criteria were the inability to read the Dutch language patient information booklet, inability to complete informed consent, prior upper abdominal surgery, and current pregnancy. The ethics committees of all participating institutions approved the trial.\n\nBODY.METHODS.RANDOMIZATION:\nSurgeons contacted the study coordinator after the patients had provided informed consent and randomization took place by opening a sealed envelope. The envelope randomization was based on a computer-generated list provided by the trial statistician.\n\nBODY.METHODS.SURGICAL PROCEDURE:\nAll patients received intravenous antibiotics prior to operation and were allocated for Helicobacter pylori eradication therapy according to established guidelines [13]. The open surgical procedure was performed through an upper abdominal midline incision. Closure of PPU was to be achieved by sutures alone or in combination with an omental patch. After repair of the defect cultures were drawn from the peritoneal fluid, after which the peritoneal cavity was lavaged. During lavage it was permissible to insufflate the stomach to test for leakage of the closed defect. No method was specified for closing the abdomen. Laparoscopic repair was performed with the patient and the team set up in the \"French\" position. Trocars were placed at the umbilicus (video scope) and on the left and right midclavicular line above the level of the umbilicus (instruments). If necessary a fourth trocar was placed in the subxiphoid space for lavage or retraction of the liver. Surgeons were free to use either 0° or 30° video scopes for the procedure. The rest of the procedure was identical to that described above for open repair. No method was specified for closing the trocar incisions.\n\nBODY.METHODS.POSTOPERATIVE FOLLOW-UP:\nPostoperative pain was scored by means of a visual analog scale (VAS) for pain on days 1, 3, 7, and 28 ranging from 0 (no pain) to 10 (severe pain). In addition, the days during which opiates were used by the patients were registered. All complications, minor and major, were monitored. The treating surgeons determined time of discharge on the basis of physical well-being, tolerance of a normal diet, and ability to use the stairs. For this reason, this was an unblinded trial. Postoperative hospital stay without correction for time spent in hospital as a result of non-medical reasons (inadequate care at home) was calculated. Patients were invited to attend the outpatient clinic at 4 weeks, 6 months, and one year postoperatively. They were asked to complete forms related to pain and use of analgesics.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData analysis was carried out according to the intention-to-treat principle as established in the trial protocol. Data were collected in a database, and statistical analyses were performed with the Statistical Package for Social Sciences for Windows (SPSS 15.0, SPSS Inc., Chicago, IL). A researcher blinded to the nature of the procedures performed all data analyses. The primary outcome of the trial was duration of hospital stay. The power analysis was performed on basis of a reduction in hospital stay by 1.5 days (10–8.5 days from admission) in favor of the laparoscopically treated group using a β of 0.80 and an α of 0.05. This resulted in a trial size of 50 patients per group. The Pearson chi-squared test was used to compare categorical variables, and the Mann-Whitney U-test was used to compare continuous variables as we could not assume normal distribution because of the relatively small numbers. In Tables 1–6 medians and interquartile ranges (IQR) are reported. All data were analyzed according to the intention-to-treat principle; i.e., patients remained in their assigned group even if during the procedure the surgeon judged the patient not to be suitable for the technique assigned or if conversion was required. Null hypotheses were tested two-sided and a P value of 0.05 or less was considered statistical significant.Table 1Baseline parametersLaparoscopic repairOpen repairP valuen = 52 n = 49 Male:female ratio1.3:11.9:1Median age (years) + IQR 66 (25.8)59 (29.5)0.185Median BMI (kg/m2) + IQR23 (4)22 (5)0.118Median duration of symptoms (h) + IQR11 (17)11 (19)0.948Median blood pressure systolic (mmHg) + IQR125 (38.5)130 (36.5)0.457Median blood pressure diastolic (mmHg) + IQR75 (25.5)75 (24.5)0.596Median heart rate (beats/min) + IQR 88 (34.0)92 (21)0.403Median body temperature (°C) + IQR 36.9 (0.92)36.8 (1.5)0.658Mannheim Peritonitis Index + IQR19.5 (8.25)16 (14)0.386Median white cell count (×109/l) + IQR 12.1 (8.9)12.1 (7.75)0.467Median ASA score + IQR 1.0 (1.0)1.5 (1.0)0.902IQR interquartile range, difference between 25th percentile and 75th percentile; BMI body mass indexASA American Society of Anesthesiologists Association score\n\nBODY.RESULTS.PATIENTS:\nA total of 109 patients were included in the trial based on a high suspicion of PPU (Fig. 1). Eight patients were excluded during operation because no gastric perforation was detected or a defect in other parts of the digestive tract was uncovered. Data for these patients were not collected and the patients were excluded from further analysis. The remaining 101 patients made up the study population; their baseline parameters are given in Table 1. Fifty-two patients were randomized for laparoscopic repair and 49 for open repair of the perforation. Forty patients were female. The mean age of the patients was 61 years. The BMI (body mass index) was equally distributed between the groups, with a median of 22.5. Patients in both groups had been suffering from symptoms for a mean duration of 11 h, and those in the laparoscopy group presented with a median Mannheim Peritonitis index [14] of 19.5, whereas those in the open group had a median Mannheim Peritonitis index of 16.Fig. 1Patient flow chart Thirty patients reported the use of non-steroidal anti-inflammatory drugs (NSAIDs; 17 laparoscopic versus 13 open), and 10 patients used proton pump inhibitors (6 laparoscopic versus 4 open). Patient history revealed gastric ulcer disease in 19 patients.\n\nBODY.RESULTS.INTRAOPERATIVE FINDINGS:\nThe discovered ulcer perforations were found to have a mean diameter of 10 mm, which did not differ between groups (Table 2). Location of the perforated ulcers was distributed equally between groups. Defects were located in the prepyloric region (n = 41), the postpyloric region (n = 34), and at the pylorus (n = 20). The median volume of lavage fluid used was 1,000 ml (range: 100–5,000 ml). The surgeon decided the amount of lavage used. There was no consensus on how much was necessary. Median blood loss did not differ between groups. Skin-to-skin time differed by 25 min, favoring open repair of PPU (Table 2).Table 2Intraoperative findingsLaparoscopic repairOpen repairP valuen = 52n = 49Median size of perforation (mm) + IQR10.0 (7.0)7.0 (6.0)0.379Number of patients with defect Pyloric812 Postpyloric2014 Prepyloric1922 Median volume of lavage (ml) + IQR1,000 (1,500)1,000 (1,425)1.000 Median bloodloss (ml) + IQR10.0 (40.0)10.0 (50.0)0.423 Skin to skin time (min) + IQR75 (47.2)50 (25.5)0.000\n\nBODY.RESULTS.INTRAOPERATIVE COMPLICATIONS:\nConversion to open surgery was required in four patients (8%). Reasons for conversion included the inability to visualize the ulcer defect because of bleeding (n = 1/52; 2%), inability to reach the defect because of perforation in the vicinity of the gastroduodenal ligament and because of a dorsal gastric ulcer (n = 2/52; 4%), and inability to find the perforation (n = 1/52; 2%).\n\nBODY.RESULTS.POSTOPERATIVE COMPLICATIONS:\nComplications were statistically equally distributed between the two groups (Table 3). There were 12 complications in 9 patients in the laparoscopic group and 24 complications in 15 patients in the open group. Mortality was 4% in the laparoscopic group and 8% in the open group. In the laparoscopic group death was caused by sepsis due to leakage at the repair site. In the open group 3 patients died because of pulmonary problems (ARDS, pneumonia), and 1 patient died after complications following a cerebrovascular accident (CVA) combined with respiratory insufficiency.Table 3Postoperative complicationsLaparoscopic repairOpen repairP valuen = 52n = 49Pneumonia21Respiratory insufficiency13ARDS1Cardiac problems22Sepsis31Leakage at repair site2Abscess3Ileus1Fascial dehiscence1Wound infection3Urinary tract infection2Incisional hernia1Cerebrovascular accident1Death24Total complications12240.061Total of patients with complications ≥19 (18%)15 (36%)\n\nBODY.RESULTS.DISCHARGE:\nTime to discharge was similar for the two groups, with a median difference of 1.5 days (Table 4). Nasogastric decompression could be stopped after 2–3 days in both groups (Table 4).Table 4Duration of hospital stay, nasogastric decompressionLaparoscopic repairOpen repairP valuen = 52n = 49Median hospital stay (days) + IQR6.5 (9.3)8.0 (7.3)0.235Median duration of nasogastric decompression (days) + IQR2.0 (3.0)3.0 (1.3)0.334\n\nBODY.RESULTS.PAIN:\nVisual analog pain scores were in favor of laparoscopic repair (Table 5; p < 0.005). Although the median duration of opiate use in the two groups was 1.0, the mean duration in the open group was found to be 0.6 days longer than in the laparoscopic group (Table 6).Table 5Postoperative painMedian VAS pain scoreMedian VAS pain scoreP valueLaparoscopic repairOpen repairDay 1 + IQR3.8 (3.0)5.15 (2.5)0.001Day 3 + IQR2.1 (2.5)3.0 (2.4)0.035Day 7 + IQR1.0 (2.0)1.85 (2.8)0.036Day 28 + IQR0.3 (0.7)0.0 (1.7)0.748Table 6Postoperative opiate usageOpiate requirementOpiate requirementP valueLaparoscopic repairOpen repairMedian duration (days) + IQR1.0 (1.25)1.0 (1.0)0.007Mean duration (days) ± SD1.0 ± 0.91.6 ± 0.90.007\n\nBODY.RESULTS.VAS APPEARANCE OF SCAR:\nThe VAS score for appearance of the scar left by the respective procedures (subjectively recorded in the same way as pain) differed by 2.3 points, favoring the laparoscopic procedure (7.7 vs. 5.4; P = 0.033)\n\nBODY.DISCUSSION:\nThe need for surgery for PPU has declined enormously in Europe and America with reported rates ranging from 50% to 80%, thanks to effective gastric acid-reducing medication [15]. For this reason, as well as because many surgeons prefer upper laparotomy, it took more time than expected to include 100 patients in our study. Reasons given by surgeons who prefer open repair were that it is a more familiar procedure and it can be completed faster than laparoscopy. It was also noted that patients often undergo operation at night, when the surgeon on call was not always laparoscopically trained. Other randomized trials have already shown the feasibility of laparoscopic repair of PPU [3, 4, 6, 10]. Only a few had more than 100 patients, and some emphasized results from subgroups of patients [8, 11, 12]. We did not subdivide our patients and included patients with risk factors for developing sepsis or conversion [10]. In eight of the original 109 patients (7%) it became evident during the operation that the patient had a diagnosis different from PPU. In the patients who were randomized for laparoscopy this discovery revealed the benefit of laparoscopy as a diagnostic procedure indicating either an upper or lower abdominoplasty or continuation of the laparoscopy [16]. Conversion rate in the laparoscopy group was 8% (4/52). This is much lower than that reported in literature, where conversion rates as high as 60% were found [3, 4, 6]. This maybe partially explained by the fact that only trained and experienced laparoscopic surgeons (those performing at least 50 laparoscopic procedures a year) participated in this trial, confirming the belief that this procedure should only be done by experienced surgeons [3–5]. Operating time was significantly longer in the laparoscopy group (75 min versus 50 min), which is comparable to reports in the literature [3, 10]. A possible explanation for the longer operative time is that laparoscopic suturing is more demanding [9, 17], especially if the edges of the perforation are infiltrated and friable. Sutures easily tear out and it is more difficult to take large bites and to tie knots properly. Use of a single-stitch method described by Siu et al. [18], fibrin glue, or a patch might solve this problem [12, 19]. Another reason for the increase in operating time is the irrigation procedure. Irrigating through a 5-mm or even a 10-mm trocar is time consuming, and suction of fluid decreases the volume of gas and reduces the pneumoperitoneum. There is no evidence that irrigation lowers the risk of sepsis [20], so it might only be necessary if there are food remnants in the abdomen; perhaps there is no need for it at all. One of the suspected risks of laparoscopic surgery is that of inducing sepsis by increasing bacterial translocation while establishing a pneumoperitoneum [6]. This danger could not be confirmed in our trial. Furthermore data suggest that there is a decrease in septic abdominal complications when laparosopic surgery is used [8]. Evidence already exists that laparoscopic correction of PPU causes less postoperative pain [6, 12, 17, 18]. The meta-analysis published by Lau [6] showed that eight out of ten studies showed a significant reduction in dosage of analgesics required in the laparoscopic group. Also, the three studies that had included VAS pain scores showed consistently lower pain scores, as was observed in our study as well. Whether this will lead to a better quality of life for patients, especially during the first weeks after surgery still needs to be analyzed. Although patients in our series who underwent laparoscopy had less postoperative pain, there was no difference in the length of hospital stay in our two groups. In fact, hospital stay overall in our patients was very long. This was most likely caused by the fact that many patients, especially the elderly, could not be discharged because of organizational reasons. Of the 101 patients, 41% were 70 years or older (24 in the laparoscopic group versus 17 in the open group). It appears that the age of PPU patients is increasing, and this will eventually represent a significant problem in the future [2, 3]. One benefit of the laparoscopic procedure not often mentioned in literature [6] is cosmetic outcome. Nowadays patients are aware of this benefit, and sometimes this is the reason why they demand laparoscopic surgery. In conclusion, the results of the LAMA trial confirm the results of other trials that laparoscopic correction of PPU is safe, feasible for the experienced laparoscopic surgeon, and causes less postoperative pain. Operating time was longer in the laparoscopic group and there was no difference in length of hospital stay or incidence of postoperative complications.\n\n**Question:** Compared to Conventional open approach what was the result of Laparoscopic surgery on Surgery duration?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
322
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Placebo what was the result of Budesonide/formoterol pMDI 320/9 μg on Mean FEV1 at 12 hours on the day of randomization?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
478
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Improved outcomes from the administration of progesterone for patients with acute severe traumatic brain injury: a randomized controlled trial\n\n ABSTRACT.BACKGROUND:\nSevere traumatic brain injury (TBI) has been increasing with greater incidence of injuries from traffic or sporting accidents. Although there are a number of animal models of TBI using progesterone for head injury, the effects of progesterone on neurologic outcome of acute TBI patients remain unclear. The aim of the present clinical study was to assess the longer-term efficacy of progesterone on the improvement in neurologic outcome of patients with acute severe TBI.\n\nABSTRACT.METHODS:\nA total of 159 patients who arrived within 8 hours of injury with a Glasgow Coma Score ≤ 8 were enrolled in the study. A prospective, randomized, placebo-controlled trial of progesterone was conducted in the Neurotrauma Center of our teaching hospital. The patients were randomized to receive either progesterone or placebo. The primary endpoint was the Glasgow Outcome Scale score 3 months after brain injury. Secondary efficacy endpoints included the modified Functional Independence Measure score and mortality. In a follow-up protocol at 6 months, the Glasgow Outcome Scale and the modified Functional Independence Measure scores were again determined.\n\nABSTRACT.RESULTS:\nOf the 159 patients randomized, 82 received progesterone and 77 received placebo. The demographic characteristics, the mechanism of injury, and the time of treatment were compared for the two groups. After 3 months and 6 months of treatment, the dichotomized Glasgow Outcome Scale score analysis exhibited more favorable outcomes among the patients who were given progesterone compared with the control individuals (P = 0.034 and P = 0.048, respectively). The modified Functional Independence Measure scores in the progesterone group were higher than those in the placebo group at both 3-month and 6-month follow-up (P < 0.05 and P < 0.01). The mortality rate of the progesterone group was significantly lower than that of the placebo group at 6-month follow-up (P < 0.05). The mean intracranial pressure values 72 hours and 7 days after injury were lower in the progesterone group than in the placebo group, but there was no statistical significance between the two groups (P > 0.05). Instances of complications and adverse events associated with the administration of progesterone were not found.\n\nABSTRACT.CONCLUSION:\nOur data suggest that acute severe TBI patients with administration of progesterone hold improved neurologic outcomes for up to 6 months. These results provide information important for further large and multicenter clinical trials on progesterone as a promising neuroprotective drug.\n\nABSTRACT.TRIAL REGISTRATION:\nACTRN12607000545460.\n\nBODY.INTRODUCTION:\nTraumatic brain injury (TBI) remains one of the leading causes of injury-related death and severe disability. The management of TBI currently includes preventing further neurological insults, managing the intracranial pressure (ICP), and surgical procedures. It is very important to search for clinically effective neuroprotective drugs to prevent secondary brain injury after TBI. In spite of many neuroprotective agents showing efficacy in experimental models of TBI, none has produced significant neuronal protection when tested in clinical trials [1,2]. Progesterone, a hormone, has steroidal, neuroactive and neurosteroidal action in the center neuronal system. Neuroprotective effects of progesterone have recently been shown in a variety of animal models, including ischemic and traumatic brain insult models [3-6]. Postinjury administration of progesterone in experimental models of head injury confers significant protection against TBI-induced cerebral edema and secondary neuronal death, promoting behavioral recovery [7,8]. Experimental evidence suggests that postinjury treatment with progesterone decreases brain edema, attenuates free radical damage, and reduces neuronal loss in TBI animal models [8-13]. Progesterone also reduces the inflammatory response and attenuates neurological abnormalities after ischemia and spinal cord injury [14-18]. In a recently published controlled study of progesterone, Wright and colleagues conducted a phase II, randomized, double-blind, placebo-controlled trial to assess the safety and benefit of administering progesterone to patients with acute TBI [19]. No serious adverse events were found in the 77 patients who received progesterone, and the patients with moderate TBI who received progesterone were more likely to have a moderate to good outcome than those were randomized to placebo at 30 days post injury. The 30-day mortality in the progesterone group was less than one-half that of the control group. This outcome suggests that progesterone causes no harms and may be a beneficial treatment for TBI [19]. Despite these potential advantages and the good safety profile of progesterone described in studies utilizing animals or humans as subjects, there is relatively little information available from assessing neuroprotective properties of progesterone in the patients with acute severe brain trauma. The effects of progesterone on neurological outcome of the TBI patients remain unclear. The purpose of the present pilot clinical study was to assess the longer-term efficacy of progesterone on improving the neurological outcome of patients with acute severe TBI.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nPatients with acute severe TBI and a Glasgow Coma Scale (GCS) score ≤ 8 after resuscitation and stabilization were entered into the study. Two hundred and thirty patients from the Neurotrauma Center of our teaching hospital were included. Male or female patients between the ages of 18 and 65 years were studied. The patients received progesterone within 8 hours after the documented time of injury. All patients admitted to the Neurotrauma Center, Clinical Medical College of Hangzhou between March 2004 and February 2007 were consecutively eligible for enrollment. We excluded patients who had received any investigational drugs 30 days prior to the enrollment, such as progesterone, estrogen and investigational compound, patients with severe anoxic intracerebral damage or brain death, and patients whose clinical condition was unstable (partial pressure of oxygen < 60 mmHg or a systolic blood pressure < 90 mmHg, or both). We also excluded pregnant patients and lactating female patients, and those for whom there was doubt whether the neurological status resulted from head trauma or acute or chronic spinal cord injury. The study was conducted in compliance with the clinical protocol approved by the Institutional Review Board and the ethical committees of Clinical Medical College of Hangzhou, according to Good Clinical Practice standards. Because of the nature of patients' injuries, subjects in this clinical study were incapable of granting informed consent. Investigators therefore obtained informed consent from the subject's legal guardian or health proxy before administering the drug. Given the urgent circumstances, we were unable to obtain permission from a legal guardian or health proxy within the stipulated time window for some patients (n = 53). Investigators therefore sought approval from the Institutional Review Board to use deferred consent. If the Institutional Review Board determined that these regulatory criteria were satisfied, the investigators were permitted to enroll subjects without consent. When the drug was administered without proxy consent, the Institutional Review Board was notified within 2 working days. We continued to try to contact the proxy consent after drug administration, and documented those attempts to the Institutional Review Board. Once contacted, the family or legally authorized representative was notified of the patient's enrollment and asked to provide written approval for the patient's continued participation. If attempts to contact proxy consent were unsuccessful, or if the patient died before the family could be contacted, we notified the Institutional Review Board and placed a full report in the patient's record and study file.\n\nBODY.MATERIALS AND METHODS.STANDARD CLINICAL MANAGEMENT:\nAfter head computerized tomography scanning, the patients were delivered to the neurosurgical intensive care unit of the teaching hospital immediately or following surgical evacuation of an intracranial hematoma. All patients received the standard treatment for management of severe TBI based on the guidelines for the management of severe head injury of the American Association of Neurologic Surgeons [20]. Particular emphasis was placed on the prevention and treatment of secondary insults, the avoidance of intracranial hypertension, maintenance of a normovolemic state as well as normothermia and normoglycemia, with ventilation to maintain the oxygen pressure at a minimum of 100 mmHg and the carbon dioxide pressure at approximately 35 mmHg.\n\nBODY.MATERIALS AND METHODS.RANDOMIZATION AND MEDICATION ADMINISTRATION:\nThe prospective, randomized, placebo-controlled, double-blind study was conducted in our neurosurgical intensive care unit. Subjects enrolled in the study were randomized to receive either progesterone (Tianjing Jinyao Pharmaceutical Co. Ltd, Tianjing, China) or matching placebo within 8 hours of the documented time of injury. Qualifying patients were randomly assigned in a 1:1 manner to receive the matching treatment with random numbers. Patients for the treatment group were given progesterone at 1.0 mg/kg via intramuscular injection and then once per 12 hours for 5 consecutive days. A single-dosage volume equivalent to 0.05 ml/kg was used in each subject. In a double-blind manner, progesterone and placebo were supplied via identical-looking solutions in identical glass vials with or without progesterone. The appearance, packaging and administration of placebo and progesterone injections were the same for the two groups. All patients, treating physicians, nursing staff, and pharmacists were blinded throughout the study period.\n\nBODY.MATERIALS AND METHODS.CLINICAL MEASUREMENTS:\nThe ICP was monitored continuously using ICP monitoring apparatus (CAMINO. MPM-1; Integra Co., San Diego, CA, USA). A computerized tomography scan was obtained in all patients at admission and this was categorized according to the modified Marshall computerized tomography scan classification: I, intracranial pathology not visible on the computerized tomography scan; II, cisterns present with shift ≤ 5 mm; lesions present, but no high-density or mixed-density lesions > 25 cm3, with bone fragments and foreign bodies; III, cisterns compressed or absent, shift ≤ 5 mm, with no high-density or mixed-density lesions > 25 cm3; IV, shift > 5 mm, with no high-density or mixed-density lesions >25 cm3; V, any surgically evacuated lesion; and VI, high-density or mixed-density lesions >25 cm3 without surgical evacuation. The patient's condition – body temperature, heart rate and respiratory rate, blood pressure, and pulse blood oxygen saturation – was monitored continuously at the bedside with monitoring apparatus (Hewlett-Packard, Palo Alto, CA, USA). Daily evaluations of neurologic status over the initial 14-day period were performed via the GCS score, adverse experiences, surgical procedures, and intracranial complications. Intake and output of fluids were also recorded. Laboratory tests including hematology, the coagulation profile and clinical chemistry were performed daily and then for 1 week after injury. A urine pregnancy test was performed at enrollment for female patients (as necessary).\n\nBODY.MATERIALS AND METHODS.NEUROLOGIC OUTCOME MEASUREMENTS:\nThe neurologic outcome was evaluated according to the Glasgow Outcome Scale (GOS) score, which contains five levels of outcome: good recovery, moderate disability, severe disability, vegetative survival, or death. For statistical analysis, GOS scores were dichotomized into favorable or unfavorable outcomes. Patients in the upper two GOS outcome groups (good recovery and moderate disability) were considered of favorable outcome, and patients in the other groups (severe disability, vegetative state, or death) were considered of unfavorable outcome. Secondary efficacy endpoints were the modified Functional Independence Measure (FIM) score and mortality. Based on previous reports [21,22], the modified FIM measurements of disability in three areas of activity (domains of self-care, motor function, and cognitive function) were chosen from the 18 items in the full FIM. Each of three items (expression, feeding, and locomotion) includes four possible levels of function ranging from total dependence (1) to independence (4). The total modified FIM scores therefore ranged from 3 to 12. The patients were assessed using the same measures both at 3 and 6 months in the follow-up protocol.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nDescriptive statistics, including proportions, means and standard deviations, were compiled for all demographic and outcome measures. Demographic and clinical data were analyzed using Fisher's exact test. The statistical analyses were conducted to assess the differences between the treatment group and the control group on specific variables. Statistical analysis was performed using contingency analysis (chi-squared) for categorical data and Student's t test for continuous data. P < 0.05 was considered statistically significant. SPSS 11.0 software package (SPSS Inc., Chicago IL, USA) was used for statistical analysis.\n\nBODY.RESULTS.PATIENTS:\nBetween March 2004 and February 2007, a total of 230 patients were screened in the present study. Of these, 159 patients meeting the protocol stipulation and condition were recruited and randomized to receive either progesterone (n = 82) or placebo (n = 77). Data were available for 154 patients (96%) at the 3-month follow-up and for 135 patients (84%) at the 6-month follow-up. Nineteen patients (11%) were lost to follow-up, three patients (1%) refused follow-up, and two patients (1%) withdrew from the trial. No subjects were enrolled in violation of the protocol stipulations (Figure 1). Figure 1Trial profile. The demographics of the progesterone and placebo groups are presented in Table 1. The cohorts were well balanced with no significant differences between the two groups. The medication history of patients, medication administration, and medical procedures were not significantly different among treatment groups. Table 1 Clinical and demographic characteristics between the two groups Admission characteristic Placebo (n = 77) Progesterone (n = 82) P value Males 57 (74) 58 (70) 0.64 Females 20 (25) 24 (29) 0.64 Mean (standard deviation) age (years) 31 (9) 30 (11) 0.52 Mean (standard deviation) time injury to administration (hours) 3.65 (1.46) 3.80 (2.03) 0.59 Mean (standard deviation) qualifying Glasgow Coma Scale score 6.1 (1.3) 6.0 (1.8) 0.68 Glasgow Coma Scale 3 to 5 20 (25) 22 (26) 0.90 Mechanism of injury Motor vehicle 62 (80) 63 (76) 0.57 Fall 8 (10) 10 (12) 0.71 Assault 4 (5) 7 (8) 0.40 Other 3 (3) 2 (2) 0.59 Surgical procedures 24 (31) 22 (26) 0.54 Pupillary response Bilaterally normal 26 (33) 26 (31) 0.78 Abnormal 51 (66) 56 (68) 0.78 Marshall computerized tomography scan classification I 0 0 II 9 (11) 7 (8) 0.50 III 22 (28) 28 (34) 0.44 IV 13 (16) 12 (14) 0.69 V 24 (31) 22 (26) 0.54 VI 9 (11) 13 (15) 0.44 Data presented as n (%) unless indicated otherwise. \n\nBODY.RESULTS.GLASGOW OUTCOME SCALE SCORES:\nThe 3-month and 6-month GOS scores between the progesterone and placebo groups are summarized in Table 2. There was a better recovery rate for the patients who were given progesterone than for those in the control group at 3-month follow-up (P = 0.044). A dichotomized analysis revealed significant differences in neurologic outcome between the treatment and control groups (Figure 2). The analysis using the dichotomization of GOS scores at 3 months post injury revealed a favorable outcome in 47% of the patients receiving progesterone and in 31% of the placebo group (P = 0.034). There was an unfavorable outcome in 53% of the patients receiving progesterone and in 70% of the placebo group (P = 0.022). At 6-month follow-up, the dichotomized GOS scores also showed a significant statistical difference between the two groups, similar to those 3 months after injury. The percentage of favorable outcome was 58% for the patients who were given progesterone and was 42% in the placebo group (P = 0.048). Forty-one percent of patients who were given progesterone and 57% of the placebo group exhibited an unfavorable outcome (P = 0.048). Table 2 Comparison of Glasgow Outcome Scale scores between the progesterone and placebo groups patients at 3-month and 6-month follow-up Glasgow Outcome Scale scores Progesterone (n = 82) Placebo (n = 77) 3 months Good recovery 21 (25) 10 (12) Moderate disability 18 (21) 14 (18) Severe disability 16 (19) 13 (16) Vegetative survival 13 (15) 16 (20) Death 15 (18) 25 (32) 6 months Good recovery 26 (31) 19 (24) Moderate disability 22 (26) 14 (18) Severe disability 9 (10) 11 (14) Vegetative survival 10 (12) 8 (10) Death 15 (18) 25 (32) Data presented as n (%). Figure 2Dichotomized Glasgow Outcome Scale scores for patients receiving either progesterone or placebo. There was a remarkably more favorable outcome among patients who were given progesterone compared with patients receiving placebo (P = 0.034) 3 months postinjury. At 6-month follow-up, the significant difference in the dichotomization of Glasgow Outcome Scale scores between the progesterone and placebo groups was similar to that after three-month injury (P = 0.048). Subgroup analysis for women also showed a significant difference in the percentage of favorable outcome between the two groups at 6-month follow-up (35% in the placebo group and 66% in the progesterone group, P = 0.036). The patients who were given progesterone in the group with GCS of 6 to 8 showed a more favorable outcome (43%) compared with the placebo group (28%) at 6-month follow-up (P = 0.044). There was no significant difference, however, in dichotomized outcomes in the group with GCS of 3 to 5 (P > 0.05).\n\nBODY.RESULTS.MODIFIED FUNCTIONAL INDEPENDENCE MEASURE SCORES:\nFigure 3 shows the modified FIM scores at 3-month and 6-month follow-up. There was a significant difference in the mean modified FIM score between two groups both at 3-month and 6-month follow-up. At the 3-month follow-up, the scores were 7.35 ± 1.89 for the placebo group and 8.02 ± 1.73 for the progesterone group (P < 0.05). Six months after injury, the placebo group showed a score of 8.95 ± 1.05 and the progesterone group presented 9.87 ± 1.17 (P < 0.01), suggesting good functional outcome in the patients treated with progesterone. Figure 3Modified Functional Independence Measure scores for patients receiving either progesterone or placebo. Modified Functional Independence Measure (FIM) scores at 3-month and 6-month follow-up from patients receiving either progesterone or placebo show that the scores in the progesterone group were significantly higher than those in the placebo group at both 3-month and 6-month follow-up. Data expressed as the mean ± standard deviation. Different from the placebo group: *P < 0.05, **P < 0.01.\n\nBODY.RESULTS.MORTALITY:\nDuring the 6 months of follow-up, a total of 40 patients (25%) died in the present study (37 patients died during their hospital stay). Seventy percent of deaths occurred within 1 week after trauma. Mortality was attributed to the heavy head injury in each case. The mortality rate in the progesterone treatment group was significantly lower at 6-month follow-up compared with the placebo group (18% versus 32%, P = 0.039).\n\nBODY.RESULTS.INTRACRANIAL PRESSURE:\nFigure 4 shows the ICP in the progesterone group patients and in the placebo group patients at 24 hours, 72 hours and 7 days after injury. The ICP was monitored continuously for 75 patients (47%), 40 in the progesterone group and 35 in the placebo group. The mean ICP shows no apparent difference at 24 hours after trauma between the two groups (progesterone group, 22.1 ± 4.3 mmHg versus placebo group, 23.2 ± 4.6 mmHg; P = 0.121). At 72 hours and 7 days after injury, the mean ICP of patients who were given progesterone was slightly lower than those of patients who received placebo, but the differences were not statistically significant (16.9 ± 3.8 mmHg and 14.8 ± 3.8 mmHg for progesterone-treated patients versus 18.2 ± 5.1 mmHg and 15.9 ± 4.1 mmHg for placebo-treated patients, respectively; P > 0.05). Figure 4Comparison of intracranial pressure between patients receiving either progesterone or placebo. The mean intracranial pressure between the progesterone and placebo group patients shows no significant differences 24 hours, 72 hours and 7 days after injury between the two groups (P > 0.05). Data expressed as the mean ± standard deviation.\n\nBODY.RESULTS.GLASGOW COMA SCALE SCORES AND CLINICAL MEASUREMENTS:\nThe mean GCS scores increased progressively in the two groups during the 14-day acute phase of the study, with no apparent differences among the treatment groups. Meanwhile, there was no obvious difference in average body temperature, heart and respiratory rates, blood pressure, pulse blood oxygen saturation, and laboratory testing between the progesterone and placebo groups.\n\nBODY.RESULTS.COMPLICATIONS AND ADVERSE EVENTS:\nProgesterone was well tolerated in the treated patients with acute severe TBI. No complication and adverse event associated with the administration of progesterone was found in this clinical study during the hospitalization periods.\n\nBODY.DISCUSSION:\nThe results of the present trial showed for the first time that progesterone administration had a longer-term efficacy on clinical outcomes in acute TBI patients. A significant increase in the proportion of patients with a favorable outcome in the progesterone group compared with the placebo group up to 6 months indicates the possibility of progesterone for treatment of acute TBI. Moreover, there were more surviving TBI patients in the treatment group than in the control group. Our results suggest the efficacy of progesterone in the treatment of acute severe TBI. Previous reports showed the evidence of efficacy in TBI animal models [8-14]. In the present study, the efficacy and safety of progesterone was confirmed in patients with acute severe TBI. Furthermore, our results using the modified FIM and GOS scores showed that progesterone administration remarkably enhanced functional recovery 6 months after injury and reduced the mortality of the patients with acute severe TBI (GCS = 6 to 8), although there was no statistical significance in the outcome improvement for GCS = 3 to 5 patients with and without progesterone treatment. The evidence of improved outcome for women patients also suggested, in part, a beneficial efficacy and feasibility of progesterone in women with TBI, in spite of the limited number of female patients in the trial. It is recognized that the pathophysiology of TBI is a multifactorial process involved in a complex and interwoven series of pathologic process following the onset of insult, such as increased extracellular glutamate concentrations, increased intracellular Ca2+, free radical overproduction and exacerbated inflammatory response. Medication targeted at a pathological single injury factor could therefore not sufficiently recover functional deficits following TBI. The ideal drugs should be able to block multiple cellular events leading to brain damage following TBI. Neuroprotective strategies currently focus on acting on only one of the mechanisms. Some efforts have been made, however, to combine agents or interventions to increase the probability of success in this setting [23,24]. Nevertheless, the use of a single pharmacologic agent or procedure to slow or block damaging chemicals that are released after brain injury is highly desirable. Progesterone has several features that make it an attractive potential drug candidate for TBI. First, progesterone could protect against brain damage via multiple mechanisms[13,15-18]. The pharmacokinetics of progesterone and its pattern of adverse reactions are well known since the drug has been safely used for a long time [25,26]. Second, with a wide therapeutic window of progesterone, a single bolus given up to 24 hours post injury may significantly reduce cerebral edema [7]. Third, progesterone may rapidly cross the blood–brain barrier and reach equilibrium with the plasma within 1 hour of administration [27-29]. Administration of progesterone soon after TBI would probably benefit the recovery of the patient. In the present double-blind trial, progesterone or placebo was dissolved in the same camellia oil and taken daily for 5 days by patients with acute TBI. Those patients administered progesterone experienced significant improvements in functioning outcome, indicating neuroprotective properties of progesterone in acute severe TBI. There was no adverse event after administration of progesterone and no further late toxicity up to 6 months in the trial. Goss and colleagues suggested that low and moderate doses of progesterone (4 to 8 mg/kg) were optimal for facilitating recovery of select behaviors, and that postinjury progesterone treatment permitted a wider dose range than preinjury treatment in rats with medial frontal cortical contusions [30]. In addition, 5 days of postinjury progesterone treatment are needed to reduce significantly the neuropathological and behavioral abnormalities found in a rodent model of TBI [13]. Wright and colleagues used intravenous progesterone at a dose of 0.71 mg/kg, followed by 0.5 mg/kg progesterone per 12 hours during the 3 following days, which appeared safe in the treatment of TBI patients [19]. In our study, the patients were received a single intramuscular injection of 1.0 mg/kg progesterone and the same dose per 12 hours for 5 consecutive days. The results in our trial showed that single higher-dose progesterone as protective therapy did not lead to any serious side effects. No obvious symptoms of hormone reaction were observed in our study. Accordingly, it can be anticipated that progesterone may be a promising treatment for severe TBI patients as it is inexpensive, widely available and has a long track record of safe use in humans to treat other diseases. The data in the present study provide very encouraging and favorable conditions that could lead to the assessment of GOS and FIM scores in TBI patients in a clinical trial. The GOS score, although useful, provides only a global assessment of function and dependence; it may not differentiate specific difference in cognitive function, motor function, or daily activities. The modified FIM score selects only three items from the 18-item score, and also distinguishes only four (as opposed to seven) levels of function. Subtle or complex deficiencies, particularly in cognitive function, may not have been identified in the dataset. A deficiency in using any one scale to measure outcome is that it is limited in its scope of measurement. The present clinical study was therefore designed to evaluated functional outcome according to the GOS and the modified FIM score. Intracranial hypertension has been considered an important factor affecting the outcome of the patients with acute severe TBI. Progesterone administration showed to decrease cerebral edema [9]. In an experimental study with male rats, there was a linear correlation between the serum progesterone level and brain edema after experimental TBI. The higher the serum progesterone level, the lower the cerebral edema [31]. In the current trial, however, no statistically significant difference was found in ICP monitoring between the groups given progesterone or placebo. It seems that progesterone treatment has little effect on directly reducing the ICP of patients with acute severe TBI. As a result of randomization, all of these parameters were homogeneous between the progesterone and placebo groups in our clinical trial. Nevertheless, some limitations are observed in the current study. The results could be influenced by a single-center trial and local perioperative standard of care. Therefore, it is necessary to use a sufficient power to assess progesterone's effects on neurologic outcomes. Our result of the significant differences in outcomes between two groups of patients emphasizes the potential value of using GOS and FIM to tailor progesterone administration and the likelihood of observing similar differences in a larger patient population; however, the possibility exists that a statistical error may have occurred because of an inadequate sample size. Further studies are needed to determine the mechanisms of action underlying the neurologic effect observed.\n\nBODY.CONCLUSION:\nThe present pilot study indicated that the use of progesterone may significantly improve neurologic outcome of patients suffering severe TBI up to 6 months after injury, providing a potential benefit to the treatment of acute severe TBI patients. Our results strongly support further large, multicenter clinical trials to examine the ways in which progesterone is achieving the profound neurologic effect and to decipher optimal conditions in which it can be used to lengthen the duration of and improve the degree of neuroprotection.\n\nBODY.KEY MESSAGES:\n• Many neuroprotective agents have been shown to be efficient on TBI in animal models, and there is no single agent that shows improvement in outcome for head injury patients. • A number of experimental models have suggested that administration of progesterone has a potential benefit for head injury. • The present clinical trial reveals that progesterone may be used as a potential safe drug for the treatment of acute severe head trauma patients.\n\nBODY.ABBREVIATIONS:\nFIM = Functional Independence Measure; GCS = Glasgow Coma Scale; GOS = Glasgow Outcome Scale; ICP = intracranial pressure; TBI = traumatic brain injury.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGMX and WQY participated in the trial design and were involved in the study analysis and summary. GMX and WMW obtained the data. GMX, JW, ZHL and WMW participated in the data analysis and interpretation of the results. All authors reviewed the final version.\n\n**Question:** Compared to placebo what was the result of progesterone on Instances of complications and adverse events?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
411
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pentobarbital versus thiopental in the treatment of refractory intracranial hypertension in patients with traumatic brain injury: a randomized controlled trial\n\n ABSTRACT.INTRODUCTION:\nExperimental research has demonstrated that the level of neuroprotection conferred by the various barbiturates is not equal. Until now no controlled studies have been conducted to compare their effectiveness, even though the Brain Trauma Foundation Guidelines recommend that such studies be undertaken. The objectives of the present study were to assess the effectiveness of pentobarbital and thiopental in terms of controlling refractory intracranial hypertension in patients with severe traumatic brain injury, and to evaluate the adverse effects of treatment.\n\nABSTRACT.METHODS:\nThis was a prospective, randomized, cohort study comparing two treatments: pentobarbital and thiopental. Patients who had suffered a severe traumatic brain injury (Glasgow Coma Scale score after resuscitation ≤ 8 points or neurological deterioration during the first week after trauma) and with refractory intracranial hypertension (intracranial pressure > 20 mmHg) first-tier measures, in accordance with the Brain Trauma Foundation Guidelines.\n\nABSTRACT.RESULTS:\nA total of 44 patients (22 in each group) were included over a 5-year period. There were no statistically significant differences in ' baseline characteristics, except for admission computed cranial tomography characteristics, using the Traumatic Coma Data Bank classification. Uncontrollable intracranial pressure occurred in 11 patients (50%) in the thiopental treatment group and in 18 patients (82%) in the pentobarbital group (P = 0.03). Under logistic regression analysis – undertaken in an effort to adjust for the cranial tomography characteristics, which were unfavourable for pentobarbital – thiopental was more effective than pentobarbital in terms of controlling intracranial pressure (odds ratio = 5.1, 95% confidence interval 1.2 to 21.9; P = 0.027). There were no significant differences between the two groups with respect to the incidence of arterial hypotension or infection.\n\nABSTRACT.CONCLUSIONS:\nThiopental appeared to be more effective than pentobarbital in controlling intracranial hypertension refractory to first-tier measures. These findings should be interpreted with caution because of the imbalance in cranial tomography characteristics and the different dosages employed in the two arms of the study. The incidence of adverse effects was similar in both groups.\n\nABSTRACT.TRIAL REGISTRATION:\n(Trial registration: US Clinical Trials registry NCT00622570.)\n\nBODY.INTRODUCTION:\nHigh dosages of barbiturates are used in patients with severe traumatic brain injury (TBI) who present with refractory intracranial hypertension (ICH) after medical and surgical treatment. This practice is recommended in the Brain Trauma Foundation (BTF) Guidelines, because this is the only second-level measure for which there is class II evidence that it can reduce intracranial pressure (ICP) [1]. Nevertheless, its effect on outcome is unproven [2], mainly because of severe medical complications. Within the family of barbiturates the oxibarbiturates and thiobarbiturates stand out, their primary representatives being pentobarbital and thiopental. Until now no controlled studies have been reported that compare the effectiveness of pentobarbital and thiopental in controlling ICH. At the experimental level, research has demonstrated that mechanisms of action and levels of neuroprotection differ between these agents [3-6]. For this reason, research is needed to compare the effectiveness of these two drugs in terms of controlling refractory ICH in patients with severe TBI. Based on various studies conducted in laboratory animals [3-6], suggesting that the neuroprotective capacity of thiopental is superior, our working hypothesis was that thiopental is more effective than pentobarbital in controlling ICP in patients with severe TBI, with a similar incidence of adverse side effects. In support of our work in the present study, the BTF Guidelines recommend that studies be undertaken to compare the effectiveness of the different barbiturates that are currently used in TBI patients [1].\n\nBODY.MATERIALS AND METHODS:\nWe conducted a prospective, randomized cohort study comparing two treatments: pentobarbital and thiopental. Our primary objective was to compare the effectiveness of these agents in controlling refractory ICH in patients with severe TBI. Secondary objectives were to compare the incidence of secondary effects, especially arterial hypotension, which was defined as the presence of mean arterial pressure (MAP) under 80 mmHg at any point during barbiturate therapy. This study was conducted at Son Dureta University Hospital (Palma de Mallorca, Spain) and was approved by the Ethics Committee of the Balearic Islands on 31 March 2002. It is registered with the US Clinical Trials Registry, with the number NCT00622570. In all cases, the patient's closest relative, legal representative, or guardian gave written informed consent for their inclusion in the study.\n\nBODY.MATERIALS AND METHODS.INCLUSION CRITERIA:\nPatients admitted to our intensive care unit (ICU) between May 2002 and July 2007 with a severe TBI (Glasgow Coma Scale [GCS] score after nonsurgical resuscitation ≤ 8) and presenting with refractory ICH (ICP > 20 mmHg), and who underwent first-level measures in accordance with the BTF Guidelines [7], were included. Refractory ICH was defined as follows: ICP 21 to 29 mmHg for 30 minutes or more, ICP of 30 to 39 mmHg for 15 minutes or more, or ICP greater than 40 mmHg for more than 1 minute, in the absence of external interventions. Included patients were required to be haemodynamically stable at the point of inclusion in the study; haemodynamic stability was defined as systolic blood pressure of 100 mmHg or greater.\n\nBODY.MATERIALS AND METHODS.EXCLUSION CRITERIA:\nWe did not include in the study patients who were younger than 15 or older than 76 years; patients with a GCS score of 3 upon admission and neurological signs of brain death (bilateral arreactive midryasis and loss of brainstem reflexes); and patients who were pregnant, had barbiturate allergy or intolerance, or had a history of severe cardiac ventricular dysfunction with an ejection fraction under 35%.\n\nBODY.MATERIALS AND METHODS.GENERAL THERAPEUTIC PROTOCOL:\nAll patients with severe TBI underwent cranial computed tomography (CT) upon admission and were categorized in accordance with the classification proposed by the Traumatic Coma Data Bank [8]. We also recorded findings of CTs conducted before inclusion of the patients in the study. The CT findings on inclusion were regarded to be the worst of the hospital stay; the prognostic value of such CT findings have been described by other authors [9]. CTs were independently reviewed and categorized by two neurosurgeons (JI and MB) who were unaware of the treatment group to which the patients had been assigned. In cases of disagreement between these investigators, a third investigator reviewed the CT images. All patients' ICP was monitored using an intraparenchymal Camino catheter (Integra Neurosciences, Plainsboro, NJ, USA). The ICP catheter was placed in the frontal region of the hemisphere with more radiological lesions on the CT. The systemic monitoring of these patients included invasive blood pressure, pulse oximetry, and a pulmonary artery thermodilution catheter. The ICP, MAP and cerebral perfusion pressure data were gathered on an hourly basis (one value every full hour) throughout the study using the Care Vue® clinical monitoring system (Phillips, Eindhoven, The Netherlands). The general treatment objectives in patients with severe TBI were to maintain MAP above 80 mmHg, ICP below 20 mmHg, and cerebral perfusion pressure above 60 mmHg. To achieve these objectives, we used liquids and/or vasoactive support with norepinephrine (noradrenaline). In patients with ICP greater than 20 mmHg, initial treatment included elevation of the head of the bed, keeping the neck straight, appropriate sedation, muscular paralysis, ventricular drainage (if the patient had visible ventricles on the CT), 20% mannitol (0.25 to 0.75 mg/kg), 7.5% hypertonic saline (2 ml/kg) and moderate hyperventilation (partial carbon dioxide tension of 30 to 35 mmHg). Neurosurgical interventions were undertaken when necessary to evacuate surgical lesions. This approach can be considered conventional treatment and is included in the BTF Guidelines as first-tier therapy [7]. Patients whose ICP remained high with conventional treatment were included in the study. Before randomization of the patient to a study group, we required that patient to have received maximal medical treatment (first-level measures). In addition, we required a CT to have been conducted within 24 hours before inclusion of the patient in the study; intravenous administration of 0.7 g/kg mannitol 1 hour before randomization; or a plasmatic osmolarity measurement above 320 mOsm/kg, in order to ensure that hyperosmolar therapy had been optimized before inclusion.\n\nBODY.MATERIALS AND METHODS.RANDOMISATION:\nRandomization was based on a computer-generated list that intercollated the two drugs. Allocation was done by the intensive care unit physician who was on duty, once the patient had been found to meet the inclusion criteria and none of the exclusion criteria. Data collection and patient follow up were conducted by the same investigator (JPB).\n\nBODY.MATERIALS AND METHODS.BLINDING OF TREATMENT GROUPS:\nThe study was not blinded because it was difficult for us to mask treatment; thiopental is liophylized for administration and pentobarbital is not.\n\nBODY.MATERIALS AND METHODS.ADMINISTRATION OF BARBITURATES AND MONITORING OF EFFECTS:\nPentobarbital was administered in accordance with the protocol established by Eisenberg and coworkers [10], using a loading dose of 10 mg/kg over 30 minutes followed by a continuous perfusion of 5 mg/kg per hour for 3 hours. This was followed by a maintenance dosage of 1 mg/kg per hour. Thiopental was administered in the form of a 2 mg/kg bolus administered over 20 seconds. If the ICP was not lowered to below 20 mmHg, then the protocol permitted a second bolus of 3 mg/kg, which could be readministered at 5 mg/kg if necessary to reduce persistently elevated ICP. The maintenance dosage was an infusion of thiopental at a rate of 3 mg/kg per hour. In both treatment groups, for cases in which the maintenance dosage did not achieve the reduction in ICP to below the 20 mmHg threshold, the maintenance dosage for both drugs could be increased by 1 mg/kg per hour, while looking for electroencephalographic burst suppression or even the flat pattern, in order to ensure that different doses of the two barbiturates were equipotent. Electroencephalography was conducted daily in a noncontinuous manner (Nicolet; Viasys Healthcare, Verona Road, Madison, WI, USA). Results were analyzed by an experienced neurologist who was blinded to the treatment of the patients. In those patients in whom barbiturate coma did not control ICP, we used decompressive craniotomy and/or external lumbar drainage, in accordance with the Munch criteria, as life-saving measures [11,12].\n\nBODY.MATERIALS AND METHODS.EFFECTIVENESS CRITERIA:\nAdequate response to treatment was defined as a decrease in ICP to below 20 mmHg, and maintenance below this threshold for at least 48 hours. To describe the ICP, we also followed the criteria previously employed by Stocchetti and coworkers [13]; the arithmetic mean of ICP data recorded during every 24-hour period, after filtering to exclude inaccurate readings, was calculated and expressed as 'mean ICP'. Three ICP blocks were considered for further analysis: less than 20 mmHg, 20 to 30 mmHg, and more than 30 mmHg. Uncontrollable ICP was defined as follows: ICP of 21 to 35 mmHg for 4 hours, ICP of 36 to 40 mmHg for 1 hour, or ICP above 41 mmHg for 5 minutes, in the absence of external interventions. We also defined as unresponsive to treatment those cases in which, because of refractory ICP, the patient needed some other treatment (surgery and/or lumbar drainage) and cases in which the patient progressed to brain death. Although it was not a main objective of the study, patients were evaluated 6 months after injury using the Glasgow Outcome Scale [14].\n\nBODY.MATERIALS AND METHODS.WITHDRAWAL OF TREATMENT:\nWhen ICP was controlled (<20 mmHg for 48 hours), we conducted a step-wise reduction in the barbiturate coma in steps that reduced the dosage by 50% every 24 hours until the infusion was suspended. In the event of ICP values rising to the study's inclusion values during the withdrawal of barbiturate treatment, the perfusion dosage was once again increased to achieve control of the patient's ICP.\n\nBODY.MATERIALS AND METHODS.SAMPLE SIZE:\nAccepting an α error of 0.05 and a β error of 0.2 in a bilateral hypothesis contrast, we estimated that 47 patients were needed in each group to detect differences of 30% or greater in the control of ICH. To calculate sample size, we assumed that the therapeutic response rate in the pentobarbital group would be 50%, excluding patients lost to follow up.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nQuantitative variables are expressed as the mean and standard deviation from the mean (SD) in normal distributions, and as median and interquartile range in cases that were not normally distributed. Qualitative variables are expressed as percentages, along with 95% confidence interval (CI). To determine whether variables followed a normal distribution, we used the Shapiro Wilks test. For the comparison of quantitative variables, Student's t-test was used if the variable followed a normal distribution. In other cases, we used the Mann-Whitney U-test. For the comparison of qualitative variables, we used χ2 or Fisher's exact test, as appropriate. Given that the randomization did not create groups that were similar in terms of types of intracranial lesions shown on the CT results, which is a prognostic variable that influences the effectiveness of barbiturate treatment in controlling ICP, we conducted a multivariate analysis using binary logistic regression, so that we would include the prognostic variables with the most plausible association with the dependent variable 'uncontrollable ICP'. These are variables such as age, GCS score at admission, and the worst CT obtained within 24 hours before inclusion of the patient in the study, as well as the type of barbiturate administered. To achieve this multivariate analysis, and given the small number of cases in each of the five groups in Marshall's classification, the CT data were grouped into focal and diffuse lesions. We also included in the model the minimum daily MAP during barbiturate treatment, given that in the second and third days of treatment there were statistically significant differences between the groups in the univariate analysis. The significant variables identified by the 'likelihood ratio' ≤ 0.1 test were used, along with those whose inclusion affected the calculation of the effect of the 'treatment group' variable. Both treatment groups were very similar in terms of other known prognostic variables, such as the presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them, so these were not included in the multivariate analysis. To analyze the variable ICP, which was determined on an hourly basis, we calculated the area under the curve (AUC) at 24, 48 and 72 hours, and also standardized by time [15]. For all comparisons, we considered statistical significance to have been achieved if the two-tailed α error probability was 5% or less (P ≤ 0.05). Statistical analyses were conducted using SPSS version 15 (SPSS Inc., Chicago, IL, USA).\n\nBODY.RESULTS:\nPreliminary results for the first 20 patients have already been published elsewhere [16]. From May 2002 to July 2007, 480 TBI patients were admitted to the intensive care unit of the Son Dureta University Hospital. Of these 480 patients, 71 (14.8%) presented with ICH refractory to first-level measures, of whom 44 were included in the study. The study was concluded prematurely because of the unexpected and slow inclusion rate; this could have modified some uncontrollable environmental factors that may affect results. The reasons for not including the remaining 27 refractory ICH cases were as follows: 13 patients were included in other studies, six were older than 76 years, five were admitted with nonreacting midriatic pupils and with clinical evidence of brain death, two presented with haemodynamic instability at the time of randomization, and one patient was transferred to a different hospital during the first 24 hours of admission, which excluded that patient from follow-up analysis. On average, the barbiturate coma was initiated in the thiopental group at 89 ± 15.5 hours after admission and in the pentobarbital group at 61 ± 14.3 hours after admission (P = 0.33). The baseline characteristics of the 44 patients included in the study, 22 randomized to each group, are presented in Table 1. There were no statistically significant differences with respect to epidemiological data, co-morbidity (data not shown) or lesions associated with TBI, although there were differences in the CT classification. Table 1 Baseline characteristics of patient population Characteristic Thiopental (n = 22) Pentobarbital (n = 22) P Sex (male; n) 19 19 1 Age (years) 26 (20 to 41) 32 (22 to 43) 0.45 ISS 25 (24 to 34) 25 (25 to 38) 0.77 SAPS II 42 (28 to 54) 43 (38 to 46) 0.95 APACHE II 23 (15 to 25) 20 (18 to 26) 0.27 APACHE III 60 (38 to 73) 52 (32 to 76) 0.41 Associated lesion (n) Thoracic injury 7 2 0.13 Abdominal injury 4 1 0.34 Extremities injury 9 5 0.20 Admission CT (n) Diffuse injury without brain swelling 12 4 0.046 Diffuse bilateral brain swelling 6 12 Diffuse unilateral brain swelling with midline shift 1 0 Any mass lesion > 25 ml 3 6 Age, ISS, SAPS II, APACHE II and APACHE III are expressed as median and interquartile range. APACHE, Acute Physiology and Chronic Health Evaluation; admission CT, admission computed tomography (according to the Traumatic Coma Data Bank); ISS, Injury Severity Score; SAPS, Simplified Acute Physiology. The summary of prognostic variables for the 44 patients is shown in Table 2. As in Table 1 the characteristics of the worst CT conducted before inclusion in the study differed between the two groups. Table 2 Prognostic variables of patient population Variable Thiopental (n = 22) Pentobarbital (n = 22) P Admission GCS score 6.5 (3.0 to 7.2) 7 (4.7 to 10.0) 0.38 Out-of-hospital hypoxia (n) 5 7 0.63 Out-of-hospital hypotension (n) 5 4 1 Pupillary reactivity (n) a One reacting 3 5 0.66 Both reacting b 12 14 Pre-enrolment CT (n) Diffuse injury without brain swelling 8 5 0.04 Diffuse bilateral brain swelling 1 8 Diffuse injury unilateral brain swelling with midline shift 5 1 Any mass lesion evacuated 7 5 Nonevacuated mass lesion 1 3 Admission GCS is expressed as median (interquartile range). a Pupillary reactivity at hospital admission. b Miotic pupils were considered as reactive. CT, computed tomography; GCS, Glasgow Coma Scale. \n\nBODY.RESULTS.EFFECTIVENESS CRITERION: CONTROL OF INTRACRANIAL PRESSURE:\nThe distribution of the ICP during the first 3 days of treatment, according to Stocchetti's criteria, is summarized in Table 3. The missing cases during these 3 days were due to brain deaths or to receipt of rescue treatment for uncontrollable ICP. Finally ICP was uncontrollable in 11 cases (50%) in the thiopental group and in 18 patients (82%) in the pentobarbital group (P = 0.03). In nonresponding patients, we chose to place a lumbar drainage in five, in three we opted for surgical treatment, and in three other patients we combined both treatments, drainage and surgery. Surgical decompression was conducted in four patients in the thiopental group and in two of the patients in the pentobarbital group. The number of hyperosmolar treatments administered (manitol and/or hypertonic saline) during the barbiturate coma was similar in both groups: 16.5 (8.0 to 24.2) in the thiopental group and 16.5 (3.0 to 21.5) in the pentobarbital group (P = 0.9). The mean ± SD duration of the barbiturate coma was 156 ± 60 hours for thiopental and 108 ± 100 hours for pentobarbital (P = 0.06). Seven (31.8%) patients presented an ICP rebound with thiopental and six (27.3%) with pentobarbital (P = 0.74) during treatment withdrawal. Table 3 Mean ICP recorded per day during the first 3 days of barbiturate coma Drug Day Mean ICP (n[%]) <20 mmHg 20 to 30 mmHg >30 mmHg Thiopental 1 10 46 11 50 1 5 2 15 71 4 19 2 10 3 12 63 6 32 1 5 Pentobarbital 1 9 41 8 36 5 23 2 8 38 9 43 4 19 3 6 43 8 57 0 0 Mean intracranial pressure (ICP) is the arithmetic mean of ICP data recorded during every 24-hour period, according to Stocchetti's criteria [ 13 ]. Data are presented as number of cases and as a percentage of the total number of cases each day. Figure 1 presents the AUC for ICP above 20 mmHg, standardized over time, as follows. The ICP value of AUC0–24 h was 458.00 mmHg·hour (95% CI = 421.84 to 494.16) in the thiopental group and 550.63 mmHg·hour (95% CI = 411.31 to 689.95) in the pentobarbital group. The AUC0–48 h was 913.18 mmHg·hour (95% CI = 814.08 to 1,012.27) in the thiopental group and 997.27 mmHg·hour (95% CI = 757.10 to 1,237.43) in the pentobarbital group. The AUC0–72 h in the thiopental group was 1,291.69 mmHg·hour (95% CI = 1,172.27 to 1,411.12) and 1,399.73 mmHg·hour (95% CI = 1,291.11 to 1,508.35) in the pentobarbital group. Standardized over time, the AUC per hour in the thiopental group was 23.90 mmHg (95% CI = 22.00 to 25.81) and in the pentobarbital group it was 29.39 mmHg (95% CI = 23.20 to 35.59). Figure 1AUC of ICP data. Presented are areas under the curve (AUCs) of the intracranial pressure (ICP) data, standardized by time, with a base value of 20 mmHg. Both treatment groups were similar in terms of known prognostic variables, such as presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them. Therefore, these were not included in the multivariate analysis. The logistic regression analysis showed that, after adjusting for the worst CT and the type of barbiturate used, thiopental was five times more likely than pentobarbital to control ICP (odds ratio = 5.1, 95% CI = 1.2 to 21.9; P = 0.027). The Hosmer-Lemeshow test indicated that the fit of the model was good (P = 0.799). The association of focal lesions in the pre-inclusion CT with ICP control was 3.6 times higher than that for the diffuse lesions. The relative risk for good control of ICP in the thiopental versus pentobarbital group was 2.26 for patients with focal lesions and 3.52 for those who presented with diffuse lesions. The other variables analyzed did not exhibit a significant relationship to ICP control, and did not modify the effect of the barbiturate treatment, including the third day minimum MAP, which was significantly different between the two treatments (data not shown).\n\nBODY.RESULTS.ADVERSE SIDE EFFECTS DURING THE BARBITURATE COMA:\nThe secondary effects during the barbiturate coma are presented in Table 4. In both groups almost all patients presented with at least one MAP measurement below 80 mmHg. There were no differences between groups with respect to the incidence of infections, Sepsis related Organ-Failure Assessment (SOFA) scores before initiation of treatment, or the maximum SOFA value [17] during the entire period of barbiturate coma. Table 4 Adverse events during barbiturate coma Adverse event Thiopental (n = 22) Pentobarbital (n = 22) P Hypotension a 21 20 1 Respiratory infection b 18 17 1 Urinary infection c 0 2 0.49 Positive blood culture 4 1 0.34 ICP catheter colonization 7 5 0.5 CNS infection (CSF) d 3 0 0.23 SOFA pre e 7 (4.5 to 9.5) 8.0 (5.5 to 9.0) 0.57 SOFA maximum f 11 (10 to 12) 11 (10 to 12) 0.94 a Hypotension is defined as detection of a medium arterial blood pressure below 80 mmHg at any time during barbiturate coma. b Respiratory infection: presence of a positive sputum culture. c Urinary infection: presence of a positive urine culture. d Central nervous system infection (CNS) infection (cerebrospinal fluid [CSF]): infection of the CNS with a positive culture in the CSF. e SOFA pre: value of the Sepsis related Organ-Failure Assessment (SOFA) score before the beginning of the barbiturate coma. f SOFA maximum: maximum value of the SOFA during the barbiturate coma, according the indication by Moreno and coworkers [ 16 ]. A thermodilution catheter was placed in 42 patients to facilitate haemodynamic control. The haemodynamic changes produced during the barbiturate coma are presented in Table 5. Differences of note include the minimum MAP, the pulmonary wedge pressure value, and the maximum norepinephrine dosage on days 2 and 3. Table 5 Systemic changes during barbiturate coma Parameter Pretreatment 1st day 2nd day 3rd day 4rd day Cardiac output (l/minute) a Thiopental 6.8 ± 1.4 6.4 ± 1.5 6.0 ± 1.4 6.7 ± 1.5 6.6 ± 1.8 Pentobarbital 7.4 ± 2.2 7.1 ± 1.9 6.5 ± 2.0 7 ± 1.4 6.1 ± 1.3 Cardiac index (l/minute per m 2 ) Thiopental 3.6 ± 0.6 3.4 ± 0.6 3.1 ± 0.6 3.6 ± 1.6 3.5 ± 0.9 Pentobarbital 3.8 ± 1.2 3.8 ± 0.8 3.4 ± 0.8 3.6 ± 0.7 3.2 ± 0.6 Peripheral venous resistance (dines/m 2 ) Thiopental 1,015 ± 325 1,022 ± 347 1,140 ± 429 1,089 ± 289 1,029 ± 253 Pentobarbital 952 ± 257 893 ± 210 1,003 ± 322 939 ± 261 914 ± 188 Pulmonary artery wedge pressure (mmHg) Thiopental 10.4 ± 4.5 9.6 ± 3.6 10.1 ± 4.1* 10.9 ± 4.6* 11.4 ± 3.5* Pentobarbital 11.6 ± 4.0 11.4 ± 3.1 12.8 ± 3.1 13.2 ± 2.1 13.9 ± 3.1 mBP (mmHg) b Thiopental 92 ± 11 75 ± 7 76 ± 9* 76 ± 6* 76 ± 8 Pentobarbital 94 ± 10 74 ± 1 68 ± 10 70 ± 1 70 ± 10 NAD (μg/kg per minute) c Thiopental 0.18 ± 0.33 0.28 ± 0.27 0.37 ± 0.3* 0.46 ± 0.39 0.56 ± 0.63 Pentobarbital 0.19 ± 0.18 0.55 ± 0.68 0.73 ± 0.69 0.60 ± 0.44 0.96 ± 0.79 P O 2 /Fi O 2 d Thiopental 284 ± 130 300 ± 139 293 ± 132 285 ± 138 254 ± 119 Pentobarbital 317 ± 127 304 ± 116 262 ± 125 211 ± 77 184 ± 92 Haemoglobin Thiopental 10.9 ± 1.6 10.7 ± 1.3 11 ± 1.2 10.8 ± 0.9 10.7 ± 1.4 Pentobarbital 10.6 ± 1.2 10.1 ± 1.0 10.4 ± 1.1 10.5 ± 1.1 10.2 ± 1.2 Temperature (°C) e Thiopental 35.8 ± 0.5 34.6 ± 1.3 34.6 ± 3.4 34.9 ± 1.0 34.9 ± 1.0 Pentobarbital 35.7 ± 1.0 34.6 ± 1.2 34.3 ± 1.3 34.4 ± 1.3 34.2 ± 1.1 a Cardiac output, cardiac index, peripheral venous resistance and pulmonary artery wedge pressure: the values are the mean values over 24 hours. b mBP: minimum value of the medium blood pressure during the day. c NAD: maximum dose of Noradrenaline bitartrate during the day. d P O 2 /Fis O 2 : ratio of partial oxygen tension to inspired fractional oxygen tension at 8:00 am. e Temperature: value of the minimum central temperature. * P < 0.05. \n\nBODY.RESULTS.SIX-MONTH OUTCOMES:\nIn the thiopental group, the neurological outcomes at 6 months (in accordance with Glasgow Outcome Scale score) were as follows: death in nine patients, vegetative state in two, severe disability in two, moderate disability in four and good recovery in four. In the pentobarbital group, the 6-month outcome was death in 16 patients, vegetative state in one, moderate disability in two and good recovery in two. In both groups one case was missing from the 6-month follow up analysis\n\nBODY.DISCUSSION:\nThe results of this study indicate that thiopental is five times more effective than pentobarbital in controlling refractory ICH. However, these findings must be interpreted with caution, given the small sample size and the fact that the study was unable to mask assignment to treatment groups. Barbiturate coma is at present the only therapy for which we have class II evidence, under BTF Guidelines [1], of efficacy in treating refractory ICH. Hence, it is perhaps the case that barbiturate coma is the most used second-level measure, with a usage frequency reported in the literature that varies from 13% to 56% [18,19]. Therefore, it is important to test the effectiveness of the various barbiturates available for controlling ICP refractory to first-level measures.\n\nBODY.DISCUSSION.DIFFERENCES BETWEEN OXIBARBITURATES AND THIOBARBITURATES:\nThe pharmacokinetic characteristics of thiopental and pentobarbital are different because their protein binding, distribution volume and clearance differ [20]. Nevertheless, the mean half life (thiopental 6 to 46 hours and pentobarbital 15 and 48 hours), which is the fundamental pharmacological parameter, differs little between the two agents. It therefore does not appear that these pharmacokinetic differences have clinical repercussions. One difference between these two groups of barbiturates is the presence of active metabolites. Thiopental has five metabolites, of which four are inactive and one (pentobarbital, or pentobarbitone) is active. Therefore, pentobarbital is an active metabolite of thiopental. This fact, along with the great intra-individual and inter-individual variability in the metabolism of these agents (caused by the existence of enzymatic induction phenomena associated with hepatic cytochrome P450), results in a weak correlation between serum concentrations and pharmacological effect. For this reason, monitoring this treatment with electroencephalography is strongly recommended. At the experimental level, various studies have compared these two medications. Hatano and coworkers [21], in a study conducted in a dog model, concluded that thiobarbiturates provoke cerebral vasoconstriction, which could help to redistribute cerebral blood flow toward ischaemic zones. Cole and colleagues [4] demonstrated that thiopental reduced the size of the ischaemic area more than did pentobarbital, even though both drugs achieved electroencephalographic burst suppression patterns. Shibuta [5] observed that thiopental, but not pentobarbital, was capable of limiting the cytotoxic damage caused by nitric oxide. Almaas and coworkers [3] observed that the different barbiturates had different neuroprotective effects with respect to oxygen and glucose deprivation in a model using human neurone cultures. Thiopental exhibited a neuroprotective effect at all the dosages studied, whereas pentobarbital was neuroprotective only at elevated dosages. Finally, in an in vitro study, Smith and colleagues [6] demonstrated that although thiopental provoked 96% inhibition of lipid peroxidation, pentobarbital had almost no effect. These experimental studies demonstrate that not all barbiturates are equal and that their neuroprotective capacity and effectiveness may differ [22]. Therefore, despite the unavoidable methodological limitations of the present study, we believe that our results may have clinical relevance.\n\nBODY.DISCUSSION.SECONDARY EFFECTS OF BARBITURATE COMA:\nThe most frequently detected secondary effect in our study, as might be expected, was arterial hypotension, which occurred in 21 patients in the thiopental group and 20 patients in the pentobarbital group. Although this incidence may be greater than that in previous studies [10], we attribute this to the definition of hypotension used (detection at any time in the barbiturate coma of MAP < 80 mmHg), which did not take the 'time' variable into account. For that reason, we collected data on other variables, such as maximum daily norepinephrine dosage and minimum daily MAP. Nearly all patients were monitored using a pulmonary artery thermodilution catheter, and arterial hypotension episodes were rigorously managed with fluid therapy and vasoactive drugs. We would note that the changes produced by pentobarbital at the cardiac and respiratory level were, in general terms, greater than those produced by thiopental. This is because (as shown in Table 5) cardiac output, cardiac index, and partial oxygen tension/fraction of inspired oxygen ratio exhibited greater changes during treatment with pentobarbital than with thiopental. This observation contrasts with the findings of previous experimental studies [23], in which it appeared that at high doses pentobarbital was safer and better tolerated than thiopental. Other complications (mostly infections) and the incidence of multiple organ dysfunction (identified using maximum SOFA) were similar in the two groups.\n\nBODY.DISCUSSION.LIMITATIONS OF THE STUDY:\nAs previously noted, this study has two important limitations. First, it was not a blinded study because the pentobarbital was not liophylized and thiopental was. Second, the sample size was small, so that small changes in the principal variable studied, namely ICP control, could significantly affect the statistical analysis. The classical view is that ICP response to barbiturates varies from 30% to 50%, and so it is possible that part of the difference found between drugs is due to poor response by the pentobarbital group as a result of any confounding bias. The randomization process is a potent mechanism that tends to eliminate bias by randomly distributing the values of all of the variables to the experimental groups. Nonetheless, the tool is not perfect and the groups frequently exhibit an imbalance in some confounding variable, especially when working with samples that are not very large. For this reason, in this study we used logistic regression analysis to eliminate any possible bias, and separate, independent analyses of the CT data were also conducted by two investigators who did not know the experimental group to which the patients belonged. Another limitation is that the dosages in the two groups were not the same. This leaves the possibility that the reason for the difference between agents that we identified is inadequate pentobarbital dose. Although in the two groups barbiturates were used with the end-point of ICP control, in this type of patient we also employ daily noncontinuous electroencephalographic monitoring. In this way, we believe that – despite different doses – the effect of the two barbiturates can be considered as equipotent because we looked for burst suppression or even the flat electroencephalographic pattern if the ICP was not controlled and the patients remained haemodynamically stable.\n\nBODY.CONCLUSION:\nIn this patient sample, thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-level measures, according to the BTF Guidelines. Nevertheless, these findings should be interpreted with caution because of the imbalance in CT characteristics and the different dosages employed in the two arms of the study. However, the present study is useful as a hypothesis testing exercise and will help to inform the design of future studies. These findings corroborate experimental evidence suggesting that there are differences in the neuroprotective mechanism between the two treatments, and this study may be a first step toward translating evidence from animal models to clinical disease. The incidence of secondary effects during treatment was similar between groups.\n\nBODY.KEY MESSAGES:\n• High doses of barbiturates are used in those patients with severe TBI who present with refractory ICH, and this recommendation is included in the BTF Guidelines. • Until now no controlled studies have been conducted to compare the effectiveness of pentobarbital and thiopental in controlling refractory ICH. Nevertheless, at the experimental level, research has demonstrated that their mechanisms and levels of neuroprotection differ. • Thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-tier measures, although these results should be interpreted with caution because of the imbalance in CT characteristics and other limitations of the study.\n\nBODY.ABBREVIATIONS:\nAUC: area under the curve; BTF: Brain Trauma Foundation; CI: confidence interval; ICH: intracranial hypertension; ICP: intracranial pressure; MAP: mean arterial pressure; SD: standard deviation; SOFA: Sepsis related Organ-Failure Assessment; TBI: traumatic brain injury.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nJPB was responsible for study design, acquisition of data, analysis and interpretation of data, and writing of the manuscript. JALP was responsible for acquisition of data and patient randomization. JH acquired data and conducted patient randomization. JMA acquired data and conducted patient randomization. JMR conducted statistical analyses. GF conducted statistical analyses. MB was responsible for designing the study and reviewing CT findings. JI was responsible for designing the study and reviewing CT findings. JI revised the article critically and gave final approval to the version to be published.\n\n**Question:** Compared to Pentobarbital what was the result of Thiopental on Hypotension?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
476
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Improved outcomes from the administration of progesterone for patients with acute severe traumatic brain injury: a randomized controlled trial\n\n ABSTRACT.BACKGROUND:\nSevere traumatic brain injury (TBI) has been increasing with greater incidence of injuries from traffic or sporting accidents. Although there are a number of animal models of TBI using progesterone for head injury, the effects of progesterone on neurologic outcome of acute TBI patients remain unclear. The aim of the present clinical study was to assess the longer-term efficacy of progesterone on the improvement in neurologic outcome of patients with acute severe TBI.\n\nABSTRACT.METHODS:\nA total of 159 patients who arrived within 8 hours of injury with a Glasgow Coma Score ≤ 8 were enrolled in the study. A prospective, randomized, placebo-controlled trial of progesterone was conducted in the Neurotrauma Center of our teaching hospital. The patients were randomized to receive either progesterone or placebo. The primary endpoint was the Glasgow Outcome Scale score 3 months after brain injury. Secondary efficacy endpoints included the modified Functional Independence Measure score and mortality. In a follow-up protocol at 6 months, the Glasgow Outcome Scale and the modified Functional Independence Measure scores were again determined.\n\nABSTRACT.RESULTS:\nOf the 159 patients randomized, 82 received progesterone and 77 received placebo. The demographic characteristics, the mechanism of injury, and the time of treatment were compared for the two groups. After 3 months and 6 months of treatment, the dichotomized Glasgow Outcome Scale score analysis exhibited more favorable outcomes among the patients who were given progesterone compared with the control individuals (P = 0.034 and P = 0.048, respectively). The modified Functional Independence Measure scores in the progesterone group were higher than those in the placebo group at both 3-month and 6-month follow-up (P < 0.05 and P < 0.01). The mortality rate of the progesterone group was significantly lower than that of the placebo group at 6-month follow-up (P < 0.05). The mean intracranial pressure values 72 hours and 7 days after injury were lower in the progesterone group than in the placebo group, but there was no statistical significance between the two groups (P > 0.05). Instances of complications and adverse events associated with the administration of progesterone were not found.\n\nABSTRACT.CONCLUSION:\nOur data suggest that acute severe TBI patients with administration of progesterone hold improved neurologic outcomes for up to 6 months. These results provide information important for further large and multicenter clinical trials on progesterone as a promising neuroprotective drug.\n\nABSTRACT.TRIAL REGISTRATION:\nACTRN12607000545460.\n\nBODY.INTRODUCTION:\nTraumatic brain injury (TBI) remains one of the leading causes of injury-related death and severe disability. The management of TBI currently includes preventing further neurological insults, managing the intracranial pressure (ICP), and surgical procedures. It is very important to search for clinically effective neuroprotective drugs to prevent secondary brain injury after TBI. In spite of many neuroprotective agents showing efficacy in experimental models of TBI, none has produced significant neuronal protection when tested in clinical trials [1,2]. Progesterone, a hormone, has steroidal, neuroactive and neurosteroidal action in the center neuronal system. Neuroprotective effects of progesterone have recently been shown in a variety of animal models, including ischemic and traumatic brain insult models [3-6]. Postinjury administration of progesterone in experimental models of head injury confers significant protection against TBI-induced cerebral edema and secondary neuronal death, promoting behavioral recovery [7,8]. Experimental evidence suggests that postinjury treatment with progesterone decreases brain edema, attenuates free radical damage, and reduces neuronal loss in TBI animal models [8-13]. Progesterone also reduces the inflammatory response and attenuates neurological abnormalities after ischemia and spinal cord injury [14-18]. In a recently published controlled study of progesterone, Wright and colleagues conducted a phase II, randomized, double-blind, placebo-controlled trial to assess the safety and benefit of administering progesterone to patients with acute TBI [19]. No serious adverse events were found in the 77 patients who received progesterone, and the patients with moderate TBI who received progesterone were more likely to have a moderate to good outcome than those were randomized to placebo at 30 days post injury. The 30-day mortality in the progesterone group was less than one-half that of the control group. This outcome suggests that progesterone causes no harms and may be a beneficial treatment for TBI [19]. Despite these potential advantages and the good safety profile of progesterone described in studies utilizing animals or humans as subjects, there is relatively little information available from assessing neuroprotective properties of progesterone in the patients with acute severe brain trauma. The effects of progesterone on neurological outcome of the TBI patients remain unclear. The purpose of the present pilot clinical study was to assess the longer-term efficacy of progesterone on improving the neurological outcome of patients with acute severe TBI.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nPatients with acute severe TBI and a Glasgow Coma Scale (GCS) score ≤ 8 after resuscitation and stabilization were entered into the study. Two hundred and thirty patients from the Neurotrauma Center of our teaching hospital were included. Male or female patients between the ages of 18 and 65 years were studied. The patients received progesterone within 8 hours after the documented time of injury. All patients admitted to the Neurotrauma Center, Clinical Medical College of Hangzhou between March 2004 and February 2007 were consecutively eligible for enrollment. We excluded patients who had received any investigational drugs 30 days prior to the enrollment, such as progesterone, estrogen and investigational compound, patients with severe anoxic intracerebral damage or brain death, and patients whose clinical condition was unstable (partial pressure of oxygen < 60 mmHg or a systolic blood pressure < 90 mmHg, or both). We also excluded pregnant patients and lactating female patients, and those for whom there was doubt whether the neurological status resulted from head trauma or acute or chronic spinal cord injury. The study was conducted in compliance with the clinical protocol approved by the Institutional Review Board and the ethical committees of Clinical Medical College of Hangzhou, according to Good Clinical Practice standards. Because of the nature of patients' injuries, subjects in this clinical study were incapable of granting informed consent. Investigators therefore obtained informed consent from the subject's legal guardian or health proxy before administering the drug. Given the urgent circumstances, we were unable to obtain permission from a legal guardian or health proxy within the stipulated time window for some patients (n = 53). Investigators therefore sought approval from the Institutional Review Board to use deferred consent. If the Institutional Review Board determined that these regulatory criteria were satisfied, the investigators were permitted to enroll subjects without consent. When the drug was administered without proxy consent, the Institutional Review Board was notified within 2 working days. We continued to try to contact the proxy consent after drug administration, and documented those attempts to the Institutional Review Board. Once contacted, the family or legally authorized representative was notified of the patient's enrollment and asked to provide written approval for the patient's continued participation. If attempts to contact proxy consent were unsuccessful, or if the patient died before the family could be contacted, we notified the Institutional Review Board and placed a full report in the patient's record and study file.\n\nBODY.MATERIALS AND METHODS.STANDARD CLINICAL MANAGEMENT:\nAfter head computerized tomography scanning, the patients were delivered to the neurosurgical intensive care unit of the teaching hospital immediately or following surgical evacuation of an intracranial hematoma. All patients received the standard treatment for management of severe TBI based on the guidelines for the management of severe head injury of the American Association of Neurologic Surgeons [20]. Particular emphasis was placed on the prevention and treatment of secondary insults, the avoidance of intracranial hypertension, maintenance of a normovolemic state as well as normothermia and normoglycemia, with ventilation to maintain the oxygen pressure at a minimum of 100 mmHg and the carbon dioxide pressure at approximately 35 mmHg.\n\nBODY.MATERIALS AND METHODS.RANDOMIZATION AND MEDICATION ADMINISTRATION:\nThe prospective, randomized, placebo-controlled, double-blind study was conducted in our neurosurgical intensive care unit. Subjects enrolled in the study were randomized to receive either progesterone (Tianjing Jinyao Pharmaceutical Co. Ltd, Tianjing, China) or matching placebo within 8 hours of the documented time of injury. Qualifying patients were randomly assigned in a 1:1 manner to receive the matching treatment with random numbers. Patients for the treatment group were given progesterone at 1.0 mg/kg via intramuscular injection and then once per 12 hours for 5 consecutive days. A single-dosage volume equivalent to 0.05 ml/kg was used in each subject. In a double-blind manner, progesterone and placebo were supplied via identical-looking solutions in identical glass vials with or without progesterone. The appearance, packaging and administration of placebo and progesterone injections were the same for the two groups. All patients, treating physicians, nursing staff, and pharmacists were blinded throughout the study period.\n\nBODY.MATERIALS AND METHODS.CLINICAL MEASUREMENTS:\nThe ICP was monitored continuously using ICP monitoring apparatus (CAMINO. MPM-1; Integra Co., San Diego, CA, USA). A computerized tomography scan was obtained in all patients at admission and this was categorized according to the modified Marshall computerized tomography scan classification: I, intracranial pathology not visible on the computerized tomography scan; II, cisterns present with shift ≤ 5 mm; lesions present, but no high-density or mixed-density lesions > 25 cm3, with bone fragments and foreign bodies; III, cisterns compressed or absent, shift ≤ 5 mm, with no high-density or mixed-density lesions > 25 cm3; IV, shift > 5 mm, with no high-density or mixed-density lesions >25 cm3; V, any surgically evacuated lesion; and VI, high-density or mixed-density lesions >25 cm3 without surgical evacuation. The patient's condition – body temperature, heart rate and respiratory rate, blood pressure, and pulse blood oxygen saturation – was monitored continuously at the bedside with monitoring apparatus (Hewlett-Packard, Palo Alto, CA, USA). Daily evaluations of neurologic status over the initial 14-day period were performed via the GCS score, adverse experiences, surgical procedures, and intracranial complications. Intake and output of fluids were also recorded. Laboratory tests including hematology, the coagulation profile and clinical chemistry were performed daily and then for 1 week after injury. A urine pregnancy test was performed at enrollment for female patients (as necessary).\n\nBODY.MATERIALS AND METHODS.NEUROLOGIC OUTCOME MEASUREMENTS:\nThe neurologic outcome was evaluated according to the Glasgow Outcome Scale (GOS) score, which contains five levels of outcome: good recovery, moderate disability, severe disability, vegetative survival, or death. For statistical analysis, GOS scores were dichotomized into favorable or unfavorable outcomes. Patients in the upper two GOS outcome groups (good recovery and moderate disability) were considered of favorable outcome, and patients in the other groups (severe disability, vegetative state, or death) were considered of unfavorable outcome. Secondary efficacy endpoints were the modified Functional Independence Measure (FIM) score and mortality. Based on previous reports [21,22], the modified FIM measurements of disability in three areas of activity (domains of self-care, motor function, and cognitive function) were chosen from the 18 items in the full FIM. Each of three items (expression, feeding, and locomotion) includes four possible levels of function ranging from total dependence (1) to independence (4). The total modified FIM scores therefore ranged from 3 to 12. The patients were assessed using the same measures both at 3 and 6 months in the follow-up protocol.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nDescriptive statistics, including proportions, means and standard deviations, were compiled for all demographic and outcome measures. Demographic and clinical data were analyzed using Fisher's exact test. The statistical analyses were conducted to assess the differences between the treatment group and the control group on specific variables. Statistical analysis was performed using contingency analysis (chi-squared) for categorical data and Student's t test for continuous data. P < 0.05 was considered statistically significant. SPSS 11.0 software package (SPSS Inc., Chicago IL, USA) was used for statistical analysis.\n\nBODY.RESULTS.PATIENTS:\nBetween March 2004 and February 2007, a total of 230 patients were screened in the present study. Of these, 159 patients meeting the protocol stipulation and condition were recruited and randomized to receive either progesterone (n = 82) or placebo (n = 77). Data were available for 154 patients (96%) at the 3-month follow-up and for 135 patients (84%) at the 6-month follow-up. Nineteen patients (11%) were lost to follow-up, three patients (1%) refused follow-up, and two patients (1%) withdrew from the trial. No subjects were enrolled in violation of the protocol stipulations (Figure 1). Figure 1Trial profile. The demographics of the progesterone and placebo groups are presented in Table 1. The cohorts were well balanced with no significant differences between the two groups. The medication history of patients, medication administration, and medical procedures were not significantly different among treatment groups. Table 1 Clinical and demographic characteristics between the two groups Admission characteristic Placebo (n = 77) Progesterone (n = 82) P value Males 57 (74) 58 (70) 0.64 Females 20 (25) 24 (29) 0.64 Mean (standard deviation) age (years) 31 (9) 30 (11) 0.52 Mean (standard deviation) time injury to administration (hours) 3.65 (1.46) 3.80 (2.03) 0.59 Mean (standard deviation) qualifying Glasgow Coma Scale score 6.1 (1.3) 6.0 (1.8) 0.68 Glasgow Coma Scale 3 to 5 20 (25) 22 (26) 0.90 Mechanism of injury Motor vehicle 62 (80) 63 (76) 0.57 Fall 8 (10) 10 (12) 0.71 Assault 4 (5) 7 (8) 0.40 Other 3 (3) 2 (2) 0.59 Surgical procedures 24 (31) 22 (26) 0.54 Pupillary response Bilaterally normal 26 (33) 26 (31) 0.78 Abnormal 51 (66) 56 (68) 0.78 Marshall computerized tomography scan classification I 0 0 II 9 (11) 7 (8) 0.50 III 22 (28) 28 (34) 0.44 IV 13 (16) 12 (14) 0.69 V 24 (31) 22 (26) 0.54 VI 9 (11) 13 (15) 0.44 Data presented as n (%) unless indicated otherwise. \n\nBODY.RESULTS.GLASGOW OUTCOME SCALE SCORES:\nThe 3-month and 6-month GOS scores between the progesterone and placebo groups are summarized in Table 2. There was a better recovery rate for the patients who were given progesterone than for those in the control group at 3-month follow-up (P = 0.044). A dichotomized analysis revealed significant differences in neurologic outcome between the treatment and control groups (Figure 2). The analysis using the dichotomization of GOS scores at 3 months post injury revealed a favorable outcome in 47% of the patients receiving progesterone and in 31% of the placebo group (P = 0.034). There was an unfavorable outcome in 53% of the patients receiving progesterone and in 70% of the placebo group (P = 0.022). At 6-month follow-up, the dichotomized GOS scores also showed a significant statistical difference between the two groups, similar to those 3 months after injury. The percentage of favorable outcome was 58% for the patients who were given progesterone and was 42% in the placebo group (P = 0.048). Forty-one percent of patients who were given progesterone and 57% of the placebo group exhibited an unfavorable outcome (P = 0.048). Table 2 Comparison of Glasgow Outcome Scale scores between the progesterone and placebo groups patients at 3-month and 6-month follow-up Glasgow Outcome Scale scores Progesterone (n = 82) Placebo (n = 77) 3 months Good recovery 21 (25) 10 (12) Moderate disability 18 (21) 14 (18) Severe disability 16 (19) 13 (16) Vegetative survival 13 (15) 16 (20) Death 15 (18) 25 (32) 6 months Good recovery 26 (31) 19 (24) Moderate disability 22 (26) 14 (18) Severe disability 9 (10) 11 (14) Vegetative survival 10 (12) 8 (10) Death 15 (18) 25 (32) Data presented as n (%). Figure 2Dichotomized Glasgow Outcome Scale scores for patients receiving either progesterone or placebo. There was a remarkably more favorable outcome among patients who were given progesterone compared with patients receiving placebo (P = 0.034) 3 months postinjury. At 6-month follow-up, the significant difference in the dichotomization of Glasgow Outcome Scale scores between the progesterone and placebo groups was similar to that after three-month injury (P = 0.048). Subgroup analysis for women also showed a significant difference in the percentage of favorable outcome between the two groups at 6-month follow-up (35% in the placebo group and 66% in the progesterone group, P = 0.036). The patients who were given progesterone in the group with GCS of 6 to 8 showed a more favorable outcome (43%) compared with the placebo group (28%) at 6-month follow-up (P = 0.044). There was no significant difference, however, in dichotomized outcomes in the group with GCS of 3 to 5 (P > 0.05).\n\nBODY.RESULTS.MODIFIED FUNCTIONAL INDEPENDENCE MEASURE SCORES:\nFigure 3 shows the modified FIM scores at 3-month and 6-month follow-up. There was a significant difference in the mean modified FIM score between two groups both at 3-month and 6-month follow-up. At the 3-month follow-up, the scores were 7.35 ± 1.89 for the placebo group and 8.02 ± 1.73 for the progesterone group (P < 0.05). Six months after injury, the placebo group showed a score of 8.95 ± 1.05 and the progesterone group presented 9.87 ± 1.17 (P < 0.01), suggesting good functional outcome in the patients treated with progesterone. Figure 3Modified Functional Independence Measure scores for patients receiving either progesterone or placebo. Modified Functional Independence Measure (FIM) scores at 3-month and 6-month follow-up from patients receiving either progesterone or placebo show that the scores in the progesterone group were significantly higher than those in the placebo group at both 3-month and 6-month follow-up. Data expressed as the mean ± standard deviation. Different from the placebo group: *P < 0.05, **P < 0.01.\n\nBODY.RESULTS.MORTALITY:\nDuring the 6 months of follow-up, a total of 40 patients (25%) died in the present study (37 patients died during their hospital stay). Seventy percent of deaths occurred within 1 week after trauma. Mortality was attributed to the heavy head injury in each case. The mortality rate in the progesterone treatment group was significantly lower at 6-month follow-up compared with the placebo group (18% versus 32%, P = 0.039).\n\nBODY.RESULTS.INTRACRANIAL PRESSURE:\nFigure 4 shows the ICP in the progesterone group patients and in the placebo group patients at 24 hours, 72 hours and 7 days after injury. The ICP was monitored continuously for 75 patients (47%), 40 in the progesterone group and 35 in the placebo group. The mean ICP shows no apparent difference at 24 hours after trauma between the two groups (progesterone group, 22.1 ± 4.3 mmHg versus placebo group, 23.2 ± 4.6 mmHg; P = 0.121). At 72 hours and 7 days after injury, the mean ICP of patients who were given progesterone was slightly lower than those of patients who received placebo, but the differences were not statistically significant (16.9 ± 3.8 mmHg and 14.8 ± 3.8 mmHg for progesterone-treated patients versus 18.2 ± 5.1 mmHg and 15.9 ± 4.1 mmHg for placebo-treated patients, respectively; P > 0.05). Figure 4Comparison of intracranial pressure between patients receiving either progesterone or placebo. The mean intracranial pressure between the progesterone and placebo group patients shows no significant differences 24 hours, 72 hours and 7 days after injury between the two groups (P > 0.05). Data expressed as the mean ± standard deviation.\n\nBODY.RESULTS.GLASGOW COMA SCALE SCORES AND CLINICAL MEASUREMENTS:\nThe mean GCS scores increased progressively in the two groups during the 14-day acute phase of the study, with no apparent differences among the treatment groups. Meanwhile, there was no obvious difference in average body temperature, heart and respiratory rates, blood pressure, pulse blood oxygen saturation, and laboratory testing between the progesterone and placebo groups.\n\nBODY.RESULTS.COMPLICATIONS AND ADVERSE EVENTS:\nProgesterone was well tolerated in the treated patients with acute severe TBI. No complication and adverse event associated with the administration of progesterone was found in this clinical study during the hospitalization periods.\n\nBODY.DISCUSSION:\nThe results of the present trial showed for the first time that progesterone administration had a longer-term efficacy on clinical outcomes in acute TBI patients. A significant increase in the proportion of patients with a favorable outcome in the progesterone group compared with the placebo group up to 6 months indicates the possibility of progesterone for treatment of acute TBI. Moreover, there were more surviving TBI patients in the treatment group than in the control group. Our results suggest the efficacy of progesterone in the treatment of acute severe TBI. Previous reports showed the evidence of efficacy in TBI animal models [8-14]. In the present study, the efficacy and safety of progesterone was confirmed in patients with acute severe TBI. Furthermore, our results using the modified FIM and GOS scores showed that progesterone administration remarkably enhanced functional recovery 6 months after injury and reduced the mortality of the patients with acute severe TBI (GCS = 6 to 8), although there was no statistical significance in the outcome improvement for GCS = 3 to 5 patients with and without progesterone treatment. The evidence of improved outcome for women patients also suggested, in part, a beneficial efficacy and feasibility of progesterone in women with TBI, in spite of the limited number of female patients in the trial. It is recognized that the pathophysiology of TBI is a multifactorial process involved in a complex and interwoven series of pathologic process following the onset of insult, such as increased extracellular glutamate concentrations, increased intracellular Ca2+, free radical overproduction and exacerbated inflammatory response. Medication targeted at a pathological single injury factor could therefore not sufficiently recover functional deficits following TBI. The ideal drugs should be able to block multiple cellular events leading to brain damage following TBI. Neuroprotective strategies currently focus on acting on only one of the mechanisms. Some efforts have been made, however, to combine agents or interventions to increase the probability of success in this setting [23,24]. Nevertheless, the use of a single pharmacologic agent or procedure to slow or block damaging chemicals that are released after brain injury is highly desirable. Progesterone has several features that make it an attractive potential drug candidate for TBI. First, progesterone could protect against brain damage via multiple mechanisms[13,15-18]. The pharmacokinetics of progesterone and its pattern of adverse reactions are well known since the drug has been safely used for a long time [25,26]. Second, with a wide therapeutic window of progesterone, a single bolus given up to 24 hours post injury may significantly reduce cerebral edema [7]. Third, progesterone may rapidly cross the blood–brain barrier and reach equilibrium with the plasma within 1 hour of administration [27-29]. Administration of progesterone soon after TBI would probably benefit the recovery of the patient. In the present double-blind trial, progesterone or placebo was dissolved in the same camellia oil and taken daily for 5 days by patients with acute TBI. Those patients administered progesterone experienced significant improvements in functioning outcome, indicating neuroprotective properties of progesterone in acute severe TBI. There was no adverse event after administration of progesterone and no further late toxicity up to 6 months in the trial. Goss and colleagues suggested that low and moderate doses of progesterone (4 to 8 mg/kg) were optimal for facilitating recovery of select behaviors, and that postinjury progesterone treatment permitted a wider dose range than preinjury treatment in rats with medial frontal cortical contusions [30]. In addition, 5 days of postinjury progesterone treatment are needed to reduce significantly the neuropathological and behavioral abnormalities found in a rodent model of TBI [13]. Wright and colleagues used intravenous progesterone at a dose of 0.71 mg/kg, followed by 0.5 mg/kg progesterone per 12 hours during the 3 following days, which appeared safe in the treatment of TBI patients [19]. In our study, the patients were received a single intramuscular injection of 1.0 mg/kg progesterone and the same dose per 12 hours for 5 consecutive days. The results in our trial showed that single higher-dose progesterone as protective therapy did not lead to any serious side effects. No obvious symptoms of hormone reaction were observed in our study. Accordingly, it can be anticipated that progesterone may be a promising treatment for severe TBI patients as it is inexpensive, widely available and has a long track record of safe use in humans to treat other diseases. The data in the present study provide very encouraging and favorable conditions that could lead to the assessment of GOS and FIM scores in TBI patients in a clinical trial. The GOS score, although useful, provides only a global assessment of function and dependence; it may not differentiate specific difference in cognitive function, motor function, or daily activities. The modified FIM score selects only three items from the 18-item score, and also distinguishes only four (as opposed to seven) levels of function. Subtle or complex deficiencies, particularly in cognitive function, may not have been identified in the dataset. A deficiency in using any one scale to measure outcome is that it is limited in its scope of measurement. The present clinical study was therefore designed to evaluated functional outcome according to the GOS and the modified FIM score. Intracranial hypertension has been considered an important factor affecting the outcome of the patients with acute severe TBI. Progesterone administration showed to decrease cerebral edema [9]. In an experimental study with male rats, there was a linear correlation between the serum progesterone level and brain edema after experimental TBI. The higher the serum progesterone level, the lower the cerebral edema [31]. In the current trial, however, no statistically significant difference was found in ICP monitoring between the groups given progesterone or placebo. It seems that progesterone treatment has little effect on directly reducing the ICP of patients with acute severe TBI. As a result of randomization, all of these parameters were homogeneous between the progesterone and placebo groups in our clinical trial. Nevertheless, some limitations are observed in the current study. The results could be influenced by a single-center trial and local perioperative standard of care. Therefore, it is necessary to use a sufficient power to assess progesterone's effects on neurologic outcomes. Our result of the significant differences in outcomes between two groups of patients emphasizes the potential value of using GOS and FIM to tailor progesterone administration and the likelihood of observing similar differences in a larger patient population; however, the possibility exists that a statistical error may have occurred because of an inadequate sample size. Further studies are needed to determine the mechanisms of action underlying the neurologic effect observed.\n\nBODY.CONCLUSION:\nThe present pilot study indicated that the use of progesterone may significantly improve neurologic outcome of patients suffering severe TBI up to 6 months after injury, providing a potential benefit to the treatment of acute severe TBI patients. Our results strongly support further large, multicenter clinical trials to examine the ways in which progesterone is achieving the profound neurologic effect and to decipher optimal conditions in which it can be used to lengthen the duration of and improve the degree of neuroprotection.\n\nBODY.KEY MESSAGES:\n• Many neuroprotective agents have been shown to be efficient on TBI in animal models, and there is no single agent that shows improvement in outcome for head injury patients. • A number of experimental models have suggested that administration of progesterone has a potential benefit for head injury. • The present clinical trial reveals that progesterone may be used as a potential safe drug for the treatment of acute severe head trauma patients.\n\nBODY.ABBREVIATIONS:\nFIM = Functional Independence Measure; GCS = Glasgow Coma Scale; GOS = Glasgow Outcome Scale; ICP = intracranial pressure; TBI = traumatic brain injury.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGMX and WQY participated in the trial design and were involved in the study analysis and summary. GMX and WMW obtained the data. GMX, JW, ZHL and WMW participated in the data analysis and interpretation of the results. All authors reviewed the final version.\n\n**Question:** Compared to placebo what was the result of progesterone on The mortality rate?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
437
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Treatment of osteoarthritis of the knee with a topical diclofenac solution: a randomised controlled, 6-week trial [ISRCTN53366886]\n\n ABSTRACT.BACKGROUND:\nTopical NSAIDs have been proven to relieve the symptoms of osteoarthritis (OA) in short-term studies (2 weeks). To justify its chronic use, efficacy of a topical NSAID over a longer term of study should be demonstrated. The efficacy and safety of a topical diclofenac solution over a 6-week treatment course in symptomatic primary OA of the knee was investigated.\n\nABSTRACT.METHODS:\n216 men and women, age 40–85 years, with radiologically confirmed primary OA of the knee and a flare of pain at baseline following discontinuation of prior therapy were enrolled into this double-blind study. Participants applied either a topical diclofenac solution (Pennsaid®) or vehicle control solution (carrier with no diclofenac); 40 drops 4 times daily directly to the painful knee(s), without massage, for 6 weeks. Pre-planned primary efficacy outcome measures included the core continuous variables pain relief and improved physical function measured by the Western Ontario and McMaster Universities (WOMAC) LK3.1 OA Index, and improved patient global assessment (PGA). Secondary efficacy measure was reduced stiffness. Safety assessments included adverse events and vital signs.\n\nABSTRACT.RESULTS:\nThe topical diclofenac group had a significantly greater mean change in score (final minus baseline) compared to the vehicle control group for pain (-5.2 vs. -3.3, p = 0.003), physical function (-13.4 vs. -6.9, p = 0.001), PGA (-1.3 vs. -0.7, p = 0.0001) and stiffness (-1.8 vs. -0.9, p = 0.002). The mean difference between treatment arms (95% confidence interval [CI]) was 1.9 (0.7 to 3.2), 6.5 (2.5 to 10.5), 0.6 (0.2 to 0.9), and 0.9 (0.3 to 1.4), respectively. Safety analyses showed that topical diclofenac caused skin irritation, mostly minor local skin dryness, in 42/107 (39%), leading to discontinuation of treatment in 5/107 (5%) participants.\n\nABSTRACT.CONCLUSION:\nThis topical diclofenac solution demonstrated relief at 6 weeks of the symptoms of primary osteoarthritis of the knee.\n\nBODY.BACKGROUND:\nMeta-analysis of previous trials of topical non-steroidal anti-inflammatory drugs (NSAIDs) concluded that they effectively treat the pain of acute soft tissue injuries [1] and chronic musculoskeletal conditions [2,3]. Current evidence-based recommendations for the management of osteoarthritis (OA) support the use of topical NSAIDs and rubefacients [4-6] as a therapeutic option potentially with fewer gastrointestinal risks than oral NSAIDs [7]. However, a recent critical meta-analysis concluded that claims of pain relief in OA by currently available topical NSAIDs are supported by only a limited number of randomised controlled trials of small size and brief duration, with no data demonstrating efficacy beyond 2 weeks [8]. In this report, we present the efficacy and safety results from a 6-week controlled trial using a newer topical diclofenac solution in knee OA. Effect size data and number-needed-to-treat (NNT) are presented, facilitating comparison with the previously reviewed data.\n\nBODY.METHODS.PARTICIPANTS AND INCLUSION/EXCLUSION CRITERIA:\nThis study was conducted from November 1999 to August 2000, at 17 medical centres across central Canada, following approval by a central ethics review board (Integrated Research Incorporated, Ethics Review Committee, Montreal, QC). Participants were recruited from the physician's private practice or the surrounding community. At the screening visit, after providing written, informed consent, each participant underwent a screening interview and was eligible to proceed to washout if all inclusion criteria and no exclusion criteria were met. Inclusion criteria specified men and non-pregnant women, age 40–85 years, with primary OA of at least one knee, and a flare of pain after withdrawal of prior therapy with either an oral NSAID or acetaminophen (used at least 3 days per week during the previous month). Primary OA was defined by deterioration and abrasion of articular cartilage (joint space narrowing) or formation of new bone (osteophytes) at the joint surface of the knee (medial tibio-femoral, lateral tibio-femoral or patello-femoral), demonstrated on a radiological examination carried out within the previous 3 months [9]. Pain was measured by the Western Ontario and McMaster Universities LK3.1 OA Index (WOMAC) 5-item pain subscale, each item scored on a 5-point Likert scale (none = 0; mild = 1; moderate = 2; severe = 3; extreme = 4) [10]. Pain was scored at the screening visit, following which prior therapy was withdrawn. The patient scored the pain again at the baseline visit. A flare was defined as an increase in total pain subscale score of at least 2 and at least 25%, with a baseline total pain score of at least 6 (out of a possible 20), and a score of ≥2 (out of a possible 4) on at least one of the 5 items in the WOMAC pain subscale. Participants were excluded if they had secondary arthritis related to systemic inflammatory arthritis (including rheumatoid arthritis, psoriatic arthritis, post-infectious arthritis and metabolic arthritis, traumatic arthritis or surgical joint replacement); corticosteroid use: (a) oral corticosteroid within the previous 14 days, or (b) intramuscular corticosteroid within 30 days, or (c) intra-articular corticosteroid into the study knee within 90 days, or (d) intra-articular corticosteroid into any other joint within 30 days, or (e) topical corticosteroid at the site of application within 14 days; intra-articular viscosupplementation (e.g., Synvisc®) into the study knee in the preceding 90 days; ongoing use of prohibited medication including NSAID, other oral analgesic, muscle relaxant, or low-dose antidepressant for any chronic pain management; ongoing use of glucosamine or chondroitin (unless used continuously for 90 days prior to study entry); sensitivity to diclofenac, acetylsalicylic acid (ASA) or any other NSAID, acetaminophen, dimethyl sulphoxide, propylene glycol, glycerine or ethanol; clinically-active renal, hepatic or peptic ulcer disease; history of alcohol or drug abuse; lactation; concomitant skin disease at the application site; current application for disability benefits on the basis of knee osteoarthritis; fibromyalgia; other painful or disabling condition affecting the knee; or participation in another investigational drug trial in the previous 30 days.\n\nBODY.METHODS.INTERVENTIONS:\nAt the baseline visit, all patients that met the final entry criterion of a flare of pain were randomly assigned to receive one of two treatments: (a) topical diclofenac solution (Pennsaid®; Dimethaid Research Inc.), consisting of 1.5% (w/w) diclofenac sodium in a patented carrier containing dimethyl sulphoxide (45.5%, w/w), propylene glycol, glycerine, ethanol and water, or (b) vehicle control solution, consisting of the complete carrier (including dimethyl sulphoxide, 45.5% w/w) but no diclofenac. Participants applied a dose of 40 drops of study solution (about 1.3 mL) to the affected knee 4 times daily for up to 6 weeks. The participant was instructed to apply 10 drops of solution to each side of the knee (front, back, medial and lateral) either dripped directly onto the knee or first into the hand, and then spread over the site without massage. Compliance was verified by weighing the solution bottles at each visit. If the other knee was painful at any time during the study, it was treated and evaluated for safety, but efficacy analysis was performed on only the study knee – the one with the greater baseline pain score (or the dominant knee if both had the same score). Consumption of acetaminophen (up to four 325-mg tablets per day) was permitted for residual knee or other body pain throughout the treatment period, but not during the washout period prior to baseline assessment or during the week prior to final assessment at week 6. ASA (≤ 325 mg/day) was permitted for cardiovascular prophylaxis.\n\nBODY.METHODS.OUTCOME MEASURES:\nThe primary outcome measures were defined as the change from baseline to final assessment of the study knee in the 3 core continuous variables [11] pain and physical function, assessed using the WOMAC subscales, and patient global assessment (PGA). There was no intermediate assessment of efficacy. The WOMAC is a validated questionnaire [12] consisting of 24 questions (5 on pain, 17 on physical function and 2 on stiffness), each scored on a 5-point Likert scale (see Participants). The PGA question asked: \"How has the osteoarthritis in your study joint been over the last 48 hours?\" and was scored on a Likert scale (very good = 0; good = 1; fair = 2; poor = 3; very poor = 4). This question focuses on the treated site, unlike a PGA in an oral NSAID trial that can probe the non-signal joints. Secondary measure was change in stiffness. Ancillary measures defined a posteriori were pain on walking – the first question of the WOMAC pain subscale (referred to as 'use-related pain' [13]) – and the following dichotomous variables: 50% improvement in pain [3]; final PGA score of \"good\" or \"very good\" [3]; and response based on OMERACT-OARSI responder criteria [14] (a responder is defined as a participant with ≥ 50% improvement in pain or function that was ≥ 20% of the scale, or ≥ 20% improvement in at least two of pain, function or PGA that was ≥ 10% of the scale).\n\nBODY.METHODS.SAFETY ANALYSES:\nSafety was assessed during all clinic visits (weeks 3 and 6) and telephone 'visits' (weeks 1 and 5). Safety variables included adverse events, application-site dermatological reactions and vital signs. Adverse events were identified using open-ended questions and a checklist covering common oral NSAID side effects. Dermatological assessment of the knee was based on a standard scale [15] and any abnormality was recorded as an adverse event. All adverse events were categorised according to Coding Symbols for Thesaurus of Adverse Reaction Terms (COSTART) [16]. Laboratory assessment was not done.\n\nBODY.METHODS.SAMPLE SIZE:\nBased on a power of 80% and a Type I error rate of α = 0.052-tailed, a sample size of 80 participants per group was required to detect an estimated important difference of 2 between the treatment arms, in the change in WOMAC pain dimension score from baseline to final (with standard deviation of 4.5). A total sample size of 200 participants (100 per treatment group) was specified in the protocol, which allowed for a non-evaluable rate of up to 20%.\n\nBODY.METHODS.RANDOMISATION AND BLINDING:\nThe study kits were prepared, labelled and numbered according to a computer-generated randomisation schedule created by an outside consultant using a randomly chosen block size of 4 or 6. They were shipped to the sites in multiples of complete blocks to ensure that a balanced number of participants was assigned to the two treatment arms within each site. As a participant qualified for study entry at the baseline visit, the investigator assigned him/her the next randomisation number in a sequential manner. The randomisation schedule was concealed from the investigators, their support staff, study participants and the sponsor's clinical research personnel, until final data lock. Except for the individual participant identification number on the label, the two study solutions were identical clear, colourless liquids packaged in opaque bottles.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nSafety analyses were performed on all randomised participants who received at least one dose of study solution. There was no imputation of missing safety data. Efficacy analyses were performed on an intent-to-treat (ITT) group, defined as a subset of all randomised participants who met critical inclusion criteria (primary OA by history, an abnormal radiological study, and any degree of knee pain), as per ICH guidelines [17]. For any missing efficacy data in the ITT analysis, the last observation was carried forward. A per-protocol group was defined based on stricter adherence to study conduct, including requirement for a moderate flare of knee pain (see Participants) and treatment continuing for at least 40 days. Baseline demographic and clinical variables were analysed by Chi-square or Student's t-Test. Adverse event incidence was analysed by Chi-square or Fisher's Exact Test. Continuous variables (WOMAC dimensions, PGA and pain on walking) were analysed by ANCOVA with baseline score as the covariate without adjustment for testing secondary/alternative objectives. The dichotomous variables were analysed by Chi-square test. All statistical tests were two-sided and were performed at the 0.05 level of significance.\n\nBODY.RESULTS.PARTICIPANT FLOW:\nTwo hundred and sixteen participants were randomised to treatment with either topical diclofenac (n = 107) or vehicle control (n = 109). All participants received their allocated intervention. More participants in the topical diclofenac group (86 [80%]) completed the entire 6-week treatment period compared to the vehicle control group (70 [64%]; p = 0.008). Discontinuation rate due to an adverse event was similar in both groups. Dropout due to lack of effect was lower for topical diclofenac (8 [7.5%]) compared to vehicle control (18 [16.5%]; p = 0.041). No participant was lost to follow-up (Fig. 1). Figure 1Flow of participants.\n\nBODY.RESULTS.BASELINE DEMOGRAPHIC AND CLINICAL CHARACTERISTICS:\nNo significant difference was found between treatment groups in baseline demographic and clinical characteristics (Table 1). The mean (SD) screening and baseline pain scores were 8.2 (2.7) and 13.0 (3.2) in the topical diclofenac group versus 8.3 (3.0) and 12.8 (3.1) in the vehicle control group (12.9 [3.2] overall). Most participants treated both knees, either from baseline or by the end of the trial. Table 1 Baseline demographic and clinical characteristics of treatment groups Topical diclofenac (n = 107) Vehicle control (n = 109) Age (years) 65.0 (11.0) 64.6 (10.9) Women, number (%) 56 (52.3) 66 (60.6) Race/ethnicity, number (%) White 88 (82.2) 91 (83.5) Black 8 (7.5) 3 (2.8) Oriental 3 (2.8) 2 (1.8) Other 8 (7.5) 13 (11.9) Weight (kg) 89.9 (18.1) 86.5 (17.3) Height (m) 1.65 (0.11) 1.65 (0.10) Heart rate (bpm) 74.1 (10.0) 74.3 (9.1) Systolic blood pressure (mm Hg) 137.6 (16.3) 133.6 (15.6) Diastolic blood pressure (mm Hg) 81.4 (9.1) 79.7 (8.7) Total x-ray score* 7.7 (5.4) 7.0 (5.0) Screening pain score 8.2 (2.7) 8.3 (3.0) Baseline † pain score 13.0 (3.2) 12.8 (3.1) Baseline † physical function score 40.7 (11.9) 40.4 (11.2) Baseline † stiffness score 5.2 (1.5) 5.2 (1.5) Patient global assessment score‡ 3.1 (0.8) 3.2 (0.8) Participants treating two knees at baseline, number (%) 64 (59.8) 70 (64.2) Participants treating two knees at final, number (%) 84 (78.5) 89 (81.7) Data are presented as mean (SD) unless otherwise indicated. *Total score of joint space narrowing, marginal osteophytes formation and subchondrial sclerosis for each knee compartment (medial, lateral, patello-femoral); maximum score possible was 27. †After washout of prior therapy; pain scale ranged from 0 (no pain) to 20 (extreme pain); physical function scale ranged from 0 (no difficulty) to 68 (extreme difficulty); stiffness scale ranged from 0 (no stiffness) to 8 (extreme stiffness). ‡Patient global assessment was measured using a Likert scale, ranging from 0 (very good) to 4 (very poor). Mean (SD) duration of treatment in the topical diclofenac group was 38.2 (9.9) days versus 34.4 (12.5) days in the vehicle control group (p = 0.013). Compliance with the dosing regime was 83.1 % and 84.5% for the topical diclofenac and vehicle control groups, respectively. No significant difference was noted in the mean (SD) consumption of rescue acetaminophen tablets per day between the topical diclofenac (0.9 [0.9]) and vehicle control groups (1.1 [1.0]; p = 0.079).\n\nBODY.RESULTS.EFFICACY ANALYSES:\nFour of 216 randomized participants were not included in the ITT analysis group because they violated major entry criteria: 2 participants lacked radiological confirmation of OA (no radiological examination for one participant and a normal examination for the other), and 2 participants had secondary OA (related to osteochondroma). Inclusion of these participants yielded the same results in a subsequent re-analysis (data not shown).\n\nBODY.RESULTS.EFFICACY ANALYSES.PLANNED ANALYSES:\nThere was a significantly greater improvement in score with topical diclofenac compared to vehicle control (Table 2) for pain (-5.2 vs. -3.3; p = 0.003,), physical function (-13.4 vs. -6.9; p = 0.001), PGA (-1.3 vs. -0.7; p = 0.0001) and stiffness (-1.8 vs. -0. 9; p = 0.002) Analysis of the per protocol group of 128 participants confirmed the statistical superiority of topical diclofenac over vehicle control for the primary and secondary outcome measures (p < 0.01; data not shown). Table 2 Efficacy evaluation of the continuous variables Efficacy variable Treatment group N Baseline score, mean (SD) Change in score mean (SD) Mean difference in change (95% CI) P-value Effect size (95% CI) Pain Topical diclofenac 105 13.0 (3.1) -5.2 (5.0) 1.9 (0.7 to 3.2) 0.003 0.41 (0.14 to 0.68) Vehicle control 107 12.7 (3.2) -3.3 (4.3) Physical function Topical diclofenac 105 40.9 (11.9) -13.4 (16.3) 6.5 (2.5 to 10.5) 0.001 0.44 (0.16 to 0.71) Vehicle control 107 40.3 (11.3) -6.9 (13.2) Patient global assessment Topical diclofenac 105 3.1 (0.8) -1.3 (1.3) 0.6 (0.2 to 0.9) 0.0001 0.47 (0.19 to 0.74) Vehicle control 107 3.2 (0.7) -0.7 (1.1) Stiffness Topical diclofenac 105 5.3 (1.4) -1.8 (2.1) 0.9 (0.3 to 1.4) 0.002 0.43 (0.15 to 0.70) Vehicle control 107 5.2 (1.5) -0.9 (2.0) Pain on walking Topical diclofenac 105 2.7 (0.8) -1.2 (1.2) 0.4 (0.1 to 0.7) 0.014 0.34 (0.07 to 0.61) Vehicle control 107 2.7 (0.8) -0.8 (1.1) \n\nBODY.RESULTS.EFFICACY ANALYSES.A POSTERIORI ANALYSES:\nThere was a significantly greater improvement in score with topical diclofenac compared to vehicle control (Table 2) for pain on walking (-1.2 vs. -0.8; p = 0.014). The response rate for at least a 50% reduction in pain (Table 3) was significantly greater following topical diclofenac treatment compared to vehicle control (46/105 [43.8%] vs. 27/107 [25.2%]; p = 0.004). The topical diclofenac group had a significantly greater number of participants with good or very good PGA response (43.8% vs. 16.8%; p <0.0001) compared to the vehicle control group and of OMERACT-OARSI responders (65.7% vs. 49.5%; p = 0.017). Table 3 Efficacy evaluation of the dichotomous variables Efficacy variables Treatment group N Number (%) of participants p-value Number-needed-to-treat (95% CI) 50% reduction in pain Topical diclofenac 105 46 (43.8) 0.004 5 (3–17) Vehicle control 107 27 (25.2) OMERACT-OARSI responder* Topical diclofenac 105 69 (65.7) 0.017 6 (3–33) Vehicle control 107 53 (49.5) Good or very good PGA response Topical diclofenac 105 46 (43.8) <0.0001 4 (3–7) Vehicle control 107 18 (16.8) *A responder is defined as a participant with ≥ 50% improvement in pain or function that was ≥ 20% of the scale, or ≥ 20% improvement in at least two of pain, function or patient global assessment that was ≥ 10% of the scale. \n\nBODY.RESULTS.ADVERSE EVENTS:\nThe major adverse effect reported was dry skin at the application site, occurring in 42/107 (39.3%) and 23/109 (21.1%; p = 0.004) of topical diclofenac and vehicle control participants, respectively (Table 4). A skin-related adverse event led to discontinuation of only 5 participants in the topical diclofenac group. All skin reactions resolved promptly upon withdrawal of treatment. Abdominal pain and dyspepsia each were reported in 4 [3.7%] participants in the topical diclofenac group compared to 1 [0.9%] participant in the vehicle control group, but this difference was not significant (p = 0.21). Table 4 Number (%) of adverse events Adverse Event Topical diclofenac (n = 107) Vehicle control (n = 109) Gastrointestinal reaction Abdominal pain 4 (3.7) 1 (0.9) Constipation 1 (0.9) 1 (0.9) Diarrhea 1 (0.9) 0 Dyspepsia 4 (3.7) 1 (0.9) Gastritis 1 (0.9) 0 Melena 0 1 (0.9) Nausea 1 (0.9) 2 (1.8) Application-site skin reaction Dry skin 42 (39.3)* 23 (21.1) Rash 2 (1.9) 4 (3.7) Paresthesia 2 (1.9) 2 (1.8) Pruritus 0 2 (1.8) Other reaction Headache 6 (5.6) 10 (9.2) Halitosis 2 (1.9) 0 Taste Perversion 4 (3.7) 2 (1.8) *p < 0.01 vs. vehicle control \n\nBODY.DISCUSSION:\nPublished guidelines have incorporated topical NSAIDs as recommended treatment for OA of the knee [4-6]. However, there has been controversy surrounding the adequacy of data supporting their benefit beyond 2 weeks [2,3,8,18]. Moreover, the studies identified in these meta-analyses generally did not conform to current standards for OA trial design [11,19]. In contrast, the present trial utilized standardized radiological and clinical entry criteria and measured efficacy with validated outcome measures. Baseline pain score was substantial; mean (SD) score was 12.9 (3.2) out of a maximum of 20, indicating a flare of pain following withdrawal of prior therapy. Analysis of all of the primary and secondary measures demonstrated that treatment with this topical diclofenac solution relieved the symptoms of primary knee OA at 6 weeks in this study population. Two other recently published trials using this topical diclofenac solution showed it to be superior to vehicle control and/or placebo; a 4-week, non-flare trial of 248 participants [20] and a 12-week, flare trial of 326 participants [21]. As with most NSAID trials, the subject population in this study was selected by the inclusion criterion of a flare of pain, which demonstrates the potential to respond to NSAID/analgesic. In clinical practice, an individual not taking an analgesic may have considered previous NSAID therapy ineffective, in which case s/he would not be expected to respond to topical diclofenac. However, where an individual is intolerant to oral NSAID, one may consider topical diclofenac as a treatment option. Comparison of efficacy results from independent trials with various treatments is facilitated by the introduction of benchmark determinants that are mathematically derived from the experimental raw data, such as effect size [22] for improvement of a continuous variable (e.g. \"How much did the patient's pain improve, relative to placebo?\"). We calculated an effect size (95% CI) of 0.41 (0.14 to 0.68) for pain relief, 0.44 (0.16 to 0.71) for improved physical function and 0.34–0.47 for improved measures of PGA, stiffness and pain on walking (Table 2). In contrast, Lin et al. [8] calculated a pooled effect size for pain relief of 0.04 (essentially no effect) in 3 placebo-controlled topical NSAID trials of 4 weeks duration. A meta-analysis of 23 oral NSAID trials for OA knee, lasting 2–13 weeks, reported a pooled effect size of 0.32 for pain reduction and 0.29 for improving physical function [23]. Another meta-analysis of 14 OA trials found a pooled effect size of 0.37 for pain reduction with oral NSAIDs and 0.44 for coxibs [24]. Zhang et al. [25], using data from 2 oral NSAID studies of 6–12 weeks duration, calculated a pooled effect size for OA pain reduction of 0.34. Efficacy of a treatment is being expressed increasingly as a dichotomous result, e.g. \"Did the patient's pain improve by 50%; yes or no?\". We derived the response rate for each dichotomous variable from our raw data, and demonstrated the superiority of topical diclofenac over vehicle control for 50% reduction in pain, achieving a good or very good final PGA response, and 'response' by OMERACT-OARSI criteria (Table 3). The benchmark determinant for comparing dichotomous efficacy results of various treatments is the number-needed-to-treat (NNT) [26]. We calculated a NNT between 4 and 6, depending upon the variable (Table 3). In their meta-analysis of topical NSAIDs, Mason et al. [3] cited 5 placebo-controlled trials of short duration for OA knee pain – 8 days (1 trial), 14 days (3 trials), and 28 days (1 trial). Their definition of clinical success, representing approximately a 50% reduction of pain, was estimated using patient or physician global assessment as the outcome measure (4 trials and 1 trial, respectively). They calculated a NNT of 5.3. Few oral NSAID studies have reported dichotomous data. Osiri et al. [26] reported a NNT for pain improvement of 4.4 with etodolac and 3.8 with tenoxicam. Defining improvement as an increase of at least 2 grades (on a 0–5 scale) in the patient's global rating of arthritis, Edwards et al. [27] reported a NNT of 11–13 for valdecoxib treatment of OA. The OMERACT-OARSI initiative used a consensus approach to derive dichotomous 'responder' criteria [14]. Through their vast meta-analysis of suitable trials, the authors found that for trials of oral NSAIDs vs. placebo the responder rates were 65.4% and 45.9% respectively. Responder rates of 60–65% have been reported for 13-week treatment of OA with celecoxib and lumiracoxib, with placebo responder rates of 49–53% [28,29]. The OMERACT-OARSI initiative did not look at topicals but we applied its criteria to this study and found a responder rate for topical diclofenac of 65.7% with a placebo responder rate of 49.5%, similar to their oral NSAID data. A caveat in the application of the mathematical benchmarks, effect size and NNT, is the influence of trial design, outcome measures and patient population on the apparent magnitude of response to a given treatment. Because the trials with topical diclofenac were designed according to the OARSI guidelines, like most recent NSAID and cyclooxygenase-2 (COX-2) inhibitor studies, such comparison of results is reasonable [19]. Although the data observed for topical diclofenac in this trial are comparable to other NSAID trials, a direct head-to-head comparison trial is required to prove equivalency of two treatments. A previously published 12-week comparative trial of 622 participants with OA knee confirmed the clinical equivalence between topical diclofenac solution and oral diclofenac [30]. Safety analysis revealed no serious clinical adverse effects and only minor application-site skin reactions, mostly skin dryness, following treatment with topical diclofenac. While dimethyl sulphoxide in the carrier acts as a penetrant [31], it also dissolves normal surface oils and leaves the skin dry. Common skin lubricants may prevent most application site reactions and any related discontinued therapy, but such products were not permitted in this trial in order to detect the maximum potential side effect profile of the study solutions. The low dropout rate due to skin reactions (5/107 [4.7%] for topical diclofenac) suggests patient acceptance of the overall topical treatment regime. The use of a checklist to prompt the patient about possible adverse events likely yielded a high estimate of the true incidence of gastrointestinal adverse reactions caused by topical diclofenac. The report of abdominal pain and dyspepsia each in 3.7% of patients is consistent with what was seen in other published trials of this topical diclofenac [20,21] and much lower than commonly experienced with oral NSAIDs or COX-2s [30]. Those other trials included results of laboratory testing and found minor abnormality of liver enzymes in 2–5%, creatinine in 1% and haemoglobin in 2% of patients, significantly lower than with oral diclofenac [30]. This safety profile can be predicted from the low systemic availability of topically applied diclofenac. Although the patient applies a daily dose (40 drops, 4 times a day) of 86 mg of diclofenac to the knee, the blood level is only 12 ng/mL [31]. The level reported after oral administration of 50 mg Voltaren® is 1500 ng/mL [32]. Similar improved safety with topical NSAIDs has been reported previously [33].\n\nBODY.CONCLUSION:\nTopical diclofenac solution provides 6-week relief of the symptoms of knee OA. The data in this and previous reports provide substantial evidence for the efficacy and safety of topical diclofenac solution in chronic OA.\n\nBODY.COMPETING INTERESTS:\nLMT and ZS are employees of Dimethaid Research Inc. PAB was a principal investigator in the trial, and was remunerated for his participation.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nPAB was a major investigator in the trial and was involved in data interpretation. LMT was involved in analysis and interpretation of the data and writing of the manuscript. ZS was involved in trial design and conduct, data review and writing of the manuscript. All authors reviewed and approved the final draft of the manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here:\n\n**Question:** Compared to vehicle control solution (carrier with no diclofenac) what was the result of topical diclofenac solution (Pennsaid®) on 50% reduction in pain?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
483
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Clinical and radiological evaluation of Trabecular Metal and the Smith–Robinson technique in anterior cervical fusion for degenerative disease: a prospective, randomized, controlled study with 2-year follow-up\n\n ABSTRACT:\nA prospective, randomized, controlled study was carried out to compare the radiological and clinical outcomes after anterior cervical decompression and fusion (ACDF) with Trabecular MetalTM (TM) to the traditional Smith–Robinson (SR) procedure with autograft. The clinical results of cervical fusion with autograft from the iliac crest are typically satisfactory, but implications from the donor site are frequently reported. Alternative materials for cervical body interfusion have shown lower fusion rates. Trabecular Metal is a porous tantalum biomaterial with structure and mechanical properties similar to that of trabecular bone and with proven osteoconductivity. As much as 80 consecutive patients planned for ACDF were randomized for fusion with either TM or tricortical autograft from the iliac crest (SR) after discectomy and decompression. Digitized plain radiographic images of 78 (98%) patients were obtained preoperatively and at 2-year follow-up and were subsequently evaluated by two senior radiologists. Fusion/non-fusion was classified by visual evaluation of the A–P and lateral views in forced flexion/extension of the cervical spine and by measuring the mobility between the fused vertebrae. MRI of 20 TM cases at 2 years was successfully used to assess the decompression of the neural structures, but was not helpful in determining fusion/non-fusion. Pain intensity in the neck, arms and pelvis/hip were rated by patients on a visual analog scale (VAS) and neck function was rated using the Neck Disability Index (NDI) the day before surgery and 4, 12 and 24 months postoperatively. Follow-ups at 12 and 24 months were performed by an unbiased observer, when patients also assessed their global outcome. Fusion rate in the SR group was 92%, and in the TM group 69% (P < 0.05). The accuracy of the measurements was calculated to be 2.4°. Operating time was shorter for fusion with TM compared with autograft; mean times were 100 min (SD 18) and 123 min (SD 23), respectively (P = 0.001). The patients' global assessments of their neck and arm symptoms 2 years postoperatively for the TM group were rated as 79% much better or better after fusion with TM and 75% using autograft. Pain scores and NDI scores were significantly improved in both groups when compared with baseline at all follow-ups, except for neck pain at 1 year for the TM group. There was no statistically significant difference in clinical outcomes between fusion techniques or between patients who appeared radiologically fused or non-fused. There was no difference in pelvic/hip pain between patients operated on with or without autograft. In our study, Trabecular Metal showed a lower fusion rate than the Smith–Robinson technique with autograft after single-level anterior cervical fusion without plating. There was no difference in clinical outcomes between the groups. The operative time was shorter with Trabecular Metal implants.\n\nBODY.INTRODUCTION:\nAnterior surgery of the cervical disc with fusion using autograft from the iliac crest was introduced in the 1950s [10, 40]. The clinical results are typically satisfactory, with at least 75–80% of the patients satisfied, reporting reduced pain intensity, improved function and neurological restitution [9, 24, 27, 30, 32, 35]. However, infections, hematomas and longstanding pain [12, 25, 28, 33, 36, 37, 50] are frequently reported complications from the donor site. Allografts have been widely used, but imply risks of producing immunogenic response from the host, which might disturb fusion healing and involve the risk of transmitting infections [2, 5, 16, 26]. The risk is low, but can still be important if the infection is severe, as shown, e.g., when HIV is detected [7]. The ideal substitute for autograft should provide all three of its fundamental properties: osteogenicity, osteoconductivity and osteoinductivity. Several implants have been tested, but no ideal substitute or surgical method has been found [44]. Previously we have reported a low fusion rate for a cervical body interfusion with carbon fiber cage (Brantigan) [45]. Trabecular Metal (TM) is a porous tantalum biomaterial with structure and mechanical properties similar to trabecular bone (Fig. 1) and has been shown to be more osteoconductive than other commercially available biomaterials [4, 11, 22].Fig. 1Trabecular MetalTM implant The objectives of the study were to measure and compare the radiological and clinical outcomes of anterior cervical decompression and fusion (ACDF) with Trabecular Metal (TM) devices and the traditional Smith–Robinson (SR) procedure with autograft.\n\nBODY.METHODS:\nAll patients scheduled for single-level anterior cervical decompression and fusion (ACDF) and fulfilling the criteria for the study were consecutively invited to participate during the period February 2002 to September 2003. Five patients declined participation and the remaining 80 provided informed consent. Study inclusion criteria were cervical radiculopathy with or without myelopathy due to degenerative disc disease (including disc herniation and/or spondylosis) with compatible MRI and clinical findings. Exclusion criteria were previous cervical spine surgery, posttraumatic neck pain, inflammatory systemic disease, another neurological disease and drug or alcohol abuse. No patient had spontaneous fusion at the adjacent segments. A flowchart of the study is presented in Fig. 2.Fig. 2Flowchart for the study After discectomy, the subchondral bony end plates were roughened by the burr until they bled, taking care that they would be able to function as a bearing surface for the implant. The posterior longitudinal ligament was removed in the majority of cases, and consequently osteophytes, if present, were removed. After decompression had been completed, randomization to fusion group was performed in the theater by a nurse using sealed envelopes. This late randomization was used to avoid surgeons' bias to treatment group during as much as possible of the surgical procedure. An implant size that could be positioned between the end plates by light tapping was chosen. The tricortical autografts were taken from the iliac crest using a saw with a twin blade. A subcutaneous catheter was placed at the donor site for administration of ropivacaine hydrochloride (NaropR) 2 or 3 days postoperatively, to reduce the pain. All patients used a soft collar for 6 weeks postoperatively. The randomization procedure yielded similar group distributions of age, gender and smoking habits (Table 1). The operated segment was C3/4 in 2 patients (both SR), C4/5 in 4 patients (2 TM, 2 SR), C5/6 in 50 patients (26 TM, 24 SR), C6/7 in 23 patients (11 TM, 12 SR) and C7/T1 in 1 patient fused with TM. See Table 2 for implant size. The operations were performed by five senior surgeons, and 70 out of the 80 patients were operated on by one of the two authors (HL, LV).Table 1Patient dataTotalTMSRAge median (range) (years)49 (27–70)48 (38–59)49 (27–70)Sex, male (no.)502426Smokers (no.)261610Myelopathy* (no.)422* All had radiculopathyTable 2Trabecular Metal implant sizeSize H × D × W (mm)No. of patients5 × 11 × 1415 × 14 × 1416 × 11 × 1466 × 14 × 14127 × 11 × 1467 × 14 × 14118 × 14 × 143Total40\n\nBODY.METHODS.CLINICAL FOLLOW-UP:\nPain intensity in the neck, arms and pelvis/hip were rated by patients on a visual analog scale (VAS, 0–100), and neck function was rated using the Neck Disability Index [46] (NDI, 0–100) the day before surgery, and 4, 12 and 24 months postoperatively. Pain drawings were obtained at the same intervals. Follow-ups at 12 and 24 months were performed by an unbiased observer (ME), and patients also assessed their global outcomes at these same follow-up intervals.\n\nBODY.METHODS.RADIOLOGICAL FOLLOW-UP:\nDigitized plain radiographic images of 78 (98%) patients were obtained preoperatively, immediately postoperatively and at 2-year follow-up, and were subsequently evaluated by two senior radiologists. Consensus about fusion or non-fusion was reached after the first evaluation in 49 cases (62%) and after the second evaluation in the remaining 29 cases (38%). The second measurement was used to calculate intra-observer variability. The entire data set was analyzed to assess inter-observer variability of radiographic measurements and associated precision of the measurements. Fusion/non-fusion was classified by visual evaluation of the A–P and lateral views in forced flexion/extension of the cervical spine, i.e., (1) the presence/absence of bone-bridging or interface lucencies between TM and bone, and (2) by measuring the differences between the angles of the spinal processes of the fused vertebrae at flexion and extension. Fusion was classified as either clearly fused (I), probably fused (IIA), probably non-fused (IIB) and clearly non-fused (III) (Figs. 3, 4, 5). Finally, the material was dichotomized so that groups I and IIA were combined to fused, and groups IIB and III to non-fused. The same classification had been used in a previous study of the Brantigan carbon fiber cage [45]. For classification in group I, radiological signs of bone bridging were required and mobility of up to 1.0° was accepted. Cases classified in group II had uncertain signs of bone fusion. Group IIA had mobility of 2.0° or less and group IIB had more than 2.0°. Group III required both the absence of bone bridging and mobility of 3.0° or more.Fig. 3Clearly fused (group I) after surgery with autograft (SR)Fig. 4Clearly fused (group I) after surgery with Trabecular Metal (TM)Fig. 5Clearly non-fused (group III) after surgery with Trabecular Metal (TM). Note the radiolucent zone above the implant. Mobility is seen between images in flexion and extension MRI was performed on 20 consecutive TM cases at 2-year follow-up. Several parameter sets suggested for TM in the published literature were tested [21, 47] in addition to our standard protocol for the degenerative cervical spine, and the parameter sets below were ultimately chosen. The scans were performed on a Siemens Vision 1.5 T MRI scanner using a cervical spine coil with a protocol consisting of T1-sagittal images (TR 500, TE 12, se), T2/PD sagittal images (TR 4000, TE 128, tse and TR 1300, TE 120, se), PD sagittal images (TR 1300, TE 60, se), T1 axial images (TR 600, TE 15, se), T2 axial images (TR 620, TE 10, 25°, Fl2d), T2 oblique images (TR 4000, TE 128, tse), T2 coronal images (TR 1485, TE 120, se) and finally PD coronal images (TR 1485, TE 60, se). Slice thickness was 4 mm in all images.\n\nBODY.METHODS.RADIOLOGICAL FOLLOW-UP.STATISTICAL METHODS:\nA rank-invariant non-parametric method for analysis of pairs ordered categorical data was used to compare the pain ratings (VAS) and NDI for the groups. The method makes it possible to separately measure order-preserved individual changes attributable to the group change, as well as an individual change in category that is different from the change of pattern in the group [41, 42]. Clinically relevant improvement, set at 10, was calculated for VAS and NDI. χ2 tests were used to compare the groups. Student's t test was used to analyze the operative and hospital time. Fischer's exact test was used to compare the fusion rate in the groups. Inter- and intra-observer correlation was calculated using kappa analysis. A value of P < 0.05 was considered to be statistically significant.\n\nBODY.RESULTS.SURGERY:\nOperation times were shorter for fusion with TM as compared to autograft; mean times were 100 min (SD 18) and 123 min (SD 23), respectively (P = 0.001). There was no difference in intra-operative bleeding between the implant groups. Of the 80 patients, 72 had less than 50 ml of bleeding. There was no statistically significant difference in the hospital time between the groups; TM mean was 3.6 days (SD 1.1) and SR mean, 4.1 days (SD 1.7) (P = 0.18).\n\nBODY.RESULTS.CLINICAL OUTCOME:\nFor patients receiving TM, the maximal pain (VAS) was reduced from median 57 in the neck and 45 in the arm before surgery, to 40 and 14 at 1 year and to 41 and 24 at 2 years postoperatively. In the group with autografts, the corresponding VAS ratings were reduced from median 66 in the neck and 60 in the arm before surgery to 36 and 28 at 1 year, and to 24 and 28 after 2 years (Fig. 6a, b). The number of patients showing clinically relevant improvement (set to at least 10 for VAS) in neck pain was 39% with TM and 63% with SR (P = 0.07), and in arm pain 50 and 58%, respectively.Fig. 6Pain rating (VAS) and Neck Disability Index preoperatively and at the follow-ups. The box plots illustrate the 25th and 75th percentiles with the median value marked in between. The range is shown by whiskers, but extreme outliers are separately shown by circles. There were no statistically significant differences between the surgical methods NDI improved from median 36 preoperatively to 30 after 2 years in patients with TM, and from 44 to 25 in the SR group (Fig. 6c). Clinically relevant improvement in NDI (set to at least 10) was found in 53% of the patients with TM and 61% with SR. The patients' global assessment of their neck and arm symptoms 2 years postoperatively for the TM group were: 41% much better, 38% better, 10% unchanged, 8% worse, and (one patient) 3% much worse. In the SR group, the assessments were: 42% patients much better, 33% better, 13% unchanged and 12% worse, i.e., 79% were much better or better after fusion with TM and 75% using autograft. At all follow-ups of 4, 12 and 24 months, pain scores (VAS) in both neck and arm, and NDI scores were significantly improved in both groups when compared with baseline, except for neck pain (VAS) at 12 months in patients fused with TM (P = 0.06). No statistically significant difference was found between the Trabecular Metal and autograft techniques for pain scores, NDI or the patients' global assessments, and at all follow-up intervals. A trend toward a higher proportion of patients with clinically relevant improvement in neck pain (at least 10 mm VAS) was measured after 2 years in patients with autografts (P = 0.07). The clinical results and corresponding P values are presented in Table 3.Table 3The clinical results and corresponding P valuesTMSRP valueMedianq1–q3Medianq1–q3TM vs. SRTM vs. baselineSR vs. baselineMaximal neck pain (VAS)Preoperative5733–726629–774 months224–55173–500.40.0002<0.0011 year403–63363–710.60.060.0052 years415–74246–660.60.0480.002Maximal arm pain (VAS)Preoperative4518–776027–734 months62–2570–340.9<0.0001<0.0011 year142–62283–720.40.0060.0462 years240–72284–630.80.0340.008Maximal pelvic pain (VAS)Preoperative00–2120–54 months00–420–120.20.50.91 year00–420–120.20.30.62 years00–1500–80.80.50.8Neck Disability IndexPreoperative3625–474430–511 year288–44279–490.80.0050.0012 years3012–47258–440.80.0010.001Clinically relevant improvement inNeck pain (at least 10 for VAS)39%63%0.07Arm pain (at least 10 for VAS)50%58%0.6NDI (at least 10)53%60%0.6Patients' global assessment at 2 years (%)Much better4142Better3833Unchanged1013Worse812Much worse30Better/much better79750.5Bold values are P values < 0.05 No differences in clinical outcomes were seen between patients who appeared radiologically fused or non-fused (P = 0.6). There was a tendency toward poorer clinical outcome for smokers compared with non-smokers, estimated by the patients' global assessments (P = 0.07).\n\nBODY.RESULTS.PELVIC PAIN:\nThere was no difference in pelvic/hip pain (at the donor site) preoperatively and at 4, 12 or 24 months, between patients fused with and without autograft. Further analysis of the pain drawings showed eight patients with markings at the right iliac crest (four SR, four TM). However, the majority had marked this as related to the pain caused by lumbago/sciatica or generalized pain. Only one patient, who had been fused with TM, marked localized pain in this area. In summary, no remaining donor site pain was marked in the pain drawings, and none was seen in the VAS scoring.\n\nBODY.RESULTS.COMPLICATIONS.FURTHER SURGERY:\nThree patients were reoperated: two of them because of non-fusion and one due to graft dislocation. All had been primarily fused with autografts (SR). They were all clearly fused 2 years postoperatively. One patient fused with TM was operated on at the adjacent segment after 19 months. The only patient with remaining symptoms due to complications 2 years after surgery had a sensory deficit below the donor site at the iliac crest (SR). Further complications in the SR group included three patients with wound infections at the iliac crest, and one of them with an infected hematoma. One patient had pneumonia and one had a lower urinary tract infection (cystitis). All infections were cured after antibiotic treatment. One patient developed a fissure in the autograft during the primary surgery. A plate was added to the fixation directly, and the fusion healed without further complications. Among the patients fused with TM, two had transient hoarseness, and one of them also had swallowing disturbances. One patient was treated with antibiotics for a urinary tract infection. In summary, nine patients in the SR group and three patients in the TM group had complications, but only one patient (SR) had symptoms 2 years after surgery.\n\nBODY.RESULTS.RADIOLOGICAL OUTCOME:\nThe fusion rate shown by the radiological analysis is presented in Table 4. All patients in group III (clearly non-fused) showed at least 4° of mobility (the limit for the group set by the classification was 3.0°). There was no statistically significant difference in the fusion rate between smokers (92%) and non-smokers (74%) (P = 0.2). Smokers operated on with TM showed an 87% fusion rate. Kappa analysis showed 0.63 and 0.66 for the intra-observer correlation, and 0.58 for inter-observer correlation.Table 4Radiological fusionFusion groupTMSRNo.PercentageNo.PercentageI (clearly fused)18463589IIA (probably fused)92313IIB (probably non-fused)51300III (clearly non-fused)71838Fusion rate (I + IIA)6992\n\nBODY.RESULTS.MAGNETIC RESONANCE IMAGING:\nMRI, of 20 TM cases was successfully used to assess decompression of the neural structures, but was not helpful in determining fusion/non-fusion attributable to metal artifacts in the area immediately surrounding the implants.\n\nBODY.DISCUSSION:\nAutograft is referred to as the gold standard for spinal fusion [43] due to its unique combination of osteogenicity, osteoconductivity and osteoinductivity. We had hypothesized that similarly high fusion rates for TM as for autograft could be obtained, but without the risk of complications from the donor site associated with autograft. The fusion rate of carbon fiber cages used in the treatment for the degenerative cervical spine was 62% in our previous study of the Brantigan cage [45], which led us to discontinue the use of the device. TM cages were chosen for the present study because of the unique microstructure of the material and because of the published affinity of osteocytes to tantalum metal [22]. These factors were hypothesized to promote bone ingrowth and enhance fusion. The fusion rate for TM in the present study was higher than for the carbon fiber cages, but lower than that of the SR group. In a recent study, Fernández-Fairen et al. [14] compared TM used as a stand-alone cage with autograft used with plate. The fusion rate was 89% for TM and 85% for autograft with plate. No statistically significant difference in radiological fusion or in clinical outcome was found between the groups. Criteria for fusion were that \"segments were deemed fused when there was evidence of bony bridging around the implant and/or <2° of variation of Cobb's angle on F/E radiographs or <2 mm of variation in the interspinous distance, in the absence of periimplant radiolucency\". We had similar criteria for fusion, besides measuring the movement between the spinal processes. The criterion accepting <2 mm movement is probably wider compared to the criterion of <2° variation of the angle [8, 13]. With less stringent criteria for fusion (more motion allowed), the apparent fusion rates increase, as demonstrated by Fasset [13]. Smokers were excluded from the study by Fernández-Fairen et al. [14], while we had 40% smokers in the group fused with TM. We found no statistically significant difference between smokers and non-smokers in our study, but it is still possible that smoking had some adverse influence on the fusion healing. On the other hand, the fusion rate in our control group with autograft was 92%, while it was 85% after autograft with plate in the study by Fernandez et al., though 25% of our patients operated on with autograft were smokers. Our patients were not randomized to fusion group until the major part of the surgical procedure including the decompression was completed, which reduced the risk for surgeons' bias, while the preoperative randomization in the study by Fernandez et al. might have had an adverse influence on the control group. Wigfield et al. [49] have presented a study with tantalum interbody implant, where inclusion of patients was halted after radiographs 6 weeks postoperatively had shown inferior end-plate lucency, raising concerns about delayed fusion or non-fusion. However, fusion was subsequently noted in all 15 patients available for follow-up at 12 months of the 17 patients operated on with tantalum implant, but the study numbers were too small for statistical analysis. Fusion was defined as less than 4° angulation between flexion and extension radiographs and absence of radiolucency extending over more than 50% of the implant/end plate interface. Baskin and Travnelis [3] compared TM with autograft in an RCT that was terminated due to concerns over delayed fusion after 39 patients had been enrolled. Of the 28 patients operated on with TM, 6 out of 16 patients (37%) who were examined with radiographs at 24 months were fused. A low fusion rate with TM was found by Zoëga and Lind [51] as well. Two years after ACDF with TM cage, none of the 13 patients had fusion. Those authors used radiostereometric analysis (RSA) for the follow-up, which is a very sensitive method for detecting motion [17, 29, 53]. Clinical outcome data showed no statistical difference between non-fused and fused patients in the present study. Earlier studies have shown divergent results concerning correlation between fusion and clinical outcome, with some pointing to the importance of the fusion for the clinical outcome [9, 27, 48] and others denying such a connection [12, 25, 31]. Addressing the fusion rate alone (without considering the clinical outcome), the use of TM as stand-alone device does not seem sufficient. The fusion rate with TM might be enhanced with an anterior plate, considering published results of TM with and without pedicle screws used in the porcine lumbar spine [54], as well as fusion rates for TM with allograft and anterior plate [35]. The use of an anterior plate in these studies suggests that initial stability may be an important factor in achieving fusion [36]. Because of the results obtained, we now use TM together with an anterior plate. Because our earlier study of the Brantigan cage showed closer correlation between radiological fusion and clinical outcome 5 years postoperatively as compared with 2 years [27], the present study will be extended. It has been advocated that a fusion cage can avoid subsidence better than an autograft, due to collapse of the latter. Some studies support this [45], while others show similar subsidence with the cage as well [15, 23]. This question was not addressed in the present study, where the radiological evaluation focused on whether the operated segment was fused or not. The accuracy of measurements of motion on digitized radiograph images was considerably higher in the present study (2.4°, 95% CI) than in our previous experience measuring on conventional radiographic films. The accuracy of measurements on conventional radiograph images has previously been estimated at 5° [17] and the cutoff for mobility has been set at 4° for studies of cervical implants. The described method using digitized radiograph images has reduced the difference in accuracy compared to the much more complex and expensive radiostereometry (RSA). We estimated the accuracy for RSA in the cervical spine at about 1° in a previous study [25, 29], which is less accurate than in the lumbar spine, mainly owing to the small size of the cervical vertebral bodies. With distortion-compensated roentgen analysis (DCRA), another technique for computerized analysis of conventional radiographs, Leivseth found an error of 2.4° [20]. MRI of 20 TM cases was successfully used to assess decompression of the neural structures, but was not helpful in determining fusion/non-fusion. The artifacts from the implants could be limited to the structures immediately surrounding the implants. Hence, the spinal canal and the foraminae could be visualized, and the decompression assessed, but interpretation of the interface between implant and vertebral body was disturbed. This is in contrast to the experience in the lumbar spine [personal communication, D Robertson] and is mainly due to the smaller size of the cervical vertebrae. The primary advantage of using an implant rather than autograft bone for ACDF is that it avoids complications associated with the donor site. Several previous studies have reported persistent pain in 15–40% of the patients 2 years after surgery [6, 12, 25, 33, 37, 50], though some studies show that this is less frequent [1, 34]. In our earlier study of the Brantigan cage, we found more donor site pain immediately postoperatively when using a conventional graft from the iliac crest as compared with using a percutaneous technique [45]. In the present study, no residual donor site pain was found at 4 months or later after surgery. In the early postoperative period, donor site pain is frequent, and it was experienced by our patients, but no assessment of the pain was made in this period. The administration of ropivacaine hydrochloride (NaropR) subcutaneously for the first few postoperative days resulted in pain reduction in our patients. This postoperative pain reduction might have reduced the tendency to persisting pain as well, due to less central sensitization caused by the postoperative pain [18, 19]. Sing et al. [38] have shown the good effects of continuous local anesthetic infusion on the acute graft-related pain as well as a remaining effect 4 years postoperatively [39]. In both groups in our study, 10% of the patients marked the pelvic/hip region on the pain drawing at 2 years, which illustrates the importance of having a control group for all follow-ups. Patients operated on with autografts were at risk of rare complications, such as neuralgia, although this did not occur in the moderate number of studied patients. Despite absence of chronic pain, we still found donor site morbidity; one patient had lasting sensory disturbance and three were treated for local infections. The clinical outcome in the present study showed 28 and 22 mm reduction in pain rating (VAS) in the neck and arm, respectively, 12 points improvement in NDI, and improvement for 77% of the patients in the global assessment. This is in accordance with earlier studies [9, 24, 25, 30, 32, 35, 45, 52].\n\nBODY.CONCLUSIONS:\nThis study of uninstrumented single-level ACDF showed a lower fusion rate with Trabecular Metal than with the Smith–Robinson technique with autograft after single-level anterior cervical fusion without plating. There were no differences in the clinical outcomes between the groups, and there were no differences in outcomes between patients who appeared radiologically fused or non-fused. The operating time was shorter with Trabecular Metal implants. No remaining donor site pain at the iliac crest was seen at 4 months or later.\n\n**Question:** Compared to anterior cervical decompression and fusion (ACDF) with Trabecular MetalTM (TM) what was the result of raditional Smith–Robinson (SR) procedure with autograft on Radiological fusion?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
484
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: The role of somatostatin in 67 consecutive pancreatectomies: a randomized clinical trial\n\n ABSTRACT.BACKGROUND:\nSomatostatin has been found to be effective in the prevention of postoperative complications in pancreatic surgery. It can inhibit the pancreatic secretions that, quite often, are responsible for complications during the postoperative period.\n\nABSTRACT.METHODS:\nWe randomized 67 patients in 2 groups. In the study group (n = 35), somatostatin was administered 30 minutes prior to surgery as well as intraoperatively and postoperatively. No medication was given to the control group (n = 32). Biopsies were taken and processed for electron microscopy and ultrastructural morphometric analysis.\n\nABSTRACT.RESULTS:\nAdministration of somatostatin reduced the exocrine granule number, and the patients suffered from fewer postoperative complications.\n\nABSTRACT.CONCLUSIONS:\nSomatostatin reduces granule number and size of pancreatic cells, which can partially explain the prophylactic effect of the drug on early complications of pancreatic surgery, and which is confirmed by the clinical findings.\n\nBODY.INTRODUCTION:\nRelease and activation of pancreatic enzymes during an operation and the postoperative period are responsible for complicating pancreatic surgery.1,2 Somatostatin can inhibit pancreatic exocrine secretion.3–8 Somatostatin involves a broad range of biological actions, which include the inhibition of pancreatic exocrine secretion. The actions of somatostatin are mediated by a family of 7 transmembrane-based G-protein-coupled receptors that comprise 5 distinct subtypes (SSTR1-5). The receptors have common signaling pathways such as inhibition of adenyl cyclase, activation of phosphotyrosine phosphatase, and modulation of mitogen-activated protein kinase. The mechanisms whereby somatostatin receptors transduce messages into intracellular responses under different conditions and in different cells are complex. Inhibition of pancreatic exocrine secretion should improve the postoperative course and consequently reduce complications after pancreatic resection.9 The aim of this study was to assess the effect of somatostatin administration on the ultra-structure of exocrine pancreatic cells by comparing electron microscopy with clinical results.\n\nBODY.METHODS.PATIENTS:\nConsecutive patients suffering mainly from pancreatic tumor (n = 60/67) and chronic pancreatitis (n = 9/67) that were suitable for pancreatic resection were enrolled in the study (Table 1). The patients who met the preliminary criteria were randomly assigned to receive a continuous intravenous infusion of somatostatin-14 (Somastin Sb, Faran, Athens, Greece). The dose was 3000 μg within 12 hours at an infusion rate of 3.5 μg/kg/h, perioperatively (30 minutes before surgery, intraoperatively, and 7 days after surgery). The study group consisted of 35 patients and the control group 32. Patients were maintained on their usual diet and fasted for 12 hours before surgery. No patient was on total parenteral nutrition. Each patient received intravenous antibiotic prophylaxis 30 minutes preoperatively and a second dose 3 hours after the start of the operation. All patients were treated in the intensive care unit for the first 24 hours. Intravenous crystalloid solutions were administrated (2.5–3.0 L/d) according to clinical requirements and these were supplemented by plasma or blood components in order to maintain a positive central venous pressure and a blood hemoglobin ≥8–9 g/dL. The patients were given nothing orally during the first 3 postoperative days. Each patient was traced up to the 90th postoperative day. The patients were treated according to the ethical guidelines of the World Medical Association Declaration of Helsinki – Ethical Principles for Medical Research Involving Human Subjects adopted by the 18th WMA General Assembly, Helsinki, Finland, June 1964, as revised in Tokyo 2004. All participants gave informed consent to participation before enrolment.\n\nBODY.METHODS.STUDY DESIGN:\nThe study was an open-label, parallel-group, simple randomized clinical trial and the patients were selected according to the CONSORT (Consolidated Standards of Reporting Trials) criteria. The operations were performed and all data were collected at the hospital-based surgical department at the General Hospital \"Agios Dimitrios\", Thessaloniki, Greece. The statistical analysis was performed using SPSS software (v. 15.0.1.1; SPSS Inc., Chicago, IL, USA). The histopathological assessment and the morphometric analysis were performed at the department of Histology and Embryology, School of Medicine, Aristotelian University of Thessaloniki. The review was standardized. It was performed by the same pathologist, who was blinded to the study group of the patients.\n\nBODY.METHODS.OPERATIVE PROCEDURES:\nAfter induction of general anesthesia, 13 patients underwent Kausch–Whipple operation, 46 Traverso–Longmire, 5 patients distal pancreatectomy and spleenectomy, and 1 distal pancreatectomy with preservation of the spleen (Table 2). All patients were operated on by the same surgical team using the same technique and type of materials. A 2-layer technique of end-to-side pancreatojejunal anastomosis was performed with 5/0 Monosyn® (B. Brawn Aesculap Melsungen AG) and 4/0 PDSII® (Ethicon), an end-to-side 1-layer choledochojejunal anastomosis was performed with 4/0 PDSII, and a 1-layer gastrojejunal anastomosis was performed with 4/0 Monosyn. The total operative time was an average of 6 hours for the Kausch–Whipple or Traverso–Longmire operation and 4 hours for the distal pancreatectomy. All patients, with the exception of those who underwent distal pancreatectomy, were transferred to the intensive care unit.\n\nBODY.METHODS.HISTOPATHOLOGY:\nAfter the division of the pancreas, a small piece from the healthy tissue (pancreatic remnant) was taken for electron microscope histopathological assessment. The mean time between injection of somatostatin, tissue resection, and fixation was 3 hours. The samples were cut into smaller pieces (1 mm3) and fixed in 3% glutaraldehyde in phosphate buffer pH 7.4 for 2 hours and postfixed in 2% osmium tetroxide for 1 hour. After staining with 1% aqueous solution of uranyl acetate for 14 hours, the tissue pieces were dehydrated in an increasing series of alcohol solutions and then embedded in EPON 812. After the observation of the morphology on the semi-thin sections stained with toluidine blue, thin sections were stained with lead citrate and then observed in a Jeol TEM 2000FXII at 80 kV (Table 3).\n\nBODY.RESULTS.CLINICAL FINDINGS:\nWithin 90 days of surgery, surgical mortality was 4.4% and morbidity was 35.8% (24/67 patients, 6 of whom were from the somatostatin group and 18 from the control group). The most frequent complication (Table 4) was fistula (25%) followed by abscess (20.8%), delayed gastric emptying, upper respiratory infection, urinary tract infection, fever, and multi-organ failure. The frequency of postoperative complications was lower in the somatostatin group than in the control group (Table 5). The levels of bilirubin and amylase were calculated both in serum and surgical drainage during the first, third, and fifth postoperative day in order to establish the presence of fistula or anastomosis leakage. Initially, hypoglycemia followed by hyperglycemia due to inhibition of insulin secretion, nausea, vomiting, and a burning sensation were the most common side effects of somatostatin. Mild side effects that did not rule out the interruption of the drug were observed in 3 patients who received somatostatin. Skin rash developed in 2 patients, and nausea with vomiting in one of these.\n\nBODY.RESULTS.HISTOLOGICAL FINDINGS:\nIn control patients the acini were normal with many membrane-bound granules of variable size, dilated rough endoplasmic reticulum, and many Golgi complexes (Figures 1 and 2). Also, we observed dense connective tissue between the acini, some destroyed cells, and some cells with pycnotic nucleus. The fine structure of the acinar cells after the administration of somatostatin was different. Many of the acinar cells had few granules or none at all. The electron density of membrane-bound granules varied. The cell organelles (rough endoplasmic reticulum, c. Golgi) were few (Figures 3 and 4). There were also acinar cells with a physiological appearance and many granules, as in the case of the control group. A reduction in size was observed in almost all acinar cells in more than 80% of cases. Selected tissue areas from the above specimens were randomized for morphometric analysis. Data were acquired by the same operator using dedicated software. In each area the number of granules and the total granular area were obtained (Table 6).\n\nBODY.RESULTS.STATISTICAL ANALYSIS:\nUsing several statistical methods we came to the following conclusions. Initially, 6 of 35 (17%) in the treated group who received somatostatin developed complications, whereas 18 of 32 (56%) in the control group developed complications. Then we hypothesized whether these two percentages were equal by using the simple test of equality, but this should be rejected because P = 0.000. In order to be more accurate we used Fisher's exact test, and came to the same conclusion (P = 0.001), ie, the percentages of the treated group and the control group are not equal. Finally, with the help of logistic regression we concluded that the patients who did not receive somatostatin (control group) had a 6.2 times higher probability of developing complications than the treatment group.\n\nBODY.DISCUSSION:\nMany clinical studies have been performed since the first observation that somatostatin, and especially its synthetic analog octreotide, can modify pancreatic exocrine secretion. Most double-blind, placebo-controlled, randomized studies have shown that administration of somatostatin in the perioperative and preoperative period reduces postoperative complications of pancreatic resection, which are currently ascribed to excess release of pancreatic enzymes.10 However, a meta-analysis of randomized controlled trials has failed to show any benefit from the administration of somatostatin, especially if the administration was done only after surgery.11 Finally, a systemic review of the Cochrane database has revealed that somatostatin can reduce the complications associated with pancreatic surgery.12 The mechanism by which somatostatin and its analog octreotide affect the exocrine secretion of the pancreas has not been adequately investigated. The administration of somatostatin reduces pancreatic enzyme secretion in response to exogenous cholecystokinin and secretin. Gullo and other researchers have shown that somatostatin can reduce amino acid uptake by the pancreas with a consequent reduction of enzymic synthesis and release, while others have demonstrated that somatostatin acts indirectly on acinar cells and inhibits secretin potentiation of secretory response by inhibiting secretin-induced c-AMP production as well as the calcium sensitivity of exocytosis.13–15 Moreover, somatostatin inhibits amylase secretion from isolated rat pancreatic acini. Other studies have suggested that somatostatin inhibits pancreatic secretion when it is injected into a central vagal site via cholecystokinin octapeptide or 2-deoxy-D-glucose-stimulated pancreatic protein secretion in a dose-dependent manner, and that this inhibition is via somatostatin receptor-2.16,17 Somatostatin acts on the neurons in the central vagal site, resulting in modulation of the vagal tone, thereby inhibiting pancreatic enzyme secretion. The parasympathetic innervation of the pancreas plays a major role in the control of pancreatic exocrine secretion. In our study, the number of patients who received somatostatin (treated group) was relatively small (n = 35). However, ultrastructurally we observed a reduction in the synthesis of pancreatic enzymes after the administration of somatostatin. The images revealed a smaller number of granules and changes in the synthetic machinery, as confirmed by morphometric analysis as well as by statistical analysis of the clinical results. In conclusion, the perioperative administration of somatostatin may provide some benefit in preventing pancreatic-related complications by diminishing the synthesis of pancreatic enzymes, and is probably associated with the inhibition of exocrine secretion by the gland.\n\n**Question:** Compared to No medication was given to the control group what was the result of somatostatin on Postoperative complications?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
421
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Six-week high-intensity exercise program for middle-aged patients with knee osteoarthritis: a randomized controlled trial [ISRCTN20244858]\n\n ABSTRACT.BACKGROUND:\nStudies on exercise in knee osteoarthritis (OA) have focused on elderly subjects. Subjects in this study were middle-aged with symptomatic and definite radiographic knee osteoarthritis. The aim was to test the effects of a short-term, high-intensity exercise program on self-reported pain, function and quality of life.\n\nABSTRACT.METHODS:\nPatients aged 36–65, with OA grade III (Kellgren & Lawrence) were recruited. They had been referred for radiographic examination due to knee pain and had no history of major knee injury. They were randomized to a twice weekly supervised one hour exercise intervention for six weeks, or to a non-intervention control group. Exercise was performed at ≥ 60% of maximum heart rate (HR max). The primary outcome measure was the Knee injury and Osteoarthritis Outcome Score (KOOS). Follow-up occurred at 6 weeks and 6 months.\n\nABSTRACT.RESULTS:\nSixty-one subjects (mean age 56 (SD 6), 51 % women, mean BMI 29.5 (SD 4.8)) were randomly assigned to intervention (n = 30) or control group (n = 31). No significant differences in the KOOS subscales assessing pain, other symptoms, or function in daily life or in sport and recreation were seen at any time point between exercisers and controls. In the exercise group, an improvement was seen at 6 weeks in the KOOS subscale quality of life compared to the control group (mean change 4.0 vs. -0.7, p = 0.05). The difference between groups was still persistent at 6 months (p = 0.02).\n\nABSTRACT.CONCLUSION:\nA six-week high-intensive exercise program had no effect on pain or function in middle-aged patients with moderate to severe radiographic knee OA. Some effect was seen on quality of life in the exercise group compared to the control group.\n\nBODY.BACKGROUND:\nExercise is considered to be one of the most important treatments for patients with mild to moderate knee osteoarthritis [1,2]. Positive effects on pain and function, as well as cost-effectiveness have been reported [3,4]. The effect size obtained on pain experience is similar to that of pharmacological treatment [3,5]. The side effects have also been reported to be favorable, including reduced risk of inactivity-related disorders, such as cardiovascular disease and diabetes [2,6,7]. Moderate levels of physical activity are not associated with radiographic progression, but activities involving a risk of severe knee injury are closely related to increased risk of developing radiographic knee osteoarthritis [8-12]. The dose-response relationship of exercise on symptoms and function is not clear and exercise recommendations in osteoarthritis guidelines are based mostly on studies on elderly people, i.e. mean age ≥ 65 [3,13-15]. It is not clear whether exercise has a similar effect on pain and function in middle-aged patients compared with elderly patients. The aim of this study was to examine the effects of a short-term, high-intensity exercise program in middle-aged subjects (age 36–65) with definite radiographic knee osteoarthritis on self-reported pain, function, and quality of life.\n\nBODY.METHODS.SUBJECTS:\nA flow chart of the recruitment process is given in Figure 1. Radiologists and orthopedic surgeons at the Halmstad County Hospital, in the south-west of Sweden, and general practitioners within the catchments area of this hospital, were informed about the study and asked to list patients with radiographic knee osteoarthritis on a \"patients eligible for research\" list. Between October 1998 and October 2001 121 patients, referred by their general practitioner for radiographic examination because of long standing knee pain, were listed. Ninety-seven fulfilled the inclusion criteria: age 35–65, living in the defined geographic area, and diagnosis of radiographic osteoarthritis of Kellgren and Lawrence grade III or more, i.e. definite osteophytes and joint space narrowing. All listed patients received written information about the study. One week after the information was sent, patients were contacted by telephone, and invited to participate in the study. Twenty-eight patients declined participation for various reasons, the most common reason being lack of time and interest. To ensure only patients with symptoms due to knee osteoarthritis and eligible for exercise intervention were included, the following exclusion criteria were used: inflammatory joint disease, anterior cruciate ligament injury, known symptomatic injury to the menisci, hip symptoms more aggravating than the knee symptoms, about to have knee replacement surgery within 6 months, and co-morbidities not allowing exercise (Figure 1). Figure 1Flowchart of recruitment process and included patients. When eight or more patients fulfilled the inclusion criteria they were invited to baseline interview and examination for determination of exclusion criteria. Randomization was performed after the baseline examination. All patients were informed that they could be randomly allocated to either the exercise or the control group. After written informed consent, sixty-five subjects were randomized. Randomization was performed by the patient drawing a sealed envelope containing a piece of folded paper with either the word \"exercise\" or \"control\" written on it. Four persons were falsely randomized (one was too old at inclusion, one had severe hip osteoarthritis, one had fibromyalgia, and one had only joint space narrowing and no significant osteophytes), and thus 61 subjects entered the study. Thirty persons were allocated to the exercise group and 31 to the control group. Patients in the control group were offered exercise classes after the six-month follow-up period.\n\nBODY.METHODS.SUBJECTS.EXERCISE GROUP:\nThe number of participants exercising together varied from two to nine. There were eight intervention groups in all. One-hour exercise sessions, twice a week for six weeks, were supervised by a physical therapist (CT). The program consisted of weight-bearing exercises aimed at increasing postural control and endurance and strength in the lower extremity (see additional file 1 for the complete exercise program). Exercises were performed at five stations at submaximal intensity (minimum 60% of maximum heart rate (HRmax)). Intensity was gradually and individually increased during the six weeks by increased lever arms or range of motion. Patients were encouraged to exercise at their most vigorous intensity possible, without losing quality in performance or severely exacerbating pain. Pain during exercise was not considered as an obstacle if the patient perceived it as \"acceptable\" and no increased symptoms were persistent after 24 hours [16]. If pain exceeded this level, exercise intensity was reduced occasionally, until the \"acceptable\" level was found. On every occasion, the heart rate of two random participants was estimated at each station using Polar pulsimeters (Polar® Accurex Plus, Polar, Sweden). The other patients had their heart rate measured by the physical therapist or themselves, palpating their carotid arteries. Notes were taken by the supervising physical therapist, on every occasion and on all patients, about exercise intensity, heart rate, and perceived exertion according to Borg's Rate of Perceived Exertion scale (RPE) at each station [17]. These data were used to give the physical therapist a view of exercise intensity and to assure the preservation or increase of intensity from time to time. Patients were encouraged to keep up and increase intensity whenever possible throughout the six weeks. Patients received a thera band to perform daily pulley exercises at home. In addition, three exercises, which were considered as the most challenging to the individual, were chosen as daily home exercises. Patients were recommended to perform some kind of weight bearing submaximal activity, such as walking or their home exercises, for at least 30 minutes or two times 15 minutes every day.\n\nBODY.METHODS.SUBJECTS.CONTROL GROUP:\nThe controls were told not to make any lifestyle changes. They met the physical therapist (CT) for one hour at three times; baseline, follow up at 6 weeks and 6 months. After six months they were offered exercise classes or instructions and a home-exercise program.\n\nBODY.METHODS.OUTCOME MEASURES.PRIMARY OUTCOME:\nThe primary outcome measure was the disease-specific Knee injury and Osteoarthritis Outcome Score (KOOS) [18,19]. The KOOS assesses the patients' self-report of pain, other symptoms, activities of daily living, sport and recreation function, and knee-related quality of life, in 42 questions which take about 10 minutes to complete. The KOOS is scored from 0 to 100, separately for each subscale, 0 indicating extreme problems and 100 indicating no problems. A change of 10 points or more is considered a clinically significant change [20]. The questionnaire and scoring manual can be found at . The Western Ontario and McMaster Osteoarthritis Index (WOMAC) [21] is included in the KOOS, and WOMAC scores can also be calculated.\n\nBODY.METHODS.OUTCOME MEASURES.SECONDARY OUTCOME:\nSecondary outcome measures were the Short Form-36 item (SF-36), ergometer test, and five tests of functional performance. The SF-36 is a generic, widely used measure of general health status, which comprises eight subscales: Physical Functioning (PF), Role-Physical (RP), Bodily Pain (BP), General Health (GH), Vitality (VT), Social Functioning (SF), Role-Emotional (RE) and Mental Health (MH) [22]. The SF-36 is self-explanatory and takes about 10 minutes to complete. The SF-36 is scored from 0 to 100, 0 indicating extreme problems and 100 indicating no problems. The subscales assessing mainly physical components (PF, RP, BP, GH) were summarized to a physical component summary score (PCS), and the mental subscales (VT, SF, RE, MH) to a mental component summary score (MCS) [23]. Values are norm-based scored, using the U.S. general population norms from 1998. Each scale has the mean of 50 and standard deviation of 10. Scale score below 50 indicates a health status below average, and a score above 50 indicates a health status above average. Questionnaires were distributed prior to randomization at baseline, after 6 weeks, and 6 months. A bicycle ergometer test and five tests of functional performance were assessed (Figure 2). Figure 2Tests of functional performance. A) Åstrand's cycle-ergometer test [24]. B) Rising on one leg from sitting on lowest possible height [25,26]. C) One-leg hop [25], [27]. D) Lateral step-up [28]. E) One-leg semi squatting; maximum number during 30 sec. [26]. F) Heel-rising on one leg; maximum number during 20 sec. [26], [29]. 1. Åstrand's bicycle-ergometer test [24] (Fig 2A). 2. Rising on one leg, from sitting on lowest possible height [25,26] (Fig 2B). 3. One-leg hop [25,27] (Fig 2C). 4. Lateral step-up [28] (Fig 2D). 5. One-leg semi squatting; maximum number during 30 seconds [26] (Fig 2E). 6. Heel-raising on one leg; maximum number during 20 seconds [26,29] (Fig 2F). Tests of functional performance were recorded on three occasions: prior to randomization at baseline, after 6 weeks, and at 6 months. To assess compliance the number of exercise occasions attended was noted.\n\nBODY.METHODS.STATISTICS:\nPost-hoc, a power analysis was performed to estimate the number of patients needed to show a clinically significant difference between groups. Estimating the least clinical significant difference to be 11 ± 15 KOOS points, a total of 30 subjects in each group were needed to detect a difference with 80% power, p = 0.05. Data were analyzed using nonparametric tests. P-values of less than or equal to 0.05 were considered to be significant, and all tests were two-tailed. To compare groups, Mann-Whitney U-test was used. Friedman's test was used for repeated measures analysis of variance. Six weeks was considered as the time-point of primary interest, and 6 months as follow-up. Wilcoxon signed rank test was performed to compare changes from baseline to six weeks and 6 months respectively. Analyses were performed using SPSS 12.0.1 for Windows [30]. The study was approved by the Research Ethics Committee at Lund University, Sweden (LU 99–98), and is in compliance with the Helsinki Declaration.\n\nBODY.RESULTS.SUBJECTS:\nThe mean age of the 61 included subjects was 56 ± 6 years, and the mean BMI was 29.5 ± 4.8 kg/m2. Patient characteristics are shown in table 1. Twenty-eight patients in each group were available for follow-up. The reasons for dropout were lack of time, reorganization at work, sudden illness, and increased knee symptoms (Figure 1). There were no clinically significant differences in baseline characteristics between the groups. Patient characteristics are shown in table 1. Table 1 Patient characteristics at baseline Exercise group n = 30 Control group n = 31 p-value Age (years) mean ± SD (range) 54.8 ± 7.1 (36–64) 57.3 ± 4.7 (46–65) 0.16 Gender number (%) women 15 (50%) 16 (52%) 0.90 BMI (kg/m) 2 mean ± SD 29.6 ± 4.5 29.5 ± 5.1 0.78 Aerobic capacity (ml O 2 /kg x min) mean ± SD 25.9 ± 6.4 25.2 ± 4.9 0.66 KOOS* pain 60 ± 18 64 ± 19 0.38 KOOS* symptoms 63 ± 20 66 ± 18 0.67 KOOS* ADL 69 ± 18 71 ± 21 0.76 KOOS* sport & recreation 34 ± 31 37 ± 29 0.54 KOOS* QOL 40 ± 15 46 ± 21 0.31 Knee Injury and Osteoarthritis Outcome Score [ 18 , 19 ] Score from 0–100, worst to best. \n\nBODY.RESULTS.COMPLIANCE:\nThe total number of performed supervised exercise sessions by the 28 patients available for follow-up in the intervention group was 302/336 (89.9%). Patients participated on average in 11 out of 12 possible exercise classes (12 classes (n = 11), 11 (n = 9), 10 (n = 6), 9 (n = 1), 2 (n = 1)). The most common reason for absence was illness not related to knee osteoarthritis, and work-related lack of time.\n\nBODY.RESULTS.BETWEEN-GROUP DIFFERENCES:\nThere was no difference between groups in pain or self-estimated function at either 6 week or 6 month follow-up. Quality of life improved significantly in the exercise group compared to the control group at 6 weeks (4.0 vs. -0.7, p = 0.05) and the results persisted at 6 months (5.1 vs. -2.3, p = 0.02, Table 2) Table 2 Comparisons of change in Knee injury and Osteoarthritis Outcome Score (KOOS) ‡ [ 18 , 19 ] subscales between exercise and control group KOOS Subscales Exercise group Control group Change in KOOS score* 95 % CI Change in KOOS score* 95 % CI p † Pain 6 w 1.8 -3.2 – 6.8 -0.3 -6.2 – 5.7 0.49 6 m 3.1 -1.9 – 8.2 -1.1 -6.6 – 4.4 0.32 Symptom 6 w 0.2 -5.1 – 5.6 -3.8 -7.7 – 0.0 0.07 6 m 1.0 -3.8 – 5.8 -3.4 -8.8 – 1.9 0.31 ADL 6 w 2.0 -2.3 – 6.3 -0.6 -7.0 – 5.8 0.96 6 m 0.9 -3.8 – 5.6 -1.9 -7.7 – 3.9 0.61 SportRec 6 w 1.2 -7.9 – 10.4 -4.4 -12.6 – 3.7 0.22 6 m 0.5 -10.1 – 11.2 -8.3 -19.5 – 2.8 0.32 QOL 6 w 4.0 -0.4 – 8.5 -0.7 -5.6 – 4.3 0.05 6 m 5.1 -0.7 – 11.0 -2.3 -9.5 – 4.9 0.02 * negative = worsening, positive = improvement † p-value for between group differences in change over time ‡ [ 18 , 19 ] The individual differences ranged from clinically significant improvement of at least 10 points to clinically significant deterioration in all KOOS subscales and in both the exercise and control group (Figure 3). Figure 3Change in KOOS pain score at six weeks. The individual change in KOOS pain at 6 weeks compared to baseline ranged from improvement to worsening, in both exercise and control group. A change of 10 points or more is considered clinically significant [20]. A similar pattern was seen for all KOOS and SF-36 subscales.\n\nBODY.RESULTS.BETWEEN-GROUP DIFFERENCES.SECONDARY OUTCOMES:\nA significant improvement was found in the exercise group compared to the control group at six weeks with regard to the SF-36 Mental Component Summary scale (MCS) (2.1 vs -1.6, p = 0.04). At six months follow-up this difference was no longer persistent (Table 3). Table 3 Comparisons of change in SF-36 Physical and Mental Components Summaries (PCS and MCS) [ 23 ] between exercise and control group. Short Form-36 item (SF-36) [22] Exercise group Control group mean 95%CI mean 95%CI p* Physical Component Summary (PCS) Baseline 42.5 24.4 – 57.5 43.8 24.2 – 57.3 0.49 Change at 6 weeks 3.0 -5.9 – 13.4 0.3 -15.2 – 12.6 0.13 Change at 6 months 3.0 -5.9 – 16.3 -0.7 -14.8 – 9.8 0.09 Mental Component Summary (MCS) Baseline 55.6 40.2 – 66.2 56.3 37.0 – 67.0 0.63 Change at 6 weeks 1.6 -10.6 – 15.0 -2.1 -16.9 – 11.5 0.04 Change at 6 months 0.7 -18.1 – 13.2 -0.7 -16.8 – 12.8 0.40 * Comparison between groups Improvements in functional performance of 0–20 % were seen in both groups at six weeks and six months. There was no difference in improvement between exercisers and controls (p = 0.08–0.9). See additional file 2 for the change in functional performance.\n\nBODY.DISCUSSION.MAIN MESSAGE:\nSix weeks of intensive exercise had no effect on self-reported pain or function in middle-aged patients with symptomatic and moderate-severe radiographic knee osteoarthritis.\n\nBODY.DISCUSSION.COMPARISONS WITH OTHER STUDIES:\nQuite opposite to previously published studies on exercise in knee osteoarthritis we found no improvement in pain or function. Possible reasons for this include our study group having moderate to severe osteoarthritis compared with mild to moderate in most previous studies, being younger than previously studied groups and the intervention being of comparably high intensity. It has been suggested that the responsiveness to exercise is modified by the loss of joint space width [31]. The homogeneity of this study population, with regard to radiographic changes, provided us the possibility to study the effects of exercise on patients with moderate to severe radiographic knee osteoarthritis. Can significant improvements of pain or self-reported function be expected in patients with radiographic knee osteoarthritis corresponding to Kellgren & Lawrence grade 3 or more? In this study, no improvements were seen on group level in pain or function. However, regular exercise in general is important to prevent diseases caused by inactivity [6], and thus patients with knee osteoarthritis should be encouraged to exercise. In clinical practice, patients with severe knee osteoarthritis should have treatments based on individual preferences and different stages of motivation [32]. It can be argued that the exercise intensity was too high for this group with moderate to severe knee osteoarthritis. Even though the intensity of each exercise was individually adapted, all individuals exercised at a minimum of 60% of HR max. It has been suggested that pain during exercise might be a protective mechanism in knee osteoarthritis, i.e. an increase in pain from too intensive exercises may restrain patients from further joint loading, which otherwise could cause further cartilage damage [33]. Patients in the current study were told to reduce the exercise intensity if pain during exercise was perceived as worse than 'acceptable', or persisted more than 24 hours. It is suggested that the different degrees of varus-valgus laxity should be taken into account in exercise interventions, to enhance the functional outcome [34,35]. Severe knee osteoarthritis is associated with a hip-knee-ankle malalignment and an increase in varus-valgus laxity compared to healthy knees [36]. It is possible that varus-valgus laxity mediated the effect of exercise on pain since all patients had radiographic changes corresponding to Kellgren and Lawrence grade III or more. Malalignment may cause increased joint loads, and greater quadriceps strength might further increase joint load by the muscles compressing the articular surfaces [37]. Younger patients are usually more physically active than elderly [38], and have higher demands on level of physical function and physical performance at work or leisure time. Thus, moderate to severe knee osteoarthritis might be perceived as more disabling by younger individuals compared to elderly. Our study population was younger (<65 years) and comprised more men (49%) than most other populations with knee osteoarthritis described in randomized controlled trials of exercise [13-15,39,40], which might have reduced the effect on self-reported function in the present study. This study showed no significant differences on self-reported pain and function either between or within groups. A post-hoc analysis was performed to study the possibility that the benefit from exercise was larger in subjects with worse pain at baseline. Fifteen patients in the exercise group were compared to 13 from the control group who had worse than total group median pain score (KOOS Pain 58 on a 0–100, worst to best scale) at baseline. The groups had comparable patient characteristics. The changes seen in these subgroups were however not different from the changes seen in the total groups. A possible limitation could be lack of power. A post-hoc analysis was performed to estimate the number of patients needed to show a clinically significant difference of 11 ± 15 KOOS-points [20]. The standard deviation of 15 is supported by results from randomized controlled trials of glucosamine supplementation [41] and a nutritional supplement [42] for knee osteoarthritis, where significant group differences were found in KOOS pain and ADL subscales. The number of subjects in each treatment arm in these RCT:s ranged from 15 to 27. The standard deviations in KOOS subscales have not previously been determined in exercise interventions. Only one of the five KOOS subscales showed a statistical significant improvement, and it can not be excluded that this result could be due to chance. The improvement of the KOOS subscale Quality Of Life in the exercise group was of doubtful clinical significance, however the improvement persisted over time, and is in accordance with previous findings of impact from exercise on mental health aspects in patients with knee osteoarthritis [31,43,44]. Group dynamics, support, or attention received may possibly have influenced the quality of life more than the exercise itself in the present study. Psychosocial factors are important determinants of physical function [45], and our results suggest that supervised exercises and follow-up are important, and that quality of life should be evaluated in osteoarthritis interventions.\n\nBODY.CONCLUSION:\nA six-week high-intensive exercise program had no effect on pain or function in middle-aged patients with moderate to severe radiographic knee OA. Some effect was seen on quality of life in the exercise group compared to the control group.\n\nBODY.COMPETING INTERESTS:\nThe author(s) declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nCT participated in design, exercise intervention, assessments and follow-ups, statistical analyses and writing. ER participated in design, analysis and interpretation of the data, and critically revised the article. IP participated in design and interpretation of the data and critically revised the article. CE initiated and obtained necessary permissions for the study, arranged the initial funding, and participated in the analyses, interpretation and revision of the manuscript. All authors read and approved the final manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: \n\nBODY.SUPPLEMENTARY MATERIAL:\nAdditional File 1Intensive exercise program CarinaClick here for file Additional File 2Tests of functional performance CarinaClick here for file\n\n**Question:** Compared to No exercise what was the result of Exercise on Knee injury and Osteoarthritis Outcome Score?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
399
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Incisional hernia after upper abdominal surgery: a randomised controlled trial of midline versus transverse incision\n\n ABSTRACT.OBJECTIVES:\nTo determine whether a transverse incision is an alternative to a midline incision in terms of incisional hernia incidence, surgical site infection, postoperative pain, hospital stay and cosmetics in cholecystectomy.\n\nABSTRACT.SUMMARY BACKGROUND DATA:\nIncisional hernias after midline incision are commonly underestimated but probably complicate between 2 and 20% of all abdominal wall closures. The midline incision is the preferred incision for surgery of the upper abdomen despite evidence that alternatives, such as the lateral paramedian and transverse incision, exist and might reduce the rate of incisional hernia. A RCT was preformed in the pre-laparoscopic cholecystectomy era the data of which were never published.\n\nABSTRACT.METHODS:\nOne hundred and fifty female patients were randomly allocated to cholecystectomy through midline or transverse incision. Early complications, the duration to discharge and the in-hospital use of analgesics was noted. Patients returned to the surgical outpatient clinic for evaluation of the cosmetic results of the scar and to evaluate possible complications such as fistula, wound dehiscence and incisional hernia after a minimum of 12 months follow-up.\n\nABSTRACT.RESULTS:\nTwo percent (1/60) of patients that had undergone the procedure through a transverse incision presented with an incisional hernia as opposed to 14% (9/63) of patients from the midline incision group (P = 0.017). Transverse incisions were found to be significantly shorter than midline incisions and associated with more pleasing appearance. More patients having undergone a midline incision, reported pain on day one, two and three postoperatively than patients from the transverse group. The use of analgesics did not differ between the two groups.\n\nABSTRACT.CONCLUSIONS:\nIn light of our results a transverse incision should, if possible, be considered as the preferred incision in acute and elective surgery of the upper abdomen when laparoscopic surgery is not an option.\n\nBODY.INTRODUCTION:\nThe rate of incisional hernia after midline incision is commonly underestimated but probably lies between 2 and 20% [1–5]. Thus, incisional hernia is a major postoperative problem. The treatment of incisional hernia is complicated by high rates of recurrences. Recently, in a randomised controlled trial published by Burger et al. [6], midline incisional hernia repair has been shown to be associated with a 10-year cumulative recurrence rate of 63 and 32% for suture and mesh repair, respectively. The midline incision is the preferred incision for surgery of the upper abdomen, despite evidence that alternatives, such as the lateral paramedian and transverse incision, exist and might reduce the rate of incisional hernia [7]. Various approaches to opening the abdomen have been advocated over time. The choice for a certain incision is dependent on the exposure necessary for the desired procedure to succeed. A midline incision, be it supraumbilical, infraumbilical or both, is an approach especially suited for emergency and exploratory surgery because of the quick and generous exposure that can be achieved within a few minutes [8, 9]. The avascular nature of the linea alba minimises blood loss during this procedure. A supraumbilical transverse incision may be utilised in case exposure of the upper abdomen is desired. During this incision, the damage inflicted to the segmental arteries and nerves is previously described as being minimal [10]. Previously, only one randomised controlled trial, comparing transverse and true midline incisions, has been published specifically addressing incisional hernia incidence [11]. To determine whether the use of a transverse incision is an alternative to a midline incision for open cholecystectomy in terms of incisional hernia incidence, surgical site infection, postoperative pain and hospital stay, this randomised controlled trial was performed. This trial was conducted in an era when laparoscopic cholecystectomy was not yet available. The possibility of low incisional hernia rates after transverse incisions and the fact that little is known about potential advantages incited us to publish the relevant results of this randomised controlled trial which has been performed in the past and has only been reported in a Dutch thesis by one of the authors (H.L.). The primary endpoint of this study was the incisional hernia incidence after 12 months of follow-up. Secondary endpoints included pain and cosmetic appearance.\n\nBODY.METHODS.PROTOCOL:\nSome 150 consecutive female patients were randomly assigned to a midline or transverse incision as an approach for elective cholecystectomy or combined cholecystectomy and cholangiography (with or without consecutive choledochotomy) (75 and 75 patients, respectively). Emergency procedures were excluded from participation. The sample size is based on an incisional hernia rate reduction from 20 to 6% at a power of 80% and an error rate of 5%. Obtaining informed consent was conducted in accordance with the ethical standards of the Helsinki Declaration of 1975. The investigation reported was performed with informed consent from all of the patients and followed the guidelines for experimental investigation with human subjects and was approved by the medical ethics committee. An independent statistician prepared closed, tamper-proof envelopes containing the random allocation (Fig. 1). Patients were randomised for one of the procedures in theatre through the opening of the envelopes.Fig. 1Flow chart of patient inclusion and follow-up Patient-related factors that were recorded were age, body mass and length and date of operation. Operation-related factors that were recorded were the exact nature of the operation, length of the incision, the thickness of the subcutaneous fat, surgeon performing the procedure, as well as the duration of the operation (skin-to-skin time). In the immediate postoperative period, the use, dose and type of analgesics was recorded and a pain score was administered. The use of analgesics (morphine 7.5 mg intra-muscular injection, 4 h minimum interval between consecutive injections) was monitored for 48 h after surgery; the pain score was administered for the first 6 days after surgery. In patients assigned to surgery through a midline incision, the skin was incised from just below the xyphoid process to just above the umbilicus. The abdominal wall was opened in the midline by incising the linea alba. A Collin type (two-bladed) self-retaining retractor was used to maintain exposure. The abdominal wall was closed in one layer using single polygalactin 910 sutures (Vicryl; Ethicon, Amersfoort, The Netherlands). The skin was consequently closed using running monofilament nylon sutures (Ethilon; Ethicon, Amersfoort, The Netherlands). Patients randomised for a transverse incision received a right-sided unilateral transverse incision between 3 and 4 cm below the costal margin. The rectus muscle was incised. The fibres of the external and internal obliques and the transverse muscles were separated in the direction of their course. Exposure was achieved through the use of a manually held single-bladed retractor. Closure of the abdominal wall was achieved by closure of the peritoneum and the posterior rectus fascia using a continuous, polygalactin 910 suture (Vicryl; Ethicon, Amersfoort, The Netherlands). The anterior rectus sheath and the fascia of the internal and external transverses were closed using simple interrupted polygalactin 910 sutures (Vicryl; Ethicon, Amersfoort, The Netherlands). Towards the end of both procedures, a Redon low-vacuum drain catheter was placed, which was guided outside the abdominal cavity approximately 5 cm from the incision. The skin was consequently closed using continuous monofilament nylon suture (Ethilon; Ethicon, Amersfoort, The Netherlands). All patients received a dose of 5,000 IU of sodium–heparin on the morning of the procedure as thrombosis prophylaxis.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nThe Pearson χ2 test was used for comparing percentages. In case of small expected numbers, a Fisher's exact test was performed. Continuous variables were analysed using the Mann–Whitney test. A P-value of 0.05 or less (two-sided) was considered to be statistically significant. Means and medians are expressed ±standard deviation (SD).\n\nBODY.METHODS.FOLLOW-UP:\nPatients returned to the surgical outpatient clinic for evaluation of the cosmetic results of the scar and to evaluate possible complications, such as fistula, wound dehiscence and incisional hernia, after a minimum of 12 months follow-up. The patient and the surgeon evaluated the cosmetic results independently and were asked to rate the scar as unsatisfactory, satisfactory or fine. Furthermore, the length and width of the scar was measured.\n\nBODY.RESULTS.STUDY GROUP:\nSome 150 consecutive patients were randomised for participation in this study during an inclusion period from April 1977 until July 1979. Seventy-five patients received a transverse incision and 75 patients a midline incision (Fig. 1). One patient was withdrawn from further follow-up after developing peritonitis and consequent acute respiratory distress syndrome (ARDS) not related to the closure of the abdominal wall 2 days after surgery (transverse incision group). The patients' average age was 51.9 and 51.4 years for the midline and the transverse incision groups, respectively. Furthermore, no differences were found in the body mass and average length between the two groups (Table 1). A cholecystectomy was performed using a transverse incision in 52 patients and utilising a midline incision in 52 patients also. Fifteen and 16 patients, respectively, underwent a combined cholangiography/cholecystectomy. A further 7 and 6 patients, respectively, were treated with a cholangiography/cholecystectomy plus additional choledochotomy and the postexploratory placement of a T-tube.Table 1Baseline characteristics of the patients undergoing surgery, according to study groupVariableMidline incisionTransverse incisionn = 75n = 74Average age (years) ± SD51.9 ± 14.851.4 ± 13.8Average weight (kg) ± SD71.3 ± 14.568 ± 14.3Average length (cm) ± SD163.5 ± 7.8164 ± 7.3\n\nBODY.RESULTS.SURGEON:\nStaff surgeons performed 17% (13/75 patients) of all procedures performed through a midline incision. The remainder of the procedures through a midline incision was carried out under staff surgeon supervision. Staff surgeons performed 14% of all procedures in the transverse incisions study group (10/74 patients) and supervised the remainder. No statistically significant difference was found between the two randomised groups (P = 0.65).\n\nBODY.RESULTS.DURATION OF SURGERY:\nNo significant difference was noted in the skin-to-skin time (in min) for the two different incisions (Table 2). Surgery utilising midline and transverse incision took 56.9 ± 29.3 and 53.2 ± 26.8 min, respectively (P = 0.35). The total duration of the procedures until extubation (in min) did not differ between the midline and transverse incisions (71.0 ± 30.5 and 67.0 ± 27.3, respectively, P = 0.34).Table 2Length of incision, thickness of subcutaneous fat and skin-to-skin time, according to study groupVariableMidline incisionTransverse incisionP-valueLength of incision (mm) ± SDa164 ± 28140 ± 24<0.0001Thickness of subcutaneous fat (mm) ± SDa34.5 ± 13.030.3 ± 12.40.05Skin-to-skin time (min) ± SDa56.9 ± 29.353.2 ± 26.80.40Width of scar (mm) ± SDb8.3 ± 1.43.3 ± 1.2<0.0001aMeasured during surgery in 75 midline and 74 transverse incisionsbMeasured at follow-up in 63 and 60 midline and transverse incisions, respectively\n\nBODY.RESULTS.PAIN AND ANALGESICS:\nSignificantly more patients, having undergone a midline incision, reported pain on day one, two and three postoperatively (P < 0.0001, Table 3). In the midline incision group, 28/75 patients required no or only one dose of analgesics; the remainder required two or more doses. Thirty-one patients operated through a transverse incision required no analgesics or only one dose; 43 patients (the remainder) required two or more. No significant difference in the use of analgesics was found between the groups (P = 0.69).Table 3Postoperatively reported pain, according to study group, shown as the number of patients reporting pain at the time points indicated (percentage), with the remainder of patients reporting no painTime point after surgeryMidline incision n = 75Transverse incision n = 74P-valuePatients reporting pain, n (%)Patients reporting pain, n (%)3–4 h68 (91)60 (81)0.09First day64 (85)39 (53)<0.0001Second day57 (76)23 (31)<0.0001Third day28 (37)9 (12)<0.0001Fourth day5 (7)3 (4)0.72Fifth day0 (0)1 (1)0.50Sixth day0 (0)1 (1)0.50\n\nBODY.RESULTS.COMPLICATIONS:\nPostoperative complications (Table 4) were seen in 16 out of 75 patients (21%) from the midline incision group and in 15% from the transverse incision group (11 patients) (P = 0.30). Briefly, one patient in each group developed cardiac complications; 8 and 6 patients developed urinary retention after the midline and transverse incisions, respectively (P = 0.59). Surgical site infections were diagnosed in 7 and 3 patients, respectively (P = 0.33).Table 4Rate of complications after surgery, according to study group, shown as the number of patients diagnosed with complications (percentage)ComplicationMidline incisionTransverse incisionP-valuen = 75 n (%)n = 75 n (%)Cardiac1 (1)1 (1)1Urinary retention8 (12)6 (8)0.59ARDS01 (1)0.50Surgical site infection7 (9)3 (4)0.33Haemorrhage1 (1)00.50Pneumonia01 (1)0.50Total17 (23)12 (16)0.30\n\nBODY.RESULTS.DISCHARGE:\nForty-five (60%) and 42 (57%) patients from the patients having undergone a midline or a transverse incision, respectively, were discharged on day 6 or 7 postoperatively. The remaining patients from each group left hospital care on day 8 or later. The duration of hospital admission did not differ between the two types of incision (P = 0.74).\n\nBODY.RESULTS.COSMETICS:\nThe width and length of all incisions was measured during the follow-up visit (Table 2). The mean width of the scar after the healing of the midline incisions was found to be 8.3 ± 1.4 mm. The mean width of the scar after the healing of the transverse incisions was measured to be 3.3 ± 1.2 mm. This observed difference is significant (P < 0.0001). The length of the incisions was 140 ± 24 mm and 164 ± 28 mm for the transverse and the midline incisions, respectively. The difference in scar length was found to be significant (P < 0.0001).\n\nBODY.FOLLOW-UP:\nEighty-one percent of all patients operated through a transverse incision were seen during the follow-up examination (n = 60). Of the patients operated through a midline incision, 63 out of 75 were seen at the outpatient clinic (84%). The patients that were lost to follow-up could either not be traced or had deceased (Fig. 1). The minimum follow-up for the evaluation of cosmetic results and hernia incidence was 12 months and the maximum was 36 months.\n\nBODY.FOLLOW-UP.INCISIONAL HERNIA:\nFrom the patients that had undergone the procedure through a transverse incision, one (1/60; 2%) presented with an incisional hernia as opposed to 9 patients from the midline incision group (9/63; 14%); 95% confidence interval (CI) 7.5–25.4%. This difference in hernia incidence is significant (P = 0.017). No significant correlation was found between the incisional hernia rate and surgical site infection (P = 0.07).\n\nBODY.FOLLOW-UP.SUBJECTIVE COSMETICS:\nPatients and surgeons alike were asked to rate the appearance of the scar during the postoperative follow-up outpatient clinic visit. Both the surgeons and the patients found the scar resulting from the transverse incision to be more cosmetically pleasing (P < 0.0001 and P = 0.03, respectively, Table 5).Table 5Number of patients and surgeons rating the cosmetics of a scar at follow-upScoreMidline incision (n = 63)Transverse incision (n = 60)Patients, n (%)Surgeons, n (%)Patients, n (%)Surgeons, n (%)Unsatisfactory6 (10)25 (40)2 (3)6 (10)Satisfactory16 (25)27 (43)9 (15)12 (20)Fine41 (65)11 (17)49 (82)42 (70)Total63636060Difference between type of incision: patients P = 0.03; surgeons P < 0.0001\n\nBODY.DISCUSSION:\nThis prospective randomised study of transverse and midline incisions for open cholecystectomy shows that a significant reduction of incisional hernia incidence can be achieved through the use of a transverse incision. Only one other study (published in 1980) reported the incidence of incisional hernia after upper abdominal midline and unilateral transverse incision in a randomised trial. No difference between the two techniques (8 and 6% incisional hernia, respectively) was found, but the relatively short follow-up of 6 months, however, may be held accountable for this finding [11]. Three retrospective studies showed rates of incisional hernia of 3.2, 5.4 and 16.5% for midline incision and 1.3, 6.7 and 13.4% for transverse incision without statistically significant differences [12–14]. The possible reason for the rather high incidence of incisional hernia in the midline incision group (14%) may lie in the use of resorbable 910 polygalactin sutures. Nevertheless, the use of the same type of resorbable suture in the closure of the transverse incisions resulted in a 2% hernia rate. There is evidence for the importance of proper technique and choice of incision as a means to reduce incisional hernia being more important than the use of suture material [7]. Furthermore, as mentioned above, it is known that the incidence of incisional hernia in the case of a midline incision lies between 2 and 20%. From our data, the NNT (numbers needed to treat) is calculated to be 8 (95% CI 5–30) and the RRR (relative risk reduction) is 88% (95% CI 23–100%). Luijendijk et al. [15] have published a hernia rate of 2% after Pfannenstiel incisions closed using 910 polygalactin, which is in agreement with our findings in the patients randomised for a transverse incision, emphasising the importance of the incision over the choice of suture material. In our study, significantly fewer patients reported pain on day 1, 2 and 3 after transverse incisions, a result that was also described by other authors [16, 17]. Greenall et al. [18] published a contradictory report (in 1980) in which no significant difference in postoperative pain was found between midline and transverse incisions. The previously mentioned study, however, only analysed 46 out of 572 patients (8%) with regard to pain, which may explain the finding. In the same way, Lacy et al. suspended visual analogue pain scoring in a study comparing midline and transverse incisions for abdominal aortic surgery. Remarkably, the two groups in our study did not differ in terms of postoperative analgesia, a finding that is also reported by Lindgren et al. [17] and Donati et al. [19]. In our study, surgeons as well as patients were significantly more satisfied with the aesthetic appearance after a transverse in comparison with a midline incision. The scars after transverse incisions were found to be significantly shorter and less wide than the midline incisions, which may account for the observed difference. A possible reason for this is that a transverse incision is executed parallel to the prevailing direction of the skin lines on the abdomen and, therefore, the tension on the wound and consequent scar is low. Cholecystectomy has come a long way since this trial. The introduction and widespread acceptance of laparoscopic technique as the treatment of choice has rendered open cholecystectomy to be an operation for exceptional, and perhaps surgically difficult, circumstances. Nowadays, the study reported is hardly feasible, yet, the results are still applicable and very relevant for other surgical procedures in the (upper) abdomen. Knowledge of the favourable results of a transverse incision may aid surgeons in their choice when finding themselves in the unfortunate position of needing conversion to open cholecystectomy. In conclusion, this investigation on transverse incisions might be helpful in reducing the incidence of incisional hernia in patients after open cholecystectomy. The midline incision is a preferred manner to achieve exposure of the abdominal cavity and is considered to be easily performed and quick. Although the midline incision is generally accepted, the incidence of incisional hernias is surprisingly high [1–5]. The choice for a particular incision should not only be based on exposure, but also on hernia incidence reduction, especially since recurrence rates after hernia repair are reported to be very high. Furthermore, the recurrence rate after incisional hernia repair is a disappointing 63 and 32% for suture and mesh repair, respectively [6]. In the light of these results, incisional hernia prevention is warranted. In this investigation, it is shown that a significant reduction (from 14.5 to 1.7%) of incisional hernia incidence was achieved by using a transverse incision. Hence, a transverse incision should be considered as the preferred incision in acute and elective surgery of the upper abdomen in which laparoscopic surgery is not an option. Full exposure of two quadrants is feasible through the use of a unilateral transverse incision in, for example, biliary, bariatric, liver and colonic surgery. The transverse incision should be part of the abdominal surgeon's armamentarium and is a preferable incision to prevent the high incidence of incisional hernia after abdominal surgery.\n\n**Question:** Compared to Midline incision what was the result of Transverse incision on Skin-to-skin time?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
239
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: A prospective, contralateral comparison of photorefractive keratectomy (PRK) versus thin-flap LASIK: assessment of visual function\n\n ABSTRACT.PURPOSE:\nTo compare differences in visual acuity, contrast sensitivity, complications, and higher-order ocular aberrations (HOAs) in eyes with stable myopia undergoing either photo-refractive keratectomy (PRK) or thin-flap laser in situ keratomileusis (LASIK) (intended flap thickness of 90 μm) using the VISX Star S4 CustomVue excimer laser and the IntraLase FS60 femtosecond laser at 1, 3, and 6 months postoperatively.\n\nABSTRACT.METHODS:\nIn this prospective, masked, and randomized pilot study, refractive surgery was performed contralaterally on 52 eyes: 26 with PRK and 26 with thin-flap LASIK. Primary outcome measures were uncorrected distance visual acuity (UDVA), corrected distance visual acuity (CDVA), contrast sensitivity, and complications.\n\nABSTRACT.RESULTS:\nAt 6 months, mean values for UDVA (logMAR) were −0.043 ± 0.668 and −0.061 ± 0.099 in the PRK and thin-flap LASIK groups, respectively (n = 25, P = 0.466). UDVA of 20/20 or better was achieved in 96% of eyes undergoing PRK and 92% of eyes undergoing thin-flap LASIK, whereas 20/15 vision or better was achieved in 73% of eyes undergoing PRK and 72% of eyes undergoing thin-flap LASIK (P > 0.600). Significant differences were not found between treatment groups in contrast sensitivity (P ≥ 0.156) or CDVA (P = 0.800) at postoperative 6 months. Types of complications differed between groups, notably 35% of eyes in the thin-flap LASIK group experiencing complications, including microstriae and 2 flap tears.\n\nABSTRACT.CONCLUSION:\nUnder well-controlled surgical conditions, PRK and thin-flap LASIK refractive surgeries achieve similar results in visual acuity, contrast sensitivity, and induction of HOAs, with differences in experienced complications.\n\nBODY.INTRODUCTION:\nRefractive surgery is one of the most commonly performed elective procedures and will likely maintain its popularity as ablation techniques become more refined and understanding of corneal wound healing improves. Two of the most common methods of refractive surgery are photorefractive keratectomy (PRK) and laser in situ keratomileusis (LASIK). The rapid improvement in vision and lack of postoperative pain associated with LASIK has made this the preferred option with patients compared with PRK, which has greater postoperative discomfort and prolonged recovery of visual acuity.1 Recently, there has been renewed interest in PRK because of increasing concerns of complications associated with LASIK flap creation, including dry eye, corneal ectasia, and flap tears.2–5 Thin-flap LASIK attempts to gain benefits of both techniques by creating a flap of between 80 and 90 μm.6–8 Use of a thinner flap results in a more biomechanically stable cornea and decreases incidence of ectasia given the thicker residual stroma.3,9 Cutting a thinner LASIK flap is less invasive to the nerves within the corneal stroma, decreasing the severity and duration of dry eye, possibly by preserving corneal sensation and blinking rate.10–14 Flap creation avoids corneal epithelium removal, allowing reduced healing time and less haze and scarring.15 The present contralateral study compares the outcomes of eyes that have undergone PRK or thin-flap LASIK using the VISX STAR S4 excimer laser (VISX Incorporated, Santa Clara, CA), with flaps created with intended thicknesses of 90 μm using the IntraLase FS60 femtosecond laser (Abbott Medical Optics [AMO], Santa Ana, CA).\n\nBODY.METHODS:\nData from myopic eyes were analyzed, with or without astigmatism, in which the dominant eye was randomized (Research Randomizer software – Urbaniak, www.randomizer.org) to PRK or thin-flap LASIK (90 μm flap) and the nondominant eye underwent the alternative treatment. All PRK and thin-flap LASIK treatments were performed using the VISX Star S4 CustomVue laser at the John A. Moran Eye Center, Salt Lake City, Utah, between February 2008 and July 2009. All surgeries were overseen by two surgeons (M.M., M.D.M.). The research protocol was approved by the University of Utah Hospital Institutional Review Board. All patients included in this study met the US Food and Drug Administration guidelines for VISX CustomVue LASIK. Mean age of patient, 13 men and 13 women, was 30.8 years (range: 23–46). Twenty-six patients (52 eyes) with stable myopia (1.5–8.5 diopters [D]) and astigmatism (0.242–3.11 D) were enrolled in the study. Eleven patients excluded from this study had clinically significant lens opacities, previous corneal or intraocular surgery, keratoconus, unstable refraction, autoimmune disease, immunosuppressive therapy, or were pregnant or breastfeeding. Correction was made for distance and patients desiring monovision correction were excluded. Contact lenses were discontinued 2 weeks prior to screening for soft contact lens wearers and 6 weeks prior to screening for rigid gas permeable lens wearers. All patients had a preoperative examination including assessment of uncorrected distance visual acuity (UDVA), corrected distance visual acuity (CDVA), tonometry, slitlamp examination of the anterior segment, and dilated fundus examination. Manifest and cycloplegic refractions were repeated on 2 separate visits to ensure reliability and stability. Corneal topography and thickness were measured using the Orbscan II v.3.0 (Bausch and Lomb, Rochester, NY). All eyes received 5 preoperative wavefront analyses with the VISX CustomVue WaveScan aberrometer v.3.62 (Fourier) (AMO), without pharmacologic intervention, under mesopic conditions, with a minimum pupil diameter of 6.0 mm. The contralateral study design was made so that each eye could act as a control for the fellow eye in each patient, allowing for study groups to be well matched. There were no violations in the randomization; all patients were analyzed as originally assigned. The randomization protocol was generated before the trial and known only to the study coordinator. In all patients, the emmetropic correction target was based on manifest refraction and wavefront analysis. All flaps were created with the IntraLase FS60 femtosecond laser at 60 kHz in a raster pattern with bed energy of 1.15 μJ, side-cut energy of 2.00 μJ, and pocket enabled. The flaps were created with an intended thickness of 90 μm, diameter of 8.4 to 9.0 mm, superior hinge angle of 55°, and a side-cut angle of 70°. Intraoperative pachymetry or optical coherence tomography were not performed to evaluate actual flap thicknesses. If the 8.0 mm maximum intended ablation diameter exceeded the flap diameter, the hinge and flap were shielded during ablation. Postoperatively, each eye undergoing thin-flap LASIK received 1 drop of gatifloxacin 0.3% (Zymar; Allergan Inc, Irvine, CA), prednisolone acetate 1% (Pred Forte, Allergan Inc), ketorolac tromethamine 0.4% (Acular LS, Allergan Inc.), and a bandage soft contact lens (Softlens Plano T, Bausch and Lomb, Rochester, NY). The prednisolone acetate was continued hourly during the first preoperative day and 4 times daily for an additional 6 days. The gatifloxacin was continued 4 times daily for 1 week. In eyes undergoing PRK all eyes had their corneas cooled with 15 mL of BSS (2.8–3.9°C) immediately following ablation. This was followed by 1 drop of a gatifloxacin 0.3% (Zymar), prednisolone acetate 1% (Pred Forte), ketorolac tromethamine 0.4% (Acular LS) and a bandage soft contact lens (Softlens Plano T). Ketorolac tromethamine was continued 4 times a day for 3 days and then discontinued. Gatifloxacin and prednisolone acetate were continued 4 times a day for 1 week with a subsequent steroid taper over 2 to 3 months per surgeon preference. Mitomycin C was not administered to any patient in the study at any time. Both bandage soft contact lenses were removed simultaneously once re-epithelialization was complete, typically on postoperative days 3 to 5. Patients were seen 1 day, 1 week, 1 month ± 10 days, 3 months ±14 days, and 6 months ±14 days. At all follow-up examinations, UDVA and CDVA were tested using a standard Snellen eye chart. Visual acuity was recorded in both Snellen notation and logarithm of the minimum angle of resolution (logMAR) format. Contrast sensitivity was measured in controlled mesopic conditions at 3, 6, 12, and 18 cycles per degree (cpd) using the Vectorvision CSV-1000E chart (Vectorvision, Greenville, OH). Higher-order aberrations (HOAs), including coma Z(3,1), trefoil Z(3,3), and spherical aberration Z(4,0), were measured using the CustomVue WaveScan at a mean diameter of 6 mm. Undilated scans of both eyes were taken preoperatively and 1, 3, and 6 months postoperatively. Primary outcome measures were UDVA, CDVA, contrast sensitivity, and complications. HOAs were measured and trended within groups as secondary measures. After the study was completed, the results were compiled and the data unmasked for statistical analysis. Refractive error, visual acuity, and HOAs were treated as continuous variables and analyzed for significance by independent t-tests. In all tests, P values <0.05 were considered statistically significant. Data analysis was done using Microsoft Excel (Microsoft Corp, Redmond, WA).\n\nBODY.RESULTS:\nMean preoperative measurements of UDVA, CDVA, sphere, and cylinder are shown in Table 1. 25 of 26 patients (50 eyes) completed the study at postoperative 6 months. One eye in the thin-flap LASIK group required PRK retreatment following a flap tear and both eyes from this patient were therefore removed from analysis of visual acuity, contrast sensitivity, and HOAs as the retreatment prevented the ability to distinguish results between the 2 surgical methods. The eyes from this patient were still included in the analysis of complications.\n\nBODY.RESULTS.VISUAL ACUITY:\nTable 2 shows visual acuity outcomes at 1, 3, and 6 months postoperatively. Statistically significant differences were found between PRK and thin-flap LASIK in UDVA at 1 month postoperatively, with thin-flap LASIK eyes showing more improvement in UDVA. Visual acuities were not statistically different between the groups at 3 or 6 months.\n\nBODY.RESULTS.STABILITY, EFFICACY, AND PREDICTABILITY:\nTable 3 shows stability, efficacy, and predictability outcomes postoperatively at 1, 3, and 6 months. CDVA was statistically different between groups at 1 month, with 24% of the PRK group losing a line or more from preoperative values, while 9% of eyes in the thin-flap LASIK group lost only 1 line at 1 month. No eyes in the thin-flap LASIK group lost more than 1 line. Also, 39% of eyes in the thin-flap group gained a line by 1 month compared with only 12% of eyes in the PRK group. At 6 months 64% and 56% of eyes had gained a line or more of CDVA in the PRK and thin-flap LASIK groups, respectively (P = 0.462).\n\nBODY.RESULTS.CONTRAST SENSITIVITY:\nContrast sensitivity measurements at 3, 6, 12, and 18 cycles per degree (cpd) in each group are shown in Figure 1. There were no differences between groups at any cpd at any time in the study (P ≥ 0.156). The thin-flap LASIK group showed no change in contrast sensitivity postoperatively (P > 0.131), while patients in the PRK group had a slight decrease in contrast sensitivity at 1 month seen at 3 and 12 cpd (P = 0.004) and (P = 0.025), respectively. At 6 months contrast sensitivity in the PRK group was still significantly decreased from baseline at 3 cpd (P = 0.013), although it did not reach a statistically significant difference at 3 months (P = 0.101).\n\nBODY.RESULTS.COMPLICATIONS:\nTypes of complications differed between the 2 groups. In the PRK group, 2 cases of epithelial defects occurred by 1 week, but had completely resolved by 6 months. Three eyes in the PRK group had mild haze appearing as early as 1 week postoperatively. Haze remained in only 1 eye at 6 months, but was classified as minimal and had no effect on UDVA or CDVA. Nine eyes (35%) in the thin-flap LASIK group experienced complications. In the thin-flap LASIK group, flap debris (1 eye), diffuse lamellar keratitis (DLK, 1 eye), and an epithelial cyst at the edge of 1 flap were observed, with no loss of UDVA or CDVA, and all resolved by 6 months. Microstriae were observed in 6 eyes, one of which was the eye described above with flap debris and the other was the eye with DLK, with no associated loss of UDVA or CDVA, with epithelial proliferation noted as filling the microstria and making them less apparent. Two eyes in the thin-flap LASIK group experienced flap tears intraoperatively – one resulting in mild flap edge scarring by 6 months that had no significant effect on visual function, and the other case affecting vision at 1 month postoperatively which was retreated with PRK at 3 months. As a result of the retreatment with the counter surgical technique, the ability to accurately compare visual acuity, contrast sensitivity, and HOAs between the 2 surgical methods was limited and both eyes from this patient were removed from analysis of these measures, but were still included in the analysis of complications.\n\nBODY.RESULTS.HIGHER-ORDER ABERRATIONS:\nAt postoperative 1, 3, and 6 months, 24 (96%), 25 (100%), and 24 (96%) eyes, respectively, in each group completed CustomVue WaveScan analysis. Total root-mean square (RMS) HOAs, coma, trefoil, and spherical aberrations are compared in Figure 2. There were no significant differences between groups in any HOAs throughout the study (P ≥ 0.101), with all P values at 6 months ≥0.63. In both groups, total HOAs (P < 0.008), spherical (P < 0.002), and coma (P = 0.008 at 3 months; P = 0.024 at 6 months) aberrations were significantly increased compared with preoperative conditions. Trefoil showed no significant change throughout the study in either group (P = 0.298).\n\nBODY.DISCUSSION/CONCLUSION:\nThe present study confirms that PRK and thin-flap LASIK are effective surgeries for the correction of low to moderate myopia. Although thin-flap LASIK showed superior visual results in the early postoperative period there was no statistically significant difference in outcomes of UDVA, CDVA, contrast sensitivity, or total RMS HOAs between PRK and thin-flap LASIK by 6 months. In a similar study comparing PRK and thin-flap LASIK, Slade et al also found that UDVA results were better in the thin-flap group early on and equalized by 6 months.16 Our study showed a similar trend, with no significant differences in any of the primary outcomes at 6 months, and with no difference in UDVA at 3 months. Visual regression in our study was similar to outcomes in Slade's study in which 42% of the PRK group lost a line or more of CDVA and 22% of the thin-flap LASIK group lost 1 line at 1 month postoperatively. Despite the use of custom ablation, postoperative increases in total HOAs, sphere, and coma were noted in our study, as also seen by Slade et al, although they noted that the increase in sphere and coma aberrations was significantly higher in the PRK group at 1 and 3 months postoperatively. As found in previous studies, there was no significant change found in trefoil at any time postoperatively.17,18 Our study showed no difference in induction of HOAs between groups at any time. Although increases in HOAs after refractive surgery have been correlated with decreases in contrast sensitivity in other studies, we demonstrate that increases in total RMS, sphere, and coma were seen postoperatively in both groups without a reliable decrease in contrast sensitivity.19,20 Slade's group found that contrast sensitivity was better in the thin-flap group at all postoperative points in the study, which may have been related to their finding of lower induction of sphere and coma aberrations in the thin-flap group compared with the PRK group. The authors recognize that the Slade study had a larger population size (n = 50 per group) and would have increased power to detect significant differences. Our study would have had increased power of analysis with a similar study group size, but results from analysis of HOAs would not likely change as P values for all HOAs at 6 months were ≥0.63. It would be difficult to make any such correlation between contrast sensitivity and HOAs from the results of this study. A loss of CDVA has been associated with the development of corneal haze in other studies, but as mentioned above none of the patients with visual regression developed haze.21–23 Findings in other studies showing that the biomechanics of eyes that have received thin-flap LASIK treatment are indistinguishable from those of PRK have led to suggestions that thin-flap LASIK is the best approach to LASIK.16 Although the present study did not find any statistically significant differences between thin-flap LASIK and PRK in terms of visual quality at 6 months, complications dealing with flap integrity in the thin-flap LASIK group were present which are not complications found in PRK. Although PRK remains a viable option for those unable to undergo LASIK, the use of thinner flaps may eliminate some of the complications seen with traditional LASIK. Larger studies are needed to better compare the complication rates of both methods and to determine how effective thin-flap LASIK will be in achieving the benefits of PRK and LASIK while avoiding the risks associated with each method. While thinner LASIK flaps attempt to preserve the biomechanical stability of the corneal stroma, at the same time, the flap itself becomes less stable, as was noted with the 2 flap tears and other complications occurring in the thin-flap LASIK group in this study. A study by Espandar and Meyer24 showed that most complications in flaps created by IntraLase femtosecond laser occurred at the hinge, which is where the 2 flap tears that occurred in this study. A thinner flap hinge would be biomechanically less stable and would increase the likelihood of intraoperative flap tear occurrence as well. Six of the 9 eyes with complications in the thin-flap LASIK group had microstriae, which are caused by the flattening of a weak corneal flap unable to maintain its curvature over the small area of stroma removed during ablation. The biomechanics of the flap and hinge, however, cannot be evaluated by the design of this study as analysis was done based on intended flap thickness, which has been shown to vary with the IntraLase FS60 femtosecond laser.25 The study could have been strengthened had intraoperative pachymetry or OCT been performed. Creating a flap with increased integrity would help prevent microstriae from forming and would also provide for a stronger hinge that would be less susceptible to flap tear. Possible ways to optimize flap integrity include modification of hinge and side-cut angle creation, as well as improved planarity and microdisruption of flap edges. This will allow improved adhesion of the flap to the underlying stroma. Continued improvements in laser technology may allow for safer creation of thinner flaps, helping to provide evidence for superior outcomes in thin-flap LASIK, permitting the biomechanical stability of PRK with the visual recovery of LASIK. Custom flap formation that minimizes weak areas susceptible to tearing will be helpful in achieving this difficult balance between corneal and flap integrity.\n\n**Question:** Compared to Pre-surgery baseline what was the result of Photo-refractive keratectomy (PRK) on Contrast sensitivity at 1 month seen at 12 cpd?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
379
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Formoterol DPI 9 μg what was the result of Budesonide/formoterol pMDI 320/9 μg on Incidence of pneumonia?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
247
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Short-term comparative study of high frequency chest wall oscillation and European airway clearance techniques in patients with cystic fibrosis\n\n ABSTRACT.BACKGROUND:\nHigh frequency chest wall oscillation (HFCWO) is standard treatment for airway clearance in the USA and has recently been introduced in the UK and Europe. There is little published research comparing HFCWO with airway clearance techniques (ACTs) frequently used in the UK and Europe. The aim of this study was to compare the short-term effects of HFCWO with usual ACTs in patients with cystic fibrosis hospitalised with an infective pulmonary exacerbation.\n\nABSTRACT.METHODS:\nA 4-day randomised crossover design was used. Patients received either HFCWO on days 1 and 3 and usual ACTs on days 2 and 4 or vice versa. Wet weight of sputum, spirometry and oxygen saturation were measured. Perceived efficacy, comfort, incidence of urinary leakage and preference were assessed. Data were analysed by mixed model analysis.\n\nABSTRACT.RESULTS:\n29 patients (72% male) of mean (SD) age 29.4 (8.4) years and mean (SD) forced expiratory volume in 1 s (FEV1) percentage predicted (FEV1%) 38 (16.7) completed the study. Significantly more sputum was expectorated during a single treatment session and over a 24 h period (mean difference 4.4 g and 6.9 g, respectively) with usual ACTs than with HFCWO (p<0.001). No statistically significant change in FEV1% or oxygen saturation was observed after either HFCWO or usual ACTs compared with baseline. 17 patients (55%) expressed a preference for their usual ACT.\n\nABSTRACT.CONCLUSIONS:\nDuring both a finite treatment period and over 24 h, less sputum was cleared using HFCWO than usual ACT. HFCWO does not appear to cause any adverse physiological effects and may influence adherence.\n\nBODY.INTRODUCTION:\nThe last four decades have seen improved survival in patients with cystic fibrosis (CF). The latest figures estimate the median life expectancy of individuals with CF born in 2000–3 to be approximately 40 years.1 Respiratory failure is the major cause of morbidity and mortality in those with CF.2 Accumulation of secretions in the CF airway precipitates chronic infection, causing a progressive deterioration in lung function and eventually respiratory failure and death.3 Airway clearance techniques (ACTs) are an essential component of the management of patients with CF and are considered standard care.4 There is a range of ACTs which augment the normal mucus clearance mechanisms of the lung to facilitate expectoration. These techniques generally aim to promote secretion clearance by altering airflow and mucus viscosity. Typically, high frequency chest wall oscillation (HFCWO) produces compression of the chest wall via an inflatable jacket linked to an air pulse generator. The generator delivers an intermittent flow of air into the jacket which rapidly compresses and releases the chest wall at a variety of frequencies. Consequently, an oscillation in airflow within the airways is achieved. HFCWO has been shown to enhance central and peripheral mucus clearance.5 A number of underlying mechanisms have been hypothesised including increased airflow-mucus interaction causing a reduction in viscolelasticity, production of an expiratory airflow bias which promotes a cephalad movement of mucus and the enhancement and stimulation of ciliary activity.6 7 Published short-term evidence has demonstrated increased sputum clearance and improved pulmonary function with HFCWO compared with no treatment.8 This and other studies have also compared HFCWO with alternative ACTs. Some have demonstrated increased sputum clearance with HFCWO compared with postural drainage and percussion (PD&P).9–11 Others found no significant difference in sputum clearance between HFCWO and PD&P,8 12 13 positive expiratory pressure (PEP),8 high frequency oral oscillation13 or intrapulmonary percussive ventilation.14 Furthermore, some of these studies found no differences in efficacy related to pulmonary function between HFCWO and PD&P,8 12 13 PEP,8 15 oscillating positive expiratory pressure (Flutter, manufactured by Axcan Scandipharm Inc, Birmingham, AL, USA)16 and high frequency oral oscillation.13 One study reported an improved outcome in forced expiratory volume in 1 s (FEV1) in the longer term using HFCWO compared with PD&P.17 Few trials have compared HFCWO with alternative ACTs which are commonly used in the UK and Europe by individuals with CF. Phillips et al18 compared HFCWO (using the Hayek Cuirass) with the active cycle of breathing techniques (ACBT) in hospitalised paediatric patients. Significantly more sputum was cleared with the ACBT. The authors concluded that HFCWO was not an effective airway clearance treatment for children with CF. It is difficult to compare this study directly with those above, as the Hayek Cuirass machine has a different operating mode to the inflatable vest system. A series of Cochrane systematic reviews have found that no one ACT is superior in terms of respiratory function and efficacy.19 Of a number of published studies on HFCWO, only two were deemed of sufficient quality to be included in these randomised control trial systematic reviews.8 12 HFCWO is widely used in the USA where it is considered standard care in CF.20 It has recently been introduced to the UK and Europe, where the mainstay of care for airway clearance in CF is the ACBT, autogenic drainage (AD) and other airway clearance regimens using small devices.4 In the USA these techniques and devices tend to be considered adjuncts, with PD&P and HFCWO remaining the most common ACTs.20 While there is a body of evidence which equates HFCWO and PD&P, there is a need for further trials to compare HFCWO with alternative ACTs to provide a more relevant evidence base for HFCWO in the UK and Europe. The aim of the present study was to compare the short-term effects of HFCWO with patients' usual ACTs in those with CF admitted to hospital with an acute exacerbation of pulmonary infection. The hypothesis was that HFCWO was superior to patients' usual ACTs.\n\nBODY.METHODS.STUDY PARTICIPANTS:\nAll patients admitted to hospital who met the entry criteria were invited to participate in the study. The inclusion criteria were a diagnosis of CF (established by genotype or sweat sodium >70 mmol/l or sweat chloride of >60 mmol/l), FEV1 ≥ 20% predicted, age ≥16 years and an infective pulmonary exacerbation as defined by Thornton et al.21 Exclusion criteria were current severe haemoptysis, rib fractures, pregnancy, inability to give consent and those whose usual ACT was HFCWO. Informed written consent was obtained for all patients and the study was approved by Brompton Harefield and National Heart and Lung Institute research ethics committee.\n\nBODY.METHODS.STUDY DESIGN:\nA randomised crossover design was used to compare HFCWO with patients' usual ACTs, which allowed within-patient variability to be controlled. Over four consecutive days, patients received either HFCWO therapy on days 1 and 3 and their normal ACT on days 2 and 4 or vice versa. Allocation to HFCWO or usual ACT on day 1 was determined using a computer-generated randomisation table.\n\nBODY.METHODS.PROTOCOLS:\nPatients performed their usual ACT or received HFCWO two times daily at the same time. Before starting the study, each patient's usual ACT was reviewed by an experienced senior respiratory physiotherapist. In addition, patients were familiarised with HFCWO (The Vest). This involved the patients using The Vest for a trial period the day before the start of the study, during which time they were given the opportunity to experience all three protocol frequencies at a variety of pressures. Each airway clearance treatment session lasted 30 min and was supervised by the same physiotherapist to ensure optimisation and standardisation of usual ACT and HFCWO performance. All nebulised and inhaled medications were taken before each treatment session in accordance with the patients' individual regimens.\n\nBODY.METHODS.HIGH FREQUENCY CHEST WALL OSCILLATION:\nThe following regimen was identified as current best practice following an in-depth review of the literature and discussion with clinical experts in the USA. Using The Vest Airway Clearance System Model 4 (Hill-Rom UK Ltd, Leicestershire, UK), each patient was fitted with an appropriately-sized, full torso, inflatable, disposable vest connected to the air pulse generator via two flexible tubes. Patients remained in an upright sitting position throughout the 30 min treatment session. HFCWO was applied for 8 min at each of three frequencies in sequence (10, 13 and 15 Hz) with each frequency followed by a 2 min rest period. The pulse pressure was set according to individual patient's reported comfort at all three frequency settings. During both the HFCWO and rest periods, patients were instructed to huff or cough as they felt necessary in order to expectorate loosened bronchial secretions.\n\nBODY.METHODS.USUAL ACT:\nUsual ACTs were in accordance with the guidelines of the International Physiotherapy Group for Cystic Fibrosis.22 Patients performed their usual ACT for 30 min, and for patients practising an assisted ACT, the physiotherapist provided percussion. Patients were allowed to perform combined ACTs where this was their usual practice. This reflected current international practice more accurately and recommendations that ACTs be adapted on an individual basis.23\n\nBODY.METHODS.OUTCOME MEASURES:\nThe primary outcome measure was wet weight of sputum expectorated during a treatment session. Patients were instructed to expectorate all sputum into a preweighed pot during and for 30 min following each treatment session. They were also instructed to collect sputum expectorated at all other times during each 24 h period. All sputum collected was weighed immediately following collection on weighing scales with an accuracy of 0.01 g (BL310; Sartorious UK Ltd, Epsom, UK). FEV1 was measured using a hand-held spirometer (2120; Vitalograph Ltd, Buckingham, UK) in accordance with internationally agreed standards.24 Measurements were taken immediately before and after a 30 min period following each treatment session. Data were analysed using Spirotrac IV Version 4.30 software (Vitalograph Ltd). Pulsed arterial oxygen saturation (SpO2) was measured transcutaneously at rest, for 5 min immediately before, 30 min during and 30 min immediately following each session. SpO2 was measured with a fingertip pulse oximeter (Konica-Minolta Pulsox-300i; Stowood Scientific Instruments, Oxford, UK). The data were analysed using Download 2001 Version 2.8.0 software (Stowood Scientific Instruments Ltd). The perceived efficacy and comfort of each ACT and the incidence of urinary leakage during treatment were measured using 10 cm visual analogue scales (VAS). Each day, after the last treatment session, patients completed three 10 cm VAS with reference to the ACT used that day. On the VAS used, 0 represented not at all effective/comfortable or no urinary leakage and 10 represented extremely effective/comfortable or a lot of urinary leakage. On the fourth and final day, participants were also asked to indicate which ACT they would prefer. An independent observer, blind to the daily method of airway clearance used, performed the spirometry, weighed the sputum samples and collected the 10 cm VAS throughout the study.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nA sample size calculation determined the number of patients required to test for superiority of HFCWO. This was based on a difference of 4 g of sputum between the usual ACT and HFCWO during a single treatment session. A square-root of within SEM of 4 g at the 5% significance level would require 24 patients to achieve 90% power. Data are presented as mean (SD), median (IQR) or n (%) as appropriate. Continuous variables were analysed using a mixed-effects linear regression model. This was to allow the results to be adjusted for a number of factors which are inherent to the design of a crossover trial. The order of treatment randomisation and the day and time of treatment were all entered into the model and their effect on the outcomes was tested. For this trial, the results were also adjusted for the method and position of treatment in the ACT session. In these models, patients were entered as random effects since it was not of interest to quantify the differences between individual patients, but it was important to account for the repeated measurements on each patient. The estimates of the fixed effect of ACT versus HFCWO are presented as mean (95% CI). A p value of 0.05 was taken to be statistically significant. All analyses were conducted using Stata 9.2 (StataCorp).\n\nBODY.RESULTS.PARTICIPANTS:\nFifty patients were invited to participate in the study, 20 declined, 29 patients completed the study and 1 patient was withdrawn due to a hypoglycaemic episode. Table 1 shows demographic and baseline characteristics of the patients who completed the study. Table 1 Patient demographics and baseline characteristics (n=29) Age (years) 29.4 (8.4) Male (%) 21 (72%) Height (cm) 171 (9) Weight (kg) 60 (11) BMI (kg/m 2 ) 20.4 (2.6) FEV 1 (l) 1.46 (0.72) FEV 1 % predicted 38 (16.7) SpO 2 (%) 94.3 (2.1) Data are presented as mean (SD) or n (%) as appropriate. BMI, body mass index; FEV 1 , forced expiratory volume in 1 s; SpO 2 , pulsed arterial oxygen saturation. Twenty-nine patients were treated with intravenous antibiotics as part of their medical management. All participants received two treatment sessions on each study day and all treatment sessions were 30 min in duration. The mean (SD) length of stay for patients was 14 (5) days and the mean day of entry to the study was day 8 (3) days.\n\nBODY.RESULTS.USUAL ACT:\nUsual ACTs included the ACBT with modified PD&P (41%; n=12) and with modified PD alone (7%; n=2), AD in sitting (28%; n=8) and with modified PD (7%; n=2), PEP (7%; n=2) and Flutter (10%; n=3).\n\nBODY.RESULTS.SPUTUM WEIGHT:\nThe wet weight of sputum expectorated with usual ACT compared with HFCWO is shown in table 2. The mean weight of sputum expectorated during a single treatment session and over a 24 h period was significantly greater with usual ACT than with HFCWO. The mean difference in wet weight of sputum expectorated during a treatment session was 4.4 g (p<0.001) and the mean difference in wet weight of sputum expectorated over a 24 h period was 6.9 g (p<0.001). These findings were not affected by order, time, day or position of treatment. Table 2 Wet weight of sputum expectorated: HFCWO compared with usual ACT Period of sputum collection Expectorated sputum wet weight (g) Usual ACT HFCWO Mean difference p Value Mean (SD) Median (IQR) Mean (SD) Median (IQR) Single treatment session 9.1 (7.9) 7.2 (3.0–14.2) 4.6 (4.1) 3.4 (1.5–6.7) 4.4 (3.5 to 5.4) <0.001 24 h (excluding treatment) * 22.4 (26.8) 12.9 (4.0–29.9) 24.9 (25.8) 15.3 (3.9–40.1) −1.5 (−4.6 to 1.6) 0.352 24 h (including treatment) 39.8 (36.3) 25.5 (14.0–57.1) 34.3 (30.7) 26.3 (12.1–46.0) 6.9 (3.1 to 10.8) <0.001 Data are presented as mean (SD) or (95% CI) or median (IQR) as appropriate. Data are adjusted for randomisation, day, time and position of treatment using a mixed effects linear regression model. * Of 116 24-h sputum samples collected, two were discarded as they were incomplete. ACT, airway clearance technique; HFCWO, high frequency chest wall oscillation. No statistically significant difference was observed in the amount of sputum expectorated when using HFCWO or usual ACT between treatments in a 24 h period.\n\nBODY.RESULTS.PHYSIOLOGICAL MEASURES:\nFEV1 and SpO2 measured before, during and after usual ACT and HFCWO treatment sessions are shown in table 3. Table 3 Forced expiratory volume in 1 s and pulsed arterial oxygen saturation at baseline, during and after treatment with usual airway clearance technique and HFCWO Usual ACT HFCWO Baseline During treatment 30 min after treatment Baseline During treatment 30 min after treatment FEV 1 % predicted 39.1 (16.9) NA 38.9 (17.1) 38.9 (16.8) NA 39.2 (16.7) SpO 2 (%) 94.4 (2.0) 94.4 (1.9) 93.9 (1.6) 94.5 (1.8) 95.0 (1.7) 94.3 (1.7) Data are presented as mean (SD). ACT, airway clearance technique; FEV 1 , forced expiratory volume in 1 s; HFCWO, high frequency chest wall oscillation; NA, not applicable; SpO 2 , pulsed arterial oxygen saturation. \n\nBODY.RESULTS.COMFORT, EFFICACY AND PREFERENCE:\nThe VAS scores for comfort, efficacy and urinary leakage during usual ACT compared with HFCWO are shown in table 4. No significant differences were observed in VAS scores for comfort or urinary leakage between HFCWO and usual ACT. Patients scored the efficacy of their usual ACT significantly higher than for HFCWO (mean difference 14 mm; p=0.002). This was not affected by the order or day of treatment. Of those patients who completed the study, 17 (55%) expressed a preference for their usual ACT over HFCWO. Preference was not predicted by the amount of sputum expectorated. Table 4 Comfort, efficacy and urinary leakage: HFCWO compared with usual ACT Self reported measure Visual analogue scale score (mm) Usual ACT HFCWO Mean difference p Value Comfort 69 (23) 70 (22) −1 (−9 to 7) 0.784 Efficacy 68 (21) 54 (26) 14 (6 to 23) 0.002 Urinary leakage 0 (1) 0 (1) −0.05 (−0.3 to 0.4) 0.791 Data are presented as mean (SD) or (95% CI) as appropriate. Data are adjusted for randomisation, day of treatment and time of treatment using a mixed effects linear regression model. ACT, airway clearance technique; HFCWO, high frequency chest wall oscillation. \n\nBODY.DISCUSSION:\nThere have been few published comparisons between HFCWO using a vest system with the ACTs of the ACBT and AD. This short-term study, carried out in individuals with CF admitted to hospital with an acute infective pulmonary exacerbation, showed that significantly more sputum was expectorated during a single treatment session and over a 24 h period using the patient's usual ACT than with HFCWO. In addition, slightly less sputum was expectorated at all other times (excluding treatment sessions) on usual ACT days compared with HFCWO, but this trend was not statistically significant. These findings were independent of order, time or day and position of treatment. Neither HFCWO nor any of the usual ACTs were associated with any adverse clinical events. A possible factor contributing to the difference in sputum clearance between HFCWO and usual ACT may have been the number and frequency of forced expiratory manoeuvres (FEMs) and the more gentle expiratory manoeuvres of the AD breath that were performed with the usual ACTs. Some studies have standardised the number of coughs and FEMs that patients performed; however, at the time of designing the protocol, the aim was to compare the regimens as currently practised internationally and the frequency of coughs and FEMs was neither standardised nor counted. In retrospect, it would have been of value to have counted the number of coughs and FEMs undertaken during each regimen, but it had not been anticipated that any differences between HFCWO and usual ACTs may be a consequence of the number of FEMs or AD breaths. Theoretically, during the three 8 min periods of HFCWO, fewer FEMs, coughs or AD breaths would be undertaken than during an equivalent period of the ACBT, AD, PEP or Flutter (all of which inherently include FEMs or AD breaths at regular intervals). This difference was supported by observations of the investigators. However, manual cough counts are subject to observer error. Objective cough monitoring using the Leicester Cough Monitor has only recently been validated and should be considered for use in further studies.25 Components of patient satisfaction include efficacy, comfort and convenience. Some studies have formally evaluated patient satisfaction and compliance. One study reported that 50% of subjects chose HFCWO compared with the Flutter, and efficacy was the most frequently cited reason for this choice.16 A later study reported that HFCWO was not preferred over PD&P and intrapulmonary percussive ventilation; furthermore, there was no significant correlation between treatment preference and sputum weight.14 The current study found that patients perceived the efficacy of HFCWO to be statistically significantly less than that of their usual ACT. However, nearly half (45%) of patients expressed a preference for HFCWO. Preference may have been affected by the novelty of a new treatment and it is unknown whether this would continue in the long term. There is no one recommended protocol for the application of HFCWO in the literature. Published studies describe differing numbers and duration of frequencies, length of treatment and airway clearance. Frequencies of 10, 13 and 15 Hz were chosen as it has been reported that maximum mucus transport occurs between 11 and 15 Hz with a peak at 13 Hz.5 6 In addition, the highest oscillated tidal volume flow (peak airflow) occurred between 10 and15 Hz in patients with CF.26 More recent research recommends an individual \"tuning\" method to identify optimum treatment frequencies. These have been shown to vary among individuals and the oscillation waveform,27 but it is unknown whether \"tuning\" increases efficacy. It is possible that a practice effect could have occurred as all patients were new to HFCWO. However, the protocol used in this study did not require the patient to perform any newly learnt physical technique. In addition, the statistical analysis ensured data were adjusted for day of treatment and found no effect. Alternatively, patients' familiarity with their usual ACT may also have had an effect on outcomes. This study was powered to detect a difference of 4 g of sputum expectorated during a single treatment session. Other studies have been based on a difference of 3–3.5 g, which is generally accepted as a clinically important difference.28 29 Wet weight sputum was felt to be an appropriate primary outcome measure in this short-term study in an acute environment. Previous work has found wet weight to be proportional to dry weight sputum.28 30 Emerging non-invasive means of measuring airway clearance may be more sensitive indicators in the future (eg, lung clearance index and electrical impedance tomography). Considering the cost benefit of HFCWO compared with other ACTs and the differing healthcare systems in the USA and the UK, it is unlikely that HFCWO will become the first choice ACT for most individuals in the UK. Further work needs to be undertaken to identify the place of HFCWO in Europe. Patient preference for a treatment regimen may positively influence adherence to treatment in the short term, and nearly half the patients who participated in this study preferred HFCWO to their usual ACT. HFCWO is a safe treatment that facilitates airway clearance in CF but, when compared with patients' usual ACTs, HFCWO led to the clearance of significantly less sputum during a single treatment session and over a 24 h period.\n\n**Question:** Compared to Usual airway clearance techniques what was the result of High frequency chest wall oscillation on Sputum expectoration between treatments in a 24-hour period?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
252
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Impact and Process Evaluation of Integrated Community and Clinic-Based HIV-1 Control: A Cluster-Randomised Trial in Eastern Zimbabwe\n\n ABSTRACT.BACKGROUND:\nHIV-1 control in sub-Saharan Africa requires cost-effective and sustainable programmes that promote behaviour change and reduce cofactor sexually transmitted infections (STIs) at the population and individual levels.\n\nABSTRACT.METHODS AND FINDINGS:\nWe measured the feasibility of community-based peer education, free condom distribution, income-generating projects, and clinic-based STI treatment and counselling services and evaluated their impact on the incidence of HIV-1 measured over a 3-y period in a cluster-randomised controlled trial in eastern Zimbabwe. Analysis of primary outcomes was on an intention-to-treat basis. The income-generating projects proved impossible to implement in the prevailing economic climate. Despite greater programme activity and knowledge in the intervention communities, the incidence rate ratio of HIV-1 was 1.27 (95% confidence interval [CI] 0.92–1.75) compared to the control communities. No evidence was found for reduced incidence of self-reported STI symptoms or high-risk sexual behaviour in the intervention communities. Males who attended programme meetings had lower HIV-1 incidence (incidence rate ratio 0.48, 95% CI 0.24–0.98), and fewer men who attended programme meetings reported unprotected sex with casual partners (odds ratio 0.45, 95% CI 0.28–0.75). More male STI patients in the intervention communities reported cessation of symptoms (odds ratio 2.49, 95% CI 1.21–5.12).\n\nABSTRACT.CONCLUSIONS:\nIntegrated peer education, condom distribution, and syndromic STI management did not reduce population-level HIV-1 incidence in a declining epidemic, despite reducing HIV-1 incidence in the immediate male target group. Our results highlight the need to assess the community-level impact of interventions that are effective amongst targeted population sub-groups.\n\nBODY.INTRODUCTION:\nHIV-1–prevalence declines may now be occurring in some sub-Saharan African countries [1]. However, there remains little direct evidence that prevention measures—rather than natural HIV-1 epidemic dynamics [2] or behaviour change prompted by mortality [3]—have contributed to the slowing of HIV-1 epidemics [4,5]. Syndromic management of sexually transmitted infections (STIs) proved effective early in an HIV-1 epidemic in north-west Tanzania [6]. Peer education to promote safe behaviours showed promise in early process evaluations [7], but a randomised controlled trial (RCT) of factory workers in Harare, Zimbabwe, done in the mid-1990s, proved inconclusive [8]. Subsequent RCTs of syndromic management [9] and mass treatment of STIs [10], together with an information, education, and communication (IEC) behaviour-change programme [9], showed no effect in more mature epidemics. Integrated implementation of synergistic community-based HIV-1 control strategies could be a more cost-effective and sustainable approach to HIV-1 prevention than parallel application of vertical (top-down) programmes [11]. One scientific evaluation of such a strategy has been reported in which a combination of IEC activities amongst the general population and syndromic STI management showed no impact on HIV-1 incidence at the population level [9], although participation in the IEC activities was associated with reduced HIV-1 infection in women [12]. We conducted a cluster-RCT to test the hypothesis that integrated implementation of combined community- and clinic-based HIV-1 prevention, in which IEC activities focus primarily on high-risk populations, can be feasible and effective in reducing HIV-1 incidence in a major maturing epidemic in eastern Zimbabwe (Protocols S1 and S2; Text S1 and S2).\n\nBODY.METHODS.PARTICIPANTS AND RANDOMISATION PROCEDURE:\nThe study communities comprised six pairs of communities matched by socio-economic type—small town, tea/coffee estate, forestry plantation, roadside trading settlement, and subsistence farming area (two pairs) (Figure 1). Each community included at least one Government or Mission health centre. It was anticipated that HIV-1 incidence would be similar within each pair of communities. Within each pair, one community was assigned at random (un-blinded coin toss by a Ministry of Health official witnessed by programme and research personnel) to receive the additional intervention and the other to be the control. These procedures were designed to ensure that Mission, non-governmental organisation, and private sector programmes (for details, please refer to the following section) would be distributed evenly between intervention and control sites. Figure 1Location of Intervention and Control Communities in Manicaland Province, Eastern Zimbabwe We assessed the effect of the intervention using results from laboratory tests for HIV-1 infection and questionnaire data collected in the baseline and 3-y follow-up rounds of a population-based, closed-cohort survey. The 12 study communities were enumerated in a phased manner, with paired communities being enumerated consecutively to minimise the effects of any seasonal factors. HIV-1–prevention activities were commenced in each intervention community shortly after completion of the baseline survey in that community. In each community, individuals eligible for the study were identified in the first round using data from household listings prepared in an initial census. All males and females aged 17–54 y and 15–44 y at last birthday (the age groups expected to have the highest incidence of HIV infection), respectively, who had slept in a household in the community for at least four nights in the previous month, and who had also done so at the same time 1 y earlier, were considered eligible for the study. In heterosexually driven HIV-1 epidemics, risk of infection can be correlated amongst marital partners [13]. Therefore, to maximise statistical power to detect differences in HIV-1 incidence, enrolment was restricted to one randomly selected member per marital group.\n\nBODY.METHODS.INTERVENTIONS:\nIntervention and control communities were to receive standard Government services including basic syndromic STI management, condom distribution from health clinics and Zimbabwe National Family Planning Council outlets, home-based care, and limited HIV/AIDS–focussed IEC activities (e.g., occasional AIDS-awareness meetings and distribution of posters and leaflets). In addition, social marketing of male and female condoms would be provided through an ongoing national programme [14]. The intervention comprised targeted and population-level strategies to promote safer sexual behaviour and to improve treatment of STIs that facilitate HIV-1 transmission. The intervention strategies were implemented by two local non-governmental organisations (Family AIDS Caring Trust and the Biomedical Research and Training Institute) and the Zimbabwe Ministry of Health and Child Welfare through an integrated programme of community- and clinic-based activities. Integration of the individual programme components was achieved through the joint involvement of the participating agencies in the planning and implementation of activities and through the inclusion of biomedical and behavioural aspects within each component. The programme design comprised three key components: (1) peer education and condom distribution amongst commercial sex workers and male clients at workplaces and in the general community, supported by income-generating projects; (2) strengthened syndromic management of STI services at local health centres; and (3) open days with HIV/AIDS IEC activities at health centres to promote safer sexual behaviour and to increase the uptake of local STI treatment services. The peer-education component was based on a model which had been developed by the Project Support Group at the University of Zimbabwe [7] and which had been widely implemented within Zimbabwe and neighbouring countries. Activities were held weekly at workplaces and at locations within the general community (e.g., beer halls and markets) where casual relationships were most frequently formed [15]. The target population comprised sex workers and male clients who form a bridge population in HIV transmission [16] between sex workers and the monogamous (or serial monogamous) majority of women [17,18]. It was posited that the high HIV-1 incidence observed amongst young women could be reduced by altering the behaviour of their older male partners whose own behaviour was intrinsically more risky [19]. The behavioural component would be reinforced in counselling sessions with STI patients and through micro-credit income-generating projects to reduce unmarried women's dependence on commercial sex work. The micro-credit scheme consisted of small interest-free loans repayable over 10 mo, provided to groups and to individuals together with training in small-business management. The targeted activities would be extended to the general population through open days held at local health centres. Besides providing basic HIV/AIDS information, it was envisaged that programme meetings and activities, by their continuous nature, would sustain high levels of awareness of the risks of HIV transmission and would facilitate renegotiation of community social norms, making safer behaviours easier to adopt. The key messages of the programme were: (1) remain faithful to one regular sexual partner; (2) use condoms consistently with any casual sexual partners; and (3) seek prompt and effective treatment for any STIs. Syndromic management of STIs at primary healthcare centres was first introduced in Zimbabwe in the 1980s [20] and formed the basis of STI diagnosis and treatment services at baseline in the intervention and control communities. It was envisaged that these services could be strengthened and made more effective through a programme of regular classroom training and on-site supervision of nursing staff, through the introduction of training in systemic counselling for STI patients, and through the provision of small quantities of treatment drugs to cover delays in routine supplies. Quality-assurance procedures applied in the intervention communities included pre- and post-training tests for peer educators and, for nursing staff, attending the syndromic STI management and systemic counselling courses, regular on-site supervision (including random spot checks) and training, refresher courses, routine planning meetings and monitoring of service statistics, and quarterly workshops where detailed programme procedures were reviewed and updated. An interim qualitative process evaluation of intervention activities was conducted during the inter-survey period, and a report on the findings was provided to the implementing organisations.\n\nBODY.METHODS.OUTCOME AND PROCESS MEASURES:\nThe primary outcome of the study was HIV-1 incidence at the community level amongst individuals who were uninfected at baseline. Blood was collected onto Whatman No. 3 filter paper and transported to the Biomedical Research and Training Institute laboratory in Harare. Blood spots were air dried at 4 °C and, for long-term (>1 mo) storage, were kept at −20 °C. For baseline studies, blood was eluted into phosphate-buffered saline, and antibodies to HIV were detected using a dipstick dot EIA (ICL-HIV-1/HIV-2 Dipstick, [PATH, http://www.path.org; produced locally in Thailand]) and a standard protocol [21,22]. All positive results and a 10% sample of negative results were confirmed using a plate EIA (Abbott Third-Generation HIV-1/HIV-2 EIA [http://www.abbott.com] or Genelavia MIXT HIV-1/HIV-2 [Sanofi Diagnostics Pasteur, Marnes La Coquette, France]). At follow-up, a similar protocol was followed. Only the samples from those participants recorded as being HIV seronegative at baseline were tested at follow-up, again using a dot EIA (ICL-HIV-1/HIV-2 Dipstick, [PATH, produced locally in India]). Where seroconversion was indicated, the frozen stored baseline sample was retested to confirm the original negative result using the same dot EIA test. Where the baseline result remained negative, the Abbott EIA test was used to confirm both baseline and follow-up results. The change in place of manufacture of the dot EIA and the exclusive use of Abbott test kits to confirm positive sera at follow-up was due only to changes in the supply of test reagents, and not to perceived changes in sensitivity or specificity [23]. Apart from the principal investigators (based in Harare, London and Oxford) and those nurses given permission by participants requesting voluntary counselling and testing (VCT), all research personnel remained blind to the HIV-1 status of individual participants. Secondary outcomes, measured at the community and individual level, were self-reported genital ulcers and urethral or vaginal discharge in the past year (STI cases), STI treatment effectiveness (self-reported cessation of symptoms), indicators of sexual and health-seeking behaviour change, and HIV/AIDS knowledge. The behaviour-change variables assessed were sexual debut, sexual partner change in the past year, non-regular partnerships in the past month, and unprotected sex with regular and casual partners in the past 3 y. The data on sexual partnerships and condom use were collected using the Informal Confidential Voting Interview method for 75% of respondents selected at random in the first round of the survey. This method includes procedures to build rapport, ensure a non-judgemental interview approach, and provide reassurance that there are no right or wrong answers to questions of a personal nature, and uses a simple secret voting-box system to reduce embarrassment and guarantee confidentiality in low-development settings [18]. Its use has been shown to be associated with greater disclosure of socially proscribed behaviour in the study population [24]. Process indicators examined comprised changes in knowledge and psychosocial status and indicators of programme coverage and quality.\n\nBODY.METHODS.SAMPLE-SIZE CALCULATIONS:\nInitial sample-size calculations assumed 20% HIV-1 prevalence at baseline, 30% loss to follow-up after 2 y, and 80% power to detect a 40% reduction in HIV-1 incidence in the intervention communities compared with control communities, assuming a background yearly incidence of 2%. Based on six pairs of communities and a co-efficient of variation between communities of 0.15, the required sample size in each community was 1,000. Funding constraints and slower than anticipated implementation of intervention activities led to revisions of the sample size for each community to 800 and the length of follow-up to 3 y, respectively. Assuming a proportionate increase in loss to follow-up to 41%, these arrangements also yielded 80% power to detect a 40% reduction in HIV-1 incidence.\n\nBODY.METHODS.STATISTICAL METHODS:\nTo test the randomisation with small numbers of communities, HIV-1 prevalence, STI history, and socio-demographic characteristics were compared at baseline for study participants in the intervention and control communities, together with uptake of STI treatment and VCT services offered at baseline. Outcome and process indicators were compared for intervention versus control communities. Analysis of the primary outcome was on an intention-to-treat basis. Incident events and person-years at risk of seroconversion were used to calculate HIV-1 incidence rates and unadjusted and adjusted incidence rate ratios (IRR) with 95% confidence intervals (CIs) for each pair of communities. Adjustment was made for sex, 3-y age group, and community-level baseline HIV prevalence. The overall IRRs (unadjusted and adjusted) were taken to be the geometric means of the IRRs for the six pairs of communities. We calculated 95% CIs for each geometric mean as geometric mean ± 1.96 × standard error of the geometric mean. Paired student t-tests on the logarithms of the pair-specific IRRs were used to test whether these differed significantly from unity [25]. The coefficient of variation between communities was calculated based on baseline HIV prevalence using a standard procedure for pair-matched studies [26]. Analyses of prevalence for secondary outcome and process variables were conducted separately for male and female respondents seen at both survey rounds by fitting logistic regression models to the individual-level data and adjusting for community pair and, where available, value of variable at baseline. Since most programme activities were targeted and overall coverage of programme activities was therefore limited, sub-group analyses, adjusted for community pair, were done for HIV-1 incidence and behavioural outcomes to assess the individual-level effects of attendance at programme meetings. Data were entered and validated using SPSS-PC (http://calcnet.mth.cmich.edu/org/spss/index.htm) and data analysis was conducted in Stata version 7 (http://www.stata.com). Statistical tests were double-sided and results were taken to be significant at the 5% level.\n\nBODY.METHODS.ETHICAL APPROVAL:\nAll study participants in the intervention and control communities were offered free VCT for HIV-1, an information sheet on HIV/AIDS, results from a diagnostic test for Trichomonas vaginalis [27] (done at baseline only), and free treatment for T. vaginalis and other STIs from a research nurse. Testing and treatment for T. vaginalis was provided because the prevalence of other curable STIs was low in the study areas [22]. Antibodies reactive with T. vaginalis were detected in DBS eluates following a previously described procedure [27,28]. Written informed consent was sought as a condition of enrolment and continuation in the study. Prior ethical approval was obtained from the Research Council of Zimbabwe, number 02187; the Applied and Qualitative Research Ethics Committee in Oxford, United Kingdom, N97.039; and the UNAIDS Research Ethics Committee, ERC 98/03.\n\nBODY.RESULTS.PARTICIPANT FLOW:\nIn round 1 of the census (July 1998 to February 2000), 5,943 and 6,037 eligible individuals in the intervention (total population size 18,104) and control (18,633) communities, respectively, were selected for recruitment into the study cohort (Figure 2). In round 2, 3 y later (July 2001 to February 2003), 1,044 (23%) and 1,144 (26%) of baseline respondents who were still alive had migrated away from the intervention and control communities, respectively, and were therefore lost to follow-up (Figure 2). At both baseline and follow-up, migrants and non-migrants had similar risks of HIV-1 infection and associated behaviour [29]. Of those still resident in the intervention and control communities, 2,664 (75%) and 2,564 (77%), respectively, were interviewed and blood samples taken for a second time. Temporary absence from the usual place of residence was the main reason for non-participation in the intervention (n = 794, 95%) and control (n = 698, 94%) communities. The overall proportions of baseline respondents followed up at the end of the study were 55% and 56% in the intervention and control communities, respectively. The median follow-up of communities was 3.0 y (range of median within communities, 3.0–3.1). Figure 2Flow-Chart Comparing Participation and Follow-Up Rates in the Intervention and Control CommunitiesIndividuals enrolled in round 1 and still resident in the study communities were considered eligible for participation in round 2.\n\nBODY.RESULTS.BASELINE DATA:\nHIV-1 prevalence was higher in the intervention communities than in the control communities (24% versus 21%, risk ratio 1.13 [95% CI 1.05–1.22], p = 0.001). T. vaginalis infection, secondary school education, and spatial mobility were more common in the control communities, whilst history of genital discharge and uptake of STI treatment and VCT services offered in the survey were low overall but more frequent in the intervention communities (Table 1). However, the differences in each case were small and were unlikely to be clinically meaningful. Table 1 Baseline Characteristics of the Study Populations \n\nBODY.RESULTS.OUTCOMES AND ESTIMATION:\nMedian follow-up per person was 2.9 y (range 1.4–3.9) and 3.0 y (range 1.5–4.1) in the intervention and control communities, respectively. In total, 4,052 individuals had 212 incident events of HIV-1 during 12,009 person-years at risk, giving an HIV-1 incidence rate of 1.77 per 100 person-years at risk. HIV-1 incidence was higher in communities with higher baseline HIV prevalence (IRR 11.49 [95% CI 1.80–73.40], p = 0.010), but this difference disappeared after adjustment for stratification by community type (p = 0.8). HIV-1 incidence was higher in the intervention communities than in the control communities overall, and in each community type, except in the forestry plantations where it was almost identical (Table 2). The difference was not significant after adjustment for sex, age group, and baseline HIV prevalence (IRR 1.27 [95% CI 0.92–1.75], p = 0.012). The observed coefficient of between-community variation was 0.14. Table 2 HIV Prevalence at Baseline and HIV Incidence and IRRs for Intervention Versus Control Communities Looking at outcome indicators for community members (rather than for communities—the unit of randomisation), self-reported STI symptoms were similar in both sets of communities (Table 3). Treatment for STI symptoms in males was effective more frequently in the intervention communities, with men in the intervention community in five of the six matched pairs reporting reduced symptom recurrence. However, more young women in the intervention than in the control communities had started sex, and reports of unprotected sex with a casual partner in the study period were more common in the intervention communities. No differences were observed in consistent condom use with regular partners between the two sets of communities. In the intervention communities, knowledge about HIV/AIDS was enhanced amongst men, and more respondents reported a close relative or family member with AIDS (sex- and age-adjusted prevalence odds ratio 1.22 [95% CI 1.05–1.42], p = 0.009). Slightly more women in the intervention communities reported that condom use within marriage was becoming acceptable, but a greater proportion of men agreed with the statement that \"condoms reduce the pleasure of sex\". Table 3 Biomedical, Sexual Behaviour, and Psychological Outcomes at Follow-up by Residence in the Intervention and Control Communities A total of 63,261 peer-education meetings were held, and 6.8 million condoms were distributed by the programme in the intervention communities (Table 4). Outputs increased over time as new communities entered the programme. However, owing to high inflation and economic decline, the micro-credit income-generating projects proved impossible to implement. We were able to obtain data on STI episodes treated at clinics in the 11 out of 12 study communities that reported cases to the administrative districts of Mutasa and Makoni. In the three intervention communities each in Mutasa and Makoni, STI cases fell by 66% and 51%, respectively, over the 3-y study period. Similar declines of 67% and 52% occurred at clinics in the four control communities in Mutasa and the one control community in Makoni. Coverage of training in syndromic STI management and systemic counselling for nursing staff was high (Table 4). Table 4 Summary of Service Statistics on Programme Output Most of the activities were targeted at high-risk groups. In the general population sample interviewed in the follow-up survey, 1,779 (35%) and 647 (13%) of 5,098 respondents reported attending an HIV/AIDS meeting and a programme meeting, respectively (Table 5). More respondents in the intervention communities than in the control communities attended an HIV/AIDS meeting (41% versus 28%, prevalence rate ratio 1.44 [95% CI 1.33–1.56], p < 0.001) and a programme meeting (20% versus 5%, 4.27 [95% CI 3.52–5.17], p < 0.001), and participation was higher among men than women (prevalence rate ratio 1.32 [95% CI 1.14–1.53], p = 0.002). Fewer women in the intervention communities had heard about HIV/AIDS from external sources or believed that STI drugs were available at their local clinics. Sixty-two (2%) out of 2,528 respondents in the control communities reported spending at least 1 d in the past month in the intervention communities; the equivalent number for respondents in the intervention communities visiting control communities was 70 (3%) out of 2,683. Table 5 Intervention Coverage \n\nBODY.RESULTS.ANCILLARY ANALYSES:\nIn exploratory analysis to assess where the intervention failed, we found that HIV-1 incidence was reduced in males (IRR 0.48 [95% CI 0.24–0.98], p = 0.044) who reported attending programme meetings, after adjustment for the targeting of activities to groups with high-risk behaviour (Table 6). Amongst men who reported one or more casual sexual partners in the past 3 y, fewer of those who attended meetings reported unprotected sex with these partners (prevalence odds ratio 0.45 [95% CI 0.27–0.75], p = 0.002). HIV-1 incidence was not associated with programme participation in women. Table 6 HIV Incidence and IRRs by Meeting Attendance and Sex \n\nBODY.DISCUSSION.INTERPRETATION:\nWe conducted a scientific trial of the feasibility and impact of an integrated community- and clinic-based HIV-1–prevention intervention. The income-generating projects apart, the intervention activities were feasible. The outputs of the programme were extensive with more than 63,000 meetings being conducted and almost 7 million condoms distributed by trained peer educators. Programme messages were considered relevant and realistic. Local STI treatment and counselling services were strengthened and promoted in accordance with the intervention protocol. For male participants, these activities improved HIV/AIDS knowledge, increased the effectiveness of STI treatment, increased consistent condom use with casual partners, and reduced HIV-1 incidence. However, the cluster-RCT results clearly show that the intervention had no positive impact at the community level and suggest possible detrimental effects on the onset of female sexual activity and condom use with casual partners over a 3-y timeframe. Did the cluster-RCT design fail to capture the true effect of the intervention? There are three possibilities: (1) inadequate statistical power; (2) insufficient follow-up; and (3) contamination of intervention within control communities. The study design provided adequate statistical power to detect a meaningful average reduction (40%) in HIV-1 incidence in the intervention versus the control communities over a 3-y observation period. In hindsight, an effect size of 40% was too optimistic and the study had insufficient power to detect a smaller effect. However, there was no trend in the results towards reduced HIV-1 incidence in the intervention communities. Largely due to migration, attrition was close to that anticipated in the study design and was comparable to other recent cohort studies [6,10,9,30]. Migrants had similar characteristics and sexual behaviour to non-migrants [29]. The results of the exploratory sub-group analysis generate the hypothesis that high-risk behaviour was reduced in males attending programme meetings but did not translate into a wider impact on HIV-1 incidence at the population level. Changes in core and bridge populations may take more time to reflect in the general population than was observed in the trial. However, a longer period of follow-up would have increased attrition, and the finding of a possible adverse effect at the population level meant that it would not have been ethical to continue with the same intervention. Future trials of behaviour-change interventions may need to include multiple rounds with phased recruitment and (where interim results are favourable) may need to consider phased intervention implementation. We minimised intervention contamination by selecting physically separated study communities, and movements between intervention and control communities were rare. However, a similar peer-education programme was implemented in one control community (small town), and HIV-1–prevention activity was considerable in all control communities that also had greater access to information from external sources. In some cases, programme messages (e.g., promotion of condom use) conflicted with those of other agencies working in the intervention communities. The effects of these other programmes could have limited our ability to detect a reduction in HIV-1 incidence caused by the current intervention. The absence of an observed effect of the intervention was not explained by differences in HIV-1 prevalence, sexual behaviour, STI cofactors, mobility, or socio-demographic composition at baseline. The earlier sexual debut in females and greater unprotected sex with casual partners seen in the intervention communities during the study period were not present at baseline but could reflect increased willingness to report high-risk behaviours in settings where there was more open discourse about HIV and AIDS. The peer-education programme could have had some effect for male but not for unmarried female participants. Preliminary findings from subsequent qualitative investigations indicate that, in the predominantly rural communities in which the study was conducted, poverty and the associated failure of income-generating projects meant that some peer educators were unable to maintain safer behaviours. Given their increased visibility within the community—intended to enhance their status and self-esteem and, thus, to reinforce their commitment to and role as models for behaviour change—they may, inadvertently, have served as negative role models and, thereby, may have contributed to the greater female early-age sexual activity. Free distribution of condoms by women still engaging in unprotected commercial sex led to their being poorly valued and reinforced their association with promiscuity.\n\nBODY.DISCUSSION.GENERALISABILITY OF FINDINGS:\nEpidemiological context can affect the impact of interventions [31], and structural obstacles can limit the pace and extent to which activities are implemented and the quality of these activities [32]. The HIV-1 epidemic stabilised in eastern Zimbabwe during the study period, with HIV-1 prevalence declining by 40%–50% in young adults [23]. This decline was accompanied by delayed sexual debut, reduced sexual partner change, and consistent condom use with casual partners [33,23]. Prevalence of syphilis, gonorrhoea, and Chlamydia is low, but non-curable herpes simplex virus type 2 remains common [22]. Risk reduction makes transmission more fragile, and an intervention could have a larger effect when set against secular behavioural changes [2]. Mathematical model simulations suggest that there would also be a greater chance of detecting a significant effect of the intervention even though there would be fewer seroconversions to power the calculation [34,35]. Structural obstacles to intervention implementation included HIV/AIDS mortality which disrupted the programme by claiming the lives of two programme coordinators and several of the nursing staff and peer-educators. Economic decline made the income-generating projects unfeasible and reduced the effectiveness of other components of the intervention. We believe that the coverage of the peer-education programme was satisfactory, given the focus on highly sexually active individuals. Meeting coverage could have been under-estimated in the survey since one-to-one discussions and activities at beer halls and other public places may not have been recognised as meetings by those present. However, the high level of spatial mobility limited the number of people who were reached at the required level of intensity and consistency, whilst national shortages of foreign currency restricted fuel and drug supplies, hampered attempts to extend community activities into the more remote rural areas, and disrupted the STI treatment programme in both the intervention and control communities. The intervention that we evaluated could have greater effect where an HIV-1 epidemic is younger, HIV-1 incidence is greater, local sexual networks are less diffuse, background STI control is weak, herpes simplex virus type 2 is less common, population mobility is lower, and/or the socio-economic climate is stable. We cannot rule out an effect of peer education in the urban intervention community since similar activities were implemented in the control community. Targeted peer education may work better in towns where bar-based sex work is more extensive. The absence of reduced HIV-1 incidence in farming estates reinforces doubts raised by the Harare factory workers study [8] concerning the efficacy of workplace peer education.\n\nBODY.DISCUSSION.OVERALL EVIDENCE:\nThese findings are important since the strategies evaluated—i.e., peer education, condom distribution, and syndromic STI management—are theory-based, have the potential for independent effects [11], and are widely promoted [36,37]. Syndromic STI management was effective in a nascent epidemic [6]. However, our disappointing findings echo those from recent trials [9,12] and emphasise the need for alternative strategies of behaviour-change promotion. Social marketing of condoms [14], larger poverty-alleviation programmes to reduce women's reliance on sex work—based on skills training and careful market research rather than on small-scale income-generating projects—and strategies which reach beyond high-activity core groups, such as the Popular Opinion Leader programme [38,39], and client-centred counselling [40], could be more viable and effective in reducing HIV-1 transmission in rural areas. Given the necessary economic conditions, unmarried women may still play a useful role in bar-based programmes since beer halls remain foci for high-risk behaviour [41,15].\n\nBODY.SUPPORTING INFORMATION.TRIAL REGISTRATION:\nThis trial has the registration number ISRNCT00390949 in the International Standard Randomized Controlled Trial Number Register. Found at: http://www.clinicaltrials.gov/ct/show/NCT00390949?order=1\n Protocol S1Protocol(35 KB DOC)Click here for additional data file. Protocol S2Revisions to Protocol(35 KB DOC)Click here for additional data file. Text S1CONSORT Checklist(48 KB DOC)Click here for additional data file. Text S2Ethical Approval, Information Letter, and Consent Forms(2.8 MB PDF)Click here for additional data file.\n\n**Question:** Compared to Communities that received standard Government services what was the result of Communities that received additional education and preventive measures on HIV-1 incidence?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
458
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Repair of Giant Midline Abdominal Wall Hernias: “Components Separation Technique” versus Prosthetic Repair\n\n ABSTRACT.BACKGROUND:\nReconstruction of giant midline abdominal wall hernias is difficult, and no data are available to decide which technique should be used. It was the aim of this study to compare the \"components separation technique\" (CST) versus prosthetic repair with e-PTFE patch (PR).\n\nABSTRACT.METHOD:\nPatients with giant midline abdominal wall hernias were randomized for CST or PR. Patients underwent operation following standard procedures. Postoperative morbidity was scored on a standard form, and patients were followed for 36 months after operation for recurrent hernia.\n\nABSTRACT.RESULTS:\nBetween November 1999 and June 2001, 39 patients were randomized for the study, 19 for CST and 18 for PR. Two patients were excluded perioperatively because of gross contamination of the operative field. No differences were found between the groups at baseline with respect to demographic details, co-morbidity, and size of the defect. There was no in-hospital mortality. Wound complications were found in 10 of 19 patients after CST and 13 of 18 patients after PR. Seroma was found more frequently after PR. In 7 of 18 patients after PR, the prosthesis had to be removed as a consequence of early or late infection. Reherniation occurred in 10 patients after CST and in 4 patients after PR.\n\nABSTRACT.CONCLUSIONS:\nRepair of abdominal wall hernias with the component separation technique compares favorably with prosthetic repair. Although the reherniation rate after CST is relatively high, the consequences of wound healing disturbances in the presence of e-PTFE patch are far-reaching, often resulting in loss of the prosthesis.\n\nBODY:\nReconstruction of giant midline abdominal wall hernias that cannot be closed primarily is a technical challenge to a surgeon. Many surgeons discourage abdominal wall reconstruction because of the technical difficulties, the high morbidity, and the relatively high recurrence rate associated with these procedures. However, many patients with large hernias have invalidating complaints such as bulging of the abdominal wall, chronic wounds, immobility, and back pain, necessitating surgical treatment. The lack of sufficient tissue requires the insertion of prosthetic material or transposition of autologous material to bridge the fascial gap. Reconstruction using pre-peritoneally placed prosthetic material is still the most frequently applied method of reconstruction.1 The increased risk of infection in case of wound complications is a relative contraindication against the use of prosthetic materials. Moreover, interposition of either peritoneum or greater omentum between the bowel and the prosthesis is often impossible, which is another reason to avoid the use of prosthetic material. In 1990 Ramirez, Ruas, and Dellon introduced the \"components separation technique (CST)\" to bridge the fascial gap without the use of prosthetic material.2 The technique is based on enlargement of the abdominal wall surface by separation and advancement of the muscular layers. In this way, defects of up to 20 cm at the waistline can be bridged. Retrospective series report promising results, but no prospective study has been published until now.3–12 It was the aim of this prospective study to compare the results of prosthetic repair with CST in patients with giant abdominal wall hernias that cannot be closed primarily. The primary endpoint of the study was reherniation; secondary endpoints were operation time and postoperative wound complications. In the present report the results of an interim analysis are presented.\n\nBODY.PATIENTS AND METHODS:\nAdult patients (18–80 years) with an incisional hernia after midline laparotomy with a craniocaudal length of at least 20 cm that could not be closed primarily, in whom the repair could be performed under clean or clean-contaminated conditions, and who were not using corticosteroid therapy were asked to participate in the study. Patients with perioperative gross contamination of the operative field were excluded from the study. After written informed consent the patients were randomized between CST and prosthetic repair by the data center of the Radboud University Nijmegen Medical Centre using envelope, the day before operation. Fully trained abdominal wall surgeons who had done at least five procedures of both techniques before the start of the study performed the operations. H.v.G. and R.P.B. performed supervision in centers not having this expertise. Before each procedure, a preoperative chest x-ray was made. Demographic data, co-morbidity (COPD, cardiovascular disease, or diabetes), body mass index, condition of the skin, size of the hernia at the time of the operative procedure, kind of anesthesia, operation time, perioperative blood loss, postoperative ICU stay, analgesia use, complications, hospital stay, and follow-up were recorded on a standard form. The study protocol was reviewed and approved by the institutional ethics commissions of all the participating hospitals. All patients gave written informed consent after receiving a thorough explanation of the study.\n\nBODY.PATIENTS AND METHODS.OPERATIVE TECHNIQUE:\nStandard thrombosis (Nadroparine 2,850 IE) and antibiotic prophylaxis (cefazoline 3 × 1 g and metronidazole 3 × 500 mg) were started preoperatively. After induction of anesthesia (combined general and epidural, if possible) and disinfection of the skin with iodine tincture, an adhesive drape was applied on the skin, if possible. The abdomen was entered via a midline laparotomy or at the lateral edge of the graft if the bowels were covered with a split skin graft. Adhesions between the ventral abdominal wall and the intra-abdominal viscera were cut, after which the length and width of the defect were measured.\n\nBODY.PATIENTS AND METHODS.COMPONENTS SEPARATION TECHNIQUE (CST GROUP):\nThe component separation technique was performed as described in detail in former publications.2,12,13 Briefly, the skin and subcutaneous fat are dissected free from the anterior rectus sheath and the aponeurosis of the external oblique muscle (Figure 1A). The aponeurosis of the external oblique muscle is transected longitudinally about 2 cm lateral from the rectus sheath, including the muscular part that inserts on the thoracic wall, which extends at least 5–7 cm cranially of the costal margin (Figure 1B). The external oblique muscle is separated from the internal oblique muscle as far laterally as possible (Figure 1B). The posterior rectal sheath is separated from the rectus abdominis muscle if tension-free closure is impossible (Figure 1C). The fascia is closed in the midline with a running polydioxanone suture (PDS-loop, Johnson & Johnson, Ltd.) of at least 4 times the length of the incision. The skin is closed over at least two closed suction drains.\nFigure 1.Operative technique of the \"components separation technique.\" 1 = rectus abdominis muscle; 2 = external oblique muscle; 3 = internal oblique muscle; 4 = transversus abdominis muscle; 5 = posterior rectal sheath. A. Dissection of skin and subcutaneous fat. B. Transaction of aponeurosis of external oblique muscle and separation of internal oblique muscle. C. Mobilization of posterior rectal sheath and closure in the midline. Adapted from Bleichrodt et al.13, with permission of Elsevier.\n\nBODY.PATIENTS AND METHODS.PROSTHETIC REPAIR (E-PTFE GROUP):\nThe skin and subcutaneous tissue are mobilized from the underlying fascia of the rectus abdominis muscle. As a consequence all epigastric perforating arteries supplying the overlying skin are separated. After adhesiolysis , a 20 × 30 cm, 1.5-mm-thick e-PTFE patch (Gore-Tex dual mesh plus with holes, W. L. Gore and associates Inc., Flagstaff, AZ, USA) is shaped in size and implanted intra-abdominally as underlay with an overlap of at least 4 cm to the aponeurosis, as described elsewhere.14 The mesh is placed intra-abdominally as an underlay and is sutured under slight tension to the ventral abdominal wall using a double row of interrupted sutures of e-PTFE 1/0 (Gore-Tex 1/0, W. L. Gore and associates Inc., Flagstaff, AZ, USA) that passed the rectus abdominis muscle. The prosthesis is implanted with the microporous side facing the intra-abdominal viscera and the macroporous side facing the fascia. (As a consequence of the large size of the hernias, the fascia could not be closed over the prosthesis in any of the patients in our series.) After implantation, the skin is closed over at least two closed suction drains.\n\nBODY.PATIENTS AND METHODS.POSTOPERATIVE CARE:\nAntibiotic prophylaxis, cefazoline 3 × 1 g and metronidazole 3 × 500 mg was started preoperatively and continued for the first 24 h postoperatively. All patients have epidural anesthesia if possible. Wounds were inspected on a daily basis with respect to hematoma, seroma, skin necrosis, and wound infection. Hematoma was defined as an accumulation of blood in the operative field for which a surgical intervention (puncture or drainage) was needed; seroma as an accumulation of fluid in the operative field for which an intervention (puncture or drainage) was needed in case of mechanical or physical limitations. Skin edge necrosis was defined as necrotic loss of full thickness skin for which surgical intervention was needed. The wound was scored on a daily basis according to CDC criteria, as follows15: grade 1: normal wound, grade 2: erythema and swelling, grade 3: purulent effluent; or grade 4: open wound. Drains were removed after 5 days or if production was less than 50 ml/24 h. The thorax was examined daily by physical examination, and a routine x-ray of the thorax was performed on the second and seventh days after the operation, to detect pneumonia and atelectasis. No specific instructions were given to the patients after operation and patients had no restriction of physical activity except heavy lifting. Follow-up was done in the outpatient clinic at 3, 6, 12, 24, and 36 months after operation. At each visit a physical examination was done to diagnose recurrent hernia. Ultrasonography or computed tomography (CT) scanning was performed on indication, especially to detect small recurrences.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSIS:\nPatients were analyzed as per intention to treat. Hernia recurrence-free survival was compared using the Kaplan-Meier methods according to the intention-to-treat principle.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSIS.POWER ANALYSIS:\nType I and II errors were set to 0.05 and 0.1, respectively. The minimum relevant difference in reherniation between groups was set to 30%, in advantage of CST. Accordingly, a minimum of 84 patients was required (two groups of 42 patients). An interim analysis was planned to evaluate the results of the trial after inclusion of 40 patients. Differences between groups were analyzed using the Fisher exact test for demographic data, preoperative and perioperative data, wound complications, reoperation, and reherniation (Table 1).\nTable 1.Study characteristic of patients with prosthetic repair or components separation techniqueGroup 1: prosthetic repairGroup 2: components separation techniqueSignificance(t-test)Age (mean)58.7 (range: 42–82)53.9 (range: 33–37)NS(Fisher exact test)Gender (women/men)6/126/13NS(t-test)BMI28.7 (range: 21.5–39.6)28.2 (range: 23.9–38.7)NSDefect (median) (cm)(t-test)Length25 (range: 20–30)25 (range: 20–33)NSWidth17 (range: 9–30)15 (range: 7–25)NSSkin (n)(t-test) Intact, full thickness1412NS Intact, split skin47NSAnesthesia (n)(Fisher exact test) General35NS Epidural and general1514NS(t-test)Operative time (min)183 (range 135–254)113 (range 63–175)p < 0.001(t-test)Blood loss (ml)420 (range 100–900)289 (range 50–1000)NSICU stay(Mann-Whitney U-test) Patients (n)63NS Time (days)2 (range: 1–6)5 (range: 1–10)NS(t-test)Pulmonary complications (n)24NS Pneumonia21NS Atelectasis03NSAnalgesia(t-test) Epidural (days)2.4 (range: 0–5)2.4 (range: 0–6)NS Morphine (days)3.3 (range: 0–8)3.6 (range: 0–10)NS(Fisher exact test)Wound complication (n)11NS Hematoma74NS Seroma32NS Skin necrosis23NSInfected mesh (n)70(t-test)Reoperation (in OR) for wound complications (n)72p = 0.05Recurrence (n)1110NSBMI: body mass index; ICU: intensive care unit; NS: not statistically significant; OR: Operation room.\n\nBODY.RESULTS:\nBetween November 1999 and June 2001, 39 patients were included in the study and were operated on by one of 5 surgeons. Two patients were excluded from the study because of gross contamination during operation. Nineteen patients, 6 women and 13 men, were randomized to the CST group: reconstruction using the components separation technique. The mean age of these 19 patients was 53.9 years (range: 33–73 years). Eighteen patients, 6 women and 12 men, were randomized to the e-PTFE group (prosthetic repair). Their mean age was 58.7 years (range: 42–82 years). In the CST group, closure of the fascia was accomplished in 18 of the 19 patients (Figure 2). In one patient the abdominal wall hernia was too large and had to be repaired using a combination of the CST and prosthetic repair. In the e-PTFE group the procedure was successful in 17 of the 18 patients. In one patient the abdominal wall hernia was too large and was reconstructed using a combination of prosthetic repair and CST. No differences were found between the groups with respect to demographic data (Table 1), co-morbidity, length and width of the defect, skin coverage, anesthesia, blood loss, and ICU stay (Table 1). All operations were performed without major intraoperative complications, except for the two excluded patients with gross perioperative contamination. The operation time for prosthetic repair was significantly longer as compared with the components separation technique (p < 0.001, Fisher exact test) (Table 1). This is mainly due to the time-consuming fixation of the patch to the fascia with a double row of single sutures.\nFigure 2.A. Preoperative view of a giant abdominal wall hernia covered with a split skin. B. Postoperative view of the same abdominal wall after reconstruction using the components separation technique.\n\nBODY.RESULTS.POSTOPERATIVE MORTALITY AND MORBIDITY:\nThere was no 30-day mortality. Major wound complications were found in 10 of the 19 patients in the CST group: wound infection (n = 3), skin necrosis (n = 2), hematoma (n = 1). Four patients developed seroma; these were not associated with the aforementioned complications. Major wound complications were found in 13 of the 18 patients in the e-PTFE group: wound infection (n = 2), skin necrosis (n = 3), hematoma (n = 1). Both wound infection and skin necrosis ultimately resulted in loss of the prosthesis (Table 1). Seven patients developed a seroma. In two of these patients seroma puncture was performed to prevent spontaneous evacuation via the midline wound; this resulted in infection and, ultimately, loss of the patch. Seven patches were removed after a median period of 94 days (range: 30–262 days). In the cases where the prosthesis was removed, the abdominal wall defect was reconstructed using CST. Pulmonary complications were found in 4 patients in the CST group and 2 in the e-PTFE group (not significant, Fisher exact test) (Table 1).\n\nBODY.RESULTS.REHERNIATION:\nFollow-up was complete in all patients. Four patients in the CST group died before the end of the follow-up period 5, 9, 10, and 12 months after the operation from unrelated causes. Two had a reherniation at the time of death. Of the remaining 15 patients, 8 had a reherniation. Recurrences occurred after a mean period of 7 months (range: 0.5–12 months). Recurrences were all located in the midline in the upper abdomen and were small. Two patients underwent reconstruction of their recurrence. One patient in whom the reconstruction was performed with a combination of CST and prosthetic bridging had a recurrent hernia at the edge of the prosthesis (Figure 3).\nFigure 3.Kaplan-Meier for recurrent hernia after prosthetic repair (n = 18) and components separation technique (n = 19). Seven of 18 prostheses were removed during the first 7 months after implantation. Reherniation rates after 36 months are similar in both groups.\n\nBODY.RESULTS.PROSTHETIC REPAIR:\nOne patient in the e-PTFE group died 6 months after the operation from an unrelated cause. Of the remaining 17 patients, 7 had an infected prosthesis that had to be removed. The abdominal wall defect was then reconstructed using CST repair. Four other patients had a small recurrent hernia after prosthetic repair, without complaints. Recurrences occurred after a mean period of 22 months (range: 6–36 months). None of these four patients underwent reoperation for their recurrence (Figure 3).\n\nBODY.DISCUSSION:\nThe present study is the first randomized controlled trial comparing different techniques to repair giant midline hernias and the first prospective trial regarding the \"component separation technique.\" Although our series is relatively small, the results suggest that repair of giant abdominal wall defects with the component separation technique compares favourably with prosthetic repair, because wound infection in patients in whom a prosthetic repair was performed had major consequences, resulting in removal of the prosthesis in 7, whereas wound infection in patients after CST had only minor consequences. Disturbed wound healing frequently complicates repair of large abdominal wall hernias. Wound complications such as hematoma, seroma, skin necrosis, and infection are reported in 12%–67% of patients after CST2–5,7–12,16 and in 12%–27% after prosthetic repair. Wound complications are associated with the extensive dissection needed in both procedures, which are often performed after intra-abdominal catastrophes. The risk is further increased by the long duration of the operative procedure and the need to mobilize the skin in dividing the epigastric perforating arteries (Figure 4). This endangers the blood supply of the skin, because then it solely depends on the intercostal arteries, which may have been damaged during former operations by introduction of drains, or by stoma construction and other procedures needed in patients with intra-abdominal sepsis.17–19 Wound complications in our series were rather frequent. Although they are mentioned in most other publications about CST, the method of follow-up is mentioned in only one other study from our own group.12Figure 4.The operation wound after performing a components separation technique for abdominal wall reconstruction, showing the large wound surface and the extensive skin dissection needed. Loss of the prosthesis may also be associated with the choice of the prosthetic material used. Several materials have been developed for hernia repair. In the present series only patients with giant and often complex hernias were included. In the majority of these patients the peritoneum or greater omentum was not available to interpose between the prosthesis and the intra-abdominal viscera. Therefore, an e-PTFE dual patch was used to bridge the fascial gap. The expanded-PTFE dual patch has significantly better mechanical properties than polypropylene-mesh. It is a soft pliable microporous material that causes no mechanical trauma to the viscera. The micropores on both sides of the patch are too small to allow ingrowth of fibrocollagenous tissue, thus preventing fibrous adhesions on the visceral side of the patch. Lack of ingrowth results in insufficient anchorage of the patch to the adjacent fascia, however, and this is a major disadvantage of e-PTFE patches.14,20,21 The patch should be placed as underlay with an overlap of at least 4 cm and fixed to the aponeurosis with a double row of single sutures.14 The e-PTFE patch is prone to infection because of its hydrophobic characteristics. To reduce the infection risk, the e-PTFE patch used is impregnated with silver salts and chlorhexidine, which both have anti-microbial properties and work synergistically.22 Moreover, antibiotic prophylaxis was given to all patients and an adhesive drape was applied to the skin. Nevertheless, 40% of our patients had an early or late infection resulting in removal of the patch. In a recent experimental study in rats with a large abdominal wall defect, it was found that impregnation with silver salts resulted in an aggravated inflammatory response around the patch and an increased reherniation rate.23 This observation may explain the increased risk for seroma formation, which is associated with prosthetic loss in this study. Some patients (n = 3, 16%) were operated under clean-contaminated condition, which means they had an accidental bowel lesion during adhesiolysis without gross contamination. We suspect that most surgeons still place a prosthetic patch for abdominal wall reconstruction in these situations, which is supported by some small series in the literature.24,25 In our opinion polypropylene, which is still the most widely used material for hernia repair, is contraindicated because of its propensity for inducing extensive visceral adhesions and occasional fistula formation.26–28 If large areas of polypropylene mesh are exposed, scar contraction will result in wrinkling of the polypropylene mesh, causing mechanical irritation, which promotes infection and carries the risk of mesh erosion into the skin or the intestine.29 If the polypropylene mesh cannot be covered with full-thickness skin, chronic infection and sinus formation will ultimately result in loss of the mesh.27 Therefore the results probably would not have been better if polypropylene mesh or polypropylene mesh based prosthesis was used. Recurrent hernia still is a major problem The only randomized controlled trial comparing open suture and mesh repair of small ventral hernias was reported by Luijendijk et al. reporting recurrence rates of 46% and 23%, respectively, after a follow-up of 36 months and 63% and 32%, respectively, after a follow-up of 75 months.1,30 In retrospective studies recurrence rates of 25%–63% in suture repair and 8%–25% in mesh repair are reported. Tension-free repair of incisional hernia is a prerequisite to prevent recurrence. In CST a tension-free repair was accomplished. In the literature recurrence rates of 0%–28% have been reported for CST, although how follow-up was accomplished is not well documented in most series.2–12 But it seems impossible to have a reherniation rate, in series of large abdominal wall defects, that is far below the reherniation rate of reconstruction of small abdominal wall defects in a well performed randomized controlled trial.1,30 Despite the high recurrence rate in the present study and our retrospective study, CST remains an attractive technique for repair of giant ventral hernias. Most recurrent hernias are small and asymptomatic and need no further treatment. In addition, the functional and cosmetic results are good and patients were satisfied. In a recent other study in 39 patients undergoing CST repair for heavily contaminated abdominal wall defects, similar results were found with respect to complications and reherniation rate (36%).31 All but one patient indicated satisfaction with the result when compared to their situation before operation. In that study, postoperative quality of life was assessed using the SF 36 questionnaire. When compared to the general population, patients had an average score or higher on pain, vitality, social functioning, and role limitations (emotional problems); the score was below average on physical functioning, role limitations (physical problems), in general health perception, and in mental health.31 On the basis of the interim analysis, the trial was discontinued because the frequency of wound complications resulting in subsequent prosthetic loss was unacceptably high. Because underlay repair necessitates transection of the perforating epigastric arteries in patient with prosthetic repair it was expected that this complication could not be prevented, whereas CST remains possible if the epigastric perforators are spared. Impregnation of the e-PTFE patch with silver salts and chlorhexidine might have contributed to this.23 Recently, a prospective randomized controlled trial has started comparing CST with CST + preperitoneal polypropylene mesh support, combining the advantages of CST and prosthetic repair.\n\n**Question:** Compared to prosthetic repair with e-PTFE patch (PR) what was the result of components separation technique (CST) on Postoperative Mortality?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
336
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Formoterol DPI 9 μg what was the result of Budesonide/formoterol pMDI 160/9 μg on Pre-dose inspiratory capacity?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
417
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Cervical ripening with prostaglandin gel and hygroscopic dilators.\n\n ABSTRACT:\nOBJECTIVE: To study the effectiveness and morbidity of adding hygroscopic cervical dilators to prostaglandin gel for cervical ripening and labor induction. STUDY DESIGN: Patients of at least 34 weeks' gestation with a medical indication for induction of labor and with a modified Bishop score of 5 or less were randomized to receive either prostaglandin gel or prostaglandin gel with hygroscopic cervical dilators. Primary outcomes were time to delivery, change in cervical score, and infection. Secondary outcomes included cesarean delivery rate and deliveries before 24 hours of induction. Continuous variables were analyzed by Wilcoxon sum rank test and categorical data by chi-square or Fisher exact test, with P < 0.05 being significant. RESULTS: Seventeen patients were randomized to intracervical prostaglandin alone and 23 patients received intracervical prostaglandin plus hygroscopic dilators. No demographic differences were noted between the groups. After six hours of ripening, the combined group achieved a greater change in Bishop score (3.6 vs. 2.1, P = 0.007) and tended to have a shorter induction time (21.7 vs. 26.4 hours, P = 0.085). The combined therapy group had a higher infection rate than the prostaglandin-only group (59% vs. 12%, P = 0.003). CONCLUSION: Combining cervical dilators with prostaglandin gel provides more effective cervical ripening and a more rapid induction to delivery interval than prostaglandin alone but with a significant and prohibitive rate of infection.\n\n**Question:** Compared to Prostaglandin gel what was the result of Prostaglandin gel plus hygroscopic cervical dilators on Changes in Bishop score after 6 hours?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
381
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Placebo what was the result of Budesonide/formoterol pMDI 320/9 μg on Incidence of pneumonia?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
454
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Concomitant therapy with Cineole (Eucalyptole) reduces exacerbations in COPD: A placebo-controlled double-blind trial\n\n ABSTRACT.BACKGROUND:\nThe clinical effects of mucolytics in patients with chronic obstructive pulmonary disease (COPD) are discussed controversially. Cineole is the main constituent of eucalyptus oil and mainly used in inflammatory airway diseases as a mucolytic agent. We hypothesised that its known mucolytic, bronchodilating and anti-inflammatory effects as concomitant therapy would reduce the exacerbation rate and show benefits on pulmonary function tests as well as quality of life in patients with COPD.\n\nABSTRACT.METHODS:\nIn this double-blind, placebo-controlled multi-center-study we randomly assigned 242 patients with stable COPD to receive 200 mg of cineole or placebo 3 times daily as concomitant therapy for 6 months during winter-time. The frequency, duration and severity of exacerbations were combined as primary outcome measures for testing as multiple criteria. Secondary outcome measures included changes of lung function, respiratory symptoms and quality of life as well as the single parameters of the exacerbations.\n\nABSTRACT.RESULTS:\nBaseline demographics, lung function and standard medication of both groups were comparable. During the treatment period of 6 months the multiple criteria frequency, severity and duration of exacerbations were significantly lower in the group treated with cineole in comparison to placebo. Secondary outcome measures validated these findings. Improvement of lung function, dyspnea and quality of life as multiple criteria were statistically significant relative to placebo. Adverse events were comparable in both groups.\n\nABSTRACT.CONCLUSION:\nConcomitant therapy with cineole reduces exacerbations as well as dyspnea and improves lung function and health status. This study further suggests cineole as an active controller of airway inflammation in COPD by intervening in the pathophysiology of airway inflammation of the mucus membrane.\n\nABSTRACT.TRIAL REGISTRATION:\nISRCTN07600011\n\nBODY.INTRODUCTION:\nChronic obstructive pulmonary disease (COPD) is considered to be a multi-component disease comprising structural and functional changes inside and outside the lungs. Effective medications for COPD are available and can reduce or prevent symptoms, increase exercise capacity, reduce the number and severity of exacerbations and improve health status. In common clinical use are bronchodilators as β-agonists, anticholinergic drugs and methylxanthines as well as glucocorticosteroids. The clinical effectiveness of these drugs has been shown in many controlled clinical studies [1-7]. Airway inflammation and mucociliary dysfunction in COPD patients have direct clinical consequences on the decline of lung function. As a consequence of cigarette smoking the ciliated epithelium is damaged and the mucus membrane becomes inflamed, resulting in decreased mucociliary transport leading to an accumulation of mucus within the airway so that the likelihood of recurrent respiratory infection is increased. Cineole has positive effects on the beat frequency of the cilias in the mucus membrane and has bronchodilating and anti-inflammatory effects. Therefore, it is appropriate to postulate that cineole will show positive influence on the exacerbations as well as on the lung function in COPD patients – even as concomitant therapy [8-13]. We conducted a randomised, placebo-controlled multi-center trial with the concomitant prescription of cineole – the main constituent of eucalyptus oil – in patients with stable COPD. The primary hypothesis was that cineole would decrease the number, severity and duration of exacerbations. Secondary outcome measures were lung function, severity of dyspnea and quality of life as well as relevant adverse effects.\n\nBODY.MATERIALS AND METHODS.ENROLMENT OF PARTICIPANTS:\nParticipants were recruited in the offices of 4 general practitioners and 7 specialists in pneumology in Germany. The study was carried out during the winter seasons 2003/2004 and 2004/2005 over a treatment period of 6 months in the winter and starting the enrolment in September at the earliest. The participants were 40 to 80 years of age and had airflow limitation with FEV1 of less than 70% and more than 30% of the predicted value (moderate to severe COPD; according to GOLD classification stages 2 and 3 of COPD) [14]. Patients with an increase of more than 15% and more than 200 ml in FEV1 after inhalation of β-agonists (at least 200 μg Salbutamol or equivalent) were excluded according to the definition of COPD of the German Airway-League. [15]. All patients were current smokers or ex-smokers with at least 10 pack years. Patients were excluded if they had severe medical conditions such as bronchial carcinoma, myocardial infarction, alcoholism, heart failure. All randomised patients provided written informed consent and the protocol was approved by the local Ethics Committees at each of the 11 participating centres.\n\nBODY.MATERIALS AND METHODS.TREATMENT GROUPS:\n242 patients were randomly assigned to one of the two treatment groups with stratification according to the clinical centres. All patients were given the necessary dose of capsules each containing 100 mg cineole or no active ingredient. For each group 2 capsules 3 times daily were prescribed resulting in a dose of 600 mg per day for the cineole or no cineole for the placebo group as concomitant therapy. Patients were instructed to take the capsules half an hour before meal so that they could not recognize the smell of cineole. Capsules with active substance and placebo looked absolutely identical and were sealed in blister stripes. The diagnosis of COPD was confirmed according to the current guidelines of \"Global Initiative for Chronic Obstructive Lung Disease\" (GOLD). Frequency, duration, severity and symptoms of exacerbations were defined according to the literature [16-18]. An exacerbation was documented when the duration was more than 3 days or a complex of at least 2 respiratory adverse events with a duration of more than 3 days occurred. Exacerbation severity was defined as: mild (Score = 1, increased need for basic medication of COPD which the individual can manage in its own normal environment), moderate (score = 2, increased need for medication and he/she feels the need to seek additional medical assistance) and severe (score = 3, patient recognise obvious and/or rapid deterioration in conditions requiring hospitalisation). Details for the number, duration and severity as well as treatment and symptoms of exacerbations were recorded in the patient's diary for each day. Since the most relevant differentiation for exacerbations are frequency, duration and severity, the multiple criteria were combined as primary outcome measures for the statistical evaluation. Secondary outcome measures were the single parameters of the exacerbation as well as lung function, symptoms and quality of life. Spirometric measurements were carried out before the beginning of the study determining reversibility of the airflow limitation by inhalation of short acting β2-agonists to assure that the reversibility of lung function was less than 200 ml or 15%. Spirometric measurement included determination of forced expiratory volume in 1 second (FEV1), forced vital capacity (FVC) and vital capacity (VC) at the beginning and after 3 and 6 months. Additionally, symptoms score were determined for dyspnea (scores: 0 = caused no problems, 1 = caused occasionally problems, 2 = caused a lot of problems, 3 = the most important problem the patient had), weekly frequency of dyspnea (scores: 0 = no day was good, 1 = 1–2 days were good, 2 = 3–4 days were good, 3 = nearly every day was good, 4 = every day was good), general conditions (scores: 0 = good, 1 = impaired, 2 = bad, 3 = very bad, 4 = unbearable), cough (scores: 0 = never, 1 = rarely, 2 = occasionally, 3 = often, 4 = very often, 5 = nearly continuously). Diagnosis-related quality of life was determined according to the \"St. George's Respiratory Questionnaire\" [19].\n\nBODY.MATERIALS AND METHODS.VISITS AND RANDOMIZATION:\nBefore randomisation we ascertained the patients' eligibility and conducted spirometry. After the randomisation the following parameters were recorded: height, weight, age, time since first symptoms for the diagnosis of COPD, documentation of allergies, concomitant disease, smoking habits (documentation of pack years), number of exacerbations in the year before during winter time, determination of quality of life and current maintenance therapy. The following control visits were carried out after 1, 2, 3, 4, 5 and 6 months recording exacerbations since last visit, frequency of dyspnea, characterisation of dyspnea, hypersecretion and cough as well as adverse events, compliance and change of therapy. Spirometry was carried out at the beginning of the study as well as after 3 and 6 months of treatment. Quality of life was determined at the beginning and at the end of the study.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nThe proposed sample size for the present trial was 240 patients for both treatment groups. The sample size was chosen to detect a minimum difference of 15% of exacerbations after 6 months of treatment. Analysis of efficacy was performed with the intention-to-treat-population including all eligible patients who received at least one dose of medication and had at least one follow-up visit. The number of all exacerbations, duration of exacerbations, degree of severity of exacerbation recorded in patients diary during the 6 months treatment period were summarised and the sums compared according to Wei-Lachin's directional test of multiple criteria (equally weighted) [20]. Additionally, single parameters characterising the exacerbations and dyspnea were analyzed exploratory as secondary outcome measures at multiple endpoints according to Wei-Lachin validating the sum-formation. The Wilcoxon-Mann-Whitney-U Test was used for all other secondary outcome measures. Data are expressed as mean values (with SD) and all tests were two-tailed. P-values of 0.05 or less were considered to indicate statistical significance.\n\nBODY.RESULTS:\nA total of 242 patients were randomised and received at least one dose of study medication. 22 patients were excluded from the statistical analysis of efficacy because they did not meet the requirements of the GOLD guidelines since FEV1/VC was > 0.7. 220 patients were eligible according to the GOLD guidelines having COPD of stage II and III. The two treatment groups were well matched with respect to baseline characteristics (table 1). The mean age of the participants at entry was 62 years in both groups. The mean duration of COPD of 13 years as well as 31 pack-years and the basic medication (i.e. ICS, β-agonists, anticholinergics and theophylline) were balanced between the two groups (table 2). Medication was not changed during the treatment period except in occurrence of exacerbations. The baseline lung function and reversibility in both groups were comparable. Treatment compliance was determined by counting the study medication at each visit and was found high and comparable across the treatment groups. Table 1 Base Line Characteristics of the Patients* CHARACTERISTIC PLACEBO (N = 110) CINEOLE (N = 110) Age – yr Mean 62.5 ± 10.2 62.2 ± 9.1 Range 40 – 79 41 – 79 Sex – M/F 75/35 66/44 Weight – kg Mean 79 ± 16 79 ± 14 Range 48 – 120 52 – 113 Height – m Mean 1.71 ± 8.8 1.70 ± 8.0 Range 1.48 – 1.90 1.54 – 1.92 Years since appearance of COPD Mean 12.8 ± 9.7 13.6 ± 10.9 Range 1 – 56 1 – 59 Severity of COPD [number of patients] Moderate COPD (II) 69 68 Severe COPD (III) 41 42 FEV 1 /VC [%] 58.0 58.7 FEV 1 [l] 1.61 ± 0.5 1.62 ± 0.5 FEV 1 % predicted value 54.4 54.9 Reversibility (increase of FEV 1 after inhalation of β-agonist) [%] 5.5 4.5 Allergies (number) 10 9 Pack years 31.5 ± 19 31.3 ± 16 * Plus – minus values are means ± SD. Table 2 Constant concomitant therapy THERAPY PLACEBO (N = 110) CINEOLE (N = 110) Inhaled β-agonists* (LABA and SABA) 83 88 Inhaled anticholinergics 29 35 Inhaled corticosteroids (ICS) 27 25 Theophylline 38 32 * including combinations \n\nBODY.RESULTS.PRIMARY OUTCOME MEASURES.EXACERBATIONS:\nAt baseline the mean exacerbation rate was 3.2 in both groups during the previous year. The number of patients with exacerbations during the treatment period in the cineole group was 31 patients (28.2%) and 50 patients (45.5%) in the placebo group. As primary outcome measure the sum of exacerbations for frequency, duration and severity at all 6 following visits as composite endpoint (equally weighted) were calculated according to the Wei-Lachin Test procedure for multiple criteria and showed a statistically significant difference for the primary outcome measure between both treatment groups (p = 0.0120) Table 3. Calculating these single parameters alone exploratory according to Mann-Whitney-U it could be proven that they were statistically significant too (i.e. for frequency 0.0069 an, duration 0.0210 and for severity 0.0240). Validating these results by Wei-Lachin-Test procedure for multiple endpoints for the number, the degree and the severity of exacerbations, the degree during the 6-month treatment the differences between both treatment groups were statistically significant (p = 0.0016, 0.0031 and 0.0025) which underlines higher sensitivity of this test-procedure. Medication of the exacerbations with additionally applied corticosteroids occurred in 17 cases in the cineole and in 25 cases in the placebo group which was not statistically significant different. Table 3 Mean of sum of number, duration and severity of exacerbations during 6 months of treatment with cineole or placebo* PLACEBO CINEOLE SCORE SCORE P VALUE† Sum of exacerbations (number)# 0.9 ± 1.46 0.4 ± 0.82 0.0069 Sum of duration (days)# 5.7 ± 8.9 4.0 ± 10.9 0.0210 Sum of severity (score)# 1.4 ± 2.2 0.8 ± 1.5 0.0242 Summarized parameter (directional test) 0.0120 * Plus – minus values are means ± SD. † P-Values are for the comparison between the two groups. # The sum of the exacerbation parameters is calculated by addition of the documented parameters at all visits. \n\nBODY.RESULTS.SECONDARY OUTCOME MEASURES.LUNG FUNCTION:\nPatients only discontinued inhaled β2-agonist prior to spirometry testing. After inhalation of a β2-agonist the reversibility of lung obstruction (increase of FEV1) at the start of the study was 4.5% in the cineole group and 5.5% in the placebo group (table 1). After 6 months of treatment the mean FEV1 increased by 78 ml (4.7%) in the cineole group (table 4). The mean differences between both groups were not statistically significant (p = 0.0627). After 6 months of treatment an increase of FVC by 62 ml (2.7%) after cineole therapy and a decline of 25 ml (1.1%) after treatment with placebo was determined. The difference concerning change of FVC and VC between both treatment groups was not clinically relevant. Table 4 Secondary outcome measures during 6 months Of treatment with cineole or placebo for change of lung function and dyspnea symptoms * LUNG FUNCTION AND SYMPTOMS PLACEBO CINEOLE BASE LINE 3 MONTHS 6 MONTHS BASE LINE 3 MONTHS 6 MONTHS p-Value FEV 1 [l] 1.61 ± 0.5 1.62 ± 0.5 1.61 ± 0.5 1.62 ± 0.5 1.67 ± 0.5 1.70 ± 0.6 0.0627 † FVC [l] 2.23 ± 0.8 2.25 ± 0.8 2.22 ± 0.7 2.33 ± 0.8 2.36 ± 0.9 2.36 ± 0.9 0.2409 † VC [l] 2.81 ± 0.8 2.71 ± 0.7 2.68 ± 0.8 2.80 ± 0.8 2.73 ± 0.8 2.72 ± 0.9 0.2060 † Trouble in breathing # 1.8 ± 0.9 2.1 ± 0.9 2.2 ± 1.0 1.9 ± 0.9 2.4 ± 1.0 2.5 ± 1.1 0.0103 & Dyspnea in the morning $ 1.1 ± 0.7 0.9 ± 0.7 0.7 ± 0.7 1.1 ± 0.8 0.7 ± 0.7 0.5 ± 0.6 0.0466 & Dyspnea at rest $ 0.7 ± 0.7 0.4 ± 0.6 0.4 ± 0.6 0.6 ± 0.6 0.3 ± 0.5 0.3 ± 0.5 0.0156 & Dyspnea during exercise $ 2.0 ± 0.6 1.8 ± 0.7 1.7 ± 0.8 2.0 ± 0.6 1.7 ± 0.7 1.5 ± 0.9 0.1252 & * Plus – minus values are means ± SD. Higher scores on the symptoms-sum-score indicate more disease activity. † P-Values are for the comparison of the changes from base line to 6 months between the two groups. & P-Values for the comparison are calculated by the multiple criteria calculation of 6 visits by Wei-Lachin between the two groups. # Scores: 0 = no day was good, 1 = 1–3 days were good, 2 = nearly every day was good, 3 = every day was good in a week. $ Scores: 0 = did not cause any problems, 1 = sometimes caused problems, 2 = caused a lot of problems, 3 = the most important problem the patient had \n\nBODY.RESULTS.SECONDARY OUTCOME MEASURES.DYSPNEA:\nThe differences between both groups after 6 months of treatment are summarised in table 4. The baseline dyspnea scores in the morning, trouble in breathing, dyspnea at rest and dyspnea during exercise were similar in both groups, indicating a moderate level of a dyspnea for most patients at the beginning of the treatment period. Calculating the values at all 6 visits at multiple endpoints the difference between both treatment groups were statistically significant for trouble in breathing, dyspnea in the morning and dyspnea at rest. Dyspnea during exercise did not show a statistically significant difference between treatment groups.\n\nBODY.RESULTS.SECONDARY OUTCOME MEASURES.QUALITY OF LIFE:\nAt 6 months the mean improvement of SGRQ total symptom score was -9.1 after treatment with cineole and -4.1 after treatment with placebo (table 5). The difference between treatment groups was not statistically significant (p = 0.0630). The improvement of the symptom score was statistically significant (p = 0.0224). The differences of changes of activity score and impact score were not statistically significant between the two groups. Table 5 Secondary outcome measures for saint george's respiratory questionnaire (sgrq): Change of total symptom score, symptom score, activity score and impact score During 6 months of treatment with cineole or placebo* SGRQ SCORES PLACEBO CINEOLE P VALUE † BASE LINE 6 MONTHS BASE LINE 6 MONTHS Symptom score 57.4 ± 20.2 48.5 ± 24.9 57.3 ± 20.4 43.8 ± 24.3 0.0224 Activity score 53.4 ± 21.9 50.0 ± 24.8 52.1 ± 20.5 43.5 ± 22.4 0.2032 Impact score 37.2 ± 20.9 33.9 ± 23.3 35.8 ± 20.2 27.4 ± 19.2 0.1126 TOTAL SYMPTOM SCORE 45.6 ± 18.9 41.3 ± 22.5 44.4 ± 17.8 34.5 ± 18.9 0.0630 * Plus – minus values are means ± SD. Lower scores on the scores indicate higher quality of life. † P-Values are for the comparison of the changes in scores from base line to 6 months treatment between the two groups. \n\nBODY.RESULTS.MULTIPLE CRITERIA:\nSymptomatic of COPD patients is characterized by lung function, dyspnea and quality of life. In order to include these relevant secondary outcome measures together we used these parameters equally weighted as multiple criteria. The increase of FEV1, amelioration of dyspnea and improvement of total score of \"SGRQ\" were calculated according to the Wei-Lachin Test procedure for multiple criteria and showed a statistically significant difference for the relevant secondary outcome measure between both treatment groups (p = 0.0024).\n\nBODY.RESULTS.MULTIPLE CRITERIA.OTHER FINDINGS:\nConcomitant therapy with β-agonists and anticholinergics, corticosteroids or combinations and methylxanthines in both groups were comparable (table 2). The global assessment of efficacy showed a significant difference, which correlated with the amelioration of clinical findings after treatment with cineole.\n\nBODY.RESULTS.SIDE EFFECTS:\nAll patients receiving the study medication (including those with FEV1/VC > 0.7) were included in the safety examination. During treatment side effects were seen in 22 patients whereas in 17 cases adverse events were not related to the study medication. In the placebo group 11 adverse events were estimated not being related to the study medication whereas 2 cases were interpreted as being related to the study medication (heartburn). During treatment with cineole 9 cases of adverse events were reported whereas 6 adverse events were reported not being related to the study medication. In 3 patients (nausea, diarrhoea, heartburn) the adverse events were estimated being related to the study medication. The difference between the two treatment groups was neither clinically relevant nor statistically significant. Safety examinations of the global assessment showed no difference between the two treatment groups. During the 6 months of treatment compliance was good in all patients.\n\nBODY.DISCUSSION:\nPatients with COPD experience exertional breathlessness caused by bronchoconstriction, mucous secretion, edema of the airway wall and loss of attachments to the terminal airways [14]. Hence pharmacological therapy has focused on the treatment of airway obstruction and inflammation to improve symptoms primarily dyspnea as well as health status. Bronchodilators are the mainstay of pharmacotherapy for patients with COPD. On the other hand it is well known that mucociliary dysfunction has direct clinical implications. Mucus is beneficial in normal quantities but in case of mucus hypersecretion when cilia fail, the mucus pool allows bacterial colonisation. The presence of pooled bacteria results in the release of bacterially-derived toxins that destroy the underlying epithelium and trigger a neutrophilic response [21]. Taking into account the known pharmacological effects of the defined natural product cineole it was assumed that this compound might be beneficial for patients with COPD. Exacerbations have been shown to be reduced in various studies evaluating treatment with inhaled β-agonists or corticosteroids or combinations. The major finding of the present study is that cineole provides a significantly greater reduction of frequency, duration and severity of exacerbations than placebo. The exacerbations were analyzed as multiple criteria for the relevant specifications frequency, duration and severity. The result for the primary outcome measure could be validated exploratory for the single parameters showing a statistical significant difference too. Therefore, both testing procedures are valid whereas the testing multiple criteria is more sensitive. This proof of efficacy is an important contribution to the known pharmacological properties of cineole which therefore is not a mucolytic agent only. The result of this study suggests important new evidence of superior therapeutic efficacy of additional therapy with cineole to better control COPD exacerbations compared to the currently recommended combined therapy with ICS and LABA. Furthermore, additional therapy with cineole may positively interact with anti-inflammatory activity of recommended airway therapies in COPD and may serve to protect airways from other environmental agents. In general, quality of life deteriorates slowly in patients with COPD. During the period of 6 months treatment of this study we observed a decrease of the scores of SGRQ in both treatment groups. The reason for this finding in the placebo group, too, seems to be due to patients receiving better medical attention when involved in clinical trials. The higher rate of exacerbations in the winter before the study began in both treatment groups is due to the same reason. Our present data with cineole therapy underline a greater improvement than after treatment with placebo. Differences in change of FEV1 were not statistically significant (p = 0.0627). These findings correlate with a decline of FEV1 in the placebo group of 0.4% and an increase of 4.8% in the cineole group. This value is nearly identical with the increase of FEV1 after the inhalation of β-agonists, when testing the reversibility, before concomitant therapy with cineole started for six months.\n\nBODY.CONCLUSION:\nThese collective findings underline that cineole not only reduces exacerbation rate but also provides clinical benefits as manifested by improved airflow obstruction, reduced severity of dyspnea and improvement of health status. Therefore, cineole can provide a useful treatment option for symptomatic patients with COPD in addition to treatment according to the guidelines. These results have to be seen in context with socio-economic aspects. As COPD is an extremely costly disease and a cause of major financial and social burden concomitant therapy with cineole can be recommended, especially due to the lack of relevant side effects and relatively low cost. The results of our study provide good evidence that cineole will show benefits as additional therapeutic regimen in patients with COPD. These findings correspond to the interpretation of the efficacy-study with Carbocysteine but not with Acetylcysteine, because this medication did not show a significant reduction of exacerbations [22,23].\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nThe study was designed and the protocol developed by HW, C S and UD. CS worked as principal investigator. Statistical analysis was carried out by UD. The results were interpreted by HW, CS and UD. All authors gave substantial critical input in revising the manuscript.\n\n**Question:** Compared to placebo what was the result of cineole on Dyspnea during exercise?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
414
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pentobarbital versus thiopental in the treatment of refractory intracranial hypertension in patients with traumatic brain injury: a randomized controlled trial\n\n ABSTRACT.INTRODUCTION:\nExperimental research has demonstrated that the level of neuroprotection conferred by the various barbiturates is not equal. Until now no controlled studies have been conducted to compare their effectiveness, even though the Brain Trauma Foundation Guidelines recommend that such studies be undertaken. The objectives of the present study were to assess the effectiveness of pentobarbital and thiopental in terms of controlling refractory intracranial hypertension in patients with severe traumatic brain injury, and to evaluate the adverse effects of treatment.\n\nABSTRACT.METHODS:\nThis was a prospective, randomized, cohort study comparing two treatments: pentobarbital and thiopental. Patients who had suffered a severe traumatic brain injury (Glasgow Coma Scale score after resuscitation ≤ 8 points or neurological deterioration during the first week after trauma) and with refractory intracranial hypertension (intracranial pressure > 20 mmHg) first-tier measures, in accordance with the Brain Trauma Foundation Guidelines.\n\nABSTRACT.RESULTS:\nA total of 44 patients (22 in each group) were included over a 5-year period. There were no statistically significant differences in ' baseline characteristics, except for admission computed cranial tomography characteristics, using the Traumatic Coma Data Bank classification. Uncontrollable intracranial pressure occurred in 11 patients (50%) in the thiopental treatment group and in 18 patients (82%) in the pentobarbital group (P = 0.03). Under logistic regression analysis – undertaken in an effort to adjust for the cranial tomography characteristics, which were unfavourable for pentobarbital – thiopental was more effective than pentobarbital in terms of controlling intracranial pressure (odds ratio = 5.1, 95% confidence interval 1.2 to 21.9; P = 0.027). There were no significant differences between the two groups with respect to the incidence of arterial hypotension or infection.\n\nABSTRACT.CONCLUSIONS:\nThiopental appeared to be more effective than pentobarbital in controlling intracranial hypertension refractory to first-tier measures. These findings should be interpreted with caution because of the imbalance in cranial tomography characteristics and the different dosages employed in the two arms of the study. The incidence of adverse effects was similar in both groups.\n\nABSTRACT.TRIAL REGISTRATION:\n(Trial registration: US Clinical Trials registry NCT00622570.)\n\nBODY.INTRODUCTION:\nHigh dosages of barbiturates are used in patients with severe traumatic brain injury (TBI) who present with refractory intracranial hypertension (ICH) after medical and surgical treatment. This practice is recommended in the Brain Trauma Foundation (BTF) Guidelines, because this is the only second-level measure for which there is class II evidence that it can reduce intracranial pressure (ICP) [1]. Nevertheless, its effect on outcome is unproven [2], mainly because of severe medical complications. Within the family of barbiturates the oxibarbiturates and thiobarbiturates stand out, their primary representatives being pentobarbital and thiopental. Until now no controlled studies have been reported that compare the effectiveness of pentobarbital and thiopental in controlling ICH. At the experimental level, research has demonstrated that mechanisms of action and levels of neuroprotection differ between these agents [3-6]. For this reason, research is needed to compare the effectiveness of these two drugs in terms of controlling refractory ICH in patients with severe TBI. Based on various studies conducted in laboratory animals [3-6], suggesting that the neuroprotective capacity of thiopental is superior, our working hypothesis was that thiopental is more effective than pentobarbital in controlling ICP in patients with severe TBI, with a similar incidence of adverse side effects. In support of our work in the present study, the BTF Guidelines recommend that studies be undertaken to compare the effectiveness of the different barbiturates that are currently used in TBI patients [1].\n\nBODY.MATERIALS AND METHODS:\nWe conducted a prospective, randomized cohort study comparing two treatments: pentobarbital and thiopental. Our primary objective was to compare the effectiveness of these agents in controlling refractory ICH in patients with severe TBI. Secondary objectives were to compare the incidence of secondary effects, especially arterial hypotension, which was defined as the presence of mean arterial pressure (MAP) under 80 mmHg at any point during barbiturate therapy. This study was conducted at Son Dureta University Hospital (Palma de Mallorca, Spain) and was approved by the Ethics Committee of the Balearic Islands on 31 March 2002. It is registered with the US Clinical Trials Registry, with the number NCT00622570. In all cases, the patient's closest relative, legal representative, or guardian gave written informed consent for their inclusion in the study.\n\nBODY.MATERIALS AND METHODS.INCLUSION CRITERIA:\nPatients admitted to our intensive care unit (ICU) between May 2002 and July 2007 with a severe TBI (Glasgow Coma Scale [GCS] score after nonsurgical resuscitation ≤ 8) and presenting with refractory ICH (ICP > 20 mmHg), and who underwent first-level measures in accordance with the BTF Guidelines [7], were included. Refractory ICH was defined as follows: ICP 21 to 29 mmHg for 30 minutes or more, ICP of 30 to 39 mmHg for 15 minutes or more, or ICP greater than 40 mmHg for more than 1 minute, in the absence of external interventions. Included patients were required to be haemodynamically stable at the point of inclusion in the study; haemodynamic stability was defined as systolic blood pressure of 100 mmHg or greater.\n\nBODY.MATERIALS AND METHODS.EXCLUSION CRITERIA:\nWe did not include in the study patients who were younger than 15 or older than 76 years; patients with a GCS score of 3 upon admission and neurological signs of brain death (bilateral arreactive midryasis and loss of brainstem reflexes); and patients who were pregnant, had barbiturate allergy or intolerance, or had a history of severe cardiac ventricular dysfunction with an ejection fraction under 35%.\n\nBODY.MATERIALS AND METHODS.GENERAL THERAPEUTIC PROTOCOL:\nAll patients with severe TBI underwent cranial computed tomography (CT) upon admission and were categorized in accordance with the classification proposed by the Traumatic Coma Data Bank [8]. We also recorded findings of CTs conducted before inclusion of the patients in the study. The CT findings on inclusion were regarded to be the worst of the hospital stay; the prognostic value of such CT findings have been described by other authors [9]. CTs were independently reviewed and categorized by two neurosurgeons (JI and MB) who were unaware of the treatment group to which the patients had been assigned. In cases of disagreement between these investigators, a third investigator reviewed the CT images. All patients' ICP was monitored using an intraparenchymal Camino catheter (Integra Neurosciences, Plainsboro, NJ, USA). The ICP catheter was placed in the frontal region of the hemisphere with more radiological lesions on the CT. The systemic monitoring of these patients included invasive blood pressure, pulse oximetry, and a pulmonary artery thermodilution catheter. The ICP, MAP and cerebral perfusion pressure data were gathered on an hourly basis (one value every full hour) throughout the study using the Care Vue® clinical monitoring system (Phillips, Eindhoven, The Netherlands). The general treatment objectives in patients with severe TBI were to maintain MAP above 80 mmHg, ICP below 20 mmHg, and cerebral perfusion pressure above 60 mmHg. To achieve these objectives, we used liquids and/or vasoactive support with norepinephrine (noradrenaline). In patients with ICP greater than 20 mmHg, initial treatment included elevation of the head of the bed, keeping the neck straight, appropriate sedation, muscular paralysis, ventricular drainage (if the patient had visible ventricles on the CT), 20% mannitol (0.25 to 0.75 mg/kg), 7.5% hypertonic saline (2 ml/kg) and moderate hyperventilation (partial carbon dioxide tension of 30 to 35 mmHg). Neurosurgical interventions were undertaken when necessary to evacuate surgical lesions. This approach can be considered conventional treatment and is included in the BTF Guidelines as first-tier therapy [7]. Patients whose ICP remained high with conventional treatment were included in the study. Before randomization of the patient to a study group, we required that patient to have received maximal medical treatment (first-level measures). In addition, we required a CT to have been conducted within 24 hours before inclusion of the patient in the study; intravenous administration of 0.7 g/kg mannitol 1 hour before randomization; or a plasmatic osmolarity measurement above 320 mOsm/kg, in order to ensure that hyperosmolar therapy had been optimized before inclusion.\n\nBODY.MATERIALS AND METHODS.RANDOMISATION:\nRandomization was based on a computer-generated list that intercollated the two drugs. Allocation was done by the intensive care unit physician who was on duty, once the patient had been found to meet the inclusion criteria and none of the exclusion criteria. Data collection and patient follow up were conducted by the same investigator (JPB).\n\nBODY.MATERIALS AND METHODS.BLINDING OF TREATMENT GROUPS:\nThe study was not blinded because it was difficult for us to mask treatment; thiopental is liophylized for administration and pentobarbital is not.\n\nBODY.MATERIALS AND METHODS.ADMINISTRATION OF BARBITURATES AND MONITORING OF EFFECTS:\nPentobarbital was administered in accordance with the protocol established by Eisenberg and coworkers [10], using a loading dose of 10 mg/kg over 30 minutes followed by a continuous perfusion of 5 mg/kg per hour for 3 hours. This was followed by a maintenance dosage of 1 mg/kg per hour. Thiopental was administered in the form of a 2 mg/kg bolus administered over 20 seconds. If the ICP was not lowered to below 20 mmHg, then the protocol permitted a second bolus of 3 mg/kg, which could be readministered at 5 mg/kg if necessary to reduce persistently elevated ICP. The maintenance dosage was an infusion of thiopental at a rate of 3 mg/kg per hour. In both treatment groups, for cases in which the maintenance dosage did not achieve the reduction in ICP to below the 20 mmHg threshold, the maintenance dosage for both drugs could be increased by 1 mg/kg per hour, while looking for electroencephalographic burst suppression or even the flat pattern, in order to ensure that different doses of the two barbiturates were equipotent. Electroencephalography was conducted daily in a noncontinuous manner (Nicolet; Viasys Healthcare, Verona Road, Madison, WI, USA). Results were analyzed by an experienced neurologist who was blinded to the treatment of the patients. In those patients in whom barbiturate coma did not control ICP, we used decompressive craniotomy and/or external lumbar drainage, in accordance with the Munch criteria, as life-saving measures [11,12].\n\nBODY.MATERIALS AND METHODS.EFFECTIVENESS CRITERIA:\nAdequate response to treatment was defined as a decrease in ICP to below 20 mmHg, and maintenance below this threshold for at least 48 hours. To describe the ICP, we also followed the criteria previously employed by Stocchetti and coworkers [13]; the arithmetic mean of ICP data recorded during every 24-hour period, after filtering to exclude inaccurate readings, was calculated and expressed as 'mean ICP'. Three ICP blocks were considered for further analysis: less than 20 mmHg, 20 to 30 mmHg, and more than 30 mmHg. Uncontrollable ICP was defined as follows: ICP of 21 to 35 mmHg for 4 hours, ICP of 36 to 40 mmHg for 1 hour, or ICP above 41 mmHg for 5 minutes, in the absence of external interventions. We also defined as unresponsive to treatment those cases in which, because of refractory ICP, the patient needed some other treatment (surgery and/or lumbar drainage) and cases in which the patient progressed to brain death. Although it was not a main objective of the study, patients were evaluated 6 months after injury using the Glasgow Outcome Scale [14].\n\nBODY.MATERIALS AND METHODS.WITHDRAWAL OF TREATMENT:\nWhen ICP was controlled (<20 mmHg for 48 hours), we conducted a step-wise reduction in the barbiturate coma in steps that reduced the dosage by 50% every 24 hours until the infusion was suspended. In the event of ICP values rising to the study's inclusion values during the withdrawal of barbiturate treatment, the perfusion dosage was once again increased to achieve control of the patient's ICP.\n\nBODY.MATERIALS AND METHODS.SAMPLE SIZE:\nAccepting an α error of 0.05 and a β error of 0.2 in a bilateral hypothesis contrast, we estimated that 47 patients were needed in each group to detect differences of 30% or greater in the control of ICH. To calculate sample size, we assumed that the therapeutic response rate in the pentobarbital group would be 50%, excluding patients lost to follow up.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nQuantitative variables are expressed as the mean and standard deviation from the mean (SD) in normal distributions, and as median and interquartile range in cases that were not normally distributed. Qualitative variables are expressed as percentages, along with 95% confidence interval (CI). To determine whether variables followed a normal distribution, we used the Shapiro Wilks test. For the comparison of quantitative variables, Student's t-test was used if the variable followed a normal distribution. In other cases, we used the Mann-Whitney U-test. For the comparison of qualitative variables, we used χ2 or Fisher's exact test, as appropriate. Given that the randomization did not create groups that were similar in terms of types of intracranial lesions shown on the CT results, which is a prognostic variable that influences the effectiveness of barbiturate treatment in controlling ICP, we conducted a multivariate analysis using binary logistic regression, so that we would include the prognostic variables with the most plausible association with the dependent variable 'uncontrollable ICP'. These are variables such as age, GCS score at admission, and the worst CT obtained within 24 hours before inclusion of the patient in the study, as well as the type of barbiturate administered. To achieve this multivariate analysis, and given the small number of cases in each of the five groups in Marshall's classification, the CT data were grouped into focal and diffuse lesions. We also included in the model the minimum daily MAP during barbiturate treatment, given that in the second and third days of treatment there were statistically significant differences between the groups in the univariate analysis. The significant variables identified by the 'likelihood ratio' ≤ 0.1 test were used, along with those whose inclusion affected the calculation of the effect of the 'treatment group' variable. Both treatment groups were very similar in terms of other known prognostic variables, such as the presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them, so these were not included in the multivariate analysis. To analyze the variable ICP, which was determined on an hourly basis, we calculated the area under the curve (AUC) at 24, 48 and 72 hours, and also standardized by time [15]. For all comparisons, we considered statistical significance to have been achieved if the two-tailed α error probability was 5% or less (P ≤ 0.05). Statistical analyses were conducted using SPSS version 15 (SPSS Inc., Chicago, IL, USA).\n\nBODY.RESULTS:\nPreliminary results for the first 20 patients have already been published elsewhere [16]. From May 2002 to July 2007, 480 TBI patients were admitted to the intensive care unit of the Son Dureta University Hospital. Of these 480 patients, 71 (14.8%) presented with ICH refractory to first-level measures, of whom 44 were included in the study. The study was concluded prematurely because of the unexpected and slow inclusion rate; this could have modified some uncontrollable environmental factors that may affect results. The reasons for not including the remaining 27 refractory ICH cases were as follows: 13 patients were included in other studies, six were older than 76 years, five were admitted with nonreacting midriatic pupils and with clinical evidence of brain death, two presented with haemodynamic instability at the time of randomization, and one patient was transferred to a different hospital during the first 24 hours of admission, which excluded that patient from follow-up analysis. On average, the barbiturate coma was initiated in the thiopental group at 89 ± 15.5 hours after admission and in the pentobarbital group at 61 ± 14.3 hours after admission (P = 0.33). The baseline characteristics of the 44 patients included in the study, 22 randomized to each group, are presented in Table 1. There were no statistically significant differences with respect to epidemiological data, co-morbidity (data not shown) or lesions associated with TBI, although there were differences in the CT classification. Table 1 Baseline characteristics of patient population Characteristic Thiopental (n = 22) Pentobarbital (n = 22) P Sex (male; n) 19 19 1 Age (years) 26 (20 to 41) 32 (22 to 43) 0.45 ISS 25 (24 to 34) 25 (25 to 38) 0.77 SAPS II 42 (28 to 54) 43 (38 to 46) 0.95 APACHE II 23 (15 to 25) 20 (18 to 26) 0.27 APACHE III 60 (38 to 73) 52 (32 to 76) 0.41 Associated lesion (n) Thoracic injury 7 2 0.13 Abdominal injury 4 1 0.34 Extremities injury 9 5 0.20 Admission CT (n) Diffuse injury without brain swelling 12 4 0.046 Diffuse bilateral brain swelling 6 12 Diffuse unilateral brain swelling with midline shift 1 0 Any mass lesion > 25 ml 3 6 Age, ISS, SAPS II, APACHE II and APACHE III are expressed as median and interquartile range. APACHE, Acute Physiology and Chronic Health Evaluation; admission CT, admission computed tomography (according to the Traumatic Coma Data Bank); ISS, Injury Severity Score; SAPS, Simplified Acute Physiology. The summary of prognostic variables for the 44 patients is shown in Table 2. As in Table 1 the characteristics of the worst CT conducted before inclusion in the study differed between the two groups. Table 2 Prognostic variables of patient population Variable Thiopental (n = 22) Pentobarbital (n = 22) P Admission GCS score 6.5 (3.0 to 7.2) 7 (4.7 to 10.0) 0.38 Out-of-hospital hypoxia (n) 5 7 0.63 Out-of-hospital hypotension (n) 5 4 1 Pupillary reactivity (n) a One reacting 3 5 0.66 Both reacting b 12 14 Pre-enrolment CT (n) Diffuse injury without brain swelling 8 5 0.04 Diffuse bilateral brain swelling 1 8 Diffuse injury unilateral brain swelling with midline shift 5 1 Any mass lesion evacuated 7 5 Nonevacuated mass lesion 1 3 Admission GCS is expressed as median (interquartile range). a Pupillary reactivity at hospital admission. b Miotic pupils were considered as reactive. CT, computed tomography; GCS, Glasgow Coma Scale. \n\nBODY.RESULTS.EFFECTIVENESS CRITERION: CONTROL OF INTRACRANIAL PRESSURE:\nThe distribution of the ICP during the first 3 days of treatment, according to Stocchetti's criteria, is summarized in Table 3. The missing cases during these 3 days were due to brain deaths or to receipt of rescue treatment for uncontrollable ICP. Finally ICP was uncontrollable in 11 cases (50%) in the thiopental group and in 18 patients (82%) in the pentobarbital group (P = 0.03). In nonresponding patients, we chose to place a lumbar drainage in five, in three we opted for surgical treatment, and in three other patients we combined both treatments, drainage and surgery. Surgical decompression was conducted in four patients in the thiopental group and in two of the patients in the pentobarbital group. The number of hyperosmolar treatments administered (manitol and/or hypertonic saline) during the barbiturate coma was similar in both groups: 16.5 (8.0 to 24.2) in the thiopental group and 16.5 (3.0 to 21.5) in the pentobarbital group (P = 0.9). The mean ± SD duration of the barbiturate coma was 156 ± 60 hours for thiopental and 108 ± 100 hours for pentobarbital (P = 0.06). Seven (31.8%) patients presented an ICP rebound with thiopental and six (27.3%) with pentobarbital (P = 0.74) during treatment withdrawal. Table 3 Mean ICP recorded per day during the first 3 days of barbiturate coma Drug Day Mean ICP (n[%]) <20 mmHg 20 to 30 mmHg >30 mmHg Thiopental 1 10 46 11 50 1 5 2 15 71 4 19 2 10 3 12 63 6 32 1 5 Pentobarbital 1 9 41 8 36 5 23 2 8 38 9 43 4 19 3 6 43 8 57 0 0 Mean intracranial pressure (ICP) is the arithmetic mean of ICP data recorded during every 24-hour period, according to Stocchetti's criteria [ 13 ]. Data are presented as number of cases and as a percentage of the total number of cases each day. Figure 1 presents the AUC for ICP above 20 mmHg, standardized over time, as follows. The ICP value of AUC0–24 h was 458.00 mmHg·hour (95% CI = 421.84 to 494.16) in the thiopental group and 550.63 mmHg·hour (95% CI = 411.31 to 689.95) in the pentobarbital group. The AUC0–48 h was 913.18 mmHg·hour (95% CI = 814.08 to 1,012.27) in the thiopental group and 997.27 mmHg·hour (95% CI = 757.10 to 1,237.43) in the pentobarbital group. The AUC0–72 h in the thiopental group was 1,291.69 mmHg·hour (95% CI = 1,172.27 to 1,411.12) and 1,399.73 mmHg·hour (95% CI = 1,291.11 to 1,508.35) in the pentobarbital group. Standardized over time, the AUC per hour in the thiopental group was 23.90 mmHg (95% CI = 22.00 to 25.81) and in the pentobarbital group it was 29.39 mmHg (95% CI = 23.20 to 35.59). Figure 1AUC of ICP data. Presented are areas under the curve (AUCs) of the intracranial pressure (ICP) data, standardized by time, with a base value of 20 mmHg. Both treatment groups were similar in terms of known prognostic variables, such as presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them. Therefore, these were not included in the multivariate analysis. The logistic regression analysis showed that, after adjusting for the worst CT and the type of barbiturate used, thiopental was five times more likely than pentobarbital to control ICP (odds ratio = 5.1, 95% CI = 1.2 to 21.9; P = 0.027). The Hosmer-Lemeshow test indicated that the fit of the model was good (P = 0.799). The association of focal lesions in the pre-inclusion CT with ICP control was 3.6 times higher than that for the diffuse lesions. The relative risk for good control of ICP in the thiopental versus pentobarbital group was 2.26 for patients with focal lesions and 3.52 for those who presented with diffuse lesions. The other variables analyzed did not exhibit a significant relationship to ICP control, and did not modify the effect of the barbiturate treatment, including the third day minimum MAP, which was significantly different between the two treatments (data not shown).\n\nBODY.RESULTS.ADVERSE SIDE EFFECTS DURING THE BARBITURATE COMA:\nThe secondary effects during the barbiturate coma are presented in Table 4. In both groups almost all patients presented with at least one MAP measurement below 80 mmHg. There were no differences between groups with respect to the incidence of infections, Sepsis related Organ-Failure Assessment (SOFA) scores before initiation of treatment, or the maximum SOFA value [17] during the entire period of barbiturate coma. Table 4 Adverse events during barbiturate coma Adverse event Thiopental (n = 22) Pentobarbital (n = 22) P Hypotension a 21 20 1 Respiratory infection b 18 17 1 Urinary infection c 0 2 0.49 Positive blood culture 4 1 0.34 ICP catheter colonization 7 5 0.5 CNS infection (CSF) d 3 0 0.23 SOFA pre e 7 (4.5 to 9.5) 8.0 (5.5 to 9.0) 0.57 SOFA maximum f 11 (10 to 12) 11 (10 to 12) 0.94 a Hypotension is defined as detection of a medium arterial blood pressure below 80 mmHg at any time during barbiturate coma. b Respiratory infection: presence of a positive sputum culture. c Urinary infection: presence of a positive urine culture. d Central nervous system infection (CNS) infection (cerebrospinal fluid [CSF]): infection of the CNS with a positive culture in the CSF. e SOFA pre: value of the Sepsis related Organ-Failure Assessment (SOFA) score before the beginning of the barbiturate coma. f SOFA maximum: maximum value of the SOFA during the barbiturate coma, according the indication by Moreno and coworkers [ 16 ]. A thermodilution catheter was placed in 42 patients to facilitate haemodynamic control. The haemodynamic changes produced during the barbiturate coma are presented in Table 5. Differences of note include the minimum MAP, the pulmonary wedge pressure value, and the maximum norepinephrine dosage on days 2 and 3. Table 5 Systemic changes during barbiturate coma Parameter Pretreatment 1st day 2nd day 3rd day 4rd day Cardiac output (l/minute) a Thiopental 6.8 ± 1.4 6.4 ± 1.5 6.0 ± 1.4 6.7 ± 1.5 6.6 ± 1.8 Pentobarbital 7.4 ± 2.2 7.1 ± 1.9 6.5 ± 2.0 7 ± 1.4 6.1 ± 1.3 Cardiac index (l/minute per m 2 ) Thiopental 3.6 ± 0.6 3.4 ± 0.6 3.1 ± 0.6 3.6 ± 1.6 3.5 ± 0.9 Pentobarbital 3.8 ± 1.2 3.8 ± 0.8 3.4 ± 0.8 3.6 ± 0.7 3.2 ± 0.6 Peripheral venous resistance (dines/m 2 ) Thiopental 1,015 ± 325 1,022 ± 347 1,140 ± 429 1,089 ± 289 1,029 ± 253 Pentobarbital 952 ± 257 893 ± 210 1,003 ± 322 939 ± 261 914 ± 188 Pulmonary artery wedge pressure (mmHg) Thiopental 10.4 ± 4.5 9.6 ± 3.6 10.1 ± 4.1* 10.9 ± 4.6* 11.4 ± 3.5* Pentobarbital 11.6 ± 4.0 11.4 ± 3.1 12.8 ± 3.1 13.2 ± 2.1 13.9 ± 3.1 mBP (mmHg) b Thiopental 92 ± 11 75 ± 7 76 ± 9* 76 ± 6* 76 ± 8 Pentobarbital 94 ± 10 74 ± 1 68 ± 10 70 ± 1 70 ± 10 NAD (μg/kg per minute) c Thiopental 0.18 ± 0.33 0.28 ± 0.27 0.37 ± 0.3* 0.46 ± 0.39 0.56 ± 0.63 Pentobarbital 0.19 ± 0.18 0.55 ± 0.68 0.73 ± 0.69 0.60 ± 0.44 0.96 ± 0.79 P O 2 /Fi O 2 d Thiopental 284 ± 130 300 ± 139 293 ± 132 285 ± 138 254 ± 119 Pentobarbital 317 ± 127 304 ± 116 262 ± 125 211 ± 77 184 ± 92 Haemoglobin Thiopental 10.9 ± 1.6 10.7 ± 1.3 11 ± 1.2 10.8 ± 0.9 10.7 ± 1.4 Pentobarbital 10.6 ± 1.2 10.1 ± 1.0 10.4 ± 1.1 10.5 ± 1.1 10.2 ± 1.2 Temperature (°C) e Thiopental 35.8 ± 0.5 34.6 ± 1.3 34.6 ± 3.4 34.9 ± 1.0 34.9 ± 1.0 Pentobarbital 35.7 ± 1.0 34.6 ± 1.2 34.3 ± 1.3 34.4 ± 1.3 34.2 ± 1.1 a Cardiac output, cardiac index, peripheral venous resistance and pulmonary artery wedge pressure: the values are the mean values over 24 hours. b mBP: minimum value of the medium blood pressure during the day. c NAD: maximum dose of Noradrenaline bitartrate during the day. d P O 2 /Fis O 2 : ratio of partial oxygen tension to inspired fractional oxygen tension at 8:00 am. e Temperature: value of the minimum central temperature. * P < 0.05. \n\nBODY.RESULTS.SIX-MONTH OUTCOMES:\nIn the thiopental group, the neurological outcomes at 6 months (in accordance with Glasgow Outcome Scale score) were as follows: death in nine patients, vegetative state in two, severe disability in two, moderate disability in four and good recovery in four. In the pentobarbital group, the 6-month outcome was death in 16 patients, vegetative state in one, moderate disability in two and good recovery in two. In both groups one case was missing from the 6-month follow up analysis\n\nBODY.DISCUSSION:\nThe results of this study indicate that thiopental is five times more effective than pentobarbital in controlling refractory ICH. However, these findings must be interpreted with caution, given the small sample size and the fact that the study was unable to mask assignment to treatment groups. Barbiturate coma is at present the only therapy for which we have class II evidence, under BTF Guidelines [1], of efficacy in treating refractory ICH. Hence, it is perhaps the case that barbiturate coma is the most used second-level measure, with a usage frequency reported in the literature that varies from 13% to 56% [18,19]. Therefore, it is important to test the effectiveness of the various barbiturates available for controlling ICP refractory to first-level measures.\n\nBODY.DISCUSSION.DIFFERENCES BETWEEN OXIBARBITURATES AND THIOBARBITURATES:\nThe pharmacokinetic characteristics of thiopental and pentobarbital are different because their protein binding, distribution volume and clearance differ [20]. Nevertheless, the mean half life (thiopental 6 to 46 hours and pentobarbital 15 and 48 hours), which is the fundamental pharmacological parameter, differs little between the two agents. It therefore does not appear that these pharmacokinetic differences have clinical repercussions. One difference between these two groups of barbiturates is the presence of active metabolites. Thiopental has five metabolites, of which four are inactive and one (pentobarbital, or pentobarbitone) is active. Therefore, pentobarbital is an active metabolite of thiopental. This fact, along with the great intra-individual and inter-individual variability in the metabolism of these agents (caused by the existence of enzymatic induction phenomena associated with hepatic cytochrome P450), results in a weak correlation between serum concentrations and pharmacological effect. For this reason, monitoring this treatment with electroencephalography is strongly recommended. At the experimental level, various studies have compared these two medications. Hatano and coworkers [21], in a study conducted in a dog model, concluded that thiobarbiturates provoke cerebral vasoconstriction, which could help to redistribute cerebral blood flow toward ischaemic zones. Cole and colleagues [4] demonstrated that thiopental reduced the size of the ischaemic area more than did pentobarbital, even though both drugs achieved electroencephalographic burst suppression patterns. Shibuta [5] observed that thiopental, but not pentobarbital, was capable of limiting the cytotoxic damage caused by nitric oxide. Almaas and coworkers [3] observed that the different barbiturates had different neuroprotective effects with respect to oxygen and glucose deprivation in a model using human neurone cultures. Thiopental exhibited a neuroprotective effect at all the dosages studied, whereas pentobarbital was neuroprotective only at elevated dosages. Finally, in an in vitro study, Smith and colleagues [6] demonstrated that although thiopental provoked 96% inhibition of lipid peroxidation, pentobarbital had almost no effect. These experimental studies demonstrate that not all barbiturates are equal and that their neuroprotective capacity and effectiveness may differ [22]. Therefore, despite the unavoidable methodological limitations of the present study, we believe that our results may have clinical relevance.\n\nBODY.DISCUSSION.SECONDARY EFFECTS OF BARBITURATE COMA:\nThe most frequently detected secondary effect in our study, as might be expected, was arterial hypotension, which occurred in 21 patients in the thiopental group and 20 patients in the pentobarbital group. Although this incidence may be greater than that in previous studies [10], we attribute this to the definition of hypotension used (detection at any time in the barbiturate coma of MAP < 80 mmHg), which did not take the 'time' variable into account. For that reason, we collected data on other variables, such as maximum daily norepinephrine dosage and minimum daily MAP. Nearly all patients were monitored using a pulmonary artery thermodilution catheter, and arterial hypotension episodes were rigorously managed with fluid therapy and vasoactive drugs. We would note that the changes produced by pentobarbital at the cardiac and respiratory level were, in general terms, greater than those produced by thiopental. This is because (as shown in Table 5) cardiac output, cardiac index, and partial oxygen tension/fraction of inspired oxygen ratio exhibited greater changes during treatment with pentobarbital than with thiopental. This observation contrasts with the findings of previous experimental studies [23], in which it appeared that at high doses pentobarbital was safer and better tolerated than thiopental. Other complications (mostly infections) and the incidence of multiple organ dysfunction (identified using maximum SOFA) were similar in the two groups.\n\nBODY.DISCUSSION.LIMITATIONS OF THE STUDY:\nAs previously noted, this study has two important limitations. First, it was not a blinded study because the pentobarbital was not liophylized and thiopental was. Second, the sample size was small, so that small changes in the principal variable studied, namely ICP control, could significantly affect the statistical analysis. The classical view is that ICP response to barbiturates varies from 30% to 50%, and so it is possible that part of the difference found between drugs is due to poor response by the pentobarbital group as a result of any confounding bias. The randomization process is a potent mechanism that tends to eliminate bias by randomly distributing the values of all of the variables to the experimental groups. Nonetheless, the tool is not perfect and the groups frequently exhibit an imbalance in some confounding variable, especially when working with samples that are not very large. For this reason, in this study we used logistic regression analysis to eliminate any possible bias, and separate, independent analyses of the CT data were also conducted by two investigators who did not know the experimental group to which the patients belonged. Another limitation is that the dosages in the two groups were not the same. This leaves the possibility that the reason for the difference between agents that we identified is inadequate pentobarbital dose. Although in the two groups barbiturates were used with the end-point of ICP control, in this type of patient we also employ daily noncontinuous electroencephalographic monitoring. In this way, we believe that – despite different doses – the effect of the two barbiturates can be considered as equipotent because we looked for burst suppression or even the flat electroencephalographic pattern if the ICP was not controlled and the patients remained haemodynamically stable.\n\nBODY.CONCLUSION:\nIn this patient sample, thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-level measures, according to the BTF Guidelines. Nevertheless, these findings should be interpreted with caution because of the imbalance in CT characteristics and the different dosages employed in the two arms of the study. However, the present study is useful as a hypothesis testing exercise and will help to inform the design of future studies. These findings corroborate experimental evidence suggesting that there are differences in the neuroprotective mechanism between the two treatments, and this study may be a first step toward translating evidence from animal models to clinical disease. The incidence of secondary effects during treatment was similar between groups.\n\nBODY.KEY MESSAGES:\n• High doses of barbiturates are used in those patients with severe TBI who present with refractory ICH, and this recommendation is included in the BTF Guidelines. • Until now no controlled studies have been conducted to compare the effectiveness of pentobarbital and thiopental in controlling refractory ICH. Nevertheless, at the experimental level, research has demonstrated that their mechanisms and levels of neuroprotection differ. • Thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-tier measures, although these results should be interpreted with caution because of the imbalance in CT characteristics and other limitations of the study.\n\nBODY.ABBREVIATIONS:\nAUC: area under the curve; BTF: Brain Trauma Foundation; CI: confidence interval; ICH: intracranial hypertension; ICP: intracranial pressure; MAP: mean arterial pressure; SD: standard deviation; SOFA: Sepsis related Organ-Failure Assessment; TBI: traumatic brain injury.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nJPB was responsible for study design, acquisition of data, analysis and interpretation of data, and writing of the manuscript. JALP was responsible for acquisition of data and patient randomization. JH acquired data and conducted patient randomization. JMA acquired data and conducted patient randomization. JMR conducted statistical analyses. GF conducted statistical analyses. MB was responsible for designing the study and reviewing CT findings. JI was responsible for designing the study and reviewing CT findings. JI revised the article critically and gave final approval to the version to be published.\n\n**Question:** Compared to Pentobarbital what was the result of Thiopental on Intracranial pressure recurrence after treatment withdrawal?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
362
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Placebo what was the result of Budesonide/formoterol pMDI 320/9 μg on Breathlessness Cough and Sputum Scale improvement?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
419
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Cervical ripening with prostaglandin gel and hygroscopic dilators.\n\n ABSTRACT:\nOBJECTIVE: To study the effectiveness and morbidity of adding hygroscopic cervical dilators to prostaglandin gel for cervical ripening and labor induction. STUDY DESIGN: Patients of at least 34 weeks' gestation with a medical indication for induction of labor and with a modified Bishop score of 5 or less were randomized to receive either prostaglandin gel or prostaglandin gel with hygroscopic cervical dilators. Primary outcomes were time to delivery, change in cervical score, and infection. Secondary outcomes included cesarean delivery rate and deliveries before 24 hours of induction. Continuous variables were analyzed by Wilcoxon sum rank test and categorical data by chi-square or Fisher exact test, with P < 0.05 being significant. RESULTS: Seventeen patients were randomized to intracervical prostaglandin alone and 23 patients received intracervical prostaglandin plus hygroscopic dilators. No demographic differences were noted between the groups. After six hours of ripening, the combined group achieved a greater change in Bishop score (3.6 vs. 2.1, P = 0.007) and tended to have a shorter induction time (21.7 vs. 26.4 hours, P = 0.085). The combined therapy group had a higher infection rate than the prostaglandin-only group (59% vs. 12%, P = 0.003). CONCLUSION: Combining cervical dilators with prostaglandin gel provides more effective cervical ripening and a more rapid induction to delivery interval than prostaglandin alone but with a significant and prohibitive rate of infection.\n\n**Question:** Compared to Prostaglandin gel what was the result of Prostaglandin gel plus hygroscopic cervical dilators on Induction time?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
439
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Treatment of osteoarthritis of the knee with a topical diclofenac solution: a randomised controlled, 6-week trial [ISRCTN53366886]\n\n ABSTRACT.BACKGROUND:\nTopical NSAIDs have been proven to relieve the symptoms of osteoarthritis (OA) in short-term studies (2 weeks). To justify its chronic use, efficacy of a topical NSAID over a longer term of study should be demonstrated. The efficacy and safety of a topical diclofenac solution over a 6-week treatment course in symptomatic primary OA of the knee was investigated.\n\nABSTRACT.METHODS:\n216 men and women, age 40–85 years, with radiologically confirmed primary OA of the knee and a flare of pain at baseline following discontinuation of prior therapy were enrolled into this double-blind study. Participants applied either a topical diclofenac solution (Pennsaid®) or vehicle control solution (carrier with no diclofenac); 40 drops 4 times daily directly to the painful knee(s), without massage, for 6 weeks. Pre-planned primary efficacy outcome measures included the core continuous variables pain relief and improved physical function measured by the Western Ontario and McMaster Universities (WOMAC) LK3.1 OA Index, and improved patient global assessment (PGA). Secondary efficacy measure was reduced stiffness. Safety assessments included adverse events and vital signs.\n\nABSTRACT.RESULTS:\nThe topical diclofenac group had a significantly greater mean change in score (final minus baseline) compared to the vehicle control group for pain (-5.2 vs. -3.3, p = 0.003), physical function (-13.4 vs. -6.9, p = 0.001), PGA (-1.3 vs. -0.7, p = 0.0001) and stiffness (-1.8 vs. -0.9, p = 0.002). The mean difference between treatment arms (95% confidence interval [CI]) was 1.9 (0.7 to 3.2), 6.5 (2.5 to 10.5), 0.6 (0.2 to 0.9), and 0.9 (0.3 to 1.4), respectively. Safety analyses showed that topical diclofenac caused skin irritation, mostly minor local skin dryness, in 42/107 (39%), leading to discontinuation of treatment in 5/107 (5%) participants.\n\nABSTRACT.CONCLUSION:\nThis topical diclofenac solution demonstrated relief at 6 weeks of the symptoms of primary osteoarthritis of the knee.\n\nBODY.BACKGROUND:\nMeta-analysis of previous trials of topical non-steroidal anti-inflammatory drugs (NSAIDs) concluded that they effectively treat the pain of acute soft tissue injuries [1] and chronic musculoskeletal conditions [2,3]. Current evidence-based recommendations for the management of osteoarthritis (OA) support the use of topical NSAIDs and rubefacients [4-6] as a therapeutic option potentially with fewer gastrointestinal risks than oral NSAIDs [7]. However, a recent critical meta-analysis concluded that claims of pain relief in OA by currently available topical NSAIDs are supported by only a limited number of randomised controlled trials of small size and brief duration, with no data demonstrating efficacy beyond 2 weeks [8]. In this report, we present the efficacy and safety results from a 6-week controlled trial using a newer topical diclofenac solution in knee OA. Effect size data and number-needed-to-treat (NNT) are presented, facilitating comparison with the previously reviewed data.\n\nBODY.METHODS.PARTICIPANTS AND INCLUSION/EXCLUSION CRITERIA:\nThis study was conducted from November 1999 to August 2000, at 17 medical centres across central Canada, following approval by a central ethics review board (Integrated Research Incorporated, Ethics Review Committee, Montreal, QC). Participants were recruited from the physician's private practice or the surrounding community. At the screening visit, after providing written, informed consent, each participant underwent a screening interview and was eligible to proceed to washout if all inclusion criteria and no exclusion criteria were met. Inclusion criteria specified men and non-pregnant women, age 40–85 years, with primary OA of at least one knee, and a flare of pain after withdrawal of prior therapy with either an oral NSAID or acetaminophen (used at least 3 days per week during the previous month). Primary OA was defined by deterioration and abrasion of articular cartilage (joint space narrowing) or formation of new bone (osteophytes) at the joint surface of the knee (medial tibio-femoral, lateral tibio-femoral or patello-femoral), demonstrated on a radiological examination carried out within the previous 3 months [9]. Pain was measured by the Western Ontario and McMaster Universities LK3.1 OA Index (WOMAC) 5-item pain subscale, each item scored on a 5-point Likert scale (none = 0; mild = 1; moderate = 2; severe = 3; extreme = 4) [10]. Pain was scored at the screening visit, following which prior therapy was withdrawn. The patient scored the pain again at the baseline visit. A flare was defined as an increase in total pain subscale score of at least 2 and at least 25%, with a baseline total pain score of at least 6 (out of a possible 20), and a score of ≥2 (out of a possible 4) on at least one of the 5 items in the WOMAC pain subscale. Participants were excluded if they had secondary arthritis related to systemic inflammatory arthritis (including rheumatoid arthritis, psoriatic arthritis, post-infectious arthritis and metabolic arthritis, traumatic arthritis or surgical joint replacement); corticosteroid use: (a) oral corticosteroid within the previous 14 days, or (b) intramuscular corticosteroid within 30 days, or (c) intra-articular corticosteroid into the study knee within 90 days, or (d) intra-articular corticosteroid into any other joint within 30 days, or (e) topical corticosteroid at the site of application within 14 days; intra-articular viscosupplementation (e.g., Synvisc®) into the study knee in the preceding 90 days; ongoing use of prohibited medication including NSAID, other oral analgesic, muscle relaxant, or low-dose antidepressant for any chronic pain management; ongoing use of glucosamine or chondroitin (unless used continuously for 90 days prior to study entry); sensitivity to diclofenac, acetylsalicylic acid (ASA) or any other NSAID, acetaminophen, dimethyl sulphoxide, propylene glycol, glycerine or ethanol; clinically-active renal, hepatic or peptic ulcer disease; history of alcohol or drug abuse; lactation; concomitant skin disease at the application site; current application for disability benefits on the basis of knee osteoarthritis; fibromyalgia; other painful or disabling condition affecting the knee; or participation in another investigational drug trial in the previous 30 days.\n\nBODY.METHODS.INTERVENTIONS:\nAt the baseline visit, all patients that met the final entry criterion of a flare of pain were randomly assigned to receive one of two treatments: (a) topical diclofenac solution (Pennsaid®; Dimethaid Research Inc.), consisting of 1.5% (w/w) diclofenac sodium in a patented carrier containing dimethyl sulphoxide (45.5%, w/w), propylene glycol, glycerine, ethanol and water, or (b) vehicle control solution, consisting of the complete carrier (including dimethyl sulphoxide, 45.5% w/w) but no diclofenac. Participants applied a dose of 40 drops of study solution (about 1.3 mL) to the affected knee 4 times daily for up to 6 weeks. The participant was instructed to apply 10 drops of solution to each side of the knee (front, back, medial and lateral) either dripped directly onto the knee or first into the hand, and then spread over the site without massage. Compliance was verified by weighing the solution bottles at each visit. If the other knee was painful at any time during the study, it was treated and evaluated for safety, but efficacy analysis was performed on only the study knee – the one with the greater baseline pain score (or the dominant knee if both had the same score). Consumption of acetaminophen (up to four 325-mg tablets per day) was permitted for residual knee or other body pain throughout the treatment period, but not during the washout period prior to baseline assessment or during the week prior to final assessment at week 6. ASA (≤ 325 mg/day) was permitted for cardiovascular prophylaxis.\n\nBODY.METHODS.OUTCOME MEASURES:\nThe primary outcome measures were defined as the change from baseline to final assessment of the study knee in the 3 core continuous variables [11] pain and physical function, assessed using the WOMAC subscales, and patient global assessment (PGA). There was no intermediate assessment of efficacy. The WOMAC is a validated questionnaire [12] consisting of 24 questions (5 on pain, 17 on physical function and 2 on stiffness), each scored on a 5-point Likert scale (see Participants). The PGA question asked: \"How has the osteoarthritis in your study joint been over the last 48 hours?\" and was scored on a Likert scale (very good = 0; good = 1; fair = 2; poor = 3; very poor = 4). This question focuses on the treated site, unlike a PGA in an oral NSAID trial that can probe the non-signal joints. Secondary measure was change in stiffness. Ancillary measures defined a posteriori were pain on walking – the first question of the WOMAC pain subscale (referred to as 'use-related pain' [13]) – and the following dichotomous variables: 50% improvement in pain [3]; final PGA score of \"good\" or \"very good\" [3]; and response based on OMERACT-OARSI responder criteria [14] (a responder is defined as a participant with ≥ 50% improvement in pain or function that was ≥ 20% of the scale, or ≥ 20% improvement in at least two of pain, function or PGA that was ≥ 10% of the scale).\n\nBODY.METHODS.SAFETY ANALYSES:\nSafety was assessed during all clinic visits (weeks 3 and 6) and telephone 'visits' (weeks 1 and 5). Safety variables included adverse events, application-site dermatological reactions and vital signs. Adverse events were identified using open-ended questions and a checklist covering common oral NSAID side effects. Dermatological assessment of the knee was based on a standard scale [15] and any abnormality was recorded as an adverse event. All adverse events were categorised according to Coding Symbols for Thesaurus of Adverse Reaction Terms (COSTART) [16]. Laboratory assessment was not done.\n\nBODY.METHODS.SAMPLE SIZE:\nBased on a power of 80% and a Type I error rate of α = 0.052-tailed, a sample size of 80 participants per group was required to detect an estimated important difference of 2 between the treatment arms, in the change in WOMAC pain dimension score from baseline to final (with standard deviation of 4.5). A total sample size of 200 participants (100 per treatment group) was specified in the protocol, which allowed for a non-evaluable rate of up to 20%.\n\nBODY.METHODS.RANDOMISATION AND BLINDING:\nThe study kits were prepared, labelled and numbered according to a computer-generated randomisation schedule created by an outside consultant using a randomly chosen block size of 4 or 6. They were shipped to the sites in multiples of complete blocks to ensure that a balanced number of participants was assigned to the two treatment arms within each site. As a participant qualified for study entry at the baseline visit, the investigator assigned him/her the next randomisation number in a sequential manner. The randomisation schedule was concealed from the investigators, their support staff, study participants and the sponsor's clinical research personnel, until final data lock. Except for the individual participant identification number on the label, the two study solutions were identical clear, colourless liquids packaged in opaque bottles.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nSafety analyses were performed on all randomised participants who received at least one dose of study solution. There was no imputation of missing safety data. Efficacy analyses were performed on an intent-to-treat (ITT) group, defined as a subset of all randomised participants who met critical inclusion criteria (primary OA by history, an abnormal radiological study, and any degree of knee pain), as per ICH guidelines [17]. For any missing efficacy data in the ITT analysis, the last observation was carried forward. A per-protocol group was defined based on stricter adherence to study conduct, including requirement for a moderate flare of knee pain (see Participants) and treatment continuing for at least 40 days. Baseline demographic and clinical variables were analysed by Chi-square or Student's t-Test. Adverse event incidence was analysed by Chi-square or Fisher's Exact Test. Continuous variables (WOMAC dimensions, PGA and pain on walking) were analysed by ANCOVA with baseline score as the covariate without adjustment for testing secondary/alternative objectives. The dichotomous variables were analysed by Chi-square test. All statistical tests were two-sided and were performed at the 0.05 level of significance.\n\nBODY.RESULTS.PARTICIPANT FLOW:\nTwo hundred and sixteen participants were randomised to treatment with either topical diclofenac (n = 107) or vehicle control (n = 109). All participants received their allocated intervention. More participants in the topical diclofenac group (86 [80%]) completed the entire 6-week treatment period compared to the vehicle control group (70 [64%]; p = 0.008). Discontinuation rate due to an adverse event was similar in both groups. Dropout due to lack of effect was lower for topical diclofenac (8 [7.5%]) compared to vehicle control (18 [16.5%]; p = 0.041). No participant was lost to follow-up (Fig. 1). Figure 1Flow of participants.\n\nBODY.RESULTS.BASELINE DEMOGRAPHIC AND CLINICAL CHARACTERISTICS:\nNo significant difference was found between treatment groups in baseline demographic and clinical characteristics (Table 1). The mean (SD) screening and baseline pain scores were 8.2 (2.7) and 13.0 (3.2) in the topical diclofenac group versus 8.3 (3.0) and 12.8 (3.1) in the vehicle control group (12.9 [3.2] overall). Most participants treated both knees, either from baseline or by the end of the trial. Table 1 Baseline demographic and clinical characteristics of treatment groups Topical diclofenac (n = 107) Vehicle control (n = 109) Age (years) 65.0 (11.0) 64.6 (10.9) Women, number (%) 56 (52.3) 66 (60.6) Race/ethnicity, number (%) White 88 (82.2) 91 (83.5) Black 8 (7.5) 3 (2.8) Oriental 3 (2.8) 2 (1.8) Other 8 (7.5) 13 (11.9) Weight (kg) 89.9 (18.1) 86.5 (17.3) Height (m) 1.65 (0.11) 1.65 (0.10) Heart rate (bpm) 74.1 (10.0) 74.3 (9.1) Systolic blood pressure (mm Hg) 137.6 (16.3) 133.6 (15.6) Diastolic blood pressure (mm Hg) 81.4 (9.1) 79.7 (8.7) Total x-ray score* 7.7 (5.4) 7.0 (5.0) Screening pain score 8.2 (2.7) 8.3 (3.0) Baseline † pain score 13.0 (3.2) 12.8 (3.1) Baseline † physical function score 40.7 (11.9) 40.4 (11.2) Baseline † stiffness score 5.2 (1.5) 5.2 (1.5) Patient global assessment score‡ 3.1 (0.8) 3.2 (0.8) Participants treating two knees at baseline, number (%) 64 (59.8) 70 (64.2) Participants treating two knees at final, number (%) 84 (78.5) 89 (81.7) Data are presented as mean (SD) unless otherwise indicated. *Total score of joint space narrowing, marginal osteophytes formation and subchondrial sclerosis for each knee compartment (medial, lateral, patello-femoral); maximum score possible was 27. †After washout of prior therapy; pain scale ranged from 0 (no pain) to 20 (extreme pain); physical function scale ranged from 0 (no difficulty) to 68 (extreme difficulty); stiffness scale ranged from 0 (no stiffness) to 8 (extreme stiffness). ‡Patient global assessment was measured using a Likert scale, ranging from 0 (very good) to 4 (very poor). Mean (SD) duration of treatment in the topical diclofenac group was 38.2 (9.9) days versus 34.4 (12.5) days in the vehicle control group (p = 0.013). Compliance with the dosing regime was 83.1 % and 84.5% for the topical diclofenac and vehicle control groups, respectively. No significant difference was noted in the mean (SD) consumption of rescue acetaminophen tablets per day between the topical diclofenac (0.9 [0.9]) and vehicle control groups (1.1 [1.0]; p = 0.079).\n\nBODY.RESULTS.EFFICACY ANALYSES:\nFour of 216 randomized participants were not included in the ITT analysis group because they violated major entry criteria: 2 participants lacked radiological confirmation of OA (no radiological examination for one participant and a normal examination for the other), and 2 participants had secondary OA (related to osteochondroma). Inclusion of these participants yielded the same results in a subsequent re-analysis (data not shown).\n\nBODY.RESULTS.EFFICACY ANALYSES.PLANNED ANALYSES:\nThere was a significantly greater improvement in score with topical diclofenac compared to vehicle control (Table 2) for pain (-5.2 vs. -3.3; p = 0.003,), physical function (-13.4 vs. -6.9; p = 0.001), PGA (-1.3 vs. -0.7; p = 0.0001) and stiffness (-1.8 vs. -0. 9; p = 0.002) Analysis of the per protocol group of 128 participants confirmed the statistical superiority of topical diclofenac over vehicle control for the primary and secondary outcome measures (p < 0.01; data not shown). Table 2 Efficacy evaluation of the continuous variables Efficacy variable Treatment group N Baseline score, mean (SD) Change in score mean (SD) Mean difference in change (95% CI) P-value Effect size (95% CI) Pain Topical diclofenac 105 13.0 (3.1) -5.2 (5.0) 1.9 (0.7 to 3.2) 0.003 0.41 (0.14 to 0.68) Vehicle control 107 12.7 (3.2) -3.3 (4.3) Physical function Topical diclofenac 105 40.9 (11.9) -13.4 (16.3) 6.5 (2.5 to 10.5) 0.001 0.44 (0.16 to 0.71) Vehicle control 107 40.3 (11.3) -6.9 (13.2) Patient global assessment Topical diclofenac 105 3.1 (0.8) -1.3 (1.3) 0.6 (0.2 to 0.9) 0.0001 0.47 (0.19 to 0.74) Vehicle control 107 3.2 (0.7) -0.7 (1.1) Stiffness Topical diclofenac 105 5.3 (1.4) -1.8 (2.1) 0.9 (0.3 to 1.4) 0.002 0.43 (0.15 to 0.70) Vehicle control 107 5.2 (1.5) -0.9 (2.0) Pain on walking Topical diclofenac 105 2.7 (0.8) -1.2 (1.2) 0.4 (0.1 to 0.7) 0.014 0.34 (0.07 to 0.61) Vehicle control 107 2.7 (0.8) -0.8 (1.1) \n\nBODY.RESULTS.EFFICACY ANALYSES.A POSTERIORI ANALYSES:\nThere was a significantly greater improvement in score with topical diclofenac compared to vehicle control (Table 2) for pain on walking (-1.2 vs. -0.8; p = 0.014). The response rate for at least a 50% reduction in pain (Table 3) was significantly greater following topical diclofenac treatment compared to vehicle control (46/105 [43.8%] vs. 27/107 [25.2%]; p = 0.004). The topical diclofenac group had a significantly greater number of participants with good or very good PGA response (43.8% vs. 16.8%; p <0.0001) compared to the vehicle control group and of OMERACT-OARSI responders (65.7% vs. 49.5%; p = 0.017). Table 3 Efficacy evaluation of the dichotomous variables Efficacy variables Treatment group N Number (%) of participants p-value Number-needed-to-treat (95% CI) 50% reduction in pain Topical diclofenac 105 46 (43.8) 0.004 5 (3–17) Vehicle control 107 27 (25.2) OMERACT-OARSI responder* Topical diclofenac 105 69 (65.7) 0.017 6 (3–33) Vehicle control 107 53 (49.5) Good or very good PGA response Topical diclofenac 105 46 (43.8) <0.0001 4 (3–7) Vehicle control 107 18 (16.8) *A responder is defined as a participant with ≥ 50% improvement in pain or function that was ≥ 20% of the scale, or ≥ 20% improvement in at least two of pain, function or patient global assessment that was ≥ 10% of the scale. \n\nBODY.RESULTS.ADVERSE EVENTS:\nThe major adverse effect reported was dry skin at the application site, occurring in 42/107 (39.3%) and 23/109 (21.1%; p = 0.004) of topical diclofenac and vehicle control participants, respectively (Table 4). A skin-related adverse event led to discontinuation of only 5 participants in the topical diclofenac group. All skin reactions resolved promptly upon withdrawal of treatment. Abdominal pain and dyspepsia each were reported in 4 [3.7%] participants in the topical diclofenac group compared to 1 [0.9%] participant in the vehicle control group, but this difference was not significant (p = 0.21). Table 4 Number (%) of adverse events Adverse Event Topical diclofenac (n = 107) Vehicle control (n = 109) Gastrointestinal reaction Abdominal pain 4 (3.7) 1 (0.9) Constipation 1 (0.9) 1 (0.9) Diarrhea 1 (0.9) 0 Dyspepsia 4 (3.7) 1 (0.9) Gastritis 1 (0.9) 0 Melena 0 1 (0.9) Nausea 1 (0.9) 2 (1.8) Application-site skin reaction Dry skin 42 (39.3)* 23 (21.1) Rash 2 (1.9) 4 (3.7) Paresthesia 2 (1.9) 2 (1.8) Pruritus 0 2 (1.8) Other reaction Headache 6 (5.6) 10 (9.2) Halitosis 2 (1.9) 0 Taste Perversion 4 (3.7) 2 (1.8) *p < 0.01 vs. vehicle control \n\nBODY.DISCUSSION:\nPublished guidelines have incorporated topical NSAIDs as recommended treatment for OA of the knee [4-6]. However, there has been controversy surrounding the adequacy of data supporting their benefit beyond 2 weeks [2,3,8,18]. Moreover, the studies identified in these meta-analyses generally did not conform to current standards for OA trial design [11,19]. In contrast, the present trial utilized standardized radiological and clinical entry criteria and measured efficacy with validated outcome measures. Baseline pain score was substantial; mean (SD) score was 12.9 (3.2) out of a maximum of 20, indicating a flare of pain following withdrawal of prior therapy. Analysis of all of the primary and secondary measures demonstrated that treatment with this topical diclofenac solution relieved the symptoms of primary knee OA at 6 weeks in this study population. Two other recently published trials using this topical diclofenac solution showed it to be superior to vehicle control and/or placebo; a 4-week, non-flare trial of 248 participants [20] and a 12-week, flare trial of 326 participants [21]. As with most NSAID trials, the subject population in this study was selected by the inclusion criterion of a flare of pain, which demonstrates the potential to respond to NSAID/analgesic. In clinical practice, an individual not taking an analgesic may have considered previous NSAID therapy ineffective, in which case s/he would not be expected to respond to topical diclofenac. However, where an individual is intolerant to oral NSAID, one may consider topical diclofenac as a treatment option. Comparison of efficacy results from independent trials with various treatments is facilitated by the introduction of benchmark determinants that are mathematically derived from the experimental raw data, such as effect size [22] for improvement of a continuous variable (e.g. \"How much did the patient's pain improve, relative to placebo?\"). We calculated an effect size (95% CI) of 0.41 (0.14 to 0.68) for pain relief, 0.44 (0.16 to 0.71) for improved physical function and 0.34–0.47 for improved measures of PGA, stiffness and pain on walking (Table 2). In contrast, Lin et al. [8] calculated a pooled effect size for pain relief of 0.04 (essentially no effect) in 3 placebo-controlled topical NSAID trials of 4 weeks duration. A meta-analysis of 23 oral NSAID trials for OA knee, lasting 2–13 weeks, reported a pooled effect size of 0.32 for pain reduction and 0.29 for improving physical function [23]. Another meta-analysis of 14 OA trials found a pooled effect size of 0.37 for pain reduction with oral NSAIDs and 0.44 for coxibs [24]. Zhang et al. [25], using data from 2 oral NSAID studies of 6–12 weeks duration, calculated a pooled effect size for OA pain reduction of 0.34. Efficacy of a treatment is being expressed increasingly as a dichotomous result, e.g. \"Did the patient's pain improve by 50%; yes or no?\". We derived the response rate for each dichotomous variable from our raw data, and demonstrated the superiority of topical diclofenac over vehicle control for 50% reduction in pain, achieving a good or very good final PGA response, and 'response' by OMERACT-OARSI criteria (Table 3). The benchmark determinant for comparing dichotomous efficacy results of various treatments is the number-needed-to-treat (NNT) [26]. We calculated a NNT between 4 and 6, depending upon the variable (Table 3). In their meta-analysis of topical NSAIDs, Mason et al. [3] cited 5 placebo-controlled trials of short duration for OA knee pain – 8 days (1 trial), 14 days (3 trials), and 28 days (1 trial). Their definition of clinical success, representing approximately a 50% reduction of pain, was estimated using patient or physician global assessment as the outcome measure (4 trials and 1 trial, respectively). They calculated a NNT of 5.3. Few oral NSAID studies have reported dichotomous data. Osiri et al. [26] reported a NNT for pain improvement of 4.4 with etodolac and 3.8 with tenoxicam. Defining improvement as an increase of at least 2 grades (on a 0–5 scale) in the patient's global rating of arthritis, Edwards et al. [27] reported a NNT of 11–13 for valdecoxib treatment of OA. The OMERACT-OARSI initiative used a consensus approach to derive dichotomous 'responder' criteria [14]. Through their vast meta-analysis of suitable trials, the authors found that for trials of oral NSAIDs vs. placebo the responder rates were 65.4% and 45.9% respectively. Responder rates of 60–65% have been reported for 13-week treatment of OA with celecoxib and lumiracoxib, with placebo responder rates of 49–53% [28,29]. The OMERACT-OARSI initiative did not look at topicals but we applied its criteria to this study and found a responder rate for topical diclofenac of 65.7% with a placebo responder rate of 49.5%, similar to their oral NSAID data. A caveat in the application of the mathematical benchmarks, effect size and NNT, is the influence of trial design, outcome measures and patient population on the apparent magnitude of response to a given treatment. Because the trials with topical diclofenac were designed according to the OARSI guidelines, like most recent NSAID and cyclooxygenase-2 (COX-2) inhibitor studies, such comparison of results is reasonable [19]. Although the data observed for topical diclofenac in this trial are comparable to other NSAID trials, a direct head-to-head comparison trial is required to prove equivalency of two treatments. A previously published 12-week comparative trial of 622 participants with OA knee confirmed the clinical equivalence between topical diclofenac solution and oral diclofenac [30]. Safety analysis revealed no serious clinical adverse effects and only minor application-site skin reactions, mostly skin dryness, following treatment with topical diclofenac. While dimethyl sulphoxide in the carrier acts as a penetrant [31], it also dissolves normal surface oils and leaves the skin dry. Common skin lubricants may prevent most application site reactions and any related discontinued therapy, but such products were not permitted in this trial in order to detect the maximum potential side effect profile of the study solutions. The low dropout rate due to skin reactions (5/107 [4.7%] for topical diclofenac) suggests patient acceptance of the overall topical treatment regime. The use of a checklist to prompt the patient about possible adverse events likely yielded a high estimate of the true incidence of gastrointestinal adverse reactions caused by topical diclofenac. The report of abdominal pain and dyspepsia each in 3.7% of patients is consistent with what was seen in other published trials of this topical diclofenac [20,21] and much lower than commonly experienced with oral NSAIDs or COX-2s [30]. Those other trials included results of laboratory testing and found minor abnormality of liver enzymes in 2–5%, creatinine in 1% and haemoglobin in 2% of patients, significantly lower than with oral diclofenac [30]. This safety profile can be predicted from the low systemic availability of topically applied diclofenac. Although the patient applies a daily dose (40 drops, 4 times a day) of 86 mg of diclofenac to the knee, the blood level is only 12 ng/mL [31]. The level reported after oral administration of 50 mg Voltaren® is 1500 ng/mL [32]. Similar improved safety with topical NSAIDs has been reported previously [33].\n\nBODY.CONCLUSION:\nTopical diclofenac solution provides 6-week relief of the symptoms of knee OA. The data in this and previous reports provide substantial evidence for the efficacy and safety of topical diclofenac solution in chronic OA.\n\nBODY.COMPETING INTERESTS:\nLMT and ZS are employees of Dimethaid Research Inc. PAB was a principal investigator in the trial, and was remunerated for his participation.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nPAB was a major investigator in the trial and was involved in data interpretation. LMT was involved in analysis and interpretation of the data and writing of the manuscript. ZS was involved in trial design and conduct, data review and writing of the manuscript. All authors reviewed and approved the final draft of the manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here:\n\n**Question:** Compared to vehicle control solution (carrier with no diclofenac) what was the result of topical diclofenac solution (Pennsaid®) on Dry skin at the application site?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
350
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Formoterol DPI 9 μg what was the result of Budesonide/formoterol pMDI 320/9 μg on Amount of exacerbations per patient-treatment year?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
274
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Randomized Clinical Trial of Laparoscopic Versus Open Repair of the Perforated Peptic Ulcer: The LAMA Trial\n\n ABSTRACT.BACKGROUND:\nLaparoscopic surgery has become popular during the last decade, mainly because it is associated with fewer postoperative complications than the conventional open approach. It remains unclear, however, if this benefit is observed after laparoscopic correction of perforated peptic ulcer (PPU). The goal of the present study was to evaluate whether laparoscopic closure of a PPU is as safe as conventional open correction.\n\nABSTRACT.METHODS:\nThe study was based on a randomized controlled trial in which nine medical centers from the Netherlands participated. A total of 109 patients with symptoms of PPU and evidence of air under the diaphragm were scheduled to receive a PPU repair. After exclusion of 8 patients during the operation, outcomes were analyzed for laparotomy (n = 49) and for the laparoscopic procedure (n = 52).\n\nABSTRACT.RESULTS:\nOperating time in the laparoscopy group was significantly longer than in the open group (75 min versus 50 min). Differences regarding postoperative dosage of opiates and the visual analog scale (VAS) for pain scoring system were in favor of the laparoscopic procedure. The VAS score on postoperative days 1, 3, and 7 was significant lower (P < 0.05) in the laparoscopic group. Complications were equally distributed. Hospital stay was also comparable: 6.5 days in the laparoscopic group versus 8.0 days in the open group (P = 0.235).\n\nABSTRACT.CONCLUSIONS:\nLaparoscopic repair of PPU is a safe procedure compared with open repair. The results considering postoperative pain favor the laparoscopic procedure.\n\nBODY.INTRODUCTION:\nThe incidence of perforated peptic ulcer (PPU) has declined over the past several years because of the introduction of anti-ulcer medication and Helicobacter eradication therapy [1, 2]. Nevertheless the incidence and mortality of PPU is 5–10%. The mortality will increase up to 50% if the perforation exists for more than 24 h [3, 4]. There are several options for treatment of PPU, but the preferred treatment is surgery by upper abdominal laparotomy [5, 6]. Mouret et al. published the first results of laparoscopic repair in 1990 [7]. He concluded that it was a good method that probably reduced postoperative wound problems and adhesions. After the success of laparoscopic cholecystectomy and other laparoscopic procedures, it was thought that patients would have less pain and a shorter hospital stay after laparoscopic correction of PPU [8, 9]. Various studies have shown that laparoscopic suturing of the perforation is feasible, but there is still no proof of real benefits of laparoscopic correction [3, 6, 10–12]. Therefore we performed a multicenter randomized trial comparing open correction of PPU with laparoscopic repair.\n\nBODY.METHODS.PARTICIPANTS:\nPatients with symptoms of the clinical diagnosis of PPU were included in nine medical centers in the Netherlands participating in the LAMA (LAparoscopische MAagperforatie) trial between March 1999 and July 2005. Eligible patients were informed of the two surgical approaches and were invited to participate in the study. Exclusion criteria were the inability to read the Dutch language patient information booklet, inability to complete informed consent, prior upper abdominal surgery, and current pregnancy. The ethics committees of all participating institutions approved the trial.\n\nBODY.METHODS.RANDOMIZATION:\nSurgeons contacted the study coordinator after the patients had provided informed consent and randomization took place by opening a sealed envelope. The envelope randomization was based on a computer-generated list provided by the trial statistician.\n\nBODY.METHODS.SURGICAL PROCEDURE:\nAll patients received intravenous antibiotics prior to operation and were allocated for Helicobacter pylori eradication therapy according to established guidelines [13]. The open surgical procedure was performed through an upper abdominal midline incision. Closure of PPU was to be achieved by sutures alone or in combination with an omental patch. After repair of the defect cultures were drawn from the peritoneal fluid, after which the peritoneal cavity was lavaged. During lavage it was permissible to insufflate the stomach to test for leakage of the closed defect. No method was specified for closing the abdomen. Laparoscopic repair was performed with the patient and the team set up in the \"French\" position. Trocars were placed at the umbilicus (video scope) and on the left and right midclavicular line above the level of the umbilicus (instruments). If necessary a fourth trocar was placed in the subxiphoid space for lavage or retraction of the liver. Surgeons were free to use either 0° or 30° video scopes for the procedure. The rest of the procedure was identical to that described above for open repair. No method was specified for closing the trocar incisions.\n\nBODY.METHODS.POSTOPERATIVE FOLLOW-UP:\nPostoperative pain was scored by means of a visual analog scale (VAS) for pain on days 1, 3, 7, and 28 ranging from 0 (no pain) to 10 (severe pain). In addition, the days during which opiates were used by the patients were registered. All complications, minor and major, were monitored. The treating surgeons determined time of discharge on the basis of physical well-being, tolerance of a normal diet, and ability to use the stairs. For this reason, this was an unblinded trial. Postoperative hospital stay without correction for time spent in hospital as a result of non-medical reasons (inadequate care at home) was calculated. Patients were invited to attend the outpatient clinic at 4 weeks, 6 months, and one year postoperatively. They were asked to complete forms related to pain and use of analgesics.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData analysis was carried out according to the intention-to-treat principle as established in the trial protocol. Data were collected in a database, and statistical analyses were performed with the Statistical Package for Social Sciences for Windows (SPSS 15.0, SPSS Inc., Chicago, IL). A researcher blinded to the nature of the procedures performed all data analyses. The primary outcome of the trial was duration of hospital stay. The power analysis was performed on basis of a reduction in hospital stay by 1.5 days (10–8.5 days from admission) in favor of the laparoscopically treated group using a β of 0.80 and an α of 0.05. This resulted in a trial size of 50 patients per group. The Pearson chi-squared test was used to compare categorical variables, and the Mann-Whitney U-test was used to compare continuous variables as we could not assume normal distribution because of the relatively small numbers. In Tables 1–6 medians and interquartile ranges (IQR) are reported. All data were analyzed according to the intention-to-treat principle; i.e., patients remained in their assigned group even if during the procedure the surgeon judged the patient not to be suitable for the technique assigned or if conversion was required. Null hypotheses were tested two-sided and a P value of 0.05 or less was considered statistical significant.Table 1Baseline parametersLaparoscopic repairOpen repairP valuen = 52 n = 49 Male:female ratio1.3:11.9:1Median age (years) + IQR 66 (25.8)59 (29.5)0.185Median BMI (kg/m2) + IQR23 (4)22 (5)0.118Median duration of symptoms (h) + IQR11 (17)11 (19)0.948Median blood pressure systolic (mmHg) + IQR125 (38.5)130 (36.5)0.457Median blood pressure diastolic (mmHg) + IQR75 (25.5)75 (24.5)0.596Median heart rate (beats/min) + IQR 88 (34.0)92 (21)0.403Median body temperature (°C) + IQR 36.9 (0.92)36.8 (1.5)0.658Mannheim Peritonitis Index + IQR19.5 (8.25)16 (14)0.386Median white cell count (×109/l) + IQR 12.1 (8.9)12.1 (7.75)0.467Median ASA score + IQR 1.0 (1.0)1.5 (1.0)0.902IQR interquartile range, difference between 25th percentile and 75th percentile; BMI body mass indexASA American Society of Anesthesiologists Association score\n\nBODY.RESULTS.PATIENTS:\nA total of 109 patients were included in the trial based on a high suspicion of PPU (Fig. 1). Eight patients were excluded during operation because no gastric perforation was detected or a defect in other parts of the digestive tract was uncovered. Data for these patients were not collected and the patients were excluded from further analysis. The remaining 101 patients made up the study population; their baseline parameters are given in Table 1. Fifty-two patients were randomized for laparoscopic repair and 49 for open repair of the perforation. Forty patients were female. The mean age of the patients was 61 years. The BMI (body mass index) was equally distributed between the groups, with a median of 22.5. Patients in both groups had been suffering from symptoms for a mean duration of 11 h, and those in the laparoscopy group presented with a median Mannheim Peritonitis index [14] of 19.5, whereas those in the open group had a median Mannheim Peritonitis index of 16.Fig. 1Patient flow chart Thirty patients reported the use of non-steroidal anti-inflammatory drugs (NSAIDs; 17 laparoscopic versus 13 open), and 10 patients used proton pump inhibitors (6 laparoscopic versus 4 open). Patient history revealed gastric ulcer disease in 19 patients.\n\nBODY.RESULTS.INTRAOPERATIVE FINDINGS:\nThe discovered ulcer perforations were found to have a mean diameter of 10 mm, which did not differ between groups (Table 2). Location of the perforated ulcers was distributed equally between groups. Defects were located in the prepyloric region (n = 41), the postpyloric region (n = 34), and at the pylorus (n = 20). The median volume of lavage fluid used was 1,000 ml (range: 100–5,000 ml). The surgeon decided the amount of lavage used. There was no consensus on how much was necessary. Median blood loss did not differ between groups. Skin-to-skin time differed by 25 min, favoring open repair of PPU (Table 2).Table 2Intraoperative findingsLaparoscopic repairOpen repairP valuen = 52n = 49Median size of perforation (mm) + IQR10.0 (7.0)7.0 (6.0)0.379Number of patients with defect Pyloric812 Postpyloric2014 Prepyloric1922 Median volume of lavage (ml) + IQR1,000 (1,500)1,000 (1,425)1.000 Median bloodloss (ml) + IQR10.0 (40.0)10.0 (50.0)0.423 Skin to skin time (min) + IQR75 (47.2)50 (25.5)0.000\n\nBODY.RESULTS.INTRAOPERATIVE COMPLICATIONS:\nConversion to open surgery was required in four patients (8%). Reasons for conversion included the inability to visualize the ulcer defect because of bleeding (n = 1/52; 2%), inability to reach the defect because of perforation in the vicinity of the gastroduodenal ligament and because of a dorsal gastric ulcer (n = 2/52; 4%), and inability to find the perforation (n = 1/52; 2%).\n\nBODY.RESULTS.POSTOPERATIVE COMPLICATIONS:\nComplications were statistically equally distributed between the two groups (Table 3). There were 12 complications in 9 patients in the laparoscopic group and 24 complications in 15 patients in the open group. Mortality was 4% in the laparoscopic group and 8% in the open group. In the laparoscopic group death was caused by sepsis due to leakage at the repair site. In the open group 3 patients died because of pulmonary problems (ARDS, pneumonia), and 1 patient died after complications following a cerebrovascular accident (CVA) combined with respiratory insufficiency.Table 3Postoperative complicationsLaparoscopic repairOpen repairP valuen = 52n = 49Pneumonia21Respiratory insufficiency13ARDS1Cardiac problems22Sepsis31Leakage at repair site2Abscess3Ileus1Fascial dehiscence1Wound infection3Urinary tract infection2Incisional hernia1Cerebrovascular accident1Death24Total complications12240.061Total of patients with complications ≥19 (18%)15 (36%)\n\nBODY.RESULTS.DISCHARGE:\nTime to discharge was similar for the two groups, with a median difference of 1.5 days (Table 4). Nasogastric decompression could be stopped after 2–3 days in both groups (Table 4).Table 4Duration of hospital stay, nasogastric decompressionLaparoscopic repairOpen repairP valuen = 52n = 49Median hospital stay (days) + IQR6.5 (9.3)8.0 (7.3)0.235Median duration of nasogastric decompression (days) + IQR2.0 (3.0)3.0 (1.3)0.334\n\nBODY.RESULTS.PAIN:\nVisual analog pain scores were in favor of laparoscopic repair (Table 5; p < 0.005). Although the median duration of opiate use in the two groups was 1.0, the mean duration in the open group was found to be 0.6 days longer than in the laparoscopic group (Table 6).Table 5Postoperative painMedian VAS pain scoreMedian VAS pain scoreP valueLaparoscopic repairOpen repairDay 1 + IQR3.8 (3.0)5.15 (2.5)0.001Day 3 + IQR2.1 (2.5)3.0 (2.4)0.035Day 7 + IQR1.0 (2.0)1.85 (2.8)0.036Day 28 + IQR0.3 (0.7)0.0 (1.7)0.748Table 6Postoperative opiate usageOpiate requirementOpiate requirementP valueLaparoscopic repairOpen repairMedian duration (days) + IQR1.0 (1.25)1.0 (1.0)0.007Mean duration (days) ± SD1.0 ± 0.91.6 ± 0.90.007\n\nBODY.RESULTS.VAS APPEARANCE OF SCAR:\nThe VAS score for appearance of the scar left by the respective procedures (subjectively recorded in the same way as pain) differed by 2.3 points, favoring the laparoscopic procedure (7.7 vs. 5.4; P = 0.033)\n\nBODY.DISCUSSION:\nThe need for surgery for PPU has declined enormously in Europe and America with reported rates ranging from 50% to 80%, thanks to effective gastric acid-reducing medication [15]. For this reason, as well as because many surgeons prefer upper laparotomy, it took more time than expected to include 100 patients in our study. Reasons given by surgeons who prefer open repair were that it is a more familiar procedure and it can be completed faster than laparoscopy. It was also noted that patients often undergo operation at night, when the surgeon on call was not always laparoscopically trained. Other randomized trials have already shown the feasibility of laparoscopic repair of PPU [3, 4, 6, 10]. Only a few had more than 100 patients, and some emphasized results from subgroups of patients [8, 11, 12]. We did not subdivide our patients and included patients with risk factors for developing sepsis or conversion [10]. In eight of the original 109 patients (7%) it became evident during the operation that the patient had a diagnosis different from PPU. In the patients who were randomized for laparoscopy this discovery revealed the benefit of laparoscopy as a diagnostic procedure indicating either an upper or lower abdominoplasty or continuation of the laparoscopy [16]. Conversion rate in the laparoscopy group was 8% (4/52). This is much lower than that reported in literature, where conversion rates as high as 60% were found [3, 4, 6]. This maybe partially explained by the fact that only trained and experienced laparoscopic surgeons (those performing at least 50 laparoscopic procedures a year) participated in this trial, confirming the belief that this procedure should only be done by experienced surgeons [3–5]. Operating time was significantly longer in the laparoscopy group (75 min versus 50 min), which is comparable to reports in the literature [3, 10]. A possible explanation for the longer operative time is that laparoscopic suturing is more demanding [9, 17], especially if the edges of the perforation are infiltrated and friable. Sutures easily tear out and it is more difficult to take large bites and to tie knots properly. Use of a single-stitch method described by Siu et al. [18], fibrin glue, or a patch might solve this problem [12, 19]. Another reason for the increase in operating time is the irrigation procedure. Irrigating through a 5-mm or even a 10-mm trocar is time consuming, and suction of fluid decreases the volume of gas and reduces the pneumoperitoneum. There is no evidence that irrigation lowers the risk of sepsis [20], so it might only be necessary if there are food remnants in the abdomen; perhaps there is no need for it at all. One of the suspected risks of laparoscopic surgery is that of inducing sepsis by increasing bacterial translocation while establishing a pneumoperitoneum [6]. This danger could not be confirmed in our trial. Furthermore data suggest that there is a decrease in septic abdominal complications when laparosopic surgery is used [8]. Evidence already exists that laparoscopic correction of PPU causes less postoperative pain [6, 12, 17, 18]. The meta-analysis published by Lau [6] showed that eight out of ten studies showed a significant reduction in dosage of analgesics required in the laparoscopic group. Also, the three studies that had included VAS pain scores showed consistently lower pain scores, as was observed in our study as well. Whether this will lead to a better quality of life for patients, especially during the first weeks after surgery still needs to be analyzed. Although patients in our series who underwent laparoscopy had less postoperative pain, there was no difference in the length of hospital stay in our two groups. In fact, hospital stay overall in our patients was very long. This was most likely caused by the fact that many patients, especially the elderly, could not be discharged because of organizational reasons. Of the 101 patients, 41% were 70 years or older (24 in the laparoscopic group versus 17 in the open group). It appears that the age of PPU patients is increasing, and this will eventually represent a significant problem in the future [2, 3]. One benefit of the laparoscopic procedure not often mentioned in literature [6] is cosmetic outcome. Nowadays patients are aware of this benefit, and sometimes this is the reason why they demand laparoscopic surgery. In conclusion, the results of the LAMA trial confirm the results of other trials that laparoscopic correction of PPU is safe, feasible for the experienced laparoscopic surgeon, and causes less postoperative pain. Operating time was longer in the laparoscopic group and there was no difference in length of hospital stay or incidence of postoperative complications.\n\n**Question:** Compared to Conventional open approach what was the result of Laparoscopic surgery on Better scar appearance score as measured by visual analog scale?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
339
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Placebo what was the result of Budesonide/formoterol pMDI 320/9 μg on Pre-dose inspiratory capacity?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
405
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Incisional hernia after upper abdominal surgery: a randomised controlled trial of midline versus transverse incision\n\n ABSTRACT.OBJECTIVES:\nTo determine whether a transverse incision is an alternative to a midline incision in terms of incisional hernia incidence, surgical site infection, postoperative pain, hospital stay and cosmetics in cholecystectomy.\n\nABSTRACT.SUMMARY BACKGROUND DATA:\nIncisional hernias after midline incision are commonly underestimated but probably complicate between 2 and 20% of all abdominal wall closures. The midline incision is the preferred incision for surgery of the upper abdomen despite evidence that alternatives, such as the lateral paramedian and transverse incision, exist and might reduce the rate of incisional hernia. A RCT was preformed in the pre-laparoscopic cholecystectomy era the data of which were never published.\n\nABSTRACT.METHODS:\nOne hundred and fifty female patients were randomly allocated to cholecystectomy through midline or transverse incision. Early complications, the duration to discharge and the in-hospital use of analgesics was noted. Patients returned to the surgical outpatient clinic for evaluation of the cosmetic results of the scar and to evaluate possible complications such as fistula, wound dehiscence and incisional hernia after a minimum of 12 months follow-up.\n\nABSTRACT.RESULTS:\nTwo percent (1/60) of patients that had undergone the procedure through a transverse incision presented with an incisional hernia as opposed to 14% (9/63) of patients from the midline incision group (P = 0.017). Transverse incisions were found to be significantly shorter than midline incisions and associated with more pleasing appearance. More patients having undergone a midline incision, reported pain on day one, two and three postoperatively than patients from the transverse group. The use of analgesics did not differ between the two groups.\n\nABSTRACT.CONCLUSIONS:\nIn light of our results a transverse incision should, if possible, be considered as the preferred incision in acute and elective surgery of the upper abdomen when laparoscopic surgery is not an option.\n\nBODY.INTRODUCTION:\nThe rate of incisional hernia after midline incision is commonly underestimated but probably lies between 2 and 20% [1–5]. Thus, incisional hernia is a major postoperative problem. The treatment of incisional hernia is complicated by high rates of recurrences. Recently, in a randomised controlled trial published by Burger et al. [6], midline incisional hernia repair has been shown to be associated with a 10-year cumulative recurrence rate of 63 and 32% for suture and mesh repair, respectively. The midline incision is the preferred incision for surgery of the upper abdomen, despite evidence that alternatives, such as the lateral paramedian and transverse incision, exist and might reduce the rate of incisional hernia [7]. Various approaches to opening the abdomen have been advocated over time. The choice for a certain incision is dependent on the exposure necessary for the desired procedure to succeed. A midline incision, be it supraumbilical, infraumbilical or both, is an approach especially suited for emergency and exploratory surgery because of the quick and generous exposure that can be achieved within a few minutes [8, 9]. The avascular nature of the linea alba minimises blood loss during this procedure. A supraumbilical transverse incision may be utilised in case exposure of the upper abdomen is desired. During this incision, the damage inflicted to the segmental arteries and nerves is previously described as being minimal [10]. Previously, only one randomised controlled trial, comparing transverse and true midline incisions, has been published specifically addressing incisional hernia incidence [11]. To determine whether the use of a transverse incision is an alternative to a midline incision for open cholecystectomy in terms of incisional hernia incidence, surgical site infection, postoperative pain and hospital stay, this randomised controlled trial was performed. This trial was conducted in an era when laparoscopic cholecystectomy was not yet available. The possibility of low incisional hernia rates after transverse incisions and the fact that little is known about potential advantages incited us to publish the relevant results of this randomised controlled trial which has been performed in the past and has only been reported in a Dutch thesis by one of the authors (H.L.). The primary endpoint of this study was the incisional hernia incidence after 12 months of follow-up. Secondary endpoints included pain and cosmetic appearance.\n\nBODY.METHODS.PROTOCOL:\nSome 150 consecutive female patients were randomly assigned to a midline or transverse incision as an approach for elective cholecystectomy or combined cholecystectomy and cholangiography (with or without consecutive choledochotomy) (75 and 75 patients, respectively). Emergency procedures were excluded from participation. The sample size is based on an incisional hernia rate reduction from 20 to 6% at a power of 80% and an error rate of 5%. Obtaining informed consent was conducted in accordance with the ethical standards of the Helsinki Declaration of 1975. The investigation reported was performed with informed consent from all of the patients and followed the guidelines for experimental investigation with human subjects and was approved by the medical ethics committee. An independent statistician prepared closed, tamper-proof envelopes containing the random allocation (Fig. 1). Patients were randomised for one of the procedures in theatre through the opening of the envelopes.Fig. 1Flow chart of patient inclusion and follow-up Patient-related factors that were recorded were age, body mass and length and date of operation. Operation-related factors that were recorded were the exact nature of the operation, length of the incision, the thickness of the subcutaneous fat, surgeon performing the procedure, as well as the duration of the operation (skin-to-skin time). In the immediate postoperative period, the use, dose and type of analgesics was recorded and a pain score was administered. The use of analgesics (morphine 7.5 mg intra-muscular injection, 4 h minimum interval between consecutive injections) was monitored for 48 h after surgery; the pain score was administered for the first 6 days after surgery. In patients assigned to surgery through a midline incision, the skin was incised from just below the xyphoid process to just above the umbilicus. The abdominal wall was opened in the midline by incising the linea alba. A Collin type (two-bladed) self-retaining retractor was used to maintain exposure. The abdominal wall was closed in one layer using single polygalactin 910 sutures (Vicryl; Ethicon, Amersfoort, The Netherlands). The skin was consequently closed using running monofilament nylon sutures (Ethilon; Ethicon, Amersfoort, The Netherlands). Patients randomised for a transverse incision received a right-sided unilateral transverse incision between 3 and 4 cm below the costal margin. The rectus muscle was incised. The fibres of the external and internal obliques and the transverse muscles were separated in the direction of their course. Exposure was achieved through the use of a manually held single-bladed retractor. Closure of the abdominal wall was achieved by closure of the peritoneum and the posterior rectus fascia using a continuous, polygalactin 910 suture (Vicryl; Ethicon, Amersfoort, The Netherlands). The anterior rectus sheath and the fascia of the internal and external transverses were closed using simple interrupted polygalactin 910 sutures (Vicryl; Ethicon, Amersfoort, The Netherlands). Towards the end of both procedures, a Redon low-vacuum drain catheter was placed, which was guided outside the abdominal cavity approximately 5 cm from the incision. The skin was consequently closed using continuous monofilament nylon suture (Ethilon; Ethicon, Amersfoort, The Netherlands). All patients received a dose of 5,000 IU of sodium–heparin on the morning of the procedure as thrombosis prophylaxis.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nThe Pearson χ2 test was used for comparing percentages. In case of small expected numbers, a Fisher's exact test was performed. Continuous variables were analysed using the Mann–Whitney test. A P-value of 0.05 or less (two-sided) was considered to be statistically significant. Means and medians are expressed ±standard deviation (SD).\n\nBODY.METHODS.FOLLOW-UP:\nPatients returned to the surgical outpatient clinic for evaluation of the cosmetic results of the scar and to evaluate possible complications, such as fistula, wound dehiscence and incisional hernia, after a minimum of 12 months follow-up. The patient and the surgeon evaluated the cosmetic results independently and were asked to rate the scar as unsatisfactory, satisfactory or fine. Furthermore, the length and width of the scar was measured.\n\nBODY.RESULTS.STUDY GROUP:\nSome 150 consecutive patients were randomised for participation in this study during an inclusion period from April 1977 until July 1979. Seventy-five patients received a transverse incision and 75 patients a midline incision (Fig. 1). One patient was withdrawn from further follow-up after developing peritonitis and consequent acute respiratory distress syndrome (ARDS) not related to the closure of the abdominal wall 2 days after surgery (transverse incision group). The patients' average age was 51.9 and 51.4 years for the midline and the transverse incision groups, respectively. Furthermore, no differences were found in the body mass and average length between the two groups (Table 1). A cholecystectomy was performed using a transverse incision in 52 patients and utilising a midline incision in 52 patients also. Fifteen and 16 patients, respectively, underwent a combined cholangiography/cholecystectomy. A further 7 and 6 patients, respectively, were treated with a cholangiography/cholecystectomy plus additional choledochotomy and the postexploratory placement of a T-tube.Table 1Baseline characteristics of the patients undergoing surgery, according to study groupVariableMidline incisionTransverse incisionn = 75n = 74Average age (years) ± SD51.9 ± 14.851.4 ± 13.8Average weight (kg) ± SD71.3 ± 14.568 ± 14.3Average length (cm) ± SD163.5 ± 7.8164 ± 7.3\n\nBODY.RESULTS.SURGEON:\nStaff surgeons performed 17% (13/75 patients) of all procedures performed through a midline incision. The remainder of the procedures through a midline incision was carried out under staff surgeon supervision. Staff surgeons performed 14% of all procedures in the transverse incisions study group (10/74 patients) and supervised the remainder. No statistically significant difference was found between the two randomised groups (P = 0.65).\n\nBODY.RESULTS.DURATION OF SURGERY:\nNo significant difference was noted in the skin-to-skin time (in min) for the two different incisions (Table 2). Surgery utilising midline and transverse incision took 56.9 ± 29.3 and 53.2 ± 26.8 min, respectively (P = 0.35). The total duration of the procedures until extubation (in min) did not differ between the midline and transverse incisions (71.0 ± 30.5 and 67.0 ± 27.3, respectively, P = 0.34).Table 2Length of incision, thickness of subcutaneous fat and skin-to-skin time, according to study groupVariableMidline incisionTransverse incisionP-valueLength of incision (mm) ± SDa164 ± 28140 ± 24<0.0001Thickness of subcutaneous fat (mm) ± SDa34.5 ± 13.030.3 ± 12.40.05Skin-to-skin time (min) ± SDa56.9 ± 29.353.2 ± 26.80.40Width of scar (mm) ± SDb8.3 ± 1.43.3 ± 1.2<0.0001aMeasured during surgery in 75 midline and 74 transverse incisionsbMeasured at follow-up in 63 and 60 midline and transverse incisions, respectively\n\nBODY.RESULTS.PAIN AND ANALGESICS:\nSignificantly more patients, having undergone a midline incision, reported pain on day one, two and three postoperatively (P < 0.0001, Table 3). In the midline incision group, 28/75 patients required no or only one dose of analgesics; the remainder required two or more doses. Thirty-one patients operated through a transverse incision required no analgesics or only one dose; 43 patients (the remainder) required two or more. No significant difference in the use of analgesics was found between the groups (P = 0.69).Table 3Postoperatively reported pain, according to study group, shown as the number of patients reporting pain at the time points indicated (percentage), with the remainder of patients reporting no painTime point after surgeryMidline incision n = 75Transverse incision n = 74P-valuePatients reporting pain, n (%)Patients reporting pain, n (%)3–4 h68 (91)60 (81)0.09First day64 (85)39 (53)<0.0001Second day57 (76)23 (31)<0.0001Third day28 (37)9 (12)<0.0001Fourth day5 (7)3 (4)0.72Fifth day0 (0)1 (1)0.50Sixth day0 (0)1 (1)0.50\n\nBODY.RESULTS.COMPLICATIONS:\nPostoperative complications (Table 4) were seen in 16 out of 75 patients (21%) from the midline incision group and in 15% from the transverse incision group (11 patients) (P = 0.30). Briefly, one patient in each group developed cardiac complications; 8 and 6 patients developed urinary retention after the midline and transverse incisions, respectively (P = 0.59). Surgical site infections were diagnosed in 7 and 3 patients, respectively (P = 0.33).Table 4Rate of complications after surgery, according to study group, shown as the number of patients diagnosed with complications (percentage)ComplicationMidline incisionTransverse incisionP-valuen = 75 n (%)n = 75 n (%)Cardiac1 (1)1 (1)1Urinary retention8 (12)6 (8)0.59ARDS01 (1)0.50Surgical site infection7 (9)3 (4)0.33Haemorrhage1 (1)00.50Pneumonia01 (1)0.50Total17 (23)12 (16)0.30\n\nBODY.RESULTS.DISCHARGE:\nForty-five (60%) and 42 (57%) patients from the patients having undergone a midline or a transverse incision, respectively, were discharged on day 6 or 7 postoperatively. The remaining patients from each group left hospital care on day 8 or later. The duration of hospital admission did not differ between the two types of incision (P = 0.74).\n\nBODY.RESULTS.COSMETICS:\nThe width and length of all incisions was measured during the follow-up visit (Table 2). The mean width of the scar after the healing of the midline incisions was found to be 8.3 ± 1.4 mm. The mean width of the scar after the healing of the transverse incisions was measured to be 3.3 ± 1.2 mm. This observed difference is significant (P < 0.0001). The length of the incisions was 140 ± 24 mm and 164 ± 28 mm for the transverse and the midline incisions, respectively. The difference in scar length was found to be significant (P < 0.0001).\n\nBODY.FOLLOW-UP:\nEighty-one percent of all patients operated through a transverse incision were seen during the follow-up examination (n = 60). Of the patients operated through a midline incision, 63 out of 75 were seen at the outpatient clinic (84%). The patients that were lost to follow-up could either not be traced or had deceased (Fig. 1). The minimum follow-up for the evaluation of cosmetic results and hernia incidence was 12 months and the maximum was 36 months.\n\nBODY.FOLLOW-UP.INCISIONAL HERNIA:\nFrom the patients that had undergone the procedure through a transverse incision, one (1/60; 2%) presented with an incisional hernia as opposed to 9 patients from the midline incision group (9/63; 14%); 95% confidence interval (CI) 7.5–25.4%. This difference in hernia incidence is significant (P = 0.017). No significant correlation was found between the incisional hernia rate and surgical site infection (P = 0.07).\n\nBODY.FOLLOW-UP.SUBJECTIVE COSMETICS:\nPatients and surgeons alike were asked to rate the appearance of the scar during the postoperative follow-up outpatient clinic visit. Both the surgeons and the patients found the scar resulting from the transverse incision to be more cosmetically pleasing (P < 0.0001 and P = 0.03, respectively, Table 5).Table 5Number of patients and surgeons rating the cosmetics of a scar at follow-upScoreMidline incision (n = 63)Transverse incision (n = 60)Patients, n (%)Surgeons, n (%)Patients, n (%)Surgeons, n (%)Unsatisfactory6 (10)25 (40)2 (3)6 (10)Satisfactory16 (25)27 (43)9 (15)12 (20)Fine41 (65)11 (17)49 (82)42 (70)Total63636060Difference between type of incision: patients P = 0.03; surgeons P < 0.0001\n\nBODY.DISCUSSION:\nThis prospective randomised study of transverse and midline incisions for open cholecystectomy shows that a significant reduction of incisional hernia incidence can be achieved through the use of a transverse incision. Only one other study (published in 1980) reported the incidence of incisional hernia after upper abdominal midline and unilateral transverse incision in a randomised trial. No difference between the two techniques (8 and 6% incisional hernia, respectively) was found, but the relatively short follow-up of 6 months, however, may be held accountable for this finding [11]. Three retrospective studies showed rates of incisional hernia of 3.2, 5.4 and 16.5% for midline incision and 1.3, 6.7 and 13.4% for transverse incision without statistically significant differences [12–14]. The possible reason for the rather high incidence of incisional hernia in the midline incision group (14%) may lie in the use of resorbable 910 polygalactin sutures. Nevertheless, the use of the same type of resorbable suture in the closure of the transverse incisions resulted in a 2% hernia rate. There is evidence for the importance of proper technique and choice of incision as a means to reduce incisional hernia being more important than the use of suture material [7]. Furthermore, as mentioned above, it is known that the incidence of incisional hernia in the case of a midline incision lies between 2 and 20%. From our data, the NNT (numbers needed to treat) is calculated to be 8 (95% CI 5–30) and the RRR (relative risk reduction) is 88% (95% CI 23–100%). Luijendijk et al. [15] have published a hernia rate of 2% after Pfannenstiel incisions closed using 910 polygalactin, which is in agreement with our findings in the patients randomised for a transverse incision, emphasising the importance of the incision over the choice of suture material. In our study, significantly fewer patients reported pain on day 1, 2 and 3 after transverse incisions, a result that was also described by other authors [16, 17]. Greenall et al. [18] published a contradictory report (in 1980) in which no significant difference in postoperative pain was found between midline and transverse incisions. The previously mentioned study, however, only analysed 46 out of 572 patients (8%) with regard to pain, which may explain the finding. In the same way, Lacy et al. suspended visual analogue pain scoring in a study comparing midline and transverse incisions for abdominal aortic surgery. Remarkably, the two groups in our study did not differ in terms of postoperative analgesia, a finding that is also reported by Lindgren et al. [17] and Donati et al. [19]. In our study, surgeons as well as patients were significantly more satisfied with the aesthetic appearance after a transverse in comparison with a midline incision. The scars after transverse incisions were found to be significantly shorter and less wide than the midline incisions, which may account for the observed difference. A possible reason for this is that a transverse incision is executed parallel to the prevailing direction of the skin lines on the abdomen and, therefore, the tension on the wound and consequent scar is low. Cholecystectomy has come a long way since this trial. The introduction and widespread acceptance of laparoscopic technique as the treatment of choice has rendered open cholecystectomy to be an operation for exceptional, and perhaps surgically difficult, circumstances. Nowadays, the study reported is hardly feasible, yet, the results are still applicable and very relevant for other surgical procedures in the (upper) abdomen. Knowledge of the favourable results of a transverse incision may aid surgeons in their choice when finding themselves in the unfortunate position of needing conversion to open cholecystectomy. In conclusion, this investigation on transverse incisions might be helpful in reducing the incidence of incisional hernia in patients after open cholecystectomy. The midline incision is a preferred manner to achieve exposure of the abdominal cavity and is considered to be easily performed and quick. Although the midline incision is generally accepted, the incidence of incisional hernias is surprisingly high [1–5]. The choice for a particular incision should not only be based on exposure, but also on hernia incidence reduction, especially since recurrence rates after hernia repair are reported to be very high. Furthermore, the recurrence rate after incisional hernia repair is a disappointing 63 and 32% for suture and mesh repair, respectively [6]. In the light of these results, incisional hernia prevention is warranted. In this investigation, it is shown that a significant reduction (from 14.5 to 1.7%) of incisional hernia incidence was achieved by using a transverse incision. Hence, a transverse incision should be considered as the preferred incision in acute and elective surgery of the upper abdomen in which laparoscopic surgery is not an option. Full exposure of two quadrants is feasible through the use of a unilateral transverse incision in, for example, biliary, bariatric, liver and colonic surgery. The transverse incision should be part of the abdominal surgeon's armamentarium and is a preferable incision to prevent the high incidence of incisional hernia after abdominal surgery.\n\n**Question:** Compared to Midline incision what was the result of Transverse incision on Scar length?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
343
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Placebo what was the result of Budesonide/formoterol pMDI 320/9 μg on 1-hour post-dose inspiratory capacity mean improvements from baseline to the average over the randomized treatment period ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
449
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Concomitant therapy with Cineole (Eucalyptole) reduces exacerbations in COPD: A placebo-controlled double-blind trial\n\n ABSTRACT.BACKGROUND:\nThe clinical effects of mucolytics in patients with chronic obstructive pulmonary disease (COPD) are discussed controversially. Cineole is the main constituent of eucalyptus oil and mainly used in inflammatory airway diseases as a mucolytic agent. We hypothesised that its known mucolytic, bronchodilating and anti-inflammatory effects as concomitant therapy would reduce the exacerbation rate and show benefits on pulmonary function tests as well as quality of life in patients with COPD.\n\nABSTRACT.METHODS:\nIn this double-blind, placebo-controlled multi-center-study we randomly assigned 242 patients with stable COPD to receive 200 mg of cineole or placebo 3 times daily as concomitant therapy for 6 months during winter-time. The frequency, duration and severity of exacerbations were combined as primary outcome measures for testing as multiple criteria. Secondary outcome measures included changes of lung function, respiratory symptoms and quality of life as well as the single parameters of the exacerbations.\n\nABSTRACT.RESULTS:\nBaseline demographics, lung function and standard medication of both groups were comparable. During the treatment period of 6 months the multiple criteria frequency, severity and duration of exacerbations were significantly lower in the group treated with cineole in comparison to placebo. Secondary outcome measures validated these findings. Improvement of lung function, dyspnea and quality of life as multiple criteria were statistically significant relative to placebo. Adverse events were comparable in both groups.\n\nABSTRACT.CONCLUSION:\nConcomitant therapy with cineole reduces exacerbations as well as dyspnea and improves lung function and health status. This study further suggests cineole as an active controller of airway inflammation in COPD by intervening in the pathophysiology of airway inflammation of the mucus membrane.\n\nABSTRACT.TRIAL REGISTRATION:\nISRCTN07600011\n\nBODY.INTRODUCTION:\nChronic obstructive pulmonary disease (COPD) is considered to be a multi-component disease comprising structural and functional changes inside and outside the lungs. Effective medications for COPD are available and can reduce or prevent symptoms, increase exercise capacity, reduce the number and severity of exacerbations and improve health status. In common clinical use are bronchodilators as β-agonists, anticholinergic drugs and methylxanthines as well as glucocorticosteroids. The clinical effectiveness of these drugs has been shown in many controlled clinical studies [1-7]. Airway inflammation and mucociliary dysfunction in COPD patients have direct clinical consequences on the decline of lung function. As a consequence of cigarette smoking the ciliated epithelium is damaged and the mucus membrane becomes inflamed, resulting in decreased mucociliary transport leading to an accumulation of mucus within the airway so that the likelihood of recurrent respiratory infection is increased. Cineole has positive effects on the beat frequency of the cilias in the mucus membrane and has bronchodilating and anti-inflammatory effects. Therefore, it is appropriate to postulate that cineole will show positive influence on the exacerbations as well as on the lung function in COPD patients – even as concomitant therapy [8-13]. We conducted a randomised, placebo-controlled multi-center trial with the concomitant prescription of cineole – the main constituent of eucalyptus oil – in patients with stable COPD. The primary hypothesis was that cineole would decrease the number, severity and duration of exacerbations. Secondary outcome measures were lung function, severity of dyspnea and quality of life as well as relevant adverse effects.\n\nBODY.MATERIALS AND METHODS.ENROLMENT OF PARTICIPANTS:\nParticipants were recruited in the offices of 4 general practitioners and 7 specialists in pneumology in Germany. The study was carried out during the winter seasons 2003/2004 and 2004/2005 over a treatment period of 6 months in the winter and starting the enrolment in September at the earliest. The participants were 40 to 80 years of age and had airflow limitation with FEV1 of less than 70% and more than 30% of the predicted value (moderate to severe COPD; according to GOLD classification stages 2 and 3 of COPD) [14]. Patients with an increase of more than 15% and more than 200 ml in FEV1 after inhalation of β-agonists (at least 200 μg Salbutamol or equivalent) were excluded according to the definition of COPD of the German Airway-League. [15]. All patients were current smokers or ex-smokers with at least 10 pack years. Patients were excluded if they had severe medical conditions such as bronchial carcinoma, myocardial infarction, alcoholism, heart failure. All randomised patients provided written informed consent and the protocol was approved by the local Ethics Committees at each of the 11 participating centres.\n\nBODY.MATERIALS AND METHODS.TREATMENT GROUPS:\n242 patients were randomly assigned to one of the two treatment groups with stratification according to the clinical centres. All patients were given the necessary dose of capsules each containing 100 mg cineole or no active ingredient. For each group 2 capsules 3 times daily were prescribed resulting in a dose of 600 mg per day for the cineole or no cineole for the placebo group as concomitant therapy. Patients were instructed to take the capsules half an hour before meal so that they could not recognize the smell of cineole. Capsules with active substance and placebo looked absolutely identical and were sealed in blister stripes. The diagnosis of COPD was confirmed according to the current guidelines of \"Global Initiative for Chronic Obstructive Lung Disease\" (GOLD). Frequency, duration, severity and symptoms of exacerbations were defined according to the literature [16-18]. An exacerbation was documented when the duration was more than 3 days or a complex of at least 2 respiratory adverse events with a duration of more than 3 days occurred. Exacerbation severity was defined as: mild (Score = 1, increased need for basic medication of COPD which the individual can manage in its own normal environment), moderate (score = 2, increased need for medication and he/she feels the need to seek additional medical assistance) and severe (score = 3, patient recognise obvious and/or rapid deterioration in conditions requiring hospitalisation). Details for the number, duration and severity as well as treatment and symptoms of exacerbations were recorded in the patient's diary for each day. Since the most relevant differentiation for exacerbations are frequency, duration and severity, the multiple criteria were combined as primary outcome measures for the statistical evaluation. Secondary outcome measures were the single parameters of the exacerbation as well as lung function, symptoms and quality of life. Spirometric measurements were carried out before the beginning of the study determining reversibility of the airflow limitation by inhalation of short acting β2-agonists to assure that the reversibility of lung function was less than 200 ml or 15%. Spirometric measurement included determination of forced expiratory volume in 1 second (FEV1), forced vital capacity (FVC) and vital capacity (VC) at the beginning and after 3 and 6 months. Additionally, symptoms score were determined for dyspnea (scores: 0 = caused no problems, 1 = caused occasionally problems, 2 = caused a lot of problems, 3 = the most important problem the patient had), weekly frequency of dyspnea (scores: 0 = no day was good, 1 = 1–2 days were good, 2 = 3–4 days were good, 3 = nearly every day was good, 4 = every day was good), general conditions (scores: 0 = good, 1 = impaired, 2 = bad, 3 = very bad, 4 = unbearable), cough (scores: 0 = never, 1 = rarely, 2 = occasionally, 3 = often, 4 = very often, 5 = nearly continuously). Diagnosis-related quality of life was determined according to the \"St. George's Respiratory Questionnaire\" [19].\n\nBODY.MATERIALS AND METHODS.VISITS AND RANDOMIZATION:\nBefore randomisation we ascertained the patients' eligibility and conducted spirometry. After the randomisation the following parameters were recorded: height, weight, age, time since first symptoms for the diagnosis of COPD, documentation of allergies, concomitant disease, smoking habits (documentation of pack years), number of exacerbations in the year before during winter time, determination of quality of life and current maintenance therapy. The following control visits were carried out after 1, 2, 3, 4, 5 and 6 months recording exacerbations since last visit, frequency of dyspnea, characterisation of dyspnea, hypersecretion and cough as well as adverse events, compliance and change of therapy. Spirometry was carried out at the beginning of the study as well as after 3 and 6 months of treatment. Quality of life was determined at the beginning and at the end of the study.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nThe proposed sample size for the present trial was 240 patients for both treatment groups. The sample size was chosen to detect a minimum difference of 15% of exacerbations after 6 months of treatment. Analysis of efficacy was performed with the intention-to-treat-population including all eligible patients who received at least one dose of medication and had at least one follow-up visit. The number of all exacerbations, duration of exacerbations, degree of severity of exacerbation recorded in patients diary during the 6 months treatment period were summarised and the sums compared according to Wei-Lachin's directional test of multiple criteria (equally weighted) [20]. Additionally, single parameters characterising the exacerbations and dyspnea were analyzed exploratory as secondary outcome measures at multiple endpoints according to Wei-Lachin validating the sum-formation. The Wilcoxon-Mann-Whitney-U Test was used for all other secondary outcome measures. Data are expressed as mean values (with SD) and all tests were two-tailed. P-values of 0.05 or less were considered to indicate statistical significance.\n\nBODY.RESULTS:\nA total of 242 patients were randomised and received at least one dose of study medication. 22 patients were excluded from the statistical analysis of efficacy because they did not meet the requirements of the GOLD guidelines since FEV1/VC was > 0.7. 220 patients were eligible according to the GOLD guidelines having COPD of stage II and III. The two treatment groups were well matched with respect to baseline characteristics (table 1). The mean age of the participants at entry was 62 years in both groups. The mean duration of COPD of 13 years as well as 31 pack-years and the basic medication (i.e. ICS, β-agonists, anticholinergics and theophylline) were balanced between the two groups (table 2). Medication was not changed during the treatment period except in occurrence of exacerbations. The baseline lung function and reversibility in both groups were comparable. Treatment compliance was determined by counting the study medication at each visit and was found high and comparable across the treatment groups. Table 1 Base Line Characteristics of the Patients* CHARACTERISTIC PLACEBO (N = 110) CINEOLE (N = 110) Age – yr Mean 62.5 ± 10.2 62.2 ± 9.1 Range 40 – 79 41 – 79 Sex – M/F 75/35 66/44 Weight – kg Mean 79 ± 16 79 ± 14 Range 48 – 120 52 – 113 Height – m Mean 1.71 ± 8.8 1.70 ± 8.0 Range 1.48 – 1.90 1.54 – 1.92 Years since appearance of COPD Mean 12.8 ± 9.7 13.6 ± 10.9 Range 1 – 56 1 – 59 Severity of COPD [number of patients] Moderate COPD (II) 69 68 Severe COPD (III) 41 42 FEV 1 /VC [%] 58.0 58.7 FEV 1 [l] 1.61 ± 0.5 1.62 ± 0.5 FEV 1 % predicted value 54.4 54.9 Reversibility (increase of FEV 1 after inhalation of β-agonist) [%] 5.5 4.5 Allergies (number) 10 9 Pack years 31.5 ± 19 31.3 ± 16 * Plus – minus values are means ± SD. Table 2 Constant concomitant therapy THERAPY PLACEBO (N = 110) CINEOLE (N = 110) Inhaled β-agonists* (LABA and SABA) 83 88 Inhaled anticholinergics 29 35 Inhaled corticosteroids (ICS) 27 25 Theophylline 38 32 * including combinations \n\nBODY.RESULTS.PRIMARY OUTCOME MEASURES.EXACERBATIONS:\nAt baseline the mean exacerbation rate was 3.2 in both groups during the previous year. The number of patients with exacerbations during the treatment period in the cineole group was 31 patients (28.2%) and 50 patients (45.5%) in the placebo group. As primary outcome measure the sum of exacerbations for frequency, duration and severity at all 6 following visits as composite endpoint (equally weighted) were calculated according to the Wei-Lachin Test procedure for multiple criteria and showed a statistically significant difference for the primary outcome measure between both treatment groups (p = 0.0120) Table 3. Calculating these single parameters alone exploratory according to Mann-Whitney-U it could be proven that they were statistically significant too (i.e. for frequency 0.0069 an, duration 0.0210 and for severity 0.0240). Validating these results by Wei-Lachin-Test procedure for multiple endpoints for the number, the degree and the severity of exacerbations, the degree during the 6-month treatment the differences between both treatment groups were statistically significant (p = 0.0016, 0.0031 and 0.0025) which underlines higher sensitivity of this test-procedure. Medication of the exacerbations with additionally applied corticosteroids occurred in 17 cases in the cineole and in 25 cases in the placebo group which was not statistically significant different. Table 3 Mean of sum of number, duration and severity of exacerbations during 6 months of treatment with cineole or placebo* PLACEBO CINEOLE SCORE SCORE P VALUE† Sum of exacerbations (number)# 0.9 ± 1.46 0.4 ± 0.82 0.0069 Sum of duration (days)# 5.7 ± 8.9 4.0 ± 10.9 0.0210 Sum of severity (score)# 1.4 ± 2.2 0.8 ± 1.5 0.0242 Summarized parameter (directional test) 0.0120 * Plus – minus values are means ± SD. † P-Values are for the comparison between the two groups. # The sum of the exacerbation parameters is calculated by addition of the documented parameters at all visits. \n\nBODY.RESULTS.SECONDARY OUTCOME MEASURES.LUNG FUNCTION:\nPatients only discontinued inhaled β2-agonist prior to spirometry testing. After inhalation of a β2-agonist the reversibility of lung obstruction (increase of FEV1) at the start of the study was 4.5% in the cineole group and 5.5% in the placebo group (table 1). After 6 months of treatment the mean FEV1 increased by 78 ml (4.7%) in the cineole group (table 4). The mean differences between both groups were not statistically significant (p = 0.0627). After 6 months of treatment an increase of FVC by 62 ml (2.7%) after cineole therapy and a decline of 25 ml (1.1%) after treatment with placebo was determined. The difference concerning change of FVC and VC between both treatment groups was not clinically relevant. Table 4 Secondary outcome measures during 6 months Of treatment with cineole or placebo for change of lung function and dyspnea symptoms * LUNG FUNCTION AND SYMPTOMS PLACEBO CINEOLE BASE LINE 3 MONTHS 6 MONTHS BASE LINE 3 MONTHS 6 MONTHS p-Value FEV 1 [l] 1.61 ± 0.5 1.62 ± 0.5 1.61 ± 0.5 1.62 ± 0.5 1.67 ± 0.5 1.70 ± 0.6 0.0627 † FVC [l] 2.23 ± 0.8 2.25 ± 0.8 2.22 ± 0.7 2.33 ± 0.8 2.36 ± 0.9 2.36 ± 0.9 0.2409 † VC [l] 2.81 ± 0.8 2.71 ± 0.7 2.68 ± 0.8 2.80 ± 0.8 2.73 ± 0.8 2.72 ± 0.9 0.2060 † Trouble in breathing # 1.8 ± 0.9 2.1 ± 0.9 2.2 ± 1.0 1.9 ± 0.9 2.4 ± 1.0 2.5 ± 1.1 0.0103 & Dyspnea in the morning $ 1.1 ± 0.7 0.9 ± 0.7 0.7 ± 0.7 1.1 ± 0.8 0.7 ± 0.7 0.5 ± 0.6 0.0466 & Dyspnea at rest $ 0.7 ± 0.7 0.4 ± 0.6 0.4 ± 0.6 0.6 ± 0.6 0.3 ± 0.5 0.3 ± 0.5 0.0156 & Dyspnea during exercise $ 2.0 ± 0.6 1.8 ± 0.7 1.7 ± 0.8 2.0 ± 0.6 1.7 ± 0.7 1.5 ± 0.9 0.1252 & * Plus – minus values are means ± SD. Higher scores on the symptoms-sum-score indicate more disease activity. † P-Values are for the comparison of the changes from base line to 6 months between the two groups. & P-Values for the comparison are calculated by the multiple criteria calculation of 6 visits by Wei-Lachin between the two groups. # Scores: 0 = no day was good, 1 = 1–3 days were good, 2 = nearly every day was good, 3 = every day was good in a week. $ Scores: 0 = did not cause any problems, 1 = sometimes caused problems, 2 = caused a lot of problems, 3 = the most important problem the patient had \n\nBODY.RESULTS.SECONDARY OUTCOME MEASURES.DYSPNEA:\nThe differences between both groups after 6 months of treatment are summarised in table 4. The baseline dyspnea scores in the morning, trouble in breathing, dyspnea at rest and dyspnea during exercise were similar in both groups, indicating a moderate level of a dyspnea for most patients at the beginning of the treatment period. Calculating the values at all 6 visits at multiple endpoints the difference between both treatment groups were statistically significant for trouble in breathing, dyspnea in the morning and dyspnea at rest. Dyspnea during exercise did not show a statistically significant difference between treatment groups.\n\nBODY.RESULTS.SECONDARY OUTCOME MEASURES.QUALITY OF LIFE:\nAt 6 months the mean improvement of SGRQ total symptom score was -9.1 after treatment with cineole and -4.1 after treatment with placebo (table 5). The difference between treatment groups was not statistically significant (p = 0.0630). The improvement of the symptom score was statistically significant (p = 0.0224). The differences of changes of activity score and impact score were not statistically significant between the two groups. Table 5 Secondary outcome measures for saint george's respiratory questionnaire (sgrq): Change of total symptom score, symptom score, activity score and impact score During 6 months of treatment with cineole or placebo* SGRQ SCORES PLACEBO CINEOLE P VALUE † BASE LINE 6 MONTHS BASE LINE 6 MONTHS Symptom score 57.4 ± 20.2 48.5 ± 24.9 57.3 ± 20.4 43.8 ± 24.3 0.0224 Activity score 53.4 ± 21.9 50.0 ± 24.8 52.1 ± 20.5 43.5 ± 22.4 0.2032 Impact score 37.2 ± 20.9 33.9 ± 23.3 35.8 ± 20.2 27.4 ± 19.2 0.1126 TOTAL SYMPTOM SCORE 45.6 ± 18.9 41.3 ± 22.5 44.4 ± 17.8 34.5 ± 18.9 0.0630 * Plus – minus values are means ± SD. Lower scores on the scores indicate higher quality of life. † P-Values are for the comparison of the changes in scores from base line to 6 months treatment between the two groups. \n\nBODY.RESULTS.MULTIPLE CRITERIA:\nSymptomatic of COPD patients is characterized by lung function, dyspnea and quality of life. In order to include these relevant secondary outcome measures together we used these parameters equally weighted as multiple criteria. The increase of FEV1, amelioration of dyspnea and improvement of total score of \"SGRQ\" were calculated according to the Wei-Lachin Test procedure for multiple criteria and showed a statistically significant difference for the relevant secondary outcome measure between both treatment groups (p = 0.0024).\n\nBODY.RESULTS.MULTIPLE CRITERIA.OTHER FINDINGS:\nConcomitant therapy with β-agonists and anticholinergics, corticosteroids or combinations and methylxanthines in both groups were comparable (table 2). The global assessment of efficacy showed a significant difference, which correlated with the amelioration of clinical findings after treatment with cineole.\n\nBODY.RESULTS.SIDE EFFECTS:\nAll patients receiving the study medication (including those with FEV1/VC > 0.7) were included in the safety examination. During treatment side effects were seen in 22 patients whereas in 17 cases adverse events were not related to the study medication. In the placebo group 11 adverse events were estimated not being related to the study medication whereas 2 cases were interpreted as being related to the study medication (heartburn). During treatment with cineole 9 cases of adverse events were reported whereas 6 adverse events were reported not being related to the study medication. In 3 patients (nausea, diarrhoea, heartburn) the adverse events were estimated being related to the study medication. The difference between the two treatment groups was neither clinically relevant nor statistically significant. Safety examinations of the global assessment showed no difference between the two treatment groups. During the 6 months of treatment compliance was good in all patients.\n\nBODY.DISCUSSION:\nPatients with COPD experience exertional breathlessness caused by bronchoconstriction, mucous secretion, edema of the airway wall and loss of attachments to the terminal airways [14]. Hence pharmacological therapy has focused on the treatment of airway obstruction and inflammation to improve symptoms primarily dyspnea as well as health status. Bronchodilators are the mainstay of pharmacotherapy for patients with COPD. On the other hand it is well known that mucociliary dysfunction has direct clinical implications. Mucus is beneficial in normal quantities but in case of mucus hypersecretion when cilia fail, the mucus pool allows bacterial colonisation. The presence of pooled bacteria results in the release of bacterially-derived toxins that destroy the underlying epithelium and trigger a neutrophilic response [21]. Taking into account the known pharmacological effects of the defined natural product cineole it was assumed that this compound might be beneficial for patients with COPD. Exacerbations have been shown to be reduced in various studies evaluating treatment with inhaled β-agonists or corticosteroids or combinations. The major finding of the present study is that cineole provides a significantly greater reduction of frequency, duration and severity of exacerbations than placebo. The exacerbations were analyzed as multiple criteria for the relevant specifications frequency, duration and severity. The result for the primary outcome measure could be validated exploratory for the single parameters showing a statistical significant difference too. Therefore, both testing procedures are valid whereas the testing multiple criteria is more sensitive. This proof of efficacy is an important contribution to the known pharmacological properties of cineole which therefore is not a mucolytic agent only. The result of this study suggests important new evidence of superior therapeutic efficacy of additional therapy with cineole to better control COPD exacerbations compared to the currently recommended combined therapy with ICS and LABA. Furthermore, additional therapy with cineole may positively interact with anti-inflammatory activity of recommended airway therapies in COPD and may serve to protect airways from other environmental agents. In general, quality of life deteriorates slowly in patients with COPD. During the period of 6 months treatment of this study we observed a decrease of the scores of SGRQ in both treatment groups. The reason for this finding in the placebo group, too, seems to be due to patients receiving better medical attention when involved in clinical trials. The higher rate of exacerbations in the winter before the study began in both treatment groups is due to the same reason. Our present data with cineole therapy underline a greater improvement than after treatment with placebo. Differences in change of FEV1 were not statistically significant (p = 0.0627). These findings correlate with a decline of FEV1 in the placebo group of 0.4% and an increase of 4.8% in the cineole group. This value is nearly identical with the increase of FEV1 after the inhalation of β-agonists, when testing the reversibility, before concomitant therapy with cineole started for six months.\n\nBODY.CONCLUSION:\nThese collective findings underline that cineole not only reduces exacerbation rate but also provides clinical benefits as manifested by improved airflow obstruction, reduced severity of dyspnea and improvement of health status. Therefore, cineole can provide a useful treatment option for symptomatic patients with COPD in addition to treatment according to the guidelines. These results have to be seen in context with socio-economic aspects. As COPD is an extremely costly disease and a cause of major financial and social burden concomitant therapy with cineole can be recommended, especially due to the lack of relevant side effects and relatively low cost. The results of our study provide good evidence that cineole will show benefits as additional therapeutic regimen in patients with COPD. These findings correspond to the interpretation of the efficacy-study with Carbocysteine but not with Acetylcysteine, because this medication did not show a significant reduction of exacerbations [22,23].\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nThe study was designed and the protocol developed by HW, C S and UD. CS worked as principal investigator. Statistical analysis was carried out by UD. The results were interpreted by HW, CS and UD. All authors gave substantial critical input in revising the manuscript.\n\n**Question:** Compared to placebo what was the result of cineole on change of FVC and VC?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
245
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Short-term comparative study of high frequency chest wall oscillation and European airway clearance techniques in patients with cystic fibrosis\n\n ABSTRACT.BACKGROUND:\nHigh frequency chest wall oscillation (HFCWO) is standard treatment for airway clearance in the USA and has recently been introduced in the UK and Europe. There is little published research comparing HFCWO with airway clearance techniques (ACTs) frequently used in the UK and Europe. The aim of this study was to compare the short-term effects of HFCWO with usual ACTs in patients with cystic fibrosis hospitalised with an infective pulmonary exacerbation.\n\nABSTRACT.METHODS:\nA 4-day randomised crossover design was used. Patients received either HFCWO on days 1 and 3 and usual ACTs on days 2 and 4 or vice versa. Wet weight of sputum, spirometry and oxygen saturation were measured. Perceived efficacy, comfort, incidence of urinary leakage and preference were assessed. Data were analysed by mixed model analysis.\n\nABSTRACT.RESULTS:\n29 patients (72% male) of mean (SD) age 29.4 (8.4) years and mean (SD) forced expiratory volume in 1 s (FEV1) percentage predicted (FEV1%) 38 (16.7) completed the study. Significantly more sputum was expectorated during a single treatment session and over a 24 h period (mean difference 4.4 g and 6.9 g, respectively) with usual ACTs than with HFCWO (p<0.001). No statistically significant change in FEV1% or oxygen saturation was observed after either HFCWO or usual ACTs compared with baseline. 17 patients (55%) expressed a preference for their usual ACT.\n\nABSTRACT.CONCLUSIONS:\nDuring both a finite treatment period and over 24 h, less sputum was cleared using HFCWO than usual ACT. HFCWO does not appear to cause any adverse physiological effects and may influence adherence.\n\nBODY.INTRODUCTION:\nThe last four decades have seen improved survival in patients with cystic fibrosis (CF). The latest figures estimate the median life expectancy of individuals with CF born in 2000–3 to be approximately 40 years.1 Respiratory failure is the major cause of morbidity and mortality in those with CF.2 Accumulation of secretions in the CF airway precipitates chronic infection, causing a progressive deterioration in lung function and eventually respiratory failure and death.3 Airway clearance techniques (ACTs) are an essential component of the management of patients with CF and are considered standard care.4 There is a range of ACTs which augment the normal mucus clearance mechanisms of the lung to facilitate expectoration. These techniques generally aim to promote secretion clearance by altering airflow and mucus viscosity. Typically, high frequency chest wall oscillation (HFCWO) produces compression of the chest wall via an inflatable jacket linked to an air pulse generator. The generator delivers an intermittent flow of air into the jacket which rapidly compresses and releases the chest wall at a variety of frequencies. Consequently, an oscillation in airflow within the airways is achieved. HFCWO has been shown to enhance central and peripheral mucus clearance.5 A number of underlying mechanisms have been hypothesised including increased airflow-mucus interaction causing a reduction in viscolelasticity, production of an expiratory airflow bias which promotes a cephalad movement of mucus and the enhancement and stimulation of ciliary activity.6 7 Published short-term evidence has demonstrated increased sputum clearance and improved pulmonary function with HFCWO compared with no treatment.8 This and other studies have also compared HFCWO with alternative ACTs. Some have demonstrated increased sputum clearance with HFCWO compared with postural drainage and percussion (PD&P).9–11 Others found no significant difference in sputum clearance between HFCWO and PD&P,8 12 13 positive expiratory pressure (PEP),8 high frequency oral oscillation13 or intrapulmonary percussive ventilation.14 Furthermore, some of these studies found no differences in efficacy related to pulmonary function between HFCWO and PD&P,8 12 13 PEP,8 15 oscillating positive expiratory pressure (Flutter, manufactured by Axcan Scandipharm Inc, Birmingham, AL, USA)16 and high frequency oral oscillation.13 One study reported an improved outcome in forced expiratory volume in 1 s (FEV1) in the longer term using HFCWO compared with PD&P.17 Few trials have compared HFCWO with alternative ACTs which are commonly used in the UK and Europe by individuals with CF. Phillips et al18 compared HFCWO (using the Hayek Cuirass) with the active cycle of breathing techniques (ACBT) in hospitalised paediatric patients. Significantly more sputum was cleared with the ACBT. The authors concluded that HFCWO was not an effective airway clearance treatment for children with CF. It is difficult to compare this study directly with those above, as the Hayek Cuirass machine has a different operating mode to the inflatable vest system. A series of Cochrane systematic reviews have found that no one ACT is superior in terms of respiratory function and efficacy.19 Of a number of published studies on HFCWO, only two were deemed of sufficient quality to be included in these randomised control trial systematic reviews.8 12 HFCWO is widely used in the USA where it is considered standard care in CF.20 It has recently been introduced to the UK and Europe, where the mainstay of care for airway clearance in CF is the ACBT, autogenic drainage (AD) and other airway clearance regimens using small devices.4 In the USA these techniques and devices tend to be considered adjuncts, with PD&P and HFCWO remaining the most common ACTs.20 While there is a body of evidence which equates HFCWO and PD&P, there is a need for further trials to compare HFCWO with alternative ACTs to provide a more relevant evidence base for HFCWO in the UK and Europe. The aim of the present study was to compare the short-term effects of HFCWO with patients' usual ACTs in those with CF admitted to hospital with an acute exacerbation of pulmonary infection. The hypothesis was that HFCWO was superior to patients' usual ACTs.\n\nBODY.METHODS.STUDY PARTICIPANTS:\nAll patients admitted to hospital who met the entry criteria were invited to participate in the study. The inclusion criteria were a diagnosis of CF (established by genotype or sweat sodium >70 mmol/l or sweat chloride of >60 mmol/l), FEV1 ≥ 20% predicted, age ≥16 years and an infective pulmonary exacerbation as defined by Thornton et al.21 Exclusion criteria were current severe haemoptysis, rib fractures, pregnancy, inability to give consent and those whose usual ACT was HFCWO. Informed written consent was obtained for all patients and the study was approved by Brompton Harefield and National Heart and Lung Institute research ethics committee.\n\nBODY.METHODS.STUDY DESIGN:\nA randomised crossover design was used to compare HFCWO with patients' usual ACTs, which allowed within-patient variability to be controlled. Over four consecutive days, patients received either HFCWO therapy on days 1 and 3 and their normal ACT on days 2 and 4 or vice versa. Allocation to HFCWO or usual ACT on day 1 was determined using a computer-generated randomisation table.\n\nBODY.METHODS.PROTOCOLS:\nPatients performed their usual ACT or received HFCWO two times daily at the same time. Before starting the study, each patient's usual ACT was reviewed by an experienced senior respiratory physiotherapist. In addition, patients were familiarised with HFCWO (The Vest). This involved the patients using The Vest for a trial period the day before the start of the study, during which time they were given the opportunity to experience all three protocol frequencies at a variety of pressures. Each airway clearance treatment session lasted 30 min and was supervised by the same physiotherapist to ensure optimisation and standardisation of usual ACT and HFCWO performance. All nebulised and inhaled medications were taken before each treatment session in accordance with the patients' individual regimens.\n\nBODY.METHODS.HIGH FREQUENCY CHEST WALL OSCILLATION:\nThe following regimen was identified as current best practice following an in-depth review of the literature and discussion with clinical experts in the USA. Using The Vest Airway Clearance System Model 4 (Hill-Rom UK Ltd, Leicestershire, UK), each patient was fitted with an appropriately-sized, full torso, inflatable, disposable vest connected to the air pulse generator via two flexible tubes. Patients remained in an upright sitting position throughout the 30 min treatment session. HFCWO was applied for 8 min at each of three frequencies in sequence (10, 13 and 15 Hz) with each frequency followed by a 2 min rest period. The pulse pressure was set according to individual patient's reported comfort at all three frequency settings. During both the HFCWO and rest periods, patients were instructed to huff or cough as they felt necessary in order to expectorate loosened bronchial secretions.\n\nBODY.METHODS.USUAL ACT:\nUsual ACTs were in accordance with the guidelines of the International Physiotherapy Group for Cystic Fibrosis.22 Patients performed their usual ACT for 30 min, and for patients practising an assisted ACT, the physiotherapist provided percussion. Patients were allowed to perform combined ACTs where this was their usual practice. This reflected current international practice more accurately and recommendations that ACTs be adapted on an individual basis.23\n\nBODY.METHODS.OUTCOME MEASURES:\nThe primary outcome measure was wet weight of sputum expectorated during a treatment session. Patients were instructed to expectorate all sputum into a preweighed pot during and for 30 min following each treatment session. They were also instructed to collect sputum expectorated at all other times during each 24 h period. All sputum collected was weighed immediately following collection on weighing scales with an accuracy of 0.01 g (BL310; Sartorious UK Ltd, Epsom, UK). FEV1 was measured using a hand-held spirometer (2120; Vitalograph Ltd, Buckingham, UK) in accordance with internationally agreed standards.24 Measurements were taken immediately before and after a 30 min period following each treatment session. Data were analysed using Spirotrac IV Version 4.30 software (Vitalograph Ltd). Pulsed arterial oxygen saturation (SpO2) was measured transcutaneously at rest, for 5 min immediately before, 30 min during and 30 min immediately following each session. SpO2 was measured with a fingertip pulse oximeter (Konica-Minolta Pulsox-300i; Stowood Scientific Instruments, Oxford, UK). The data were analysed using Download 2001 Version 2.8.0 software (Stowood Scientific Instruments Ltd). The perceived efficacy and comfort of each ACT and the incidence of urinary leakage during treatment were measured using 10 cm visual analogue scales (VAS). Each day, after the last treatment session, patients completed three 10 cm VAS with reference to the ACT used that day. On the VAS used, 0 represented not at all effective/comfortable or no urinary leakage and 10 represented extremely effective/comfortable or a lot of urinary leakage. On the fourth and final day, participants were also asked to indicate which ACT they would prefer. An independent observer, blind to the daily method of airway clearance used, performed the spirometry, weighed the sputum samples and collected the 10 cm VAS throughout the study.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nA sample size calculation determined the number of patients required to test for superiority of HFCWO. This was based on a difference of 4 g of sputum between the usual ACT and HFCWO during a single treatment session. A square-root of within SEM of 4 g at the 5% significance level would require 24 patients to achieve 90% power. Data are presented as mean (SD), median (IQR) or n (%) as appropriate. Continuous variables were analysed using a mixed-effects linear regression model. This was to allow the results to be adjusted for a number of factors which are inherent to the design of a crossover trial. The order of treatment randomisation and the day and time of treatment were all entered into the model and their effect on the outcomes was tested. For this trial, the results were also adjusted for the method and position of treatment in the ACT session. In these models, patients were entered as random effects since it was not of interest to quantify the differences between individual patients, but it was important to account for the repeated measurements on each patient. The estimates of the fixed effect of ACT versus HFCWO are presented as mean (95% CI). A p value of 0.05 was taken to be statistically significant. All analyses were conducted using Stata 9.2 (StataCorp).\n\nBODY.RESULTS.PARTICIPANTS:\nFifty patients were invited to participate in the study, 20 declined, 29 patients completed the study and 1 patient was withdrawn due to a hypoglycaemic episode. Table 1 shows demographic and baseline characteristics of the patients who completed the study. Table 1 Patient demographics and baseline characteristics (n=29) Age (years) 29.4 (8.4) Male (%) 21 (72%) Height (cm) 171 (9) Weight (kg) 60 (11) BMI (kg/m 2 ) 20.4 (2.6) FEV 1 (l) 1.46 (0.72) FEV 1 % predicted 38 (16.7) SpO 2 (%) 94.3 (2.1) Data are presented as mean (SD) or n (%) as appropriate. BMI, body mass index; FEV 1 , forced expiratory volume in 1 s; SpO 2 , pulsed arterial oxygen saturation. Twenty-nine patients were treated with intravenous antibiotics as part of their medical management. All participants received two treatment sessions on each study day and all treatment sessions were 30 min in duration. The mean (SD) length of stay for patients was 14 (5) days and the mean day of entry to the study was day 8 (3) days.\n\nBODY.RESULTS.USUAL ACT:\nUsual ACTs included the ACBT with modified PD&P (41%; n=12) and with modified PD alone (7%; n=2), AD in sitting (28%; n=8) and with modified PD (7%; n=2), PEP (7%; n=2) and Flutter (10%; n=3).\n\nBODY.RESULTS.SPUTUM WEIGHT:\nThe wet weight of sputum expectorated with usual ACT compared with HFCWO is shown in table 2. The mean weight of sputum expectorated during a single treatment session and over a 24 h period was significantly greater with usual ACT than with HFCWO. The mean difference in wet weight of sputum expectorated during a treatment session was 4.4 g (p<0.001) and the mean difference in wet weight of sputum expectorated over a 24 h period was 6.9 g (p<0.001). These findings were not affected by order, time, day or position of treatment. Table 2 Wet weight of sputum expectorated: HFCWO compared with usual ACT Period of sputum collection Expectorated sputum wet weight (g) Usual ACT HFCWO Mean difference p Value Mean (SD) Median (IQR) Mean (SD) Median (IQR) Single treatment session 9.1 (7.9) 7.2 (3.0–14.2) 4.6 (4.1) 3.4 (1.5–6.7) 4.4 (3.5 to 5.4) <0.001 24 h (excluding treatment) * 22.4 (26.8) 12.9 (4.0–29.9) 24.9 (25.8) 15.3 (3.9–40.1) −1.5 (−4.6 to 1.6) 0.352 24 h (including treatment) 39.8 (36.3) 25.5 (14.0–57.1) 34.3 (30.7) 26.3 (12.1–46.0) 6.9 (3.1 to 10.8) <0.001 Data are presented as mean (SD) or (95% CI) or median (IQR) as appropriate. Data are adjusted for randomisation, day, time and position of treatment using a mixed effects linear regression model. * Of 116 24-h sputum samples collected, two were discarded as they were incomplete. ACT, airway clearance technique; HFCWO, high frequency chest wall oscillation. No statistically significant difference was observed in the amount of sputum expectorated when using HFCWO or usual ACT between treatments in a 24 h period.\n\nBODY.RESULTS.PHYSIOLOGICAL MEASURES:\nFEV1 and SpO2 measured before, during and after usual ACT and HFCWO treatment sessions are shown in table 3. Table 3 Forced expiratory volume in 1 s and pulsed arterial oxygen saturation at baseline, during and after treatment with usual airway clearance technique and HFCWO Usual ACT HFCWO Baseline During treatment 30 min after treatment Baseline During treatment 30 min after treatment FEV 1 % predicted 39.1 (16.9) NA 38.9 (17.1) 38.9 (16.8) NA 39.2 (16.7) SpO 2 (%) 94.4 (2.0) 94.4 (1.9) 93.9 (1.6) 94.5 (1.8) 95.0 (1.7) 94.3 (1.7) Data are presented as mean (SD). ACT, airway clearance technique; FEV 1 , forced expiratory volume in 1 s; HFCWO, high frequency chest wall oscillation; NA, not applicable; SpO 2 , pulsed arterial oxygen saturation. \n\nBODY.RESULTS.COMFORT, EFFICACY AND PREFERENCE:\nThe VAS scores for comfort, efficacy and urinary leakage during usual ACT compared with HFCWO are shown in table 4. No significant differences were observed in VAS scores for comfort or urinary leakage between HFCWO and usual ACT. Patients scored the efficacy of their usual ACT significantly higher than for HFCWO (mean difference 14 mm; p=0.002). This was not affected by the order or day of treatment. Of those patients who completed the study, 17 (55%) expressed a preference for their usual ACT over HFCWO. Preference was not predicted by the amount of sputum expectorated. Table 4 Comfort, efficacy and urinary leakage: HFCWO compared with usual ACT Self reported measure Visual analogue scale score (mm) Usual ACT HFCWO Mean difference p Value Comfort 69 (23) 70 (22) −1 (−9 to 7) 0.784 Efficacy 68 (21) 54 (26) 14 (6 to 23) 0.002 Urinary leakage 0 (1) 0 (1) −0.05 (−0.3 to 0.4) 0.791 Data are presented as mean (SD) or (95% CI) as appropriate. Data are adjusted for randomisation, day of treatment and time of treatment using a mixed effects linear regression model. ACT, airway clearance technique; HFCWO, high frequency chest wall oscillation. \n\nBODY.DISCUSSION:\nThere have been few published comparisons between HFCWO using a vest system with the ACTs of the ACBT and AD. This short-term study, carried out in individuals with CF admitted to hospital with an acute infective pulmonary exacerbation, showed that significantly more sputum was expectorated during a single treatment session and over a 24 h period using the patient's usual ACT than with HFCWO. In addition, slightly less sputum was expectorated at all other times (excluding treatment sessions) on usual ACT days compared with HFCWO, but this trend was not statistically significant. These findings were independent of order, time or day and position of treatment. Neither HFCWO nor any of the usual ACTs were associated with any adverse clinical events. A possible factor contributing to the difference in sputum clearance between HFCWO and usual ACT may have been the number and frequency of forced expiratory manoeuvres (FEMs) and the more gentle expiratory manoeuvres of the AD breath that were performed with the usual ACTs. Some studies have standardised the number of coughs and FEMs that patients performed; however, at the time of designing the protocol, the aim was to compare the regimens as currently practised internationally and the frequency of coughs and FEMs was neither standardised nor counted. In retrospect, it would have been of value to have counted the number of coughs and FEMs undertaken during each regimen, but it had not been anticipated that any differences between HFCWO and usual ACTs may be a consequence of the number of FEMs or AD breaths. Theoretically, during the three 8 min periods of HFCWO, fewer FEMs, coughs or AD breaths would be undertaken than during an equivalent period of the ACBT, AD, PEP or Flutter (all of which inherently include FEMs or AD breaths at regular intervals). This difference was supported by observations of the investigators. However, manual cough counts are subject to observer error. Objective cough monitoring using the Leicester Cough Monitor has only recently been validated and should be considered for use in further studies.25 Components of patient satisfaction include efficacy, comfort and convenience. Some studies have formally evaluated patient satisfaction and compliance. One study reported that 50% of subjects chose HFCWO compared with the Flutter, and efficacy was the most frequently cited reason for this choice.16 A later study reported that HFCWO was not preferred over PD&P and intrapulmonary percussive ventilation; furthermore, there was no significant correlation between treatment preference and sputum weight.14 The current study found that patients perceived the efficacy of HFCWO to be statistically significantly less than that of their usual ACT. However, nearly half (45%) of patients expressed a preference for HFCWO. Preference may have been affected by the novelty of a new treatment and it is unknown whether this would continue in the long term. There is no one recommended protocol for the application of HFCWO in the literature. Published studies describe differing numbers and duration of frequencies, length of treatment and airway clearance. Frequencies of 10, 13 and 15 Hz were chosen as it has been reported that maximum mucus transport occurs between 11 and 15 Hz with a peak at 13 Hz.5 6 In addition, the highest oscillated tidal volume flow (peak airflow) occurred between 10 and15 Hz in patients with CF.26 More recent research recommends an individual \"tuning\" method to identify optimum treatment frequencies. These have been shown to vary among individuals and the oscillation waveform,27 but it is unknown whether \"tuning\" increases efficacy. It is possible that a practice effect could have occurred as all patients were new to HFCWO. However, the protocol used in this study did not require the patient to perform any newly learnt physical technique. In addition, the statistical analysis ensured data were adjusted for day of treatment and found no effect. Alternatively, patients' familiarity with their usual ACT may also have had an effect on outcomes. This study was powered to detect a difference of 4 g of sputum expectorated during a single treatment session. Other studies have been based on a difference of 3–3.5 g, which is generally accepted as a clinically important difference.28 29 Wet weight sputum was felt to be an appropriate primary outcome measure in this short-term study in an acute environment. Previous work has found wet weight to be proportional to dry weight sputum.28 30 Emerging non-invasive means of measuring airway clearance may be more sensitive indicators in the future (eg, lung clearance index and electrical impedance tomography). Considering the cost benefit of HFCWO compared with other ACTs and the differing healthcare systems in the USA and the UK, it is unlikely that HFCWO will become the first choice ACT for most individuals in the UK. Further work needs to be undertaken to identify the place of HFCWO in Europe. Patient preference for a treatment regimen may positively influence adherence to treatment in the short term, and nearly half the patients who participated in this study preferred HFCWO to their usual ACT. HFCWO is a safe treatment that facilitates airway clearance in CF but, when compared with patients' usual ACTs, HFCWO led to the clearance of significantly less sputum during a single treatment session and over a 24 h period.\n\n**Question:** Compared to Usual airway clearance techniques what was the result of High frequency chest wall oscillation on O2 saturation?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
424
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Six-week high-intensity exercise program for middle-aged patients with knee osteoarthritis: a randomized controlled trial [ISRCTN20244858]\n\n ABSTRACT.BACKGROUND:\nStudies on exercise in knee osteoarthritis (OA) have focused on elderly subjects. Subjects in this study were middle-aged with symptomatic and definite radiographic knee osteoarthritis. The aim was to test the effects of a short-term, high-intensity exercise program on self-reported pain, function and quality of life.\n\nABSTRACT.METHODS:\nPatients aged 36–65, with OA grade III (Kellgren & Lawrence) were recruited. They had been referred for radiographic examination due to knee pain and had no history of major knee injury. They were randomized to a twice weekly supervised one hour exercise intervention for six weeks, or to a non-intervention control group. Exercise was performed at ≥ 60% of maximum heart rate (HR max). The primary outcome measure was the Knee injury and Osteoarthritis Outcome Score (KOOS). Follow-up occurred at 6 weeks and 6 months.\n\nABSTRACT.RESULTS:\nSixty-one subjects (mean age 56 (SD 6), 51 % women, mean BMI 29.5 (SD 4.8)) were randomly assigned to intervention (n = 30) or control group (n = 31). No significant differences in the KOOS subscales assessing pain, other symptoms, or function in daily life or in sport and recreation were seen at any time point between exercisers and controls. In the exercise group, an improvement was seen at 6 weeks in the KOOS subscale quality of life compared to the control group (mean change 4.0 vs. -0.7, p = 0.05). The difference between groups was still persistent at 6 months (p = 0.02).\n\nABSTRACT.CONCLUSION:\nA six-week high-intensive exercise program had no effect on pain or function in middle-aged patients with moderate to severe radiographic knee OA. Some effect was seen on quality of life in the exercise group compared to the control group.\n\nBODY.BACKGROUND:\nExercise is considered to be one of the most important treatments for patients with mild to moderate knee osteoarthritis [1,2]. Positive effects on pain and function, as well as cost-effectiveness have been reported [3,4]. The effect size obtained on pain experience is similar to that of pharmacological treatment [3,5]. The side effects have also been reported to be favorable, including reduced risk of inactivity-related disorders, such as cardiovascular disease and diabetes [2,6,7]. Moderate levels of physical activity are not associated with radiographic progression, but activities involving a risk of severe knee injury are closely related to increased risk of developing radiographic knee osteoarthritis [8-12]. The dose-response relationship of exercise on symptoms and function is not clear and exercise recommendations in osteoarthritis guidelines are based mostly on studies on elderly people, i.e. mean age ≥ 65 [3,13-15]. It is not clear whether exercise has a similar effect on pain and function in middle-aged patients compared with elderly patients. The aim of this study was to examine the effects of a short-term, high-intensity exercise program in middle-aged subjects (age 36–65) with definite radiographic knee osteoarthritis on self-reported pain, function, and quality of life.\n\nBODY.METHODS.SUBJECTS:\nA flow chart of the recruitment process is given in Figure 1. Radiologists and orthopedic surgeons at the Halmstad County Hospital, in the south-west of Sweden, and general practitioners within the catchments area of this hospital, were informed about the study and asked to list patients with radiographic knee osteoarthritis on a \"patients eligible for research\" list. Between October 1998 and October 2001 121 patients, referred by their general practitioner for radiographic examination because of long standing knee pain, were listed. Ninety-seven fulfilled the inclusion criteria: age 35–65, living in the defined geographic area, and diagnosis of radiographic osteoarthritis of Kellgren and Lawrence grade III or more, i.e. definite osteophytes and joint space narrowing. All listed patients received written information about the study. One week after the information was sent, patients were contacted by telephone, and invited to participate in the study. Twenty-eight patients declined participation for various reasons, the most common reason being lack of time and interest. To ensure only patients with symptoms due to knee osteoarthritis and eligible for exercise intervention were included, the following exclusion criteria were used: inflammatory joint disease, anterior cruciate ligament injury, known symptomatic injury to the menisci, hip symptoms more aggravating than the knee symptoms, about to have knee replacement surgery within 6 months, and co-morbidities not allowing exercise (Figure 1). Figure 1Flowchart of recruitment process and included patients. When eight or more patients fulfilled the inclusion criteria they were invited to baseline interview and examination for determination of exclusion criteria. Randomization was performed after the baseline examination. All patients were informed that they could be randomly allocated to either the exercise or the control group. After written informed consent, sixty-five subjects were randomized. Randomization was performed by the patient drawing a sealed envelope containing a piece of folded paper with either the word \"exercise\" or \"control\" written on it. Four persons were falsely randomized (one was too old at inclusion, one had severe hip osteoarthritis, one had fibromyalgia, and one had only joint space narrowing and no significant osteophytes), and thus 61 subjects entered the study. Thirty persons were allocated to the exercise group and 31 to the control group. Patients in the control group were offered exercise classes after the six-month follow-up period.\n\nBODY.METHODS.SUBJECTS.EXERCISE GROUP:\nThe number of participants exercising together varied from two to nine. There were eight intervention groups in all. One-hour exercise sessions, twice a week for six weeks, were supervised by a physical therapist (CT). The program consisted of weight-bearing exercises aimed at increasing postural control and endurance and strength in the lower extremity (see additional file 1 for the complete exercise program). Exercises were performed at five stations at submaximal intensity (minimum 60% of maximum heart rate (HRmax)). Intensity was gradually and individually increased during the six weeks by increased lever arms or range of motion. Patients were encouraged to exercise at their most vigorous intensity possible, without losing quality in performance or severely exacerbating pain. Pain during exercise was not considered as an obstacle if the patient perceived it as \"acceptable\" and no increased symptoms were persistent after 24 hours [16]. If pain exceeded this level, exercise intensity was reduced occasionally, until the \"acceptable\" level was found. On every occasion, the heart rate of two random participants was estimated at each station using Polar pulsimeters (Polar® Accurex Plus, Polar, Sweden). The other patients had their heart rate measured by the physical therapist or themselves, palpating their carotid arteries. Notes were taken by the supervising physical therapist, on every occasion and on all patients, about exercise intensity, heart rate, and perceived exertion according to Borg's Rate of Perceived Exertion scale (RPE) at each station [17]. These data were used to give the physical therapist a view of exercise intensity and to assure the preservation or increase of intensity from time to time. Patients were encouraged to keep up and increase intensity whenever possible throughout the six weeks. Patients received a thera band to perform daily pulley exercises at home. In addition, three exercises, which were considered as the most challenging to the individual, were chosen as daily home exercises. Patients were recommended to perform some kind of weight bearing submaximal activity, such as walking or their home exercises, for at least 30 minutes or two times 15 minutes every day.\n\nBODY.METHODS.SUBJECTS.CONTROL GROUP:\nThe controls were told not to make any lifestyle changes. They met the physical therapist (CT) for one hour at three times; baseline, follow up at 6 weeks and 6 months. After six months they were offered exercise classes or instructions and a home-exercise program.\n\nBODY.METHODS.OUTCOME MEASURES.PRIMARY OUTCOME:\nThe primary outcome measure was the disease-specific Knee injury and Osteoarthritis Outcome Score (KOOS) [18,19]. The KOOS assesses the patients' self-report of pain, other symptoms, activities of daily living, sport and recreation function, and knee-related quality of life, in 42 questions which take about 10 minutes to complete. The KOOS is scored from 0 to 100, separately for each subscale, 0 indicating extreme problems and 100 indicating no problems. A change of 10 points or more is considered a clinically significant change [20]. The questionnaire and scoring manual can be found at . The Western Ontario and McMaster Osteoarthritis Index (WOMAC) [21] is included in the KOOS, and WOMAC scores can also be calculated.\n\nBODY.METHODS.OUTCOME MEASURES.SECONDARY OUTCOME:\nSecondary outcome measures were the Short Form-36 item (SF-36), ergometer test, and five tests of functional performance. The SF-36 is a generic, widely used measure of general health status, which comprises eight subscales: Physical Functioning (PF), Role-Physical (RP), Bodily Pain (BP), General Health (GH), Vitality (VT), Social Functioning (SF), Role-Emotional (RE) and Mental Health (MH) [22]. The SF-36 is self-explanatory and takes about 10 minutes to complete. The SF-36 is scored from 0 to 100, 0 indicating extreme problems and 100 indicating no problems. The subscales assessing mainly physical components (PF, RP, BP, GH) were summarized to a physical component summary score (PCS), and the mental subscales (VT, SF, RE, MH) to a mental component summary score (MCS) [23]. Values are norm-based scored, using the U.S. general population norms from 1998. Each scale has the mean of 50 and standard deviation of 10. Scale score below 50 indicates a health status below average, and a score above 50 indicates a health status above average. Questionnaires were distributed prior to randomization at baseline, after 6 weeks, and 6 months. A bicycle ergometer test and five tests of functional performance were assessed (Figure 2). Figure 2Tests of functional performance. A) Åstrand's cycle-ergometer test [24]. B) Rising on one leg from sitting on lowest possible height [25,26]. C) One-leg hop [25], [27]. D) Lateral step-up [28]. E) One-leg semi squatting; maximum number during 30 sec. [26]. F) Heel-rising on one leg; maximum number during 20 sec. [26], [29]. 1. Åstrand's bicycle-ergometer test [24] (Fig 2A). 2. Rising on one leg, from sitting on lowest possible height [25,26] (Fig 2B). 3. One-leg hop [25,27] (Fig 2C). 4. Lateral step-up [28] (Fig 2D). 5. One-leg semi squatting; maximum number during 30 seconds [26] (Fig 2E). 6. Heel-raising on one leg; maximum number during 20 seconds [26,29] (Fig 2F). Tests of functional performance were recorded on three occasions: prior to randomization at baseline, after 6 weeks, and at 6 months. To assess compliance the number of exercise occasions attended was noted.\n\nBODY.METHODS.STATISTICS:\nPost-hoc, a power analysis was performed to estimate the number of patients needed to show a clinically significant difference between groups. Estimating the least clinical significant difference to be 11 ± 15 KOOS points, a total of 30 subjects in each group were needed to detect a difference with 80% power, p = 0.05. Data were analyzed using nonparametric tests. P-values of less than or equal to 0.05 were considered to be significant, and all tests were two-tailed. To compare groups, Mann-Whitney U-test was used. Friedman's test was used for repeated measures analysis of variance. Six weeks was considered as the time-point of primary interest, and 6 months as follow-up. Wilcoxon signed rank test was performed to compare changes from baseline to six weeks and 6 months respectively. Analyses were performed using SPSS 12.0.1 for Windows [30]. The study was approved by the Research Ethics Committee at Lund University, Sweden (LU 99–98), and is in compliance with the Helsinki Declaration.\n\nBODY.RESULTS.SUBJECTS:\nThe mean age of the 61 included subjects was 56 ± 6 years, and the mean BMI was 29.5 ± 4.8 kg/m2. Patient characteristics are shown in table 1. Twenty-eight patients in each group were available for follow-up. The reasons for dropout were lack of time, reorganization at work, sudden illness, and increased knee symptoms (Figure 1). There were no clinically significant differences in baseline characteristics between the groups. Patient characteristics are shown in table 1. Table 1 Patient characteristics at baseline Exercise group n = 30 Control group n = 31 p-value Age (years) mean ± SD (range) 54.8 ± 7.1 (36–64) 57.3 ± 4.7 (46–65) 0.16 Gender number (%) women 15 (50%) 16 (52%) 0.90 BMI (kg/m) 2 mean ± SD 29.6 ± 4.5 29.5 ± 5.1 0.78 Aerobic capacity (ml O 2 /kg x min) mean ± SD 25.9 ± 6.4 25.2 ± 4.9 0.66 KOOS* pain 60 ± 18 64 ± 19 0.38 KOOS* symptoms 63 ± 20 66 ± 18 0.67 KOOS* ADL 69 ± 18 71 ± 21 0.76 KOOS* sport & recreation 34 ± 31 37 ± 29 0.54 KOOS* QOL 40 ± 15 46 ± 21 0.31 Knee Injury and Osteoarthritis Outcome Score [ 18 , 19 ] Score from 0–100, worst to best. \n\nBODY.RESULTS.COMPLIANCE:\nThe total number of performed supervised exercise sessions by the 28 patients available for follow-up in the intervention group was 302/336 (89.9%). Patients participated on average in 11 out of 12 possible exercise classes (12 classes (n = 11), 11 (n = 9), 10 (n = 6), 9 (n = 1), 2 (n = 1)). The most common reason for absence was illness not related to knee osteoarthritis, and work-related lack of time.\n\nBODY.RESULTS.BETWEEN-GROUP DIFFERENCES:\nThere was no difference between groups in pain or self-estimated function at either 6 week or 6 month follow-up. Quality of life improved significantly in the exercise group compared to the control group at 6 weeks (4.0 vs. -0.7, p = 0.05) and the results persisted at 6 months (5.1 vs. -2.3, p = 0.02, Table 2) Table 2 Comparisons of change in Knee injury and Osteoarthritis Outcome Score (KOOS) ‡ [ 18 , 19 ] subscales between exercise and control group KOOS Subscales Exercise group Control group Change in KOOS score* 95 % CI Change in KOOS score* 95 % CI p † Pain 6 w 1.8 -3.2 – 6.8 -0.3 -6.2 – 5.7 0.49 6 m 3.1 -1.9 – 8.2 -1.1 -6.6 – 4.4 0.32 Symptom 6 w 0.2 -5.1 – 5.6 -3.8 -7.7 – 0.0 0.07 6 m 1.0 -3.8 – 5.8 -3.4 -8.8 – 1.9 0.31 ADL 6 w 2.0 -2.3 – 6.3 -0.6 -7.0 – 5.8 0.96 6 m 0.9 -3.8 – 5.6 -1.9 -7.7 – 3.9 0.61 SportRec 6 w 1.2 -7.9 – 10.4 -4.4 -12.6 – 3.7 0.22 6 m 0.5 -10.1 – 11.2 -8.3 -19.5 – 2.8 0.32 QOL 6 w 4.0 -0.4 – 8.5 -0.7 -5.6 – 4.3 0.05 6 m 5.1 -0.7 – 11.0 -2.3 -9.5 – 4.9 0.02 * negative = worsening, positive = improvement † p-value for between group differences in change over time ‡ [ 18 , 19 ] The individual differences ranged from clinically significant improvement of at least 10 points to clinically significant deterioration in all KOOS subscales and in both the exercise and control group (Figure 3). Figure 3Change in KOOS pain score at six weeks. The individual change in KOOS pain at 6 weeks compared to baseline ranged from improvement to worsening, in both exercise and control group. A change of 10 points or more is considered clinically significant [20]. A similar pattern was seen for all KOOS and SF-36 subscales.\n\nBODY.RESULTS.BETWEEN-GROUP DIFFERENCES.SECONDARY OUTCOMES:\nA significant improvement was found in the exercise group compared to the control group at six weeks with regard to the SF-36 Mental Component Summary scale (MCS) (2.1 vs -1.6, p = 0.04). At six months follow-up this difference was no longer persistent (Table 3). Table 3 Comparisons of change in SF-36 Physical and Mental Components Summaries (PCS and MCS) [ 23 ] between exercise and control group. Short Form-36 item (SF-36) [22] Exercise group Control group mean 95%CI mean 95%CI p* Physical Component Summary (PCS) Baseline 42.5 24.4 – 57.5 43.8 24.2 – 57.3 0.49 Change at 6 weeks 3.0 -5.9 – 13.4 0.3 -15.2 – 12.6 0.13 Change at 6 months 3.0 -5.9 – 16.3 -0.7 -14.8 – 9.8 0.09 Mental Component Summary (MCS) Baseline 55.6 40.2 – 66.2 56.3 37.0 – 67.0 0.63 Change at 6 weeks 1.6 -10.6 – 15.0 -2.1 -16.9 – 11.5 0.04 Change at 6 months 0.7 -18.1 – 13.2 -0.7 -16.8 – 12.8 0.40 * Comparison between groups Improvements in functional performance of 0–20 % were seen in both groups at six weeks and six months. There was no difference in improvement between exercisers and controls (p = 0.08–0.9). See additional file 2 for the change in functional performance.\n\nBODY.DISCUSSION.MAIN MESSAGE:\nSix weeks of intensive exercise had no effect on self-reported pain or function in middle-aged patients with symptomatic and moderate-severe radiographic knee osteoarthritis.\n\nBODY.DISCUSSION.COMPARISONS WITH OTHER STUDIES:\nQuite opposite to previously published studies on exercise in knee osteoarthritis we found no improvement in pain or function. Possible reasons for this include our study group having moderate to severe osteoarthritis compared with mild to moderate in most previous studies, being younger than previously studied groups and the intervention being of comparably high intensity. It has been suggested that the responsiveness to exercise is modified by the loss of joint space width [31]. The homogeneity of this study population, with regard to radiographic changes, provided us the possibility to study the effects of exercise on patients with moderate to severe radiographic knee osteoarthritis. Can significant improvements of pain or self-reported function be expected in patients with radiographic knee osteoarthritis corresponding to Kellgren & Lawrence grade 3 or more? In this study, no improvements were seen on group level in pain or function. However, regular exercise in general is important to prevent diseases caused by inactivity [6], and thus patients with knee osteoarthritis should be encouraged to exercise. In clinical practice, patients with severe knee osteoarthritis should have treatments based on individual preferences and different stages of motivation [32]. It can be argued that the exercise intensity was too high for this group with moderate to severe knee osteoarthritis. Even though the intensity of each exercise was individually adapted, all individuals exercised at a minimum of 60% of HR max. It has been suggested that pain during exercise might be a protective mechanism in knee osteoarthritis, i.e. an increase in pain from too intensive exercises may restrain patients from further joint loading, which otherwise could cause further cartilage damage [33]. Patients in the current study were told to reduce the exercise intensity if pain during exercise was perceived as worse than 'acceptable', or persisted more than 24 hours. It is suggested that the different degrees of varus-valgus laxity should be taken into account in exercise interventions, to enhance the functional outcome [34,35]. Severe knee osteoarthritis is associated with a hip-knee-ankle malalignment and an increase in varus-valgus laxity compared to healthy knees [36]. It is possible that varus-valgus laxity mediated the effect of exercise on pain since all patients had radiographic changes corresponding to Kellgren and Lawrence grade III or more. Malalignment may cause increased joint loads, and greater quadriceps strength might further increase joint load by the muscles compressing the articular surfaces [37]. Younger patients are usually more physically active than elderly [38], and have higher demands on level of physical function and physical performance at work or leisure time. Thus, moderate to severe knee osteoarthritis might be perceived as more disabling by younger individuals compared to elderly. Our study population was younger (<65 years) and comprised more men (49%) than most other populations with knee osteoarthritis described in randomized controlled trials of exercise [13-15,39,40], which might have reduced the effect on self-reported function in the present study. This study showed no significant differences on self-reported pain and function either between or within groups. A post-hoc analysis was performed to study the possibility that the benefit from exercise was larger in subjects with worse pain at baseline. Fifteen patients in the exercise group were compared to 13 from the control group who had worse than total group median pain score (KOOS Pain 58 on a 0–100, worst to best scale) at baseline. The groups had comparable patient characteristics. The changes seen in these subgroups were however not different from the changes seen in the total groups. A possible limitation could be lack of power. A post-hoc analysis was performed to estimate the number of patients needed to show a clinically significant difference of 11 ± 15 KOOS-points [20]. The standard deviation of 15 is supported by results from randomized controlled trials of glucosamine supplementation [41] and a nutritional supplement [42] for knee osteoarthritis, where significant group differences were found in KOOS pain and ADL subscales. The number of subjects in each treatment arm in these RCT:s ranged from 15 to 27. The standard deviations in KOOS subscales have not previously been determined in exercise interventions. Only one of the five KOOS subscales showed a statistical significant improvement, and it can not be excluded that this result could be due to chance. The improvement of the KOOS subscale Quality Of Life in the exercise group was of doubtful clinical significance, however the improvement persisted over time, and is in accordance with previous findings of impact from exercise on mental health aspects in patients with knee osteoarthritis [31,43,44]. Group dynamics, support, or attention received may possibly have influenced the quality of life more than the exercise itself in the present study. Psychosocial factors are important determinants of physical function [45], and our results suggest that supervised exercises and follow-up are important, and that quality of life should be evaluated in osteoarthritis interventions.\n\nBODY.CONCLUSION:\nA six-week high-intensive exercise program had no effect on pain or function in middle-aged patients with moderate to severe radiographic knee OA. Some effect was seen on quality of life in the exercise group compared to the control group.\n\nBODY.COMPETING INTERESTS:\nThe author(s) declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nCT participated in design, exercise intervention, assessments and follow-ups, statistical analyses and writing. ER participated in design, analysis and interpretation of the data, and critically revised the article. IP participated in design and interpretation of the data and critically revised the article. CE initiated and obtained necessary permissions for the study, arranged the initial funding, and participated in the analyses, interpretation and revision of the manuscript. All authors read and approved the final manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: \n\nBODY.SUPPLEMENTARY MATERIAL:\nAdditional File 1Intensive exercise program CarinaClick here for file Additional File 2Tests of functional performance CarinaClick here for file\n\n**Question:** Compared to No exercise what was the result of Exercise on Baseline characteristics?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
225
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: A heart failure self-management program for patients of all literacy levels: A randomized, controlled trial [ISRCTN11535170]\n\n ABSTRACT.BACKGROUND:\nSelf-management programs for patients with heart failure can reduce hospitalizations and mortality. However, no programs have analyzed their usefulness for patients with low literacy. We compared the efficacy of a heart failure self-management program designed for patients with low literacy versus usual care.\n\nABSTRACT.METHODS:\nWe performed a 12-month randomized controlled trial. From November 2001 to April 2003, we enrolled participants aged 30–80, who had heart failure and took furosemide. Intervention patients received education on self-care emphasizing daily weight measurement, diuretic dose self-adjustment, and symptom recognition and response. Picture-based educational materials, a digital scale, and scheduled telephone follow-up were provided to reinforce adherence. Control patients received a generic heart failure brochure and usual care. Primary outcomes were combined hospitalization or death, and heart failure-related quality of life.\n\nABSTRACT.RESULTS:\n123 patients (64 control, 59 intervention) participated; 41% had inadequate literacy. Patients in the intervention group had a lower rate of hospitalization or death (crude incidence rate ratio (IRR) = 0.69; CI 0.4, 1.2; adjusted IRR = 0.53; CI 0.32, 0.89). This difference was larger for patients with low literacy (IRR = 0.39; CI 0.16, 0.91) than for higher literacy (IRR = 0.56; CI 0.3, 1.04), but the interaction was not statistically significant. At 12 months, more patients in the intervention group reported monitoring weights daily (79% vs. 29%, p < 0.0001). After adjusting for baseline demographic and treatment differences, we found no difference in heart failure-related quality of life at 12 months (difference = -2; CI -5, +9).\n\nABSTRACT.CONCLUSION:\nA primary care-based heart failure self-management program designed for patients with low literacy reduces the risk of hospitalizations or death.\n\nBODY.BACKGROUND:\nLimited literacy skills are common among adults in the United States [1]. Low literacy is associated with increased risk of hospitalization and worse control of chronic diseases [1-4]. Heart failure is a common chronic illness requiring multiple medications and significant self-care. Heart failure is the leading cause of hospitalization in the Medicare population [5]. The complexity of care for heart failure puts people with low literacy at considerable risk for adverse outcomes including hospitalization, worse quality of life, and mortality. Heart failure disease-management interventions appear effective in reducing rehospitalizations and improving quality of life [6]. Most randomized clinical trials of heart failure disease management completed over the last 10 years have enrolled patients during, or shortly after, hospitalization and reported the outcome of readmission [6]. Although the designs of these programs vary, several have tested education and support to enhance patient self-management as the main component of the intervention [7-10]. The content of self-management education usually includes teaching to understand medications, reduce salt intake, monitor daily weights, and recognize symptoms. Most programs include structured follow-up either by home visit, phone, or mail. Only a few, uncontrolled studies specifically ask patients to self-adjust their diuretics [11,12]. Heart failure self-management programs may be particularly effective for vulnerable populations, such as those with poor literacy [13,14]. However, to our knowledge, no previous studies have explicitly examined the role of self-management programs in a low literacy population. A recently published study and accompanying editorial suggested that such self-management support may be most effective among vulnerable populations [13,14]. Low literacy may represent a vulnerability for which we should design our programs. Disease management for patients with low literacy may require refined approaches to foster self-management skills. We developed a heart failure self-management program for use by patients with a variety of literacy levels [15]. We performed a randomized controlled trial comparing our self-management program to usual care among outpatients to test if the program could reduce hospitalizations and improve heart failure-related quality of life.\n\nBODY.METHODS.STUDY DESIGN:\nWe conducted a randomized controlled trial in the University of North Carolina (UNC) General Internal Medicine Practice, which serves a wide socioeconomic range of patients. The practice, staffed by over 20 attending faculty and 70 medical residents, cares for over 500 patients with heart failure.\n\nBODY.METHODS.STUDY PARTICIPANTS:\nTo be eligible, patients had to have a clinical diagnosis of heart failure confirmed by their primary provider through a direct interview, and one of the following: 1) chest x-ray findings consistent with heart failure, 2) ejection fraction <40% by any method, or 3) a history of peripheral edema. They also had to have New York Heart Association class II-IV symptoms within the last 3 months. Patients were excluded if they had moderate to severe dementia (based on the treating physician's clinical judgment), terminal illness with life expectancy less than 6 months, severe hearing impairment, blindness, current substance abuse, a serum creatinine >4 mg/dl or on dialysis, a requirement of supplemental oxygen at home, lacked a telephone, or were scheduled to undergo cardiac surgery or awaiting heart transplant. We did not exclude patients on the basis of literacy skill because we felt patients of all literacy levels would benefit from this intervention. Patients who read well often prefer information presented in an easy-to-read format [16]. We accepted referrals from the cardiology clinic if patients met eligibility criteria. This study was approved by the Institutional Review Board of the UNC School of Medicine, and all participants gave informed consent prior to enrollment. For participants who could not adequately read the informed consent document, the research assistant read and explained it to them. They were asked to sign a short form indicating that the informed consent document was reviewed and they agreed to participate. When the short form was used, a witness was asked to attest to the adequacy of the consent process.\n\nBODY.METHODS.PROCEDURES:\nParticipants were recruited between November 2001 and April 2003 from the General Internal Medicine and Cardiology Practices at UNC Hospitals. A trained research assistant screened all patients age 30–80 for use of furosemide. If the patient was on furosemide, their physician was queried about the presence of heart failure. If the patient met eligibility criteria and consented to participate, baseline data were collected. We then randomized patients by concealed allocation based on a random number generator to receive the intervention or usual care. All patients were followed for one year. All data were collected in the General Internal Medicine Practice.\n\nBODY.METHODS.INTERVENTION:\nThe intervention was delivered in the General Internal Medicine Practice. The educational materials and disease management intervention were previously described in detail, and the intervention is summarized here [15]. The intervention began with a 1-hour educational session with a clinical pharmacist or health educator during a regular clinic visit. Patients were given an educational booklet designed for low literacy patients (written below the 6th grade level and extensively pre-tested in focus groups and a pilot study [15]) and a digital scale. The educator and patient reviewed the booklet together, including management scenarios. As part of the educational session, patients were taught to identify signs of heart failure exacerbation, perform daily weight assessment, and adjust their diuretic dose. Because this intervention was aimed at patients with low literacy, the health educator used pedagogic strategies felt to improve comprehension for patients with low literacy [17]. For example, the educator had the patient teach back the information [18], engaged the patient in filling out the notebook, and used brainstorming to help the patient incorporate self-management into their lives. The educator, patient, and primary care physician collaborated to establish the patient's \"good weight\" (i.e., where the patient's heart failure was stable) and baseline diuretic dose. The educator then filled in the management plan in the patient's notebook to help the patient better manage weight fluctuations and self-adjust the diuretic dose based on weight (Figure 1). The general plan involved doubling the dosage if weight went up and halving it if weight went down. The program coordinator then made scheduled follow-up phone calls (days 3, 7, 14, 21, 28, 56) and monthly during months 3–6. The follow-up phone calls, each lasting 5–15 minutes, were designed to reinforce the educational session and provide motivation for the patients. Again, the program coordinator had the patient describe their self-management practices and offered feedback to improve them. Patients experiencing worsening symptoms were scheduled acute visits with their physician. We did not provide specialized nursing assessment, care or medication advice beyond diuretic dosing. If the patient's doctor determined that the good weight had changed, the program coordinator would revise the care plan with the patient. Patients enrolled in the control group received a general heart failure education pamphlet written at approximately the 7th grade level, and continued with usual care from their primary physician. The only contacts between the research team and the control patients were at enrollment and data collection.\n\nBODY.METHODS.MEASURES:\nWe assessed outcomes at 6 and 12 months through in-person interviews and review of the medical record. To be sensitive to low literacy, all interviews were conducted verbally by a trained research assistant. If patients were unable to come to clinic for the interview, it was conducted by phone. The research assistant was not blinded to the patient's study group. Primary outcomes were death or all-cause readmission and heart failure-related quality of life at the end of 12 months. Data on hospitalization dates were obtained from the patient and confirmed by medical chart review. All admissions, regardless of hospital or cause, were counted. For exploratory analyses, we classified reason for admission as cardiac or non-cardiac. Cardiac admissions included those primarily for heart failure (e.g., shortness of breath and edema relieved by diuresis) and other cardiac causes such as chest pain, arrhythmias, or syncope. Cause of admission was determined by chart review by one of the authors (D.D.) who was blinded to treatment allocation. Heart failure-related quality of life was assessed using a modified version of the Minnesota Living with Heart Failure Questionnaire (MLHF). The MLHF is a 21 question instrument with a 6-point Likert scale response option and scores ranging from 0 to 105 [19]. In pilot testing of the MLHF, we found that low literacy patients had trouble answering questions with the standard 6-point Likert scale [15], so we changed the response scale to 4 points, using a visual display with stars to represent increasing severity. The 4-point Likert scale was scored as 0, 1, 3, and 5 to approximate standard scores on the MLHF. Secondary measures included heart failure self-efficacy, knowledge, and behaviors. Self-efficacy was measured with an 8 item scale developed for the behaviors needed in this trial as suggested by self-efficacy scale developers [20]. Respondents used a 4-point Likert scale yielding a total score from 0–24. We assessed heart failure knowledge using a knowledge test previously developed for this population [15], Heart failure self-management behavior was assessed by asking patients how often they weighed themselves. We used patient self-report and the medical chart to measure age, gender, race, insurance status, income, years of education, medication use, years with heart failure, and the presence of co-morbidities. We measured literacy using the Short Test of Functional Health Literacy in Adults (S-TOFHLA) [21], a well-validated scale that correlates well with other measures of reading ability [22]. Patients who scored in the inadequate literacy range on the S-TOFHLA were considered to have \"low literacy.\" The cut-point for inadequate literacy is roughly analogous to the 4th grade reading level.\n\nBODY.METHODS.SAMPLE SIZE:\nSample size was based on pilot study results showing a 9-point improvement in MLHF scores over 3-months with the intervention [15]. Detecting a 9-point difference between intervention and control group with 80% power and alpha set at 0.05 required 70 patients per group. We aimed to enroll 150 patients to account for possible attrition, but stopped at 127 because funding ended. We did not power this study to detect differences in hospitalization, but studies with even smaller numbers of patients have shown a difference for that outcome [7].\n\nBODY.METHODS.STATISTICAL METHODS:\nPatients who did not return any phone calls and did not return for follow-up assessment did not have outcome data for analysis. Patients who withdrew from the study were censored at the time of withdrawal; any data collected prior to withdrawal were included in the analysis. Baseline differences between groups were assessed using t-tests for continuous outcomes and chi-squared tests for categorical outcomes. For MLHF, heart failure self-efficacy and heart failure knowledge, we used two-sample t-tests. Non-parametric tests were also performed for all comparisons, but results did not differ from the parametric tests. Because of the small sample size and the unequal distribution of baseline characteristics, we adjusted for baseline differences using linear regression. Analyses of self-reported outcomes, such as MLHF, excluded patients who died or withdrew from the study before 6 or 12 month data was collected. For hospitalization or death, we used negative binomial regression and censored patients at the time of death or withdrawal from the study. Based on the likelihood ratio test, negative binomial regression was a better fit for the data than a Poisson regression. Additionally, the Vuong test confirmed that a zero-inflated model was inappropriate [23]. Because of uneven distribution of baseline characteristics, we performed analysis of covariance with negative binomial regression to control for baseline differences [24]. We identified the following variables that could contribute to hospitalization or death based on previous studies: age, race, gender, literacy level, hypertension, diabetes, creatinine, MLHF score, use of β-blockers, angiotensin converting enzyme (ACE) inhibitors or angiotensin receptor blockers (ARBs), use of digoxin, and presence of systolic dysfunction [7,25]. Variables were not included in the model if the relationship between the variable and the study group or outcome had a p value greater than 0.3. We started with a model including the following items to arrive at the best point estimate: age, gender, hypertension, creatinine, MLHF, use of β-blockers, and use of ACE inhibitors or ARBs. We then eliminated variables from the model if p > 0.30, and if the point estimate remained within 10% of the initial estimate. We prespecified a subgroup analysis in patients with low literacy to analyze if the intervention had a similar effect. The same analysis described above was repeated for the subgroups of patients with low literacy and those with higher literacy. The initial multivariate model for the subgroups analysis included: age, gender, hypertension, MLHF, use of β-blockers, and use of ACE inhibitors or ARBs.\n\nBODY.METHODS.ROLE OF THE FUNDING SOURCE:\nThe funding sources had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; or preparation, review, or approval of the manuscript.\n\nBODY.RESULTS.PATIENTS:\nWe screened 919 patients on furosemide between November 2001 and April 2003. 127 met eligibility criteria and agreed to participate (Figure 2). Of those not enrolled, 407 did not have heart failure according to their physician, 367 did not meet eligibility criteria and 27 declined to participate. Of those randomized to the control group, 1 never returned after the first visit, 1 withdrew during the study and 4 died during the study. Follow-up was completed for all of the remaining participants (98%) (Figure 3). Of those randomized to the intervention group, 3 never returned after the first visit, 4 withdrew during the study and 3 died during the study. Follow-up was completed for all of the remaining participants (93%). At baseline, most characteristics were similar between the two groups (Table 1). However, the control group had more participants with hypertension, fewer with diabetes, and fewer men. Of heart failure related characteristics, the control group had more participants with systolic dysfunction, and taking β-blockers. The intervention group had more participants taking ACE inhibitors or ARBs, and digoxin. Regardless of these differences, none were statistically significant. The control group did have statistically significantly higher baseline MLHF scores representing worse symptoms at baseline.\n\nBODY.RESULTS.HOSPITALIZATION OR DEATH:\nThere were 68 hospitalizations (65) or deaths (3) in the intervention group and 111 (107 hospitalizations, 4 deaths) in the control group. The crude all-cause hospital admission or death incidence rate ratio (IRR) was 0.69 (95% CI 0.40, 1.19). After adjusting for age, gender, use of ACE inhibitor or ARB, use of a β-blocker, presence of hypertension, and baseline MLHF, intervention patients were less likely to have the outcome (IRR = 0.53; 95% CI 0.32, 0.89). 61% of patients in the control group had at least one hospitalization or died, and 42% of patients in the intervention group had at least 1 hospitalization or died (p = 0.13).\n\nBODY.RESULTS.CARDIAC HOSPITALIZATION:\n39% of patients in the control group and 34% of patients in the intervention group had at least one hospitalization for cardiac causes (p = 0.55). The unadjusted IRR was 0.79 (95% CI 0.42, 1.5). After adjusting for baseline differences, the IRR was 0.85 (95% CI 0.44, 1.7).\n\nBODY.RESULTS.HEART FAILURE-RELATED QUALITY OF LIFE:\nIn unadjusted analysis, the control group, on average, improved 5 points on the MLHF and the intervention group improved by 1 point. The difference was not statistically significant (3.5 points, 95% CI 11, -4, p = 0.36). After adjusting for baseline differences between the groups, the difference was 2 points (95% CI 9, -5, p = 0.59) suggesting no effect on heart failure-related quality of life.\n\nBODY.RESULTS.OTHER OUTCOMES.KNOWLEDGE:\nHeart failure related knowledge improved more in the intervention group than in the control group. Mean difference in score improvement was 12 percentage points (95% CI 6, 18; p < 0.001).\n\nBODY.RESULTS.OTHER OUTCOMES.SELF-EFFICACY:\nHeart failure self-efficacy improved more in the intervention group than in the control group. Mean difference in score improvement was 2 points (95% CI 0.7, 3.1; p = 0.0026).\n\nBODY.RESULTS.OTHER OUTCOMES.SELF-CARE BEHAVIOR:\nSignificantly more patients in the intervention group than in the control group reported daily weight measurement at 12 months (79% vs. 29%, p < 0.001).\n\nBODY.RESULTS.SUBGROUP ANALYSES ACCORDING TO LITERACY:\nTwenty-four patients in each group had inadequate literacy based on the S-TOFHLA (Table 2). Among these patients, there was no difference in quality of life score in unadjusted and adjusted analyses (difference = -1.6; 95% CI -15, 12); p = 0.81). For the combined outcome of hospitalization or death, the unadjusted IRR was 0.77 (95% CI 0.30, 1.94). After adjusting for baseline differences, the IRR was 0.39 (95% CI 0.16, 0.91). Seventy-five patients had marginal or adequate literacy based on the S-TOFHLA. We found no difference in quality of life score in unadjusted and adjusted analyses (difference = -4.2; 95% CI -14, 6; p = 0.40). Among patients in the higher literacy group, the unadjusted IRR for hospitalization or death was 0.65 (95% CI 0.33, 1.3). After adjusting for baseline differences, the IRR was 0.56 (95% CI 0.30, 1.04). We did not find a statistically significant effect modification between literacy and the intervention.\n\nBODY.DISCUSSION:\nA heart failure self-management program designed for patients with low literacy reduced the rate of the combined endpoint of hospitalization or death. The prespecified subgroup analyses suggest that patients with low literacy benefited as much from the intervention as the patients with higher literacy. The success of our intervention reflects the goals of our program. We designed an easy-to-read and use educational booklet and self-management plan, and focused on overcoming barriers to learning self-management [15]. Our intervention was founded on teaching self-management. We focused on helping patients understand signs and symptoms of worsening heart failure and perform self-adjustment of diuretics based on weight fluctuation. Many care providers would not attempt to teach patients, particularly those with low literacy, how to self-adjust their diuretic medication. We found that, with careful teaching, many patients incorporated this strategy into their daily routine successfully, as demonstrated by improved self-care behaviors. Teaching self-adjustment of diuretics, rather than the conventional teaching to call the care provider if weight fluctuates, empowers patients to take more control over their illness. Self-adjustment of diuretic dose is a prominent aspect of the self-management training we provided to the intervention patients. Other programs to improve patient self-management have not been explicit in teaching patients to self-adjust their diuretic dose based on weight fluctuation. Although our outcomes are comparable to others', using this approach puts more control into the hands of the patient. Furthermore, our intervention appears effective among patients with low literacy skills, a group often overlooked for empowering interventions. Our study adds to the growing literature on disease management programs for patients with heart failure [6], particularly those that focus on self-management training [7-10]. Studies focusing on self-management training have demonstrated comparable improvements in hospitalization rates to more comprehensive programs that aim to improve the quality of pharmaceutical prescribing, provide home visits, and take place in specialized cardiology clinics [6]. Such comprehensive programs have also been shown to reduce mortality, but self-management programs have not [6]. We did not detect any difference in heart failure related quality of life which was the outcome we powered our study to detect. Other self-management studies that have found improved quality of life have enrolled patients during a heart failure hospitalization [8,9]; however, we enrolled patients in the outpatient setting while they were clinically stable. Improving quality of life for stable outpatients may be more difficult for this type of intervention. We have previously reported that patients with diabetes and low literacy benefited more from a disease management intervention than those with higher literacy skills [26]. A similar result in two different chronic diseases substantiates the claim that appropriately designed disease management programs may have greater effect for low literacy or vulnerable populations, who are most at risk for adverse outcomes with usual care. This finding is particularly important in light of the recent study by DeBusk and colleagues that did not find a reduction in hospitalization with a well-designed comprehensive intervention [13]. The authors and an accompanying editorial [14] suggested that the failure to detect improvement may have occurred because the patients studied were less at-risk than in other studies. They called for more research to determine better ways of targeting disease management. We believe that low literacy is an important marker for vulnerability to adverse outcomes, and that disease management programs targeted to patients with low literacy may be an effective way of focusing resources on those most able to benefit. If patients with low literacy are to be preferentially recruited for such programs, innovative outreach and screening efforts will likely be required, as patients with low literacy may face particular barriers to accessing such care. This study should be interpreted in light of its limitations. Research assistants were not blind to group assignment during the assessment of self-reported outcomes. As such, patients in the intervention may have been more likely to inflate their responses in an effort to please the interviewer. This effect would tend to inflate patient responses to the subjective assessments of heart failure-related quality of life, self-efficacy, and self-care behaviors. The MLHF questionnaire was modified from its original form to make it easier for patients with low literacy to respond. This change in the scale may have changed its ability to detect important changes in heart failure related quality of life. Because the groups' mean scores were almost identical, we do not feel this limitation changed our results. In a similar vein, most questionnaires are not validated in low literacy populations, raising questions as to their ability to perform to the same standards. Our sample size was small, which did not allow for an even distribution of baseline variables among the groups. We controlled for baseline differences between groups in our analysis. While it is controversial whether or not to control for baseline differences in randomized controlled trials, some analysts have argued that doing so improves the power without introducing bias [24]. A larger, multi-site study would offer better control of confounders, better generalizability, and more power to determine differences in effect according to literacy. We did not collect data on the resources needed to implement this type of intervention in usual settings, and such a study and cost-effectiveness analysis would be helpful for most interventions of this type. We used health educators, not nurses or physicians, to deliver the intervention. By using less highly trained individuals to deliver the intervention, we enabled nurses and physicians to perform clinical tasks more commensurate with their training. Other studies that have performed global cost estimates have found that the savings from reductions in hospitalizations exceed the cost of the intervention [6].\n\nBODY.CONCLUSION:\nIn conclusion, our heart failure self-management program, designed for patients of all literacy levels, appears to reduce rates of hospitalization and death. Patients with low literacy, and other vulnerable patients, may stand to benefit most from these programs. Further research into the design, implementation, and dissemination of disease management programs for low literacy patients will be crucial for meeting the health care needs of the growing population of patients with chronic illness.\n\nBODY.COMPETING INTERESTS:\nDrs. DeWalt and Pignone have received honoraria and grants from Pfizer, Inc., Dr. Rothman has received grants from Pfizer, Inc., and Dr. Sueta is in their speakers bureau.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nDD conceived of the study, participated in its design and coordination, performed statistical analyses, interpretation of the data, and drafted the manuscript. RM, MB conceived of the study and participated in its coordination. MK, KC coordinated the study, and collected the data, RR, CS participated in study design and interpretation of the data. MP conceived of the study, participated in its design and coordination, and interpretation of the data. All authors reviewed the manuscript for important intellectual content and gave final approval.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here:\n\n**Question:** Compared to Standard information about self-care what was the result of Follow-up and thorough education on self-care on Cardiac-related hospitalization?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
464
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Comparison of intravenous immunoglobulin and plasma exchange in treatment of mechanically ventilated children with Guillain Barré syndrome: a randomized study\n\n ABSTRACT.INTRODUCTION:\nRespiratory failure is a life threatening complication of Guillain Barré syndrome (GBS). There is no consensus on the specific treatment for this subset of children with GBS.\n\nABSTRACT.METHODS:\nThis was a prospective randomized study to compare the outcome of intravenous immunoglobulin (IVIG) and plasma exchange (PE) treatment in children with GBS requiring mechanical ventilation. Forty-one children with GBS requiring endotracheal mechanical ventilation (MV) within 14 days from disease onset were included. The ages of the children ranged from 49 to 143 months. Randomly, 20 children received a five-day course of IVIG (0.4 g/kg/day) and 21 children received a five-day course of one volume PE daily. Lumbar puncture (LP) was performed in 36 patients (18 in each group).\n\nABSTRACT.RESULTS:\nBoth groups had comparable age (p = 0.764), weight (p = 0.764), duration of illness prior to MV (p = 0.854), preceding diarrhea (p = 0.751), cranial nerve involvement (p = 0.756), muscle power using Medical Research Council (MRC) sum score (p = 0.266) and cerebrospinal fluid (CSF) protein (p = 0.606). Children in the PE group had a shorter period of MV (median 11 days, IQR 11.0 to 13.0) compared to IVIG group (median 13 days, IQR 11.3 to 14.5) with p = 0.037. Those in the PE group had a tendency for a shorter Pediatric Intensive Care Unit (PICU) stay (p = 0.094). A total of 20/21 (95.2%) and 18/20 (90%) children in the PE and IVIG groups respectively could walk unaided within four weeks after PICU discharge (p = 0.606). There was a negative correlation between CSF protein and duration of mechanical ventilation in the PE group (p = 0.037), but not in the IVIG group (p = 0.132).\n\nABSTRACT.CONCLUSIONS:\nIn children with GBS requiring MV, PE is superior to IVIG regarding the duration of MV but not PICU stay or the short term neurological outcome. The negative correlation between CSF protein values and duration of MV in PE group requires further evaluation of its clinical usefulness.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicaltrials.gov Identifier NCT01306578\n\nBODY.INTRODUCTION:\nGuillain-Barré syndrome (GBS) is, currently, the most common cause of acute flaccid paralysis following the worldwide decline in incidence of poliomyelitis. Incidence varies according to age, geographic areas and diagnostic criteria used for inclusion. Annual incidence in western countries varies from 1.1 to 1.8/100,000 population per year [1-5] with a considerably lower annual incidence of 0.66/100,000 population per year in each of Taiwan [6] and China [7]. GBS usually follows infection by a number of bacterial and viral agents with Campylobacter jejuni representing the most common preceding infection [8-11]. The syndrome is also reported to rarely temporally follow vaccination with measles vaccine [12,13], tetanus toxoid [14], rabies vaccine [15], oral polio vaccine [16], polysaccharide meningococcal vaccine [17], measles-rubella vaccine [18], flu vaccine [19] and hepatitis B vaccine [19]. Since the publishing of the first report of the condition by Guillain, Barré, and Strohl in 1916, GBS has remained a clinically-diagnosed disorder. The condition is a polyneuropathy involving mainly motor but sometimes also sensory and autonomic nerves. It starts with rapidly progressive bilateral and relatively symmetric weakness in the lower limbs with diminished or absent deep tendon reflexes. Paralysis follows an ascending pattern involving trunk, upper limb and, finally, bulbar muscles. There can be numbness, parathesia and muscle pain and tenderness. Labile blood pressure with postural hypotension and labile heart rate with episodes of bradycardia up to asystole rarely occur denoting autonomic neuropathy. van Doorn et al. categorize diagnostic features of the condition into features required for diagnosis, including progressive weakness in both arms and legs, and areflexia or hyporeflexia, and features that strongly support the diagnosis, including progression of symptoms to a nadir over days to four weeks, relative symmetry of symptoms, mild sensory symptoms or signs, cranial nerve involvement, autonomic dysfunction, pain, a high concentration of protein in CSF without increase in cells and typical electro-diagnostic features [20]. A common, yet not an early, feature of GBS is increased cerebrospinal fluid (CSF) protein (> 45 mg/dL) without CSF pleocytosis (< 10 cells/mm3), often referred to as cytoalbuminous dissociation [21]. Electromyography may be used to confirm the diagnosis in the small subset of patients where the diagnosis is not straightforward. It is also useful to sub-classify patients into motor axonal neuropathy and acute inflammatory demyelinating polyneuropathy [22]. A recent study conducted in Egypt on children with GBS found that acute inflammatory demyelinating polyneuropathy, was the most common type (76%) while, acute motor axonal neuropathy, acute motor sensory axonal neuropathy and unclassified forms represented 8% each [23]. Respiratory failure is one of the most serious complications of GBS. It affects 15% of children with the condition [24]. The ability to predict the occurrence of respiratory failure and need for mechanical ventilation (MV) among patients with GBS has long been a target for neurologists and intensivists alike. Some bedside indicators of the likelihood of requiring MV are rapid disease progression, bulbar dysfunction, bilateral facial weakness, or dysautonomia, inability to stand, inability to lift the elbows or head, elevated liver enzymes and abnormal pulmonary function test [25-27]. Electrophysiological evidence of demyelination was also suggested to predict the need for endotracheal MV [28]. Treatment of GBS is a multidisciplinary effort. The general care of the child with muscle weakness includes regular monitoring of pulmonary and cardiovascular function for possible involvement of respiratory muscles and autonomic neuropathy respectively, prevention of infection and deep vein thrombosis, pain management, early physiotherapy, early rehabilitation once muscle power improvement starts and psychosocial support for the affected children and their families [20]. Specific treatment of severely affected children comprises intravenous immunoglobulin (IVIG) or plasma exchange (PE). Performed on more than 200 patients each, two large trials in the mid-1980s confirmed the beneficial role of PE in treatment of patients with GBS compared to the conventional treatment of the time [29,30]. The routine use of IVIG as the first line of treatment in GBS followed the publication of a randomized controlled trial (RCT) in 1992 showing a similar, if not a superior, effect of IVIG compared to PE [31]. A recent systematic review of heterogeneous study populations showed there was no evidence for a better outcome with either of the two modalities of treatment. There is also no evidence of a beneficial effect of adding corticosteroids to the treatment [32]. The objective of this study is to compare PE and IVIG as a first line treatment for children with severe GBS requiring MV regarding the duration of MV, PICU stay and short term neurological outcome.\n\nBODY.MATERIALS AND METHODS:\nChildren with GBS admitted to the Pediatric Intensive Care Unit (PICU) at Mansoura University Children Hospital, Mansoura, Egypt, with the need for MV were prospectively enrolled in the study. Cases were diagnosed to have GBS according to clinical criteria by van Doorn et al. [20]. Patients were eligible for inclusion if they required MV based on the indications listed below, and if the duration of muscle weakness did not exceed 14 days on enrollment. Children were not eligible for inclusion if they had muscle weakness for longer than 14 days before requiring MV and if IVIG or PE was started prior to enrollment. All patients were ventilated using endotracheal MV. Children were intubated if they were unable to protect their airway, had increased work of breathing (WOB), had PaO2 less than 70 mmHg in room air requiring increasing FiO2, or showed CO2 retention. When children were able to trigger spontaneous breathing, they were changed to a pressure-support spontaneous ventilation mode with continuous positive airway pressure of 5 cm H2O. Pressure support was gradually weaned to 10 cm H2O. If secretions were manageable and airway reflexes intact, a daily spontaneous breathing trial (SBT) was performed using a T-piece for two hours. Patients were extubated if SBT was successful. An SBT was deemed successful if there was no diaphoresis, increased WOB or apnea, tachycardia (defined by increase in the heart rate of 40 bpm or more) and if SpO2, pH, PaO2 and PaCO2 remained close to pre-SBT values. The decisions to initiate, wean and terminate MV were made independently by the attending consultant in accordance with and in strict adherence to the unit guidelines as above. Over a period of three years, from January 2007 to December 2009, 44 children were admitted with GBS requiring MV; 41 children fulfilled inclusion criteria and were randomized to receive either IVIG (20 children) or PE (21 children) for initial treatment. Randomization was done by computer-generated random tables. IVIG was administered in a dose of 0.4 g/kg/day for five days. Patients in the PE group received a daily one-volume PE for five consecutive days. The sample size yields a study power of 86.9%. On admission, the muscle power was recorded using the Medical Research Council (MRC) sum score [33]. Lumbar puncture (LP) was performed in the second week of illness in 36 out of the 41 children (18 in each group). LP was performed at the discretion of the attending consultant. The primary outcome measure was the duration of mechanical ventilation and secondary outcome measures were length of PICU stay and ability to walk unaided within four weeks of PICU discharge. Institutional research ethics committee approval was granted and an informed consent was obtained from legal guardians of children included in the study. Statistical analysis was performed using Statistical Package for the Social Sciences, Version 17 (SPSS, Inc., Chicago, IL, USA). p-value was considered significant if less than .05.\n\nBODY.RESULTS:\nChildren in the two treatment groups were comparable as regards base line characteristics, such as age, weight, duration of illness prior to requiring mechanical ventilation, presence or absence of preceding diarrhea, cranial nerve affection, severity of muscle weakness on PICU admission and CSF protein when available (Table 1). Table 1 Comparison of IVIG and PE groups regarding base line variables IVIG group ( n = 20) PE group ( n = 21) p- value Age (months) 106.0 ± 22.8 (74.3 to 113.5) 96.0 ± 32.8 (65.5 to 135.0) 0.764 1 Weight (kg) 32.5 ± 7.0 (23.0 to 34.8) 29.0 ± 10.1 (20.0 to 41.5) 0.764 1 DOI (days) 9.0 ± 2.7 (7.0 to 12.0) 9.0 ± 2.8 (6.5 to 11.5) 0.854 1 Diarrhea (%) Yes 13 (65%) 12 (57.1%) 0.751 2 No 7 (35%) 9 (42.9%) Cranial nerve affection (%) Yes 8 (40%) 10 (47.6%) 0.756 2 No 12 (60%) 11 (52.4%) MRC sum score 12.0 ± 4.8 (8.5 to 15.5) 12.0 ± 5.9 (4.0 to 12.0) 0.266 1 CSF protein (mg/dL) 152.1 ± 55.7 (88.3 to 173.6) 148.4 ± 43.0 (117.5 to 166.5) 0.606 1 IVIG, intravenous immunoglobulin; PE, plasma exchange; DOI, Duration of illness prior to requiring mechanical ventilation; MRC, Medical Research Council score. Data presented as median ± SD (interquartile range) 1 Mann Whitney test 2 Chi square test. There was a statistically insignificant better outcome in the PE group compared to the IVIG group. Favorable outcome was defined as the child's ability to walk independently for 10 meters (Grade 2 on GBS disability score) [34] within four weeks from PICU discharge. The post discharge management and physiotherapy were standardized for children in the two groups. In the IVIG group, favorable outcome was observed in 90% (18/20) of children compared to 95.2% (20/21) in the PE group (Table 2). Table 2 Comparison of PICU stay and duration of mechanical ventilation in the IVIG and PE groups PICU stay (days) Mechanical ventilation (Days) Favorable outcome (%) Yes No IVIG group 16.5 ± 2.1 (15.3 to 18.8) 13.0 ± 2.1 (11.3 to 14.5) 18 (90%) 2 (10%) PE group 15.0 ± 2.6 (13.0 to 17.0) 11.0 ± 1.5 (11.0 to 13.0) 20 (95.2%) 1 (4.8%) p- value .094 1 0.037 1 0.606 2 IVIG, intravenous immunoglobulin; PE, plasma exchange. Data presented as median ± SD (interquartile range) 1 Mann Whitney test 2 Chi square test. Children receiving PE had a significantly shorter period of mechanical ventilation compared to those receiving IVIG. The hospital stay was shorter in the PE group without statistical significance (Table 2). For all patients, there was a statistically significant negative correlation between CSF protein and duration of mechanical ventilation (p = .024). Examining the treatment groups separately, the significant negative correlation remained for the PE group (p-value = 0.037) and not for the IVIG group (p-value 0.132) (Table 3). Table 3 Correlation between CSF protein and duration of mechanical ventilation All patients IVIG group PE group CSF protein (mg/dL) 149.3 ± 49.0 (110.5 to 169.0) 152.1 ± 55.7 (88.3 to 173.6) 148.4 ± 43.0 (117.5 to 166.5) Mechanical ventilation (days) 12.0 ± 1.9 (11.0 to 13.0) 13.0 ± 2.1 (11.3 to 14.5) 11.0 ± 1.5 (11.0 to 13.0) p -value 0.024 1 0.132 1 0.037 1 CSF, cerebrospinal fluid; IVIG, intravenous immunoglobulin; PE, plasma exchange. Data presented as median ± SD (interquartile range) 1 Pearson test. There was no significant side effect attributable to any of the treatment modalities in any of the studied patients.\n\nBODY.DISCUSSION:\nRespiratory failure among children with GBS is a serious complication requiring intensive supportive treatment in addition to the specific treatment. The two treatment groups had no significant complications attributable to treatment intervention apart from minor hypotension episodes responding to fluid boluses in the PE group. This confirms the safety of both IVIG and PE for treating children with GBS. The results of this study suggest that PE is more useful than IVIG as a specific treatment for the subset of children with severe rapidly progressive GBS requiring MV. PE is believed to act by removal of circulating autoantibodies [35,36], while IVIG, among other mechanisms, is thought to work through blocking antibody production both in vivo [37] and in vitro [38,39]. Removal of autoantibodies, by PE, creates a concentration gradient between the lowered blood level and the extravascular space forcing antibody movement from the extra to the intra vascular space to be removed during the subsequent session [40]. Specific anti-ganglioside antibody levels were recently found to be associated with disease severity [41]. Children with severe, rapidly progressive GBS, as those included in this study, most likely have an intense autoantibody production with a high percentage of these antibodies already bound to nerves on development of respiratory failure. This might provide an explanation of why this subset of patients preferentially benefit from removal of already bound antibodies, PE, in comparison to blocking antibody production, IVIG. The clinical usefulness of this relatively small difference in the duration of mechanical ventilation between PE and IVIG groups waits to be confirmed in a larger, probably multi-center, study. CSF protein was elevated in all patients (Table 3) with no statistically significant difference between the two treatment groups (Table 1). On post hoc analysis, there was, however, a negative correlation between CSF protein level and duration of MV in PE but not IVIG group. This finding supports the above explanation of a shorter duration of MV in the PE group especially in view of a RCT showing CSF filtration to be at least as effective as PE for treatment of GBS [42] and the suggestion of a blood-CSF barrier dysfunction in adults and children with GBS [43]. PE group had a tendency for a shorter PICU stay, p = 0.094 with a comparable ability of children to walk unaided within four weeks from PICU discharge (Table 2). So, despite a shorter duration of MV, there was no difference between PE and IVIG groups regarding PICU stay or short term neurological outcome. To our knowledge, this is the first randomized controlled study comparing PE and IVIG for treatment of children with rapidly progressive GBS requiring MV. An RCT conducted in adults with GBS showed no difference in the duration of MV in PE, IVIG and combined treatment groups [44]. This difference can be accounted for by differences in the age and PE protocol used. It would have been more informative to perform an electrophysiological study for the study children to confirm homogeneity of the study population. It would also add to the understanding of these results to study kinetics of autoantibodies in future research with a similar design.\n\nBODY.CONCLUSIONS:\nRapidly progressive GBS necessitating MV in children responds favorably to both IVIG and PE, with PE being superior in regard to the duration of MV but not PICU stay or short term neurological outcome. The finding of a negative correlation between CSF protein values and duration of MV in the PE group might serve as a basis for future research aiming at a better understanding of autoantibody kinetics during treatment of GBS.\n\nBODY.KEY MESSAGES:\n• Children with GBS requiring MV respond favorably to both IVIG and PE. • Using a weaning and extubation protocol, children receiving PE had a shorter duration of MV.\n\nBODY.ABBREVIATIONS:\nCSF: cerebrospinal fluid; DOI: duration of Illness; GBS: Guillain-Barré syndrome; IVIG: intravenous immunoglobulin; LP: lumbar puncture; MRC: Medical Research Council; MV: mechanical ventilation; PE: plasma exchange; PICU: pediatric intensive care unit; SBT: spontaneous breathing trial; WOB: work of breathing.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nMAE formulated the research idea, designed the plan, performed statistical analysis and proofread the draft. AME co-designed the plan and supervised the plasma exchange making sure of uniformity of the procedure in all studied subjects and proofread the draft. AMA followed up patients on PICU, made sure the plan was followed, and helped MAE in performing statistical analysis. ME followed up patients on PICU, drafted the manuscript, and designed statistical methodology. AAA co-formulated the research idea, co-designed the plan, followed up patients on PICU, and generated and was responsible for the random assignment of the groups. HME followed up patients on PICU, co-drafted the manuscript with ME and made sure PICU management of patients complied with the unit guidelines. All authors read and approved the final manuscript.\n\nBODY.AUTHORS' INFORMATION:\nHME is one of the founding members and the current president of the ESPIC (Egyptian Society of Pediatric Intensive Care). MAE is a member of the Board of Directors of WFPICCS (World Federation of Pediatric Intensive Care Societies) and the ambassador of WFPICCS in Egypt. An abstract of this article has been presented by MAE as an oral presentation at the 6th World Congress of Pediatric Intensive Care, Sydney, 2011.\n\n**Question:** Compared to intravenous immunoglobulin (IVIG) what was the result of plasma exchange (PE) on Period of mechanical ventilation ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
354
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Placebo what was the result of Budesonide/formoterol pMDI 160/9 μg on Dyspnoea score improvement?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
426
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Six-week high-intensity exercise program for middle-aged patients with knee osteoarthritis: a randomized controlled trial [ISRCTN20244858]\n\n ABSTRACT.BACKGROUND:\nStudies on exercise in knee osteoarthritis (OA) have focused on elderly subjects. Subjects in this study were middle-aged with symptomatic and definite radiographic knee osteoarthritis. The aim was to test the effects of a short-term, high-intensity exercise program on self-reported pain, function and quality of life.\n\nABSTRACT.METHODS:\nPatients aged 36–65, with OA grade III (Kellgren & Lawrence) were recruited. They had been referred for radiographic examination due to knee pain and had no history of major knee injury. They were randomized to a twice weekly supervised one hour exercise intervention for six weeks, or to a non-intervention control group. Exercise was performed at ≥ 60% of maximum heart rate (HR max). The primary outcome measure was the Knee injury and Osteoarthritis Outcome Score (KOOS). Follow-up occurred at 6 weeks and 6 months.\n\nABSTRACT.RESULTS:\nSixty-one subjects (mean age 56 (SD 6), 51 % women, mean BMI 29.5 (SD 4.8)) were randomly assigned to intervention (n = 30) or control group (n = 31). No significant differences in the KOOS subscales assessing pain, other symptoms, or function in daily life or in sport and recreation were seen at any time point between exercisers and controls. In the exercise group, an improvement was seen at 6 weeks in the KOOS subscale quality of life compared to the control group (mean change 4.0 vs. -0.7, p = 0.05). The difference between groups was still persistent at 6 months (p = 0.02).\n\nABSTRACT.CONCLUSION:\nA six-week high-intensive exercise program had no effect on pain or function in middle-aged patients with moderate to severe radiographic knee OA. Some effect was seen on quality of life in the exercise group compared to the control group.\n\nBODY.BACKGROUND:\nExercise is considered to be one of the most important treatments for patients with mild to moderate knee osteoarthritis [1,2]. Positive effects on pain and function, as well as cost-effectiveness have been reported [3,4]. The effect size obtained on pain experience is similar to that of pharmacological treatment [3,5]. The side effects have also been reported to be favorable, including reduced risk of inactivity-related disorders, such as cardiovascular disease and diabetes [2,6,7]. Moderate levels of physical activity are not associated with radiographic progression, but activities involving a risk of severe knee injury are closely related to increased risk of developing radiographic knee osteoarthritis [8-12]. The dose-response relationship of exercise on symptoms and function is not clear and exercise recommendations in osteoarthritis guidelines are based mostly on studies on elderly people, i.e. mean age ≥ 65 [3,13-15]. It is not clear whether exercise has a similar effect on pain and function in middle-aged patients compared with elderly patients. The aim of this study was to examine the effects of a short-term, high-intensity exercise program in middle-aged subjects (age 36–65) with definite radiographic knee osteoarthritis on self-reported pain, function, and quality of life.\n\nBODY.METHODS.SUBJECTS:\nA flow chart of the recruitment process is given in Figure 1. Radiologists and orthopedic surgeons at the Halmstad County Hospital, in the south-west of Sweden, and general practitioners within the catchments area of this hospital, were informed about the study and asked to list patients with radiographic knee osteoarthritis on a \"patients eligible for research\" list. Between October 1998 and October 2001 121 patients, referred by their general practitioner for radiographic examination because of long standing knee pain, were listed. Ninety-seven fulfilled the inclusion criteria: age 35–65, living in the defined geographic area, and diagnosis of radiographic osteoarthritis of Kellgren and Lawrence grade III or more, i.e. definite osteophytes and joint space narrowing. All listed patients received written information about the study. One week after the information was sent, patients were contacted by telephone, and invited to participate in the study. Twenty-eight patients declined participation for various reasons, the most common reason being lack of time and interest. To ensure only patients with symptoms due to knee osteoarthritis and eligible for exercise intervention were included, the following exclusion criteria were used: inflammatory joint disease, anterior cruciate ligament injury, known symptomatic injury to the menisci, hip symptoms more aggravating than the knee symptoms, about to have knee replacement surgery within 6 months, and co-morbidities not allowing exercise (Figure 1). Figure 1Flowchart of recruitment process and included patients. When eight or more patients fulfilled the inclusion criteria they were invited to baseline interview and examination for determination of exclusion criteria. Randomization was performed after the baseline examination. All patients were informed that they could be randomly allocated to either the exercise or the control group. After written informed consent, sixty-five subjects were randomized. Randomization was performed by the patient drawing a sealed envelope containing a piece of folded paper with either the word \"exercise\" or \"control\" written on it. Four persons were falsely randomized (one was too old at inclusion, one had severe hip osteoarthritis, one had fibromyalgia, and one had only joint space narrowing and no significant osteophytes), and thus 61 subjects entered the study. Thirty persons were allocated to the exercise group and 31 to the control group. Patients in the control group were offered exercise classes after the six-month follow-up period.\n\nBODY.METHODS.SUBJECTS.EXERCISE GROUP:\nThe number of participants exercising together varied from two to nine. There were eight intervention groups in all. One-hour exercise sessions, twice a week for six weeks, were supervised by a physical therapist (CT). The program consisted of weight-bearing exercises aimed at increasing postural control and endurance and strength in the lower extremity (see additional file 1 for the complete exercise program). Exercises were performed at five stations at submaximal intensity (minimum 60% of maximum heart rate (HRmax)). Intensity was gradually and individually increased during the six weeks by increased lever arms or range of motion. Patients were encouraged to exercise at their most vigorous intensity possible, without losing quality in performance or severely exacerbating pain. Pain during exercise was not considered as an obstacle if the patient perceived it as \"acceptable\" and no increased symptoms were persistent after 24 hours [16]. If pain exceeded this level, exercise intensity was reduced occasionally, until the \"acceptable\" level was found. On every occasion, the heart rate of two random participants was estimated at each station using Polar pulsimeters (Polar® Accurex Plus, Polar, Sweden). The other patients had their heart rate measured by the physical therapist or themselves, palpating their carotid arteries. Notes were taken by the supervising physical therapist, on every occasion and on all patients, about exercise intensity, heart rate, and perceived exertion according to Borg's Rate of Perceived Exertion scale (RPE) at each station [17]. These data were used to give the physical therapist a view of exercise intensity and to assure the preservation or increase of intensity from time to time. Patients were encouraged to keep up and increase intensity whenever possible throughout the six weeks. Patients received a thera band to perform daily pulley exercises at home. In addition, three exercises, which were considered as the most challenging to the individual, were chosen as daily home exercises. Patients were recommended to perform some kind of weight bearing submaximal activity, such as walking or their home exercises, for at least 30 minutes or two times 15 minutes every day.\n\nBODY.METHODS.SUBJECTS.CONTROL GROUP:\nThe controls were told not to make any lifestyle changes. They met the physical therapist (CT) for one hour at three times; baseline, follow up at 6 weeks and 6 months. After six months they were offered exercise classes or instructions and a home-exercise program.\n\nBODY.METHODS.OUTCOME MEASURES.PRIMARY OUTCOME:\nThe primary outcome measure was the disease-specific Knee injury and Osteoarthritis Outcome Score (KOOS) [18,19]. The KOOS assesses the patients' self-report of pain, other symptoms, activities of daily living, sport and recreation function, and knee-related quality of life, in 42 questions which take about 10 minutes to complete. The KOOS is scored from 0 to 100, separately for each subscale, 0 indicating extreme problems and 100 indicating no problems. A change of 10 points or more is considered a clinically significant change [20]. The questionnaire and scoring manual can be found at . The Western Ontario and McMaster Osteoarthritis Index (WOMAC) [21] is included in the KOOS, and WOMAC scores can also be calculated.\n\nBODY.METHODS.OUTCOME MEASURES.SECONDARY OUTCOME:\nSecondary outcome measures were the Short Form-36 item (SF-36), ergometer test, and five tests of functional performance. The SF-36 is a generic, widely used measure of general health status, which comprises eight subscales: Physical Functioning (PF), Role-Physical (RP), Bodily Pain (BP), General Health (GH), Vitality (VT), Social Functioning (SF), Role-Emotional (RE) and Mental Health (MH) [22]. The SF-36 is self-explanatory and takes about 10 minutes to complete. The SF-36 is scored from 0 to 100, 0 indicating extreme problems and 100 indicating no problems. The subscales assessing mainly physical components (PF, RP, BP, GH) were summarized to a physical component summary score (PCS), and the mental subscales (VT, SF, RE, MH) to a mental component summary score (MCS) [23]. Values are norm-based scored, using the U.S. general population norms from 1998. Each scale has the mean of 50 and standard deviation of 10. Scale score below 50 indicates a health status below average, and a score above 50 indicates a health status above average. Questionnaires were distributed prior to randomization at baseline, after 6 weeks, and 6 months. A bicycle ergometer test and five tests of functional performance were assessed (Figure 2). Figure 2Tests of functional performance. A) Åstrand's cycle-ergometer test [24]. B) Rising on one leg from sitting on lowest possible height [25,26]. C) One-leg hop [25], [27]. D) Lateral step-up [28]. E) One-leg semi squatting; maximum number during 30 sec. [26]. F) Heel-rising on one leg; maximum number during 20 sec. [26], [29]. 1. Åstrand's bicycle-ergometer test [24] (Fig 2A). 2. Rising on one leg, from sitting on lowest possible height [25,26] (Fig 2B). 3. One-leg hop [25,27] (Fig 2C). 4. Lateral step-up [28] (Fig 2D). 5. One-leg semi squatting; maximum number during 30 seconds [26] (Fig 2E). 6. Heel-raising on one leg; maximum number during 20 seconds [26,29] (Fig 2F). Tests of functional performance were recorded on three occasions: prior to randomization at baseline, after 6 weeks, and at 6 months. To assess compliance the number of exercise occasions attended was noted.\n\nBODY.METHODS.STATISTICS:\nPost-hoc, a power analysis was performed to estimate the number of patients needed to show a clinically significant difference between groups. Estimating the least clinical significant difference to be 11 ± 15 KOOS points, a total of 30 subjects in each group were needed to detect a difference with 80% power, p = 0.05. Data were analyzed using nonparametric tests. P-values of less than or equal to 0.05 were considered to be significant, and all tests were two-tailed. To compare groups, Mann-Whitney U-test was used. Friedman's test was used for repeated measures analysis of variance. Six weeks was considered as the time-point of primary interest, and 6 months as follow-up. Wilcoxon signed rank test was performed to compare changes from baseline to six weeks and 6 months respectively. Analyses were performed using SPSS 12.0.1 for Windows [30]. The study was approved by the Research Ethics Committee at Lund University, Sweden (LU 99–98), and is in compliance with the Helsinki Declaration.\n\nBODY.RESULTS.SUBJECTS:\nThe mean age of the 61 included subjects was 56 ± 6 years, and the mean BMI was 29.5 ± 4.8 kg/m2. Patient characteristics are shown in table 1. Twenty-eight patients in each group were available for follow-up. The reasons for dropout were lack of time, reorganization at work, sudden illness, and increased knee symptoms (Figure 1). There were no clinically significant differences in baseline characteristics between the groups. Patient characteristics are shown in table 1. Table 1 Patient characteristics at baseline Exercise group n = 30 Control group n = 31 p-value Age (years) mean ± SD (range) 54.8 ± 7.1 (36–64) 57.3 ± 4.7 (46–65) 0.16 Gender number (%) women 15 (50%) 16 (52%) 0.90 BMI (kg/m) 2 mean ± SD 29.6 ± 4.5 29.5 ± 5.1 0.78 Aerobic capacity (ml O 2 /kg x min) mean ± SD 25.9 ± 6.4 25.2 ± 4.9 0.66 KOOS* pain 60 ± 18 64 ± 19 0.38 KOOS* symptoms 63 ± 20 66 ± 18 0.67 KOOS* ADL 69 ± 18 71 ± 21 0.76 KOOS* sport & recreation 34 ± 31 37 ± 29 0.54 KOOS* QOL 40 ± 15 46 ± 21 0.31 Knee Injury and Osteoarthritis Outcome Score [ 18 , 19 ] Score from 0–100, worst to best. \n\nBODY.RESULTS.COMPLIANCE:\nThe total number of performed supervised exercise sessions by the 28 patients available for follow-up in the intervention group was 302/336 (89.9%). Patients participated on average in 11 out of 12 possible exercise classes (12 classes (n = 11), 11 (n = 9), 10 (n = 6), 9 (n = 1), 2 (n = 1)). The most common reason for absence was illness not related to knee osteoarthritis, and work-related lack of time.\n\nBODY.RESULTS.BETWEEN-GROUP DIFFERENCES:\nThere was no difference between groups in pain or self-estimated function at either 6 week or 6 month follow-up. Quality of life improved significantly in the exercise group compared to the control group at 6 weeks (4.0 vs. -0.7, p = 0.05) and the results persisted at 6 months (5.1 vs. -2.3, p = 0.02, Table 2) Table 2 Comparisons of change in Knee injury and Osteoarthritis Outcome Score (KOOS) ‡ [ 18 , 19 ] subscales between exercise and control group KOOS Subscales Exercise group Control group Change in KOOS score* 95 % CI Change in KOOS score* 95 % CI p † Pain 6 w 1.8 -3.2 – 6.8 -0.3 -6.2 – 5.7 0.49 6 m 3.1 -1.9 – 8.2 -1.1 -6.6 – 4.4 0.32 Symptom 6 w 0.2 -5.1 – 5.6 -3.8 -7.7 – 0.0 0.07 6 m 1.0 -3.8 – 5.8 -3.4 -8.8 – 1.9 0.31 ADL 6 w 2.0 -2.3 – 6.3 -0.6 -7.0 – 5.8 0.96 6 m 0.9 -3.8 – 5.6 -1.9 -7.7 – 3.9 0.61 SportRec 6 w 1.2 -7.9 – 10.4 -4.4 -12.6 – 3.7 0.22 6 m 0.5 -10.1 – 11.2 -8.3 -19.5 – 2.8 0.32 QOL 6 w 4.0 -0.4 – 8.5 -0.7 -5.6 – 4.3 0.05 6 m 5.1 -0.7 – 11.0 -2.3 -9.5 – 4.9 0.02 * negative = worsening, positive = improvement † p-value for between group differences in change over time ‡ [ 18 , 19 ] The individual differences ranged from clinically significant improvement of at least 10 points to clinically significant deterioration in all KOOS subscales and in both the exercise and control group (Figure 3). Figure 3Change in KOOS pain score at six weeks. The individual change in KOOS pain at 6 weeks compared to baseline ranged from improvement to worsening, in both exercise and control group. A change of 10 points or more is considered clinically significant [20]. A similar pattern was seen for all KOOS and SF-36 subscales.\n\nBODY.RESULTS.BETWEEN-GROUP DIFFERENCES.SECONDARY OUTCOMES:\nA significant improvement was found in the exercise group compared to the control group at six weeks with regard to the SF-36 Mental Component Summary scale (MCS) (2.1 vs -1.6, p = 0.04). At six months follow-up this difference was no longer persistent (Table 3). Table 3 Comparisons of change in SF-36 Physical and Mental Components Summaries (PCS and MCS) [ 23 ] between exercise and control group. Short Form-36 item (SF-36) [22] Exercise group Control group mean 95%CI mean 95%CI p* Physical Component Summary (PCS) Baseline 42.5 24.4 – 57.5 43.8 24.2 – 57.3 0.49 Change at 6 weeks 3.0 -5.9 – 13.4 0.3 -15.2 – 12.6 0.13 Change at 6 months 3.0 -5.9 – 16.3 -0.7 -14.8 – 9.8 0.09 Mental Component Summary (MCS) Baseline 55.6 40.2 – 66.2 56.3 37.0 – 67.0 0.63 Change at 6 weeks 1.6 -10.6 – 15.0 -2.1 -16.9 – 11.5 0.04 Change at 6 months 0.7 -18.1 – 13.2 -0.7 -16.8 – 12.8 0.40 * Comparison between groups Improvements in functional performance of 0–20 % were seen in both groups at six weeks and six months. There was no difference in improvement between exercisers and controls (p = 0.08–0.9). See additional file 2 for the change in functional performance.\n\nBODY.DISCUSSION.MAIN MESSAGE:\nSix weeks of intensive exercise had no effect on self-reported pain or function in middle-aged patients with symptomatic and moderate-severe radiographic knee osteoarthritis.\n\nBODY.DISCUSSION.COMPARISONS WITH OTHER STUDIES:\nQuite opposite to previously published studies on exercise in knee osteoarthritis we found no improvement in pain or function. Possible reasons for this include our study group having moderate to severe osteoarthritis compared with mild to moderate in most previous studies, being younger than previously studied groups and the intervention being of comparably high intensity. It has been suggested that the responsiveness to exercise is modified by the loss of joint space width [31]. The homogeneity of this study population, with regard to radiographic changes, provided us the possibility to study the effects of exercise on patients with moderate to severe radiographic knee osteoarthritis. Can significant improvements of pain or self-reported function be expected in patients with radiographic knee osteoarthritis corresponding to Kellgren & Lawrence grade 3 or more? In this study, no improvements were seen on group level in pain or function. However, regular exercise in general is important to prevent diseases caused by inactivity [6], and thus patients with knee osteoarthritis should be encouraged to exercise. In clinical practice, patients with severe knee osteoarthritis should have treatments based on individual preferences and different stages of motivation [32]. It can be argued that the exercise intensity was too high for this group with moderate to severe knee osteoarthritis. Even though the intensity of each exercise was individually adapted, all individuals exercised at a minimum of 60% of HR max. It has been suggested that pain during exercise might be a protective mechanism in knee osteoarthritis, i.e. an increase in pain from too intensive exercises may restrain patients from further joint loading, which otherwise could cause further cartilage damage [33]. Patients in the current study were told to reduce the exercise intensity if pain during exercise was perceived as worse than 'acceptable', or persisted more than 24 hours. It is suggested that the different degrees of varus-valgus laxity should be taken into account in exercise interventions, to enhance the functional outcome [34,35]. Severe knee osteoarthritis is associated with a hip-knee-ankle malalignment and an increase in varus-valgus laxity compared to healthy knees [36]. It is possible that varus-valgus laxity mediated the effect of exercise on pain since all patients had radiographic changes corresponding to Kellgren and Lawrence grade III or more. Malalignment may cause increased joint loads, and greater quadriceps strength might further increase joint load by the muscles compressing the articular surfaces [37]. Younger patients are usually more physically active than elderly [38], and have higher demands on level of physical function and physical performance at work or leisure time. Thus, moderate to severe knee osteoarthritis might be perceived as more disabling by younger individuals compared to elderly. Our study population was younger (<65 years) and comprised more men (49%) than most other populations with knee osteoarthritis described in randomized controlled trials of exercise [13-15,39,40], which might have reduced the effect on self-reported function in the present study. This study showed no significant differences on self-reported pain and function either between or within groups. A post-hoc analysis was performed to study the possibility that the benefit from exercise was larger in subjects with worse pain at baseline. Fifteen patients in the exercise group were compared to 13 from the control group who had worse than total group median pain score (KOOS Pain 58 on a 0–100, worst to best scale) at baseline. The groups had comparable patient characteristics. The changes seen in these subgroups were however not different from the changes seen in the total groups. A possible limitation could be lack of power. A post-hoc analysis was performed to estimate the number of patients needed to show a clinically significant difference of 11 ± 15 KOOS-points [20]. The standard deviation of 15 is supported by results from randomized controlled trials of glucosamine supplementation [41] and a nutritional supplement [42] for knee osteoarthritis, where significant group differences were found in KOOS pain and ADL subscales. The number of subjects in each treatment arm in these RCT:s ranged from 15 to 27. The standard deviations in KOOS subscales have not previously been determined in exercise interventions. Only one of the five KOOS subscales showed a statistical significant improvement, and it can not be excluded that this result could be due to chance. The improvement of the KOOS subscale Quality Of Life in the exercise group was of doubtful clinical significance, however the improvement persisted over time, and is in accordance with previous findings of impact from exercise on mental health aspects in patients with knee osteoarthritis [31,43,44]. Group dynamics, support, or attention received may possibly have influenced the quality of life more than the exercise itself in the present study. Psychosocial factors are important determinants of physical function [45], and our results suggest that supervised exercises and follow-up are important, and that quality of life should be evaluated in osteoarthritis interventions.\n\nBODY.CONCLUSION:\nA six-week high-intensive exercise program had no effect on pain or function in middle-aged patients with moderate to severe radiographic knee OA. Some effect was seen on quality of life in the exercise group compared to the control group.\n\nBODY.COMPETING INTERESTS:\nThe author(s) declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nCT participated in design, exercise intervention, assessments and follow-ups, statistical analyses and writing. ER participated in design, analysis and interpretation of the data, and critically revised the article. IP participated in design and interpretation of the data and critically revised the article. CE initiated and obtained necessary permissions for the study, arranged the initial funding, and participated in the analyses, interpretation and revision of the manuscript. All authors read and approved the final manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: \n\nBODY.SUPPLEMENTARY MATERIAL:\nAdditional File 1Intensive exercise program CarinaClick here for file Additional File 2Tests of functional performance CarinaClick here for file\n\n**Question:** Compared to No exercise what was the result of Exercise on SF-36 Mental Component Summary scale at 6 months?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
398
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Incisional hernia after upper abdominal surgery: a randomised controlled trial of midline versus transverse incision\n\n ABSTRACT.OBJECTIVES:\nTo determine whether a transverse incision is an alternative to a midline incision in terms of incisional hernia incidence, surgical site infection, postoperative pain, hospital stay and cosmetics in cholecystectomy.\n\nABSTRACT.SUMMARY BACKGROUND DATA:\nIncisional hernias after midline incision are commonly underestimated but probably complicate between 2 and 20% of all abdominal wall closures. The midline incision is the preferred incision for surgery of the upper abdomen despite evidence that alternatives, such as the lateral paramedian and transverse incision, exist and might reduce the rate of incisional hernia. A RCT was preformed in the pre-laparoscopic cholecystectomy era the data of which were never published.\n\nABSTRACT.METHODS:\nOne hundred and fifty female patients were randomly allocated to cholecystectomy through midline or transverse incision. Early complications, the duration to discharge and the in-hospital use of analgesics was noted. Patients returned to the surgical outpatient clinic for evaluation of the cosmetic results of the scar and to evaluate possible complications such as fistula, wound dehiscence and incisional hernia after a minimum of 12 months follow-up.\n\nABSTRACT.RESULTS:\nTwo percent (1/60) of patients that had undergone the procedure through a transverse incision presented with an incisional hernia as opposed to 14% (9/63) of patients from the midline incision group (P = 0.017). Transverse incisions were found to be significantly shorter than midline incisions and associated with more pleasing appearance. More patients having undergone a midline incision, reported pain on day one, two and three postoperatively than patients from the transverse group. The use of analgesics did not differ between the two groups.\n\nABSTRACT.CONCLUSIONS:\nIn light of our results a transverse incision should, if possible, be considered as the preferred incision in acute and elective surgery of the upper abdomen when laparoscopic surgery is not an option.\n\nBODY.INTRODUCTION:\nThe rate of incisional hernia after midline incision is commonly underestimated but probably lies between 2 and 20% [1–5]. Thus, incisional hernia is a major postoperative problem. The treatment of incisional hernia is complicated by high rates of recurrences. Recently, in a randomised controlled trial published by Burger et al. [6], midline incisional hernia repair has been shown to be associated with a 10-year cumulative recurrence rate of 63 and 32% for suture and mesh repair, respectively. The midline incision is the preferred incision for surgery of the upper abdomen, despite evidence that alternatives, such as the lateral paramedian and transverse incision, exist and might reduce the rate of incisional hernia [7]. Various approaches to opening the abdomen have been advocated over time. The choice for a certain incision is dependent on the exposure necessary for the desired procedure to succeed. A midline incision, be it supraumbilical, infraumbilical or both, is an approach especially suited for emergency and exploratory surgery because of the quick and generous exposure that can be achieved within a few minutes [8, 9]. The avascular nature of the linea alba minimises blood loss during this procedure. A supraumbilical transverse incision may be utilised in case exposure of the upper abdomen is desired. During this incision, the damage inflicted to the segmental arteries and nerves is previously described as being minimal [10]. Previously, only one randomised controlled trial, comparing transverse and true midline incisions, has been published specifically addressing incisional hernia incidence [11]. To determine whether the use of a transverse incision is an alternative to a midline incision for open cholecystectomy in terms of incisional hernia incidence, surgical site infection, postoperative pain and hospital stay, this randomised controlled trial was performed. This trial was conducted in an era when laparoscopic cholecystectomy was not yet available. The possibility of low incisional hernia rates after transverse incisions and the fact that little is known about potential advantages incited us to publish the relevant results of this randomised controlled trial which has been performed in the past and has only been reported in a Dutch thesis by one of the authors (H.L.). The primary endpoint of this study was the incisional hernia incidence after 12 months of follow-up. Secondary endpoints included pain and cosmetic appearance.\n\nBODY.METHODS.PROTOCOL:\nSome 150 consecutive female patients were randomly assigned to a midline or transverse incision as an approach for elective cholecystectomy or combined cholecystectomy and cholangiography (with or without consecutive choledochotomy) (75 and 75 patients, respectively). Emergency procedures were excluded from participation. The sample size is based on an incisional hernia rate reduction from 20 to 6% at a power of 80% and an error rate of 5%. Obtaining informed consent was conducted in accordance with the ethical standards of the Helsinki Declaration of 1975. The investigation reported was performed with informed consent from all of the patients and followed the guidelines for experimental investigation with human subjects and was approved by the medical ethics committee. An independent statistician prepared closed, tamper-proof envelopes containing the random allocation (Fig. 1). Patients were randomised for one of the procedures in theatre through the opening of the envelopes.Fig. 1Flow chart of patient inclusion and follow-up Patient-related factors that were recorded were age, body mass and length and date of operation. Operation-related factors that were recorded were the exact nature of the operation, length of the incision, the thickness of the subcutaneous fat, surgeon performing the procedure, as well as the duration of the operation (skin-to-skin time). In the immediate postoperative period, the use, dose and type of analgesics was recorded and a pain score was administered. The use of analgesics (morphine 7.5 mg intra-muscular injection, 4 h minimum interval between consecutive injections) was monitored for 48 h after surgery; the pain score was administered for the first 6 days after surgery. In patients assigned to surgery through a midline incision, the skin was incised from just below the xyphoid process to just above the umbilicus. The abdominal wall was opened in the midline by incising the linea alba. A Collin type (two-bladed) self-retaining retractor was used to maintain exposure. The abdominal wall was closed in one layer using single polygalactin 910 sutures (Vicryl; Ethicon, Amersfoort, The Netherlands). The skin was consequently closed using running monofilament nylon sutures (Ethilon; Ethicon, Amersfoort, The Netherlands). Patients randomised for a transverse incision received a right-sided unilateral transverse incision between 3 and 4 cm below the costal margin. The rectus muscle was incised. The fibres of the external and internal obliques and the transverse muscles were separated in the direction of their course. Exposure was achieved through the use of a manually held single-bladed retractor. Closure of the abdominal wall was achieved by closure of the peritoneum and the posterior rectus fascia using a continuous, polygalactin 910 suture (Vicryl; Ethicon, Amersfoort, The Netherlands). The anterior rectus sheath and the fascia of the internal and external transverses were closed using simple interrupted polygalactin 910 sutures (Vicryl; Ethicon, Amersfoort, The Netherlands). Towards the end of both procedures, a Redon low-vacuum drain catheter was placed, which was guided outside the abdominal cavity approximately 5 cm from the incision. The skin was consequently closed using continuous monofilament nylon suture (Ethilon; Ethicon, Amersfoort, The Netherlands). All patients received a dose of 5,000 IU of sodium–heparin on the morning of the procedure as thrombosis prophylaxis.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nThe Pearson χ2 test was used for comparing percentages. In case of small expected numbers, a Fisher's exact test was performed. Continuous variables were analysed using the Mann–Whitney test. A P-value of 0.05 or less (two-sided) was considered to be statistically significant. Means and medians are expressed ±standard deviation (SD).\n\nBODY.METHODS.FOLLOW-UP:\nPatients returned to the surgical outpatient clinic for evaluation of the cosmetic results of the scar and to evaluate possible complications, such as fistula, wound dehiscence and incisional hernia, after a minimum of 12 months follow-up. The patient and the surgeon evaluated the cosmetic results independently and were asked to rate the scar as unsatisfactory, satisfactory or fine. Furthermore, the length and width of the scar was measured.\n\nBODY.RESULTS.STUDY GROUP:\nSome 150 consecutive patients were randomised for participation in this study during an inclusion period from April 1977 until July 1979. Seventy-five patients received a transverse incision and 75 patients a midline incision (Fig. 1). One patient was withdrawn from further follow-up after developing peritonitis and consequent acute respiratory distress syndrome (ARDS) not related to the closure of the abdominal wall 2 days after surgery (transverse incision group). The patients' average age was 51.9 and 51.4 years for the midline and the transverse incision groups, respectively. Furthermore, no differences were found in the body mass and average length between the two groups (Table 1). A cholecystectomy was performed using a transverse incision in 52 patients and utilising a midline incision in 52 patients also. Fifteen and 16 patients, respectively, underwent a combined cholangiography/cholecystectomy. A further 7 and 6 patients, respectively, were treated with a cholangiography/cholecystectomy plus additional choledochotomy and the postexploratory placement of a T-tube.Table 1Baseline characteristics of the patients undergoing surgery, according to study groupVariableMidline incisionTransverse incisionn = 75n = 74Average age (years) ± SD51.9 ± 14.851.4 ± 13.8Average weight (kg) ± SD71.3 ± 14.568 ± 14.3Average length (cm) ± SD163.5 ± 7.8164 ± 7.3\n\nBODY.RESULTS.SURGEON:\nStaff surgeons performed 17% (13/75 patients) of all procedures performed through a midline incision. The remainder of the procedures through a midline incision was carried out under staff surgeon supervision. Staff surgeons performed 14% of all procedures in the transverse incisions study group (10/74 patients) and supervised the remainder. No statistically significant difference was found between the two randomised groups (P = 0.65).\n\nBODY.RESULTS.DURATION OF SURGERY:\nNo significant difference was noted in the skin-to-skin time (in min) for the two different incisions (Table 2). Surgery utilising midline and transverse incision took 56.9 ± 29.3 and 53.2 ± 26.8 min, respectively (P = 0.35). The total duration of the procedures until extubation (in min) did not differ between the midline and transverse incisions (71.0 ± 30.5 and 67.0 ± 27.3, respectively, P = 0.34).Table 2Length of incision, thickness of subcutaneous fat and skin-to-skin time, according to study groupVariableMidline incisionTransverse incisionP-valueLength of incision (mm) ± SDa164 ± 28140 ± 24<0.0001Thickness of subcutaneous fat (mm) ± SDa34.5 ± 13.030.3 ± 12.40.05Skin-to-skin time (min) ± SDa56.9 ± 29.353.2 ± 26.80.40Width of scar (mm) ± SDb8.3 ± 1.43.3 ± 1.2<0.0001aMeasured during surgery in 75 midline and 74 transverse incisionsbMeasured at follow-up in 63 and 60 midline and transverse incisions, respectively\n\nBODY.RESULTS.PAIN AND ANALGESICS:\nSignificantly more patients, having undergone a midline incision, reported pain on day one, two and three postoperatively (P < 0.0001, Table 3). In the midline incision group, 28/75 patients required no or only one dose of analgesics; the remainder required two or more doses. Thirty-one patients operated through a transverse incision required no analgesics or only one dose; 43 patients (the remainder) required two or more. No significant difference in the use of analgesics was found between the groups (P = 0.69).Table 3Postoperatively reported pain, according to study group, shown as the number of patients reporting pain at the time points indicated (percentage), with the remainder of patients reporting no painTime point after surgeryMidline incision n = 75Transverse incision n = 74P-valuePatients reporting pain, n (%)Patients reporting pain, n (%)3–4 h68 (91)60 (81)0.09First day64 (85)39 (53)<0.0001Second day57 (76)23 (31)<0.0001Third day28 (37)9 (12)<0.0001Fourth day5 (7)3 (4)0.72Fifth day0 (0)1 (1)0.50Sixth day0 (0)1 (1)0.50\n\nBODY.RESULTS.COMPLICATIONS:\nPostoperative complications (Table 4) were seen in 16 out of 75 patients (21%) from the midline incision group and in 15% from the transverse incision group (11 patients) (P = 0.30). Briefly, one patient in each group developed cardiac complications; 8 and 6 patients developed urinary retention after the midline and transverse incisions, respectively (P = 0.59). Surgical site infections were diagnosed in 7 and 3 patients, respectively (P = 0.33).Table 4Rate of complications after surgery, according to study group, shown as the number of patients diagnosed with complications (percentage)ComplicationMidline incisionTransverse incisionP-valuen = 75 n (%)n = 75 n (%)Cardiac1 (1)1 (1)1Urinary retention8 (12)6 (8)0.59ARDS01 (1)0.50Surgical site infection7 (9)3 (4)0.33Haemorrhage1 (1)00.50Pneumonia01 (1)0.50Total17 (23)12 (16)0.30\n\nBODY.RESULTS.DISCHARGE:\nForty-five (60%) and 42 (57%) patients from the patients having undergone a midline or a transverse incision, respectively, were discharged on day 6 or 7 postoperatively. The remaining patients from each group left hospital care on day 8 or later. The duration of hospital admission did not differ between the two types of incision (P = 0.74).\n\nBODY.RESULTS.COSMETICS:\nThe width and length of all incisions was measured during the follow-up visit (Table 2). The mean width of the scar after the healing of the midline incisions was found to be 8.3 ± 1.4 mm. The mean width of the scar after the healing of the transverse incisions was measured to be 3.3 ± 1.2 mm. This observed difference is significant (P < 0.0001). The length of the incisions was 140 ± 24 mm and 164 ± 28 mm for the transverse and the midline incisions, respectively. The difference in scar length was found to be significant (P < 0.0001).\n\nBODY.FOLLOW-UP:\nEighty-one percent of all patients operated through a transverse incision were seen during the follow-up examination (n = 60). Of the patients operated through a midline incision, 63 out of 75 were seen at the outpatient clinic (84%). The patients that were lost to follow-up could either not be traced or had deceased (Fig. 1). The minimum follow-up for the evaluation of cosmetic results and hernia incidence was 12 months and the maximum was 36 months.\n\nBODY.FOLLOW-UP.INCISIONAL HERNIA:\nFrom the patients that had undergone the procedure through a transverse incision, one (1/60; 2%) presented with an incisional hernia as opposed to 9 patients from the midline incision group (9/63; 14%); 95% confidence interval (CI) 7.5–25.4%. This difference in hernia incidence is significant (P = 0.017). No significant correlation was found between the incisional hernia rate and surgical site infection (P = 0.07).\n\nBODY.FOLLOW-UP.SUBJECTIVE COSMETICS:\nPatients and surgeons alike were asked to rate the appearance of the scar during the postoperative follow-up outpatient clinic visit. Both the surgeons and the patients found the scar resulting from the transverse incision to be more cosmetically pleasing (P < 0.0001 and P = 0.03, respectively, Table 5).Table 5Number of patients and surgeons rating the cosmetics of a scar at follow-upScoreMidline incision (n = 63)Transverse incision (n = 60)Patients, n (%)Surgeons, n (%)Patients, n (%)Surgeons, n (%)Unsatisfactory6 (10)25 (40)2 (3)6 (10)Satisfactory16 (25)27 (43)9 (15)12 (20)Fine41 (65)11 (17)49 (82)42 (70)Total63636060Difference between type of incision: patients P = 0.03; surgeons P < 0.0001\n\nBODY.DISCUSSION:\nThis prospective randomised study of transverse and midline incisions for open cholecystectomy shows that a significant reduction of incisional hernia incidence can be achieved through the use of a transverse incision. Only one other study (published in 1980) reported the incidence of incisional hernia after upper abdominal midline and unilateral transverse incision in a randomised trial. No difference between the two techniques (8 and 6% incisional hernia, respectively) was found, but the relatively short follow-up of 6 months, however, may be held accountable for this finding [11]. Three retrospective studies showed rates of incisional hernia of 3.2, 5.4 and 16.5% for midline incision and 1.3, 6.7 and 13.4% for transverse incision without statistically significant differences [12–14]. The possible reason for the rather high incidence of incisional hernia in the midline incision group (14%) may lie in the use of resorbable 910 polygalactin sutures. Nevertheless, the use of the same type of resorbable suture in the closure of the transverse incisions resulted in a 2% hernia rate. There is evidence for the importance of proper technique and choice of incision as a means to reduce incisional hernia being more important than the use of suture material [7]. Furthermore, as mentioned above, it is known that the incidence of incisional hernia in the case of a midline incision lies between 2 and 20%. From our data, the NNT (numbers needed to treat) is calculated to be 8 (95% CI 5–30) and the RRR (relative risk reduction) is 88% (95% CI 23–100%). Luijendijk et al. [15] have published a hernia rate of 2% after Pfannenstiel incisions closed using 910 polygalactin, which is in agreement with our findings in the patients randomised for a transverse incision, emphasising the importance of the incision over the choice of suture material. In our study, significantly fewer patients reported pain on day 1, 2 and 3 after transverse incisions, a result that was also described by other authors [16, 17]. Greenall et al. [18] published a contradictory report (in 1980) in which no significant difference in postoperative pain was found between midline and transverse incisions. The previously mentioned study, however, only analysed 46 out of 572 patients (8%) with regard to pain, which may explain the finding. In the same way, Lacy et al. suspended visual analogue pain scoring in a study comparing midline and transverse incisions for abdominal aortic surgery. Remarkably, the two groups in our study did not differ in terms of postoperative analgesia, a finding that is also reported by Lindgren et al. [17] and Donati et al. [19]. In our study, surgeons as well as patients were significantly more satisfied with the aesthetic appearance after a transverse in comparison with a midline incision. The scars after transverse incisions were found to be significantly shorter and less wide than the midline incisions, which may account for the observed difference. A possible reason for this is that a transverse incision is executed parallel to the prevailing direction of the skin lines on the abdomen and, therefore, the tension on the wound and consequent scar is low. Cholecystectomy has come a long way since this trial. The introduction and widespread acceptance of laparoscopic technique as the treatment of choice has rendered open cholecystectomy to be an operation for exceptional, and perhaps surgically difficult, circumstances. Nowadays, the study reported is hardly feasible, yet, the results are still applicable and very relevant for other surgical procedures in the (upper) abdomen. Knowledge of the favourable results of a transverse incision may aid surgeons in their choice when finding themselves in the unfortunate position of needing conversion to open cholecystectomy. In conclusion, this investigation on transverse incisions might be helpful in reducing the incidence of incisional hernia in patients after open cholecystectomy. The midline incision is a preferred manner to achieve exposure of the abdominal cavity and is considered to be easily performed and quick. Although the midline incision is generally accepted, the incidence of incisional hernias is surprisingly high [1–5]. The choice for a particular incision should not only be based on exposure, but also on hernia incidence reduction, especially since recurrence rates after hernia repair are reported to be very high. Furthermore, the recurrence rate after incisional hernia repair is a disappointing 63 and 32% for suture and mesh repair, respectively [6]. In the light of these results, incisional hernia prevention is warranted. In this investigation, it is shown that a significant reduction (from 14.5 to 1.7%) of incisional hernia incidence was achieved by using a transverse incision. Hence, a transverse incision should be considered as the preferred incision in acute and elective surgery of the upper abdomen in which laparoscopic surgery is not an option. Full exposure of two quadrants is feasible through the use of a unilateral transverse incision in, for example, biliary, bariatric, liver and colonic surgery. The transverse incision should be part of the abdominal surgeon's armamentarium and is a preferable incision to prevent the high incidence of incisional hernia after abdominal surgery.\n\n**Question:** Compared to Midline incision what was the result of Transverse incision on Surgery duration?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
240
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: A prospective, contralateral comparison of photorefractive keratectomy (PRK) versus thin-flap LASIK: assessment of visual function\n\n ABSTRACT.PURPOSE:\nTo compare differences in visual acuity, contrast sensitivity, complications, and higher-order ocular aberrations (HOAs) in eyes with stable myopia undergoing either photo-refractive keratectomy (PRK) or thin-flap laser in situ keratomileusis (LASIK) (intended flap thickness of 90 μm) using the VISX Star S4 CustomVue excimer laser and the IntraLase FS60 femtosecond laser at 1, 3, and 6 months postoperatively.\n\nABSTRACT.METHODS:\nIn this prospective, masked, and randomized pilot study, refractive surgery was performed contralaterally on 52 eyes: 26 with PRK and 26 with thin-flap LASIK. Primary outcome measures were uncorrected distance visual acuity (UDVA), corrected distance visual acuity (CDVA), contrast sensitivity, and complications.\n\nABSTRACT.RESULTS:\nAt 6 months, mean values for UDVA (logMAR) were −0.043 ± 0.668 and −0.061 ± 0.099 in the PRK and thin-flap LASIK groups, respectively (n = 25, P = 0.466). UDVA of 20/20 or better was achieved in 96% of eyes undergoing PRK and 92% of eyes undergoing thin-flap LASIK, whereas 20/15 vision or better was achieved in 73% of eyes undergoing PRK and 72% of eyes undergoing thin-flap LASIK (P > 0.600). Significant differences were not found between treatment groups in contrast sensitivity (P ≥ 0.156) or CDVA (P = 0.800) at postoperative 6 months. Types of complications differed between groups, notably 35% of eyes in the thin-flap LASIK group experiencing complications, including microstriae and 2 flap tears.\n\nABSTRACT.CONCLUSION:\nUnder well-controlled surgical conditions, PRK and thin-flap LASIK refractive surgeries achieve similar results in visual acuity, contrast sensitivity, and induction of HOAs, with differences in experienced complications.\n\nBODY.INTRODUCTION:\nRefractive surgery is one of the most commonly performed elective procedures and will likely maintain its popularity as ablation techniques become more refined and understanding of corneal wound healing improves. Two of the most common methods of refractive surgery are photorefractive keratectomy (PRK) and laser in situ keratomileusis (LASIK). The rapid improvement in vision and lack of postoperative pain associated with LASIK has made this the preferred option with patients compared with PRK, which has greater postoperative discomfort and prolonged recovery of visual acuity.1 Recently, there has been renewed interest in PRK because of increasing concerns of complications associated with LASIK flap creation, including dry eye, corneal ectasia, and flap tears.2–5 Thin-flap LASIK attempts to gain benefits of both techniques by creating a flap of between 80 and 90 μm.6–8 Use of a thinner flap results in a more biomechanically stable cornea and decreases incidence of ectasia given the thicker residual stroma.3,9 Cutting a thinner LASIK flap is less invasive to the nerves within the corneal stroma, decreasing the severity and duration of dry eye, possibly by preserving corneal sensation and blinking rate.10–14 Flap creation avoids corneal epithelium removal, allowing reduced healing time and less haze and scarring.15 The present contralateral study compares the outcomes of eyes that have undergone PRK or thin-flap LASIK using the VISX STAR S4 excimer laser (VISX Incorporated, Santa Clara, CA), with flaps created with intended thicknesses of 90 μm using the IntraLase FS60 femtosecond laser (Abbott Medical Optics [AMO], Santa Ana, CA).\n\nBODY.METHODS:\nData from myopic eyes were analyzed, with or without astigmatism, in which the dominant eye was randomized (Research Randomizer software – Urbaniak, www.randomizer.org) to PRK or thin-flap LASIK (90 μm flap) and the nondominant eye underwent the alternative treatment. All PRK and thin-flap LASIK treatments were performed using the VISX Star S4 CustomVue laser at the John A. Moran Eye Center, Salt Lake City, Utah, between February 2008 and July 2009. All surgeries were overseen by two surgeons (M.M., M.D.M.). The research protocol was approved by the University of Utah Hospital Institutional Review Board. All patients included in this study met the US Food and Drug Administration guidelines for VISX CustomVue LASIK. Mean age of patient, 13 men and 13 women, was 30.8 years (range: 23–46). Twenty-six patients (52 eyes) with stable myopia (1.5–8.5 diopters [D]) and astigmatism (0.242–3.11 D) were enrolled in the study. Eleven patients excluded from this study had clinically significant lens opacities, previous corneal or intraocular surgery, keratoconus, unstable refraction, autoimmune disease, immunosuppressive therapy, or were pregnant or breastfeeding. Correction was made for distance and patients desiring monovision correction were excluded. Contact lenses were discontinued 2 weeks prior to screening for soft contact lens wearers and 6 weeks prior to screening for rigid gas permeable lens wearers. All patients had a preoperative examination including assessment of uncorrected distance visual acuity (UDVA), corrected distance visual acuity (CDVA), tonometry, slitlamp examination of the anterior segment, and dilated fundus examination. Manifest and cycloplegic refractions were repeated on 2 separate visits to ensure reliability and stability. Corneal topography and thickness were measured using the Orbscan II v.3.0 (Bausch and Lomb, Rochester, NY). All eyes received 5 preoperative wavefront analyses with the VISX CustomVue WaveScan aberrometer v.3.62 (Fourier) (AMO), without pharmacologic intervention, under mesopic conditions, with a minimum pupil diameter of 6.0 mm. The contralateral study design was made so that each eye could act as a control for the fellow eye in each patient, allowing for study groups to be well matched. There were no violations in the randomization; all patients were analyzed as originally assigned. The randomization protocol was generated before the trial and known only to the study coordinator. In all patients, the emmetropic correction target was based on manifest refraction and wavefront analysis. All flaps were created with the IntraLase FS60 femtosecond laser at 60 kHz in a raster pattern with bed energy of 1.15 μJ, side-cut energy of 2.00 μJ, and pocket enabled. The flaps were created with an intended thickness of 90 μm, diameter of 8.4 to 9.0 mm, superior hinge angle of 55°, and a side-cut angle of 70°. Intraoperative pachymetry or optical coherence tomography were not performed to evaluate actual flap thicknesses. If the 8.0 mm maximum intended ablation diameter exceeded the flap diameter, the hinge and flap were shielded during ablation. Postoperatively, each eye undergoing thin-flap LASIK received 1 drop of gatifloxacin 0.3% (Zymar; Allergan Inc, Irvine, CA), prednisolone acetate 1% (Pred Forte, Allergan Inc), ketorolac tromethamine 0.4% (Acular LS, Allergan Inc.), and a bandage soft contact lens (Softlens Plano T, Bausch and Lomb, Rochester, NY). The prednisolone acetate was continued hourly during the first preoperative day and 4 times daily for an additional 6 days. The gatifloxacin was continued 4 times daily for 1 week. In eyes undergoing PRK all eyes had their corneas cooled with 15 mL of BSS (2.8–3.9°C) immediately following ablation. This was followed by 1 drop of a gatifloxacin 0.3% (Zymar), prednisolone acetate 1% (Pred Forte), ketorolac tromethamine 0.4% (Acular LS) and a bandage soft contact lens (Softlens Plano T). Ketorolac tromethamine was continued 4 times a day for 3 days and then discontinued. Gatifloxacin and prednisolone acetate were continued 4 times a day for 1 week with a subsequent steroid taper over 2 to 3 months per surgeon preference. Mitomycin C was not administered to any patient in the study at any time. Both bandage soft contact lenses were removed simultaneously once re-epithelialization was complete, typically on postoperative days 3 to 5. Patients were seen 1 day, 1 week, 1 month ± 10 days, 3 months ±14 days, and 6 months ±14 days. At all follow-up examinations, UDVA and CDVA were tested using a standard Snellen eye chart. Visual acuity was recorded in both Snellen notation and logarithm of the minimum angle of resolution (logMAR) format. Contrast sensitivity was measured in controlled mesopic conditions at 3, 6, 12, and 18 cycles per degree (cpd) using the Vectorvision CSV-1000E chart (Vectorvision, Greenville, OH). Higher-order aberrations (HOAs), including coma Z(3,1), trefoil Z(3,3), and spherical aberration Z(4,0), were measured using the CustomVue WaveScan at a mean diameter of 6 mm. Undilated scans of both eyes were taken preoperatively and 1, 3, and 6 months postoperatively. Primary outcome measures were UDVA, CDVA, contrast sensitivity, and complications. HOAs were measured and trended within groups as secondary measures. After the study was completed, the results were compiled and the data unmasked for statistical analysis. Refractive error, visual acuity, and HOAs were treated as continuous variables and analyzed for significance by independent t-tests. In all tests, P values <0.05 were considered statistically significant. Data analysis was done using Microsoft Excel (Microsoft Corp, Redmond, WA).\n\nBODY.RESULTS:\nMean preoperative measurements of UDVA, CDVA, sphere, and cylinder are shown in Table 1. 25 of 26 patients (50 eyes) completed the study at postoperative 6 months. One eye in the thin-flap LASIK group required PRK retreatment following a flap tear and both eyes from this patient were therefore removed from analysis of visual acuity, contrast sensitivity, and HOAs as the retreatment prevented the ability to distinguish results between the 2 surgical methods. The eyes from this patient were still included in the analysis of complications.\n\nBODY.RESULTS.VISUAL ACUITY:\nTable 2 shows visual acuity outcomes at 1, 3, and 6 months postoperatively. Statistically significant differences were found between PRK and thin-flap LASIK in UDVA at 1 month postoperatively, with thin-flap LASIK eyes showing more improvement in UDVA. Visual acuities were not statistically different between the groups at 3 or 6 months.\n\nBODY.RESULTS.STABILITY, EFFICACY, AND PREDICTABILITY:\nTable 3 shows stability, efficacy, and predictability outcomes postoperatively at 1, 3, and 6 months. CDVA was statistically different between groups at 1 month, with 24% of the PRK group losing a line or more from preoperative values, while 9% of eyes in the thin-flap LASIK group lost only 1 line at 1 month. No eyes in the thin-flap LASIK group lost more than 1 line. Also, 39% of eyes in the thin-flap group gained a line by 1 month compared with only 12% of eyes in the PRK group. At 6 months 64% and 56% of eyes had gained a line or more of CDVA in the PRK and thin-flap LASIK groups, respectively (P = 0.462).\n\nBODY.RESULTS.CONTRAST SENSITIVITY:\nContrast sensitivity measurements at 3, 6, 12, and 18 cycles per degree (cpd) in each group are shown in Figure 1. There were no differences between groups at any cpd at any time in the study (P ≥ 0.156). The thin-flap LASIK group showed no change in contrast sensitivity postoperatively (P > 0.131), while patients in the PRK group had a slight decrease in contrast sensitivity at 1 month seen at 3 and 12 cpd (P = 0.004) and (P = 0.025), respectively. At 6 months contrast sensitivity in the PRK group was still significantly decreased from baseline at 3 cpd (P = 0.013), although it did not reach a statistically significant difference at 3 months (P = 0.101).\n\nBODY.RESULTS.COMPLICATIONS:\nTypes of complications differed between the 2 groups. In the PRK group, 2 cases of epithelial defects occurred by 1 week, but had completely resolved by 6 months. Three eyes in the PRK group had mild haze appearing as early as 1 week postoperatively. Haze remained in only 1 eye at 6 months, but was classified as minimal and had no effect on UDVA or CDVA. Nine eyes (35%) in the thin-flap LASIK group experienced complications. In the thin-flap LASIK group, flap debris (1 eye), diffuse lamellar keratitis (DLK, 1 eye), and an epithelial cyst at the edge of 1 flap were observed, with no loss of UDVA or CDVA, and all resolved by 6 months. Microstriae were observed in 6 eyes, one of which was the eye described above with flap debris and the other was the eye with DLK, with no associated loss of UDVA or CDVA, with epithelial proliferation noted as filling the microstria and making them less apparent. Two eyes in the thin-flap LASIK group experienced flap tears intraoperatively – one resulting in mild flap edge scarring by 6 months that had no significant effect on visual function, and the other case affecting vision at 1 month postoperatively which was retreated with PRK at 3 months. As a result of the retreatment with the counter surgical technique, the ability to accurately compare visual acuity, contrast sensitivity, and HOAs between the 2 surgical methods was limited and both eyes from this patient were removed from analysis of these measures, but were still included in the analysis of complications.\n\nBODY.RESULTS.HIGHER-ORDER ABERRATIONS:\nAt postoperative 1, 3, and 6 months, 24 (96%), 25 (100%), and 24 (96%) eyes, respectively, in each group completed CustomVue WaveScan analysis. Total root-mean square (RMS) HOAs, coma, trefoil, and spherical aberrations are compared in Figure 2. There were no significant differences between groups in any HOAs throughout the study (P ≥ 0.101), with all P values at 6 months ≥0.63. In both groups, total HOAs (P < 0.008), spherical (P < 0.002), and coma (P = 0.008 at 3 months; P = 0.024 at 6 months) aberrations were significantly increased compared with preoperative conditions. Trefoil showed no significant change throughout the study in either group (P = 0.298).\n\nBODY.DISCUSSION/CONCLUSION:\nThe present study confirms that PRK and thin-flap LASIK are effective surgeries for the correction of low to moderate myopia. Although thin-flap LASIK showed superior visual results in the early postoperative period there was no statistically significant difference in outcomes of UDVA, CDVA, contrast sensitivity, or total RMS HOAs between PRK and thin-flap LASIK by 6 months. In a similar study comparing PRK and thin-flap LASIK, Slade et al also found that UDVA results were better in the thin-flap group early on and equalized by 6 months.16 Our study showed a similar trend, with no significant differences in any of the primary outcomes at 6 months, and with no difference in UDVA at 3 months. Visual regression in our study was similar to outcomes in Slade's study in which 42% of the PRK group lost a line or more of CDVA and 22% of the thin-flap LASIK group lost 1 line at 1 month postoperatively. Despite the use of custom ablation, postoperative increases in total HOAs, sphere, and coma were noted in our study, as also seen by Slade et al, although they noted that the increase in sphere and coma aberrations was significantly higher in the PRK group at 1 and 3 months postoperatively. As found in previous studies, there was no significant change found in trefoil at any time postoperatively.17,18 Our study showed no difference in induction of HOAs between groups at any time. Although increases in HOAs after refractive surgery have been correlated with decreases in contrast sensitivity in other studies, we demonstrate that increases in total RMS, sphere, and coma were seen postoperatively in both groups without a reliable decrease in contrast sensitivity.19,20 Slade's group found that contrast sensitivity was better in the thin-flap group at all postoperative points in the study, which may have been related to their finding of lower induction of sphere and coma aberrations in the thin-flap group compared with the PRK group. The authors recognize that the Slade study had a larger population size (n = 50 per group) and would have increased power to detect significant differences. Our study would have had increased power of analysis with a similar study group size, but results from analysis of HOAs would not likely change as P values for all HOAs at 6 months were ≥0.63. It would be difficult to make any such correlation between contrast sensitivity and HOAs from the results of this study. A loss of CDVA has been associated with the development of corneal haze in other studies, but as mentioned above none of the patients with visual regression developed haze.21–23 Findings in other studies showing that the biomechanics of eyes that have received thin-flap LASIK treatment are indistinguishable from those of PRK have led to suggestions that thin-flap LASIK is the best approach to LASIK.16 Although the present study did not find any statistically significant differences between thin-flap LASIK and PRK in terms of visual quality at 6 months, complications dealing with flap integrity in the thin-flap LASIK group were present which are not complications found in PRK. Although PRK remains a viable option for those unable to undergo LASIK, the use of thinner flaps may eliminate some of the complications seen with traditional LASIK. Larger studies are needed to better compare the complication rates of both methods and to determine how effective thin-flap LASIK will be in achieving the benefits of PRK and LASIK while avoiding the risks associated with each method. While thinner LASIK flaps attempt to preserve the biomechanical stability of the corneal stroma, at the same time, the flap itself becomes less stable, as was noted with the 2 flap tears and other complications occurring in the thin-flap LASIK group in this study. A study by Espandar and Meyer24 showed that most complications in flaps created by IntraLase femtosecond laser occurred at the hinge, which is where the 2 flap tears that occurred in this study. A thinner flap hinge would be biomechanically less stable and would increase the likelihood of intraoperative flap tear occurrence as well. Six of the 9 eyes with complications in the thin-flap LASIK group had microstriae, which are caused by the flattening of a weak corneal flap unable to maintain its curvature over the small area of stroma removed during ablation. The biomechanics of the flap and hinge, however, cannot be evaluated by the design of this study as analysis was done based on intended flap thickness, which has been shown to vary with the IntraLase FS60 femtosecond laser.25 The study could have been strengthened had intraoperative pachymetry or OCT been performed. Creating a flap with increased integrity would help prevent microstriae from forming and would also provide for a stronger hinge that would be less susceptible to flap tear. Possible ways to optimize flap integrity include modification of hinge and side-cut angle creation, as well as improved planarity and microdisruption of flap edges. This will allow improved adhesion of the flap to the underlying stroma. Continued improvements in laser technology may allow for safer creation of thinner flaps, helping to provide evidence for superior outcomes in thin-flap LASIK, permitting the biomechanical stability of PRK with the visual recovery of LASIK. Custom flap formation that minimizes weak areas susceptible to tearing will be helpful in achieving this difficult balance between corneal and flap integrity.\n\n**Question:** Compared to Pre-surgery baseline what was the result of Photo-refractive keratectomy (PRK) on Contrast sensitivity at 6 months seen at 3 cpd?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
271
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Randomized Clinical Trial of Laparoscopic Versus Open Repair of the Perforated Peptic Ulcer: The LAMA Trial\n\n ABSTRACT.BACKGROUND:\nLaparoscopic surgery has become popular during the last decade, mainly because it is associated with fewer postoperative complications than the conventional open approach. It remains unclear, however, if this benefit is observed after laparoscopic correction of perforated peptic ulcer (PPU). The goal of the present study was to evaluate whether laparoscopic closure of a PPU is as safe as conventional open correction.\n\nABSTRACT.METHODS:\nThe study was based on a randomized controlled trial in which nine medical centers from the Netherlands participated. A total of 109 patients with symptoms of PPU and evidence of air under the diaphragm were scheduled to receive a PPU repair. After exclusion of 8 patients during the operation, outcomes were analyzed for laparotomy (n = 49) and for the laparoscopic procedure (n = 52).\n\nABSTRACT.RESULTS:\nOperating time in the laparoscopy group was significantly longer than in the open group (75 min versus 50 min). Differences regarding postoperative dosage of opiates and the visual analog scale (VAS) for pain scoring system were in favor of the laparoscopic procedure. The VAS score on postoperative days 1, 3, and 7 was significant lower (P < 0.05) in the laparoscopic group. Complications were equally distributed. Hospital stay was also comparable: 6.5 days in the laparoscopic group versus 8.0 days in the open group (P = 0.235).\n\nABSTRACT.CONCLUSIONS:\nLaparoscopic repair of PPU is a safe procedure compared with open repair. The results considering postoperative pain favor the laparoscopic procedure.\n\nBODY.INTRODUCTION:\nThe incidence of perforated peptic ulcer (PPU) has declined over the past several years because of the introduction of anti-ulcer medication and Helicobacter eradication therapy [1, 2]. Nevertheless the incidence and mortality of PPU is 5–10%. The mortality will increase up to 50% if the perforation exists for more than 24 h [3, 4]. There are several options for treatment of PPU, but the preferred treatment is surgery by upper abdominal laparotomy [5, 6]. Mouret et al. published the first results of laparoscopic repair in 1990 [7]. He concluded that it was a good method that probably reduced postoperative wound problems and adhesions. After the success of laparoscopic cholecystectomy and other laparoscopic procedures, it was thought that patients would have less pain and a shorter hospital stay after laparoscopic correction of PPU [8, 9]. Various studies have shown that laparoscopic suturing of the perforation is feasible, but there is still no proof of real benefits of laparoscopic correction [3, 6, 10–12]. Therefore we performed a multicenter randomized trial comparing open correction of PPU with laparoscopic repair.\n\nBODY.METHODS.PARTICIPANTS:\nPatients with symptoms of the clinical diagnosis of PPU were included in nine medical centers in the Netherlands participating in the LAMA (LAparoscopische MAagperforatie) trial between March 1999 and July 2005. Eligible patients were informed of the two surgical approaches and were invited to participate in the study. Exclusion criteria were the inability to read the Dutch language patient information booklet, inability to complete informed consent, prior upper abdominal surgery, and current pregnancy. The ethics committees of all participating institutions approved the trial.\n\nBODY.METHODS.RANDOMIZATION:\nSurgeons contacted the study coordinator after the patients had provided informed consent and randomization took place by opening a sealed envelope. The envelope randomization was based on a computer-generated list provided by the trial statistician.\n\nBODY.METHODS.SURGICAL PROCEDURE:\nAll patients received intravenous antibiotics prior to operation and were allocated for Helicobacter pylori eradication therapy according to established guidelines [13]. The open surgical procedure was performed through an upper abdominal midline incision. Closure of PPU was to be achieved by sutures alone or in combination with an omental patch. After repair of the defect cultures were drawn from the peritoneal fluid, after which the peritoneal cavity was lavaged. During lavage it was permissible to insufflate the stomach to test for leakage of the closed defect. No method was specified for closing the abdomen. Laparoscopic repair was performed with the patient and the team set up in the \"French\" position. Trocars were placed at the umbilicus (video scope) and on the left and right midclavicular line above the level of the umbilicus (instruments). If necessary a fourth trocar was placed in the subxiphoid space for lavage or retraction of the liver. Surgeons were free to use either 0° or 30° video scopes for the procedure. The rest of the procedure was identical to that described above for open repair. No method was specified for closing the trocar incisions.\n\nBODY.METHODS.POSTOPERATIVE FOLLOW-UP:\nPostoperative pain was scored by means of a visual analog scale (VAS) for pain on days 1, 3, 7, and 28 ranging from 0 (no pain) to 10 (severe pain). In addition, the days during which opiates were used by the patients were registered. All complications, minor and major, were monitored. The treating surgeons determined time of discharge on the basis of physical well-being, tolerance of a normal diet, and ability to use the stairs. For this reason, this was an unblinded trial. Postoperative hospital stay without correction for time spent in hospital as a result of non-medical reasons (inadequate care at home) was calculated. Patients were invited to attend the outpatient clinic at 4 weeks, 6 months, and one year postoperatively. They were asked to complete forms related to pain and use of analgesics.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData analysis was carried out according to the intention-to-treat principle as established in the trial protocol. Data were collected in a database, and statistical analyses were performed with the Statistical Package for Social Sciences for Windows (SPSS 15.0, SPSS Inc., Chicago, IL). A researcher blinded to the nature of the procedures performed all data analyses. The primary outcome of the trial was duration of hospital stay. The power analysis was performed on basis of a reduction in hospital stay by 1.5 days (10–8.5 days from admission) in favor of the laparoscopically treated group using a β of 0.80 and an α of 0.05. This resulted in a trial size of 50 patients per group. The Pearson chi-squared test was used to compare categorical variables, and the Mann-Whitney U-test was used to compare continuous variables as we could not assume normal distribution because of the relatively small numbers. In Tables 1–6 medians and interquartile ranges (IQR) are reported. All data were analyzed according to the intention-to-treat principle; i.e., patients remained in their assigned group even if during the procedure the surgeon judged the patient not to be suitable for the technique assigned or if conversion was required. Null hypotheses were tested two-sided and a P value of 0.05 or less was considered statistical significant.Table 1Baseline parametersLaparoscopic repairOpen repairP valuen = 52 n = 49 Male:female ratio1.3:11.9:1Median age (years) + IQR 66 (25.8)59 (29.5)0.185Median BMI (kg/m2) + IQR23 (4)22 (5)0.118Median duration of symptoms (h) + IQR11 (17)11 (19)0.948Median blood pressure systolic (mmHg) + IQR125 (38.5)130 (36.5)0.457Median blood pressure diastolic (mmHg) + IQR75 (25.5)75 (24.5)0.596Median heart rate (beats/min) + IQR 88 (34.0)92 (21)0.403Median body temperature (°C) + IQR 36.9 (0.92)36.8 (1.5)0.658Mannheim Peritonitis Index + IQR19.5 (8.25)16 (14)0.386Median white cell count (×109/l) + IQR 12.1 (8.9)12.1 (7.75)0.467Median ASA score + IQR 1.0 (1.0)1.5 (1.0)0.902IQR interquartile range, difference between 25th percentile and 75th percentile; BMI body mass indexASA American Society of Anesthesiologists Association score\n\nBODY.RESULTS.PATIENTS:\nA total of 109 patients were included in the trial based on a high suspicion of PPU (Fig. 1). Eight patients were excluded during operation because no gastric perforation was detected or a defect in other parts of the digestive tract was uncovered. Data for these patients were not collected and the patients were excluded from further analysis. The remaining 101 patients made up the study population; their baseline parameters are given in Table 1. Fifty-two patients were randomized for laparoscopic repair and 49 for open repair of the perforation. Forty patients were female. The mean age of the patients was 61 years. The BMI (body mass index) was equally distributed between the groups, with a median of 22.5. Patients in both groups had been suffering from symptoms for a mean duration of 11 h, and those in the laparoscopy group presented with a median Mannheim Peritonitis index [14] of 19.5, whereas those in the open group had a median Mannheim Peritonitis index of 16.Fig. 1Patient flow chart Thirty patients reported the use of non-steroidal anti-inflammatory drugs (NSAIDs; 17 laparoscopic versus 13 open), and 10 patients used proton pump inhibitors (6 laparoscopic versus 4 open). Patient history revealed gastric ulcer disease in 19 patients.\n\nBODY.RESULTS.INTRAOPERATIVE FINDINGS:\nThe discovered ulcer perforations were found to have a mean diameter of 10 mm, which did not differ between groups (Table 2). Location of the perforated ulcers was distributed equally between groups. Defects were located in the prepyloric region (n = 41), the postpyloric region (n = 34), and at the pylorus (n = 20). The median volume of lavage fluid used was 1,000 ml (range: 100–5,000 ml). The surgeon decided the amount of lavage used. There was no consensus on how much was necessary. Median blood loss did not differ between groups. Skin-to-skin time differed by 25 min, favoring open repair of PPU (Table 2).Table 2Intraoperative findingsLaparoscopic repairOpen repairP valuen = 52n = 49Median size of perforation (mm) + IQR10.0 (7.0)7.0 (6.0)0.379Number of patients with defect Pyloric812 Postpyloric2014 Prepyloric1922 Median volume of lavage (ml) + IQR1,000 (1,500)1,000 (1,425)1.000 Median bloodloss (ml) + IQR10.0 (40.0)10.0 (50.0)0.423 Skin to skin time (min) + IQR75 (47.2)50 (25.5)0.000\n\nBODY.RESULTS.INTRAOPERATIVE COMPLICATIONS:\nConversion to open surgery was required in four patients (8%). Reasons for conversion included the inability to visualize the ulcer defect because of bleeding (n = 1/52; 2%), inability to reach the defect because of perforation in the vicinity of the gastroduodenal ligament and because of a dorsal gastric ulcer (n = 2/52; 4%), and inability to find the perforation (n = 1/52; 2%).\n\nBODY.RESULTS.POSTOPERATIVE COMPLICATIONS:\nComplications were statistically equally distributed between the two groups (Table 3). There were 12 complications in 9 patients in the laparoscopic group and 24 complications in 15 patients in the open group. Mortality was 4% in the laparoscopic group and 8% in the open group. In the laparoscopic group death was caused by sepsis due to leakage at the repair site. In the open group 3 patients died because of pulmonary problems (ARDS, pneumonia), and 1 patient died after complications following a cerebrovascular accident (CVA) combined with respiratory insufficiency.Table 3Postoperative complicationsLaparoscopic repairOpen repairP valuen = 52n = 49Pneumonia21Respiratory insufficiency13ARDS1Cardiac problems22Sepsis31Leakage at repair site2Abscess3Ileus1Fascial dehiscence1Wound infection3Urinary tract infection2Incisional hernia1Cerebrovascular accident1Death24Total complications12240.061Total of patients with complications ≥19 (18%)15 (36%)\n\nBODY.RESULTS.DISCHARGE:\nTime to discharge was similar for the two groups, with a median difference of 1.5 days (Table 4). Nasogastric decompression could be stopped after 2–3 days in both groups (Table 4).Table 4Duration of hospital stay, nasogastric decompressionLaparoscopic repairOpen repairP valuen = 52n = 49Median hospital stay (days) + IQR6.5 (9.3)8.0 (7.3)0.235Median duration of nasogastric decompression (days) + IQR2.0 (3.0)3.0 (1.3)0.334\n\nBODY.RESULTS.PAIN:\nVisual analog pain scores were in favor of laparoscopic repair (Table 5; p < 0.005). Although the median duration of opiate use in the two groups was 1.0, the mean duration in the open group was found to be 0.6 days longer than in the laparoscopic group (Table 6).Table 5Postoperative painMedian VAS pain scoreMedian VAS pain scoreP valueLaparoscopic repairOpen repairDay 1 + IQR3.8 (3.0)5.15 (2.5)0.001Day 3 + IQR2.1 (2.5)3.0 (2.4)0.035Day 7 + IQR1.0 (2.0)1.85 (2.8)0.036Day 28 + IQR0.3 (0.7)0.0 (1.7)0.748Table 6Postoperative opiate usageOpiate requirementOpiate requirementP valueLaparoscopic repairOpen repairMedian duration (days) + IQR1.0 (1.25)1.0 (1.0)0.007Mean duration (days) ± SD1.0 ± 0.91.6 ± 0.90.007\n\nBODY.RESULTS.VAS APPEARANCE OF SCAR:\nThe VAS score for appearance of the scar left by the respective procedures (subjectively recorded in the same way as pain) differed by 2.3 points, favoring the laparoscopic procedure (7.7 vs. 5.4; P = 0.033)\n\nBODY.DISCUSSION:\nThe need for surgery for PPU has declined enormously in Europe and America with reported rates ranging from 50% to 80%, thanks to effective gastric acid-reducing medication [15]. For this reason, as well as because many surgeons prefer upper laparotomy, it took more time than expected to include 100 patients in our study. Reasons given by surgeons who prefer open repair were that it is a more familiar procedure and it can be completed faster than laparoscopy. It was also noted that patients often undergo operation at night, when the surgeon on call was not always laparoscopically trained. Other randomized trials have already shown the feasibility of laparoscopic repair of PPU [3, 4, 6, 10]. Only a few had more than 100 patients, and some emphasized results from subgroups of patients [8, 11, 12]. We did not subdivide our patients and included patients with risk factors for developing sepsis or conversion [10]. In eight of the original 109 patients (7%) it became evident during the operation that the patient had a diagnosis different from PPU. In the patients who were randomized for laparoscopy this discovery revealed the benefit of laparoscopy as a diagnostic procedure indicating either an upper or lower abdominoplasty or continuation of the laparoscopy [16]. Conversion rate in the laparoscopy group was 8% (4/52). This is much lower than that reported in literature, where conversion rates as high as 60% were found [3, 4, 6]. This maybe partially explained by the fact that only trained and experienced laparoscopic surgeons (those performing at least 50 laparoscopic procedures a year) participated in this trial, confirming the belief that this procedure should only be done by experienced surgeons [3–5]. Operating time was significantly longer in the laparoscopy group (75 min versus 50 min), which is comparable to reports in the literature [3, 10]. A possible explanation for the longer operative time is that laparoscopic suturing is more demanding [9, 17], especially if the edges of the perforation are infiltrated and friable. Sutures easily tear out and it is more difficult to take large bites and to tie knots properly. Use of a single-stitch method described by Siu et al. [18], fibrin glue, or a patch might solve this problem [12, 19]. Another reason for the increase in operating time is the irrigation procedure. Irrigating through a 5-mm or even a 10-mm trocar is time consuming, and suction of fluid decreases the volume of gas and reduces the pneumoperitoneum. There is no evidence that irrigation lowers the risk of sepsis [20], so it might only be necessary if there are food remnants in the abdomen; perhaps there is no need for it at all. One of the suspected risks of laparoscopic surgery is that of inducing sepsis by increasing bacterial translocation while establishing a pneumoperitoneum [6]. This danger could not be confirmed in our trial. Furthermore data suggest that there is a decrease in septic abdominal complications when laparosopic surgery is used [8]. Evidence already exists that laparoscopic correction of PPU causes less postoperative pain [6, 12, 17, 18]. The meta-analysis published by Lau [6] showed that eight out of ten studies showed a significant reduction in dosage of analgesics required in the laparoscopic group. Also, the three studies that had included VAS pain scores showed consistently lower pain scores, as was observed in our study as well. Whether this will lead to a better quality of life for patients, especially during the first weeks after surgery still needs to be analyzed. Although patients in our series who underwent laparoscopy had less postoperative pain, there was no difference in the length of hospital stay in our two groups. In fact, hospital stay overall in our patients was very long. This was most likely caused by the fact that many patients, especially the elderly, could not be discharged because of organizational reasons. Of the 101 patients, 41% were 70 years or older (24 in the laparoscopic group versus 17 in the open group). It appears that the age of PPU patients is increasing, and this will eventually represent a significant problem in the future [2, 3]. One benefit of the laparoscopic procedure not often mentioned in literature [6] is cosmetic outcome. Nowadays patients are aware of this benefit, and sometimes this is the reason why they demand laparoscopic surgery. In conclusion, the results of the LAMA trial confirm the results of other trials that laparoscopic correction of PPU is safe, feasible for the experienced laparoscopic surgeon, and causes less postoperative pain. Operating time was longer in the laparoscopic group and there was no difference in length of hospital stay or incidence of postoperative complications.\n\n**Question:** Compared to Conventional open approach what was the result of Laparoscopic surgery on Ulcer location ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
229
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: A prospective, contralateral comparison of photorefractive keratectomy (PRK) versus thin-flap LASIK: assessment of visual function\n\n ABSTRACT.PURPOSE:\nTo compare differences in visual acuity, contrast sensitivity, complications, and higher-order ocular aberrations (HOAs) in eyes with stable myopia undergoing either photo-refractive keratectomy (PRK) or thin-flap laser in situ keratomileusis (LASIK) (intended flap thickness of 90 μm) using the VISX Star S4 CustomVue excimer laser and the IntraLase FS60 femtosecond laser at 1, 3, and 6 months postoperatively.\n\nABSTRACT.METHODS:\nIn this prospective, masked, and randomized pilot study, refractive surgery was performed contralaterally on 52 eyes: 26 with PRK and 26 with thin-flap LASIK. Primary outcome measures were uncorrected distance visual acuity (UDVA), corrected distance visual acuity (CDVA), contrast sensitivity, and complications.\n\nABSTRACT.RESULTS:\nAt 6 months, mean values for UDVA (logMAR) were −0.043 ± 0.668 and −0.061 ± 0.099 in the PRK and thin-flap LASIK groups, respectively (n = 25, P = 0.466). UDVA of 20/20 or better was achieved in 96% of eyes undergoing PRK and 92% of eyes undergoing thin-flap LASIK, whereas 20/15 vision or better was achieved in 73% of eyes undergoing PRK and 72% of eyes undergoing thin-flap LASIK (P > 0.600). Significant differences were not found between treatment groups in contrast sensitivity (P ≥ 0.156) or CDVA (P = 0.800) at postoperative 6 months. Types of complications differed between groups, notably 35% of eyes in the thin-flap LASIK group experiencing complications, including microstriae and 2 flap tears.\n\nABSTRACT.CONCLUSION:\nUnder well-controlled surgical conditions, PRK and thin-flap LASIK refractive surgeries achieve similar results in visual acuity, contrast sensitivity, and induction of HOAs, with differences in experienced complications.\n\nBODY.INTRODUCTION:\nRefractive surgery is one of the most commonly performed elective procedures and will likely maintain its popularity as ablation techniques become more refined and understanding of corneal wound healing improves. Two of the most common methods of refractive surgery are photorefractive keratectomy (PRK) and laser in situ keratomileusis (LASIK). The rapid improvement in vision and lack of postoperative pain associated with LASIK has made this the preferred option with patients compared with PRK, which has greater postoperative discomfort and prolonged recovery of visual acuity.1 Recently, there has been renewed interest in PRK because of increasing concerns of complications associated with LASIK flap creation, including dry eye, corneal ectasia, and flap tears.2–5 Thin-flap LASIK attempts to gain benefits of both techniques by creating a flap of between 80 and 90 μm.6–8 Use of a thinner flap results in a more biomechanically stable cornea and decreases incidence of ectasia given the thicker residual stroma.3,9 Cutting a thinner LASIK flap is less invasive to the nerves within the corneal stroma, decreasing the severity and duration of dry eye, possibly by preserving corneal sensation and blinking rate.10–14 Flap creation avoids corneal epithelium removal, allowing reduced healing time and less haze and scarring.15 The present contralateral study compares the outcomes of eyes that have undergone PRK or thin-flap LASIK using the VISX STAR S4 excimer laser (VISX Incorporated, Santa Clara, CA), with flaps created with intended thicknesses of 90 μm using the IntraLase FS60 femtosecond laser (Abbott Medical Optics [AMO], Santa Ana, CA).\n\nBODY.METHODS:\nData from myopic eyes were analyzed, with or without astigmatism, in which the dominant eye was randomized (Research Randomizer software – Urbaniak, www.randomizer.org) to PRK or thin-flap LASIK (90 μm flap) and the nondominant eye underwent the alternative treatment. All PRK and thin-flap LASIK treatments were performed using the VISX Star S4 CustomVue laser at the John A. Moran Eye Center, Salt Lake City, Utah, between February 2008 and July 2009. All surgeries were overseen by two surgeons (M.M., M.D.M.). The research protocol was approved by the University of Utah Hospital Institutional Review Board. All patients included in this study met the US Food and Drug Administration guidelines for VISX CustomVue LASIK. Mean age of patient, 13 men and 13 women, was 30.8 years (range: 23–46). Twenty-six patients (52 eyes) with stable myopia (1.5–8.5 diopters [D]) and astigmatism (0.242–3.11 D) were enrolled in the study. Eleven patients excluded from this study had clinically significant lens opacities, previous corneal or intraocular surgery, keratoconus, unstable refraction, autoimmune disease, immunosuppressive therapy, or were pregnant or breastfeeding. Correction was made for distance and patients desiring monovision correction were excluded. Contact lenses were discontinued 2 weeks prior to screening for soft contact lens wearers and 6 weeks prior to screening for rigid gas permeable lens wearers. All patients had a preoperative examination including assessment of uncorrected distance visual acuity (UDVA), corrected distance visual acuity (CDVA), tonometry, slitlamp examination of the anterior segment, and dilated fundus examination. Manifest and cycloplegic refractions were repeated on 2 separate visits to ensure reliability and stability. Corneal topography and thickness were measured using the Orbscan II v.3.0 (Bausch and Lomb, Rochester, NY). All eyes received 5 preoperative wavefront analyses with the VISX CustomVue WaveScan aberrometer v.3.62 (Fourier) (AMO), without pharmacologic intervention, under mesopic conditions, with a minimum pupil diameter of 6.0 mm. The contralateral study design was made so that each eye could act as a control for the fellow eye in each patient, allowing for study groups to be well matched. There were no violations in the randomization; all patients were analyzed as originally assigned. The randomization protocol was generated before the trial and known only to the study coordinator. In all patients, the emmetropic correction target was based on manifest refraction and wavefront analysis. All flaps were created with the IntraLase FS60 femtosecond laser at 60 kHz in a raster pattern with bed energy of 1.15 μJ, side-cut energy of 2.00 μJ, and pocket enabled. The flaps were created with an intended thickness of 90 μm, diameter of 8.4 to 9.0 mm, superior hinge angle of 55°, and a side-cut angle of 70°. Intraoperative pachymetry or optical coherence tomography were not performed to evaluate actual flap thicknesses. If the 8.0 mm maximum intended ablation diameter exceeded the flap diameter, the hinge and flap were shielded during ablation. Postoperatively, each eye undergoing thin-flap LASIK received 1 drop of gatifloxacin 0.3% (Zymar; Allergan Inc, Irvine, CA), prednisolone acetate 1% (Pred Forte, Allergan Inc), ketorolac tromethamine 0.4% (Acular LS, Allergan Inc.), and a bandage soft contact lens (Softlens Plano T, Bausch and Lomb, Rochester, NY). The prednisolone acetate was continued hourly during the first preoperative day and 4 times daily for an additional 6 days. The gatifloxacin was continued 4 times daily for 1 week. In eyes undergoing PRK all eyes had their corneas cooled with 15 mL of BSS (2.8–3.9°C) immediately following ablation. This was followed by 1 drop of a gatifloxacin 0.3% (Zymar), prednisolone acetate 1% (Pred Forte), ketorolac tromethamine 0.4% (Acular LS) and a bandage soft contact lens (Softlens Plano T). Ketorolac tromethamine was continued 4 times a day for 3 days and then discontinued. Gatifloxacin and prednisolone acetate were continued 4 times a day for 1 week with a subsequent steroid taper over 2 to 3 months per surgeon preference. Mitomycin C was not administered to any patient in the study at any time. Both bandage soft contact lenses were removed simultaneously once re-epithelialization was complete, typically on postoperative days 3 to 5. Patients were seen 1 day, 1 week, 1 month ± 10 days, 3 months ±14 days, and 6 months ±14 days. At all follow-up examinations, UDVA and CDVA were tested using a standard Snellen eye chart. Visual acuity was recorded in both Snellen notation and logarithm of the minimum angle of resolution (logMAR) format. Contrast sensitivity was measured in controlled mesopic conditions at 3, 6, 12, and 18 cycles per degree (cpd) using the Vectorvision CSV-1000E chart (Vectorvision, Greenville, OH). Higher-order aberrations (HOAs), including coma Z(3,1), trefoil Z(3,3), and spherical aberration Z(4,0), were measured using the CustomVue WaveScan at a mean diameter of 6 mm. Undilated scans of both eyes were taken preoperatively and 1, 3, and 6 months postoperatively. Primary outcome measures were UDVA, CDVA, contrast sensitivity, and complications. HOAs were measured and trended within groups as secondary measures. After the study was completed, the results were compiled and the data unmasked for statistical analysis. Refractive error, visual acuity, and HOAs were treated as continuous variables and analyzed for significance by independent t-tests. In all tests, P values <0.05 were considered statistically significant. Data analysis was done using Microsoft Excel (Microsoft Corp, Redmond, WA).\n\nBODY.RESULTS:\nMean preoperative measurements of UDVA, CDVA, sphere, and cylinder are shown in Table 1. 25 of 26 patients (50 eyes) completed the study at postoperative 6 months. One eye in the thin-flap LASIK group required PRK retreatment following a flap tear and both eyes from this patient were therefore removed from analysis of visual acuity, contrast sensitivity, and HOAs as the retreatment prevented the ability to distinguish results between the 2 surgical methods. The eyes from this patient were still included in the analysis of complications.\n\nBODY.RESULTS.VISUAL ACUITY:\nTable 2 shows visual acuity outcomes at 1, 3, and 6 months postoperatively. Statistically significant differences were found between PRK and thin-flap LASIK in UDVA at 1 month postoperatively, with thin-flap LASIK eyes showing more improvement in UDVA. Visual acuities were not statistically different between the groups at 3 or 6 months.\n\nBODY.RESULTS.STABILITY, EFFICACY, AND PREDICTABILITY:\nTable 3 shows stability, efficacy, and predictability outcomes postoperatively at 1, 3, and 6 months. CDVA was statistically different between groups at 1 month, with 24% of the PRK group losing a line or more from preoperative values, while 9% of eyes in the thin-flap LASIK group lost only 1 line at 1 month. No eyes in the thin-flap LASIK group lost more than 1 line. Also, 39% of eyes in the thin-flap group gained a line by 1 month compared with only 12% of eyes in the PRK group. At 6 months 64% and 56% of eyes had gained a line or more of CDVA in the PRK and thin-flap LASIK groups, respectively (P = 0.462).\n\nBODY.RESULTS.CONTRAST SENSITIVITY:\nContrast sensitivity measurements at 3, 6, 12, and 18 cycles per degree (cpd) in each group are shown in Figure 1. There were no differences between groups at any cpd at any time in the study (P ≥ 0.156). The thin-flap LASIK group showed no change in contrast sensitivity postoperatively (P > 0.131), while patients in the PRK group had a slight decrease in contrast sensitivity at 1 month seen at 3 and 12 cpd (P = 0.004) and (P = 0.025), respectively. At 6 months contrast sensitivity in the PRK group was still significantly decreased from baseline at 3 cpd (P = 0.013), although it did not reach a statistically significant difference at 3 months (P = 0.101).\n\nBODY.RESULTS.COMPLICATIONS:\nTypes of complications differed between the 2 groups. In the PRK group, 2 cases of epithelial defects occurred by 1 week, but had completely resolved by 6 months. Three eyes in the PRK group had mild haze appearing as early as 1 week postoperatively. Haze remained in only 1 eye at 6 months, but was classified as minimal and had no effect on UDVA or CDVA. Nine eyes (35%) in the thin-flap LASIK group experienced complications. In the thin-flap LASIK group, flap debris (1 eye), diffuse lamellar keratitis (DLK, 1 eye), and an epithelial cyst at the edge of 1 flap were observed, with no loss of UDVA or CDVA, and all resolved by 6 months. Microstriae were observed in 6 eyes, one of which was the eye described above with flap debris and the other was the eye with DLK, with no associated loss of UDVA or CDVA, with epithelial proliferation noted as filling the microstria and making them less apparent. Two eyes in the thin-flap LASIK group experienced flap tears intraoperatively – one resulting in mild flap edge scarring by 6 months that had no significant effect on visual function, and the other case affecting vision at 1 month postoperatively which was retreated with PRK at 3 months. As a result of the retreatment with the counter surgical technique, the ability to accurately compare visual acuity, contrast sensitivity, and HOAs between the 2 surgical methods was limited and both eyes from this patient were removed from analysis of these measures, but were still included in the analysis of complications.\n\nBODY.RESULTS.HIGHER-ORDER ABERRATIONS:\nAt postoperative 1, 3, and 6 months, 24 (96%), 25 (100%), and 24 (96%) eyes, respectively, in each group completed CustomVue WaveScan analysis. Total root-mean square (RMS) HOAs, coma, trefoil, and spherical aberrations are compared in Figure 2. There were no significant differences between groups in any HOAs throughout the study (P ≥ 0.101), with all P values at 6 months ≥0.63. In both groups, total HOAs (P < 0.008), spherical (P < 0.002), and coma (P = 0.008 at 3 months; P = 0.024 at 6 months) aberrations were significantly increased compared with preoperative conditions. Trefoil showed no significant change throughout the study in either group (P = 0.298).\n\nBODY.DISCUSSION/CONCLUSION:\nThe present study confirms that PRK and thin-flap LASIK are effective surgeries for the correction of low to moderate myopia. Although thin-flap LASIK showed superior visual results in the early postoperative period there was no statistically significant difference in outcomes of UDVA, CDVA, contrast sensitivity, or total RMS HOAs between PRK and thin-flap LASIK by 6 months. In a similar study comparing PRK and thin-flap LASIK, Slade et al also found that UDVA results were better in the thin-flap group early on and equalized by 6 months.16 Our study showed a similar trend, with no significant differences in any of the primary outcomes at 6 months, and with no difference in UDVA at 3 months. Visual regression in our study was similar to outcomes in Slade's study in which 42% of the PRK group lost a line or more of CDVA and 22% of the thin-flap LASIK group lost 1 line at 1 month postoperatively. Despite the use of custom ablation, postoperative increases in total HOAs, sphere, and coma were noted in our study, as also seen by Slade et al, although they noted that the increase in sphere and coma aberrations was significantly higher in the PRK group at 1 and 3 months postoperatively. As found in previous studies, there was no significant change found in trefoil at any time postoperatively.17,18 Our study showed no difference in induction of HOAs between groups at any time. Although increases in HOAs after refractive surgery have been correlated with decreases in contrast sensitivity in other studies, we demonstrate that increases in total RMS, sphere, and coma were seen postoperatively in both groups without a reliable decrease in contrast sensitivity.19,20 Slade's group found that contrast sensitivity was better in the thin-flap group at all postoperative points in the study, which may have been related to their finding of lower induction of sphere and coma aberrations in the thin-flap group compared with the PRK group. The authors recognize that the Slade study had a larger population size (n = 50 per group) and would have increased power to detect significant differences. Our study would have had increased power of analysis with a similar study group size, but results from analysis of HOAs would not likely change as P values for all HOAs at 6 months were ≥0.63. It would be difficult to make any such correlation between contrast sensitivity and HOAs from the results of this study. A loss of CDVA has been associated with the development of corneal haze in other studies, but as mentioned above none of the patients with visual regression developed haze.21–23 Findings in other studies showing that the biomechanics of eyes that have received thin-flap LASIK treatment are indistinguishable from those of PRK have led to suggestions that thin-flap LASIK is the best approach to LASIK.16 Although the present study did not find any statistically significant differences between thin-flap LASIK and PRK in terms of visual quality at 6 months, complications dealing with flap integrity in the thin-flap LASIK group were present which are not complications found in PRK. Although PRK remains a viable option for those unable to undergo LASIK, the use of thinner flaps may eliminate some of the complications seen with traditional LASIK. Larger studies are needed to better compare the complication rates of both methods and to determine how effective thin-flap LASIK will be in achieving the benefits of PRK and LASIK while avoiding the risks associated with each method. While thinner LASIK flaps attempt to preserve the biomechanical stability of the corneal stroma, at the same time, the flap itself becomes less stable, as was noted with the 2 flap tears and other complications occurring in the thin-flap LASIK group in this study. A study by Espandar and Meyer24 showed that most complications in flaps created by IntraLase femtosecond laser occurred at the hinge, which is where the 2 flap tears that occurred in this study. A thinner flap hinge would be biomechanically less stable and would increase the likelihood of intraoperative flap tear occurrence as well. Six of the 9 eyes with complications in the thin-flap LASIK group had microstriae, which are caused by the flattening of a weak corneal flap unable to maintain its curvature over the small area of stroma removed during ablation. The biomechanics of the flap and hinge, however, cannot be evaluated by the design of this study as analysis was done based on intended flap thickness, which has been shown to vary with the IntraLase FS60 femtosecond laser.25 The study could have been strengthened had intraoperative pachymetry or OCT been performed. Creating a flap with increased integrity would help prevent microstriae from forming and would also provide for a stronger hinge that would be less susceptible to flap tear. Possible ways to optimize flap integrity include modification of hinge and side-cut angle creation, as well as improved planarity and microdisruption of flap edges. This will allow improved adhesion of the flap to the underlying stroma. Continued improvements in laser technology may allow for safer creation of thinner flaps, helping to provide evidence for superior outcomes in thin-flap LASIK, permitting the biomechanical stability of PRK with the visual recovery of LASIK. Custom flap formation that minimizes weak areas susceptible to tearing will be helpful in achieving this difficult balance between corneal and flap integrity.\n\n**Question:** Compared to Thin-flap laser in situ keratomileusis (LASIK) what was the result of Photo-refractive keratectomy (PRK) on Uncorrected distance visual acuity at 6 months?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
251
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Short-term comparative study of high frequency chest wall oscillation and European airway clearance techniques in patients with cystic fibrosis\n\n ABSTRACT.BACKGROUND:\nHigh frequency chest wall oscillation (HFCWO) is standard treatment for airway clearance in the USA and has recently been introduced in the UK and Europe. There is little published research comparing HFCWO with airway clearance techniques (ACTs) frequently used in the UK and Europe. The aim of this study was to compare the short-term effects of HFCWO with usual ACTs in patients with cystic fibrosis hospitalised with an infective pulmonary exacerbation.\n\nABSTRACT.METHODS:\nA 4-day randomised crossover design was used. Patients received either HFCWO on days 1 and 3 and usual ACTs on days 2 and 4 or vice versa. Wet weight of sputum, spirometry and oxygen saturation were measured. Perceived efficacy, comfort, incidence of urinary leakage and preference were assessed. Data were analysed by mixed model analysis.\n\nABSTRACT.RESULTS:\n29 patients (72% male) of mean (SD) age 29.4 (8.4) years and mean (SD) forced expiratory volume in 1 s (FEV1) percentage predicted (FEV1%) 38 (16.7) completed the study. Significantly more sputum was expectorated during a single treatment session and over a 24 h period (mean difference 4.4 g and 6.9 g, respectively) with usual ACTs than with HFCWO (p<0.001). No statistically significant change in FEV1% or oxygen saturation was observed after either HFCWO or usual ACTs compared with baseline. 17 patients (55%) expressed a preference for their usual ACT.\n\nABSTRACT.CONCLUSIONS:\nDuring both a finite treatment period and over 24 h, less sputum was cleared using HFCWO than usual ACT. HFCWO does not appear to cause any adverse physiological effects and may influence adherence.\n\nBODY.INTRODUCTION:\nThe last four decades have seen improved survival in patients with cystic fibrosis (CF). The latest figures estimate the median life expectancy of individuals with CF born in 2000–3 to be approximately 40 years.1 Respiratory failure is the major cause of morbidity and mortality in those with CF.2 Accumulation of secretions in the CF airway precipitates chronic infection, causing a progressive deterioration in lung function and eventually respiratory failure and death.3 Airway clearance techniques (ACTs) are an essential component of the management of patients with CF and are considered standard care.4 There is a range of ACTs which augment the normal mucus clearance mechanisms of the lung to facilitate expectoration. These techniques generally aim to promote secretion clearance by altering airflow and mucus viscosity. Typically, high frequency chest wall oscillation (HFCWO) produces compression of the chest wall via an inflatable jacket linked to an air pulse generator. The generator delivers an intermittent flow of air into the jacket which rapidly compresses and releases the chest wall at a variety of frequencies. Consequently, an oscillation in airflow within the airways is achieved. HFCWO has been shown to enhance central and peripheral mucus clearance.5 A number of underlying mechanisms have been hypothesised including increased airflow-mucus interaction causing a reduction in viscolelasticity, production of an expiratory airflow bias which promotes a cephalad movement of mucus and the enhancement and stimulation of ciliary activity.6 7 Published short-term evidence has demonstrated increased sputum clearance and improved pulmonary function with HFCWO compared with no treatment.8 This and other studies have also compared HFCWO with alternative ACTs. Some have demonstrated increased sputum clearance with HFCWO compared with postural drainage and percussion (PD&P).9–11 Others found no significant difference in sputum clearance between HFCWO and PD&P,8 12 13 positive expiratory pressure (PEP),8 high frequency oral oscillation13 or intrapulmonary percussive ventilation.14 Furthermore, some of these studies found no differences in efficacy related to pulmonary function between HFCWO and PD&P,8 12 13 PEP,8 15 oscillating positive expiratory pressure (Flutter, manufactured by Axcan Scandipharm Inc, Birmingham, AL, USA)16 and high frequency oral oscillation.13 One study reported an improved outcome in forced expiratory volume in 1 s (FEV1) in the longer term using HFCWO compared with PD&P.17 Few trials have compared HFCWO with alternative ACTs which are commonly used in the UK and Europe by individuals with CF. Phillips et al18 compared HFCWO (using the Hayek Cuirass) with the active cycle of breathing techniques (ACBT) in hospitalised paediatric patients. Significantly more sputum was cleared with the ACBT. The authors concluded that HFCWO was not an effective airway clearance treatment for children with CF. It is difficult to compare this study directly with those above, as the Hayek Cuirass machine has a different operating mode to the inflatable vest system. A series of Cochrane systematic reviews have found that no one ACT is superior in terms of respiratory function and efficacy.19 Of a number of published studies on HFCWO, only two were deemed of sufficient quality to be included in these randomised control trial systematic reviews.8 12 HFCWO is widely used in the USA where it is considered standard care in CF.20 It has recently been introduced to the UK and Europe, where the mainstay of care for airway clearance in CF is the ACBT, autogenic drainage (AD) and other airway clearance regimens using small devices.4 In the USA these techniques and devices tend to be considered adjuncts, with PD&P and HFCWO remaining the most common ACTs.20 While there is a body of evidence which equates HFCWO and PD&P, there is a need for further trials to compare HFCWO with alternative ACTs to provide a more relevant evidence base for HFCWO in the UK and Europe. The aim of the present study was to compare the short-term effects of HFCWO with patients' usual ACTs in those with CF admitted to hospital with an acute exacerbation of pulmonary infection. The hypothesis was that HFCWO was superior to patients' usual ACTs.\n\nBODY.METHODS.STUDY PARTICIPANTS:\nAll patients admitted to hospital who met the entry criteria were invited to participate in the study. The inclusion criteria were a diagnosis of CF (established by genotype or sweat sodium >70 mmol/l or sweat chloride of >60 mmol/l), FEV1 ≥ 20% predicted, age ≥16 years and an infective pulmonary exacerbation as defined by Thornton et al.21 Exclusion criteria were current severe haemoptysis, rib fractures, pregnancy, inability to give consent and those whose usual ACT was HFCWO. Informed written consent was obtained for all patients and the study was approved by Brompton Harefield and National Heart and Lung Institute research ethics committee.\n\nBODY.METHODS.STUDY DESIGN:\nA randomised crossover design was used to compare HFCWO with patients' usual ACTs, which allowed within-patient variability to be controlled. Over four consecutive days, patients received either HFCWO therapy on days 1 and 3 and their normal ACT on days 2 and 4 or vice versa. Allocation to HFCWO or usual ACT on day 1 was determined using a computer-generated randomisation table.\n\nBODY.METHODS.PROTOCOLS:\nPatients performed their usual ACT or received HFCWO two times daily at the same time. Before starting the study, each patient's usual ACT was reviewed by an experienced senior respiratory physiotherapist. In addition, patients were familiarised with HFCWO (The Vest). This involved the patients using The Vest for a trial period the day before the start of the study, during which time they were given the opportunity to experience all three protocol frequencies at a variety of pressures. Each airway clearance treatment session lasted 30 min and was supervised by the same physiotherapist to ensure optimisation and standardisation of usual ACT and HFCWO performance. All nebulised and inhaled medications were taken before each treatment session in accordance with the patients' individual regimens.\n\nBODY.METHODS.HIGH FREQUENCY CHEST WALL OSCILLATION:\nThe following regimen was identified as current best practice following an in-depth review of the literature and discussion with clinical experts in the USA. Using The Vest Airway Clearance System Model 4 (Hill-Rom UK Ltd, Leicestershire, UK), each patient was fitted with an appropriately-sized, full torso, inflatable, disposable vest connected to the air pulse generator via two flexible tubes. Patients remained in an upright sitting position throughout the 30 min treatment session. HFCWO was applied for 8 min at each of three frequencies in sequence (10, 13 and 15 Hz) with each frequency followed by a 2 min rest period. The pulse pressure was set according to individual patient's reported comfort at all three frequency settings. During both the HFCWO and rest periods, patients were instructed to huff or cough as they felt necessary in order to expectorate loosened bronchial secretions.\n\nBODY.METHODS.USUAL ACT:\nUsual ACTs were in accordance with the guidelines of the International Physiotherapy Group for Cystic Fibrosis.22 Patients performed their usual ACT for 30 min, and for patients practising an assisted ACT, the physiotherapist provided percussion. Patients were allowed to perform combined ACTs where this was their usual practice. This reflected current international practice more accurately and recommendations that ACTs be adapted on an individual basis.23\n\nBODY.METHODS.OUTCOME MEASURES:\nThe primary outcome measure was wet weight of sputum expectorated during a treatment session. Patients were instructed to expectorate all sputum into a preweighed pot during and for 30 min following each treatment session. They were also instructed to collect sputum expectorated at all other times during each 24 h period. All sputum collected was weighed immediately following collection on weighing scales with an accuracy of 0.01 g (BL310; Sartorious UK Ltd, Epsom, UK). FEV1 was measured using a hand-held spirometer (2120; Vitalograph Ltd, Buckingham, UK) in accordance with internationally agreed standards.24 Measurements were taken immediately before and after a 30 min period following each treatment session. Data were analysed using Spirotrac IV Version 4.30 software (Vitalograph Ltd). Pulsed arterial oxygen saturation (SpO2) was measured transcutaneously at rest, for 5 min immediately before, 30 min during and 30 min immediately following each session. SpO2 was measured with a fingertip pulse oximeter (Konica-Minolta Pulsox-300i; Stowood Scientific Instruments, Oxford, UK). The data were analysed using Download 2001 Version 2.8.0 software (Stowood Scientific Instruments Ltd). The perceived efficacy and comfort of each ACT and the incidence of urinary leakage during treatment were measured using 10 cm visual analogue scales (VAS). Each day, after the last treatment session, patients completed three 10 cm VAS with reference to the ACT used that day. On the VAS used, 0 represented not at all effective/comfortable or no urinary leakage and 10 represented extremely effective/comfortable or a lot of urinary leakage. On the fourth and final day, participants were also asked to indicate which ACT they would prefer. An independent observer, blind to the daily method of airway clearance used, performed the spirometry, weighed the sputum samples and collected the 10 cm VAS throughout the study.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nA sample size calculation determined the number of patients required to test for superiority of HFCWO. This was based on a difference of 4 g of sputum between the usual ACT and HFCWO during a single treatment session. A square-root of within SEM of 4 g at the 5% significance level would require 24 patients to achieve 90% power. Data are presented as mean (SD), median (IQR) or n (%) as appropriate. Continuous variables were analysed using a mixed-effects linear regression model. This was to allow the results to be adjusted for a number of factors which are inherent to the design of a crossover trial. The order of treatment randomisation and the day and time of treatment were all entered into the model and their effect on the outcomes was tested. For this trial, the results were also adjusted for the method and position of treatment in the ACT session. In these models, patients were entered as random effects since it was not of interest to quantify the differences between individual patients, but it was important to account for the repeated measurements on each patient. The estimates of the fixed effect of ACT versus HFCWO are presented as mean (95% CI). A p value of 0.05 was taken to be statistically significant. All analyses were conducted using Stata 9.2 (StataCorp).\n\nBODY.RESULTS.PARTICIPANTS:\nFifty patients were invited to participate in the study, 20 declined, 29 patients completed the study and 1 patient was withdrawn due to a hypoglycaemic episode. Table 1 shows demographic and baseline characteristics of the patients who completed the study. Table 1 Patient demographics and baseline characteristics (n=29) Age (years) 29.4 (8.4) Male (%) 21 (72%) Height (cm) 171 (9) Weight (kg) 60 (11) BMI (kg/m 2 ) 20.4 (2.6) FEV 1 (l) 1.46 (0.72) FEV 1 % predicted 38 (16.7) SpO 2 (%) 94.3 (2.1) Data are presented as mean (SD) or n (%) as appropriate. BMI, body mass index; FEV 1 , forced expiratory volume in 1 s; SpO 2 , pulsed arterial oxygen saturation. Twenty-nine patients were treated with intravenous antibiotics as part of their medical management. All participants received two treatment sessions on each study day and all treatment sessions were 30 min in duration. The mean (SD) length of stay for patients was 14 (5) days and the mean day of entry to the study was day 8 (3) days.\n\nBODY.RESULTS.USUAL ACT:\nUsual ACTs included the ACBT with modified PD&P (41%; n=12) and with modified PD alone (7%; n=2), AD in sitting (28%; n=8) and with modified PD (7%; n=2), PEP (7%; n=2) and Flutter (10%; n=3).\n\nBODY.RESULTS.SPUTUM WEIGHT:\nThe wet weight of sputum expectorated with usual ACT compared with HFCWO is shown in table 2. The mean weight of sputum expectorated during a single treatment session and over a 24 h period was significantly greater with usual ACT than with HFCWO. The mean difference in wet weight of sputum expectorated during a treatment session was 4.4 g (p<0.001) and the mean difference in wet weight of sputum expectorated over a 24 h period was 6.9 g (p<0.001). These findings were not affected by order, time, day or position of treatment. Table 2 Wet weight of sputum expectorated: HFCWO compared with usual ACT Period of sputum collection Expectorated sputum wet weight (g) Usual ACT HFCWO Mean difference p Value Mean (SD) Median (IQR) Mean (SD) Median (IQR) Single treatment session 9.1 (7.9) 7.2 (3.0–14.2) 4.6 (4.1) 3.4 (1.5–6.7) 4.4 (3.5 to 5.4) <0.001 24 h (excluding treatment) * 22.4 (26.8) 12.9 (4.0–29.9) 24.9 (25.8) 15.3 (3.9–40.1) −1.5 (−4.6 to 1.6) 0.352 24 h (including treatment) 39.8 (36.3) 25.5 (14.0–57.1) 34.3 (30.7) 26.3 (12.1–46.0) 6.9 (3.1 to 10.8) <0.001 Data are presented as mean (SD) or (95% CI) or median (IQR) as appropriate. Data are adjusted for randomisation, day, time and position of treatment using a mixed effects linear regression model. * Of 116 24-h sputum samples collected, two were discarded as they were incomplete. ACT, airway clearance technique; HFCWO, high frequency chest wall oscillation. No statistically significant difference was observed in the amount of sputum expectorated when using HFCWO or usual ACT between treatments in a 24 h period.\n\nBODY.RESULTS.PHYSIOLOGICAL MEASURES:\nFEV1 and SpO2 measured before, during and after usual ACT and HFCWO treatment sessions are shown in table 3. Table 3 Forced expiratory volume in 1 s and pulsed arterial oxygen saturation at baseline, during and after treatment with usual airway clearance technique and HFCWO Usual ACT HFCWO Baseline During treatment 30 min after treatment Baseline During treatment 30 min after treatment FEV 1 % predicted 39.1 (16.9) NA 38.9 (17.1) 38.9 (16.8) NA 39.2 (16.7) SpO 2 (%) 94.4 (2.0) 94.4 (1.9) 93.9 (1.6) 94.5 (1.8) 95.0 (1.7) 94.3 (1.7) Data are presented as mean (SD). ACT, airway clearance technique; FEV 1 , forced expiratory volume in 1 s; HFCWO, high frequency chest wall oscillation; NA, not applicable; SpO 2 , pulsed arterial oxygen saturation. \n\nBODY.RESULTS.COMFORT, EFFICACY AND PREFERENCE:\nThe VAS scores for comfort, efficacy and urinary leakage during usual ACT compared with HFCWO are shown in table 4. No significant differences were observed in VAS scores for comfort or urinary leakage between HFCWO and usual ACT. Patients scored the efficacy of their usual ACT significantly higher than for HFCWO (mean difference 14 mm; p=0.002). This was not affected by the order or day of treatment. Of those patients who completed the study, 17 (55%) expressed a preference for their usual ACT over HFCWO. Preference was not predicted by the amount of sputum expectorated. Table 4 Comfort, efficacy and urinary leakage: HFCWO compared with usual ACT Self reported measure Visual analogue scale score (mm) Usual ACT HFCWO Mean difference p Value Comfort 69 (23) 70 (22) −1 (−9 to 7) 0.784 Efficacy 68 (21) 54 (26) 14 (6 to 23) 0.002 Urinary leakage 0 (1) 0 (1) −0.05 (−0.3 to 0.4) 0.791 Data are presented as mean (SD) or (95% CI) as appropriate. Data are adjusted for randomisation, day of treatment and time of treatment using a mixed effects linear regression model. ACT, airway clearance technique; HFCWO, high frequency chest wall oscillation. \n\nBODY.DISCUSSION:\nThere have been few published comparisons between HFCWO using a vest system with the ACTs of the ACBT and AD. This short-term study, carried out in individuals with CF admitted to hospital with an acute infective pulmonary exacerbation, showed that significantly more sputum was expectorated during a single treatment session and over a 24 h period using the patient's usual ACT than with HFCWO. In addition, slightly less sputum was expectorated at all other times (excluding treatment sessions) on usual ACT days compared with HFCWO, but this trend was not statistically significant. These findings were independent of order, time or day and position of treatment. Neither HFCWO nor any of the usual ACTs were associated with any adverse clinical events. A possible factor contributing to the difference in sputum clearance between HFCWO and usual ACT may have been the number and frequency of forced expiratory manoeuvres (FEMs) and the more gentle expiratory manoeuvres of the AD breath that were performed with the usual ACTs. Some studies have standardised the number of coughs and FEMs that patients performed; however, at the time of designing the protocol, the aim was to compare the regimens as currently practised internationally and the frequency of coughs and FEMs was neither standardised nor counted. In retrospect, it would have been of value to have counted the number of coughs and FEMs undertaken during each regimen, but it had not been anticipated that any differences between HFCWO and usual ACTs may be a consequence of the number of FEMs or AD breaths. Theoretically, during the three 8 min periods of HFCWO, fewer FEMs, coughs or AD breaths would be undertaken than during an equivalent period of the ACBT, AD, PEP or Flutter (all of which inherently include FEMs or AD breaths at regular intervals). This difference was supported by observations of the investigators. However, manual cough counts are subject to observer error. Objective cough monitoring using the Leicester Cough Monitor has only recently been validated and should be considered for use in further studies.25 Components of patient satisfaction include efficacy, comfort and convenience. Some studies have formally evaluated patient satisfaction and compliance. One study reported that 50% of subjects chose HFCWO compared with the Flutter, and efficacy was the most frequently cited reason for this choice.16 A later study reported that HFCWO was not preferred over PD&P and intrapulmonary percussive ventilation; furthermore, there was no significant correlation between treatment preference and sputum weight.14 The current study found that patients perceived the efficacy of HFCWO to be statistically significantly less than that of their usual ACT. However, nearly half (45%) of patients expressed a preference for HFCWO. Preference may have been affected by the novelty of a new treatment and it is unknown whether this would continue in the long term. There is no one recommended protocol for the application of HFCWO in the literature. Published studies describe differing numbers and duration of frequencies, length of treatment and airway clearance. Frequencies of 10, 13 and 15 Hz were chosen as it has been reported that maximum mucus transport occurs between 11 and 15 Hz with a peak at 13 Hz.5 6 In addition, the highest oscillated tidal volume flow (peak airflow) occurred between 10 and15 Hz in patients with CF.26 More recent research recommends an individual \"tuning\" method to identify optimum treatment frequencies. These have been shown to vary among individuals and the oscillation waveform,27 but it is unknown whether \"tuning\" increases efficacy. It is possible that a practice effect could have occurred as all patients were new to HFCWO. However, the protocol used in this study did not require the patient to perform any newly learnt physical technique. In addition, the statistical analysis ensured data were adjusted for day of treatment and found no effect. Alternatively, patients' familiarity with their usual ACT may also have had an effect on outcomes. This study was powered to detect a difference of 4 g of sputum expectorated during a single treatment session. Other studies have been based on a difference of 3–3.5 g, which is generally accepted as a clinically important difference.28 29 Wet weight sputum was felt to be an appropriate primary outcome measure in this short-term study in an acute environment. Previous work has found wet weight to be proportional to dry weight sputum.28 30 Emerging non-invasive means of measuring airway clearance may be more sensitive indicators in the future (eg, lung clearance index and electrical impedance tomography). Considering the cost benefit of HFCWO compared with other ACTs and the differing healthcare systems in the USA and the UK, it is unlikely that HFCWO will become the first choice ACT for most individuals in the UK. Further work needs to be undertaken to identify the place of HFCWO in Europe. Patient preference for a treatment regimen may positively influence adherence to treatment in the short term, and nearly half the patients who participated in this study preferred HFCWO to their usual ACT. HFCWO is a safe treatment that facilitates airway clearance in CF but, when compared with patients' usual ACTs, HFCWO led to the clearance of significantly less sputum during a single treatment session and over a 24 h period.\n\n**Question:** Compared to Usual airway clearance techniques what was the result of High frequency chest wall oscillation on Adverse events?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
342
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Placebo what was the result of Budesonide/formoterol pMDI 160/9 μg on 1-hour post-dose inspiratory capacity mean improvements from baseline to the average over the randomized treatment period ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
260
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Impact and Process Evaluation of Integrated Community and Clinic-Based HIV-1 Control: A Cluster-Randomised Trial in Eastern Zimbabwe\n\n ABSTRACT.BACKGROUND:\nHIV-1 control in sub-Saharan Africa requires cost-effective and sustainable programmes that promote behaviour change and reduce cofactor sexually transmitted infections (STIs) at the population and individual levels.\n\nABSTRACT.METHODS AND FINDINGS:\nWe measured the feasibility of community-based peer education, free condom distribution, income-generating projects, and clinic-based STI treatment and counselling services and evaluated their impact on the incidence of HIV-1 measured over a 3-y period in a cluster-randomised controlled trial in eastern Zimbabwe. Analysis of primary outcomes was on an intention-to-treat basis. The income-generating projects proved impossible to implement in the prevailing economic climate. Despite greater programme activity and knowledge in the intervention communities, the incidence rate ratio of HIV-1 was 1.27 (95% confidence interval [CI] 0.92–1.75) compared to the control communities. No evidence was found for reduced incidence of self-reported STI symptoms or high-risk sexual behaviour in the intervention communities. Males who attended programme meetings had lower HIV-1 incidence (incidence rate ratio 0.48, 95% CI 0.24–0.98), and fewer men who attended programme meetings reported unprotected sex with casual partners (odds ratio 0.45, 95% CI 0.28–0.75). More male STI patients in the intervention communities reported cessation of symptoms (odds ratio 2.49, 95% CI 1.21–5.12).\n\nABSTRACT.CONCLUSIONS:\nIntegrated peer education, condom distribution, and syndromic STI management did not reduce population-level HIV-1 incidence in a declining epidemic, despite reducing HIV-1 incidence in the immediate male target group. Our results highlight the need to assess the community-level impact of interventions that are effective amongst targeted population sub-groups.\n\nBODY.INTRODUCTION:\nHIV-1–prevalence declines may now be occurring in some sub-Saharan African countries [1]. However, there remains little direct evidence that prevention measures—rather than natural HIV-1 epidemic dynamics [2] or behaviour change prompted by mortality [3]—have contributed to the slowing of HIV-1 epidemics [4,5]. Syndromic management of sexually transmitted infections (STIs) proved effective early in an HIV-1 epidemic in north-west Tanzania [6]. Peer education to promote safe behaviours showed promise in early process evaluations [7], but a randomised controlled trial (RCT) of factory workers in Harare, Zimbabwe, done in the mid-1990s, proved inconclusive [8]. Subsequent RCTs of syndromic management [9] and mass treatment of STIs [10], together with an information, education, and communication (IEC) behaviour-change programme [9], showed no effect in more mature epidemics. Integrated implementation of synergistic community-based HIV-1 control strategies could be a more cost-effective and sustainable approach to HIV-1 prevention than parallel application of vertical (top-down) programmes [11]. One scientific evaluation of such a strategy has been reported in which a combination of IEC activities amongst the general population and syndromic STI management showed no impact on HIV-1 incidence at the population level [9], although participation in the IEC activities was associated with reduced HIV-1 infection in women [12]. We conducted a cluster-RCT to test the hypothesis that integrated implementation of combined community- and clinic-based HIV-1 prevention, in which IEC activities focus primarily on high-risk populations, can be feasible and effective in reducing HIV-1 incidence in a major maturing epidemic in eastern Zimbabwe (Protocols S1 and S2; Text S1 and S2).\n\nBODY.METHODS.PARTICIPANTS AND RANDOMISATION PROCEDURE:\nThe study communities comprised six pairs of communities matched by socio-economic type—small town, tea/coffee estate, forestry plantation, roadside trading settlement, and subsistence farming area (two pairs) (Figure 1). Each community included at least one Government or Mission health centre. It was anticipated that HIV-1 incidence would be similar within each pair of communities. Within each pair, one community was assigned at random (un-blinded coin toss by a Ministry of Health official witnessed by programme and research personnel) to receive the additional intervention and the other to be the control. These procedures were designed to ensure that Mission, non-governmental organisation, and private sector programmes (for details, please refer to the following section) would be distributed evenly between intervention and control sites. Figure 1Location of Intervention and Control Communities in Manicaland Province, Eastern Zimbabwe We assessed the effect of the intervention using results from laboratory tests for HIV-1 infection and questionnaire data collected in the baseline and 3-y follow-up rounds of a population-based, closed-cohort survey. The 12 study communities were enumerated in a phased manner, with paired communities being enumerated consecutively to minimise the effects of any seasonal factors. HIV-1–prevention activities were commenced in each intervention community shortly after completion of the baseline survey in that community. In each community, individuals eligible for the study were identified in the first round using data from household listings prepared in an initial census. All males and females aged 17–54 y and 15–44 y at last birthday (the age groups expected to have the highest incidence of HIV infection), respectively, who had slept in a household in the community for at least four nights in the previous month, and who had also done so at the same time 1 y earlier, were considered eligible for the study. In heterosexually driven HIV-1 epidemics, risk of infection can be correlated amongst marital partners [13]. Therefore, to maximise statistical power to detect differences in HIV-1 incidence, enrolment was restricted to one randomly selected member per marital group.\n\nBODY.METHODS.INTERVENTIONS:\nIntervention and control communities were to receive standard Government services including basic syndromic STI management, condom distribution from health clinics and Zimbabwe National Family Planning Council outlets, home-based care, and limited HIV/AIDS–focussed IEC activities (e.g., occasional AIDS-awareness meetings and distribution of posters and leaflets). In addition, social marketing of male and female condoms would be provided through an ongoing national programme [14]. The intervention comprised targeted and population-level strategies to promote safer sexual behaviour and to improve treatment of STIs that facilitate HIV-1 transmission. The intervention strategies were implemented by two local non-governmental organisations (Family AIDS Caring Trust and the Biomedical Research and Training Institute) and the Zimbabwe Ministry of Health and Child Welfare through an integrated programme of community- and clinic-based activities. Integration of the individual programme components was achieved through the joint involvement of the participating agencies in the planning and implementation of activities and through the inclusion of biomedical and behavioural aspects within each component. The programme design comprised three key components: (1) peer education and condom distribution amongst commercial sex workers and male clients at workplaces and in the general community, supported by income-generating projects; (2) strengthened syndromic management of STI services at local health centres; and (3) open days with HIV/AIDS IEC activities at health centres to promote safer sexual behaviour and to increase the uptake of local STI treatment services. The peer-education component was based on a model which had been developed by the Project Support Group at the University of Zimbabwe [7] and which had been widely implemented within Zimbabwe and neighbouring countries. Activities were held weekly at workplaces and at locations within the general community (e.g., beer halls and markets) where casual relationships were most frequently formed [15]. The target population comprised sex workers and male clients who form a bridge population in HIV transmission [16] between sex workers and the monogamous (or serial monogamous) majority of women [17,18]. It was posited that the high HIV-1 incidence observed amongst young women could be reduced by altering the behaviour of their older male partners whose own behaviour was intrinsically more risky [19]. The behavioural component would be reinforced in counselling sessions with STI patients and through micro-credit income-generating projects to reduce unmarried women's dependence on commercial sex work. The micro-credit scheme consisted of small interest-free loans repayable over 10 mo, provided to groups and to individuals together with training in small-business management. The targeted activities would be extended to the general population through open days held at local health centres. Besides providing basic HIV/AIDS information, it was envisaged that programme meetings and activities, by their continuous nature, would sustain high levels of awareness of the risks of HIV transmission and would facilitate renegotiation of community social norms, making safer behaviours easier to adopt. The key messages of the programme were: (1) remain faithful to one regular sexual partner; (2) use condoms consistently with any casual sexual partners; and (3) seek prompt and effective treatment for any STIs. Syndromic management of STIs at primary healthcare centres was first introduced in Zimbabwe in the 1980s [20] and formed the basis of STI diagnosis and treatment services at baseline in the intervention and control communities. It was envisaged that these services could be strengthened and made more effective through a programme of regular classroom training and on-site supervision of nursing staff, through the introduction of training in systemic counselling for STI patients, and through the provision of small quantities of treatment drugs to cover delays in routine supplies. Quality-assurance procedures applied in the intervention communities included pre- and post-training tests for peer educators and, for nursing staff, attending the syndromic STI management and systemic counselling courses, regular on-site supervision (including random spot checks) and training, refresher courses, routine planning meetings and monitoring of service statistics, and quarterly workshops where detailed programme procedures were reviewed and updated. An interim qualitative process evaluation of intervention activities was conducted during the inter-survey period, and a report on the findings was provided to the implementing organisations.\n\nBODY.METHODS.OUTCOME AND PROCESS MEASURES:\nThe primary outcome of the study was HIV-1 incidence at the community level amongst individuals who were uninfected at baseline. Blood was collected onto Whatman No. 3 filter paper and transported to the Biomedical Research and Training Institute laboratory in Harare. Blood spots were air dried at 4 °C and, for long-term (>1 mo) storage, were kept at −20 °C. For baseline studies, blood was eluted into phosphate-buffered saline, and antibodies to HIV were detected using a dipstick dot EIA (ICL-HIV-1/HIV-2 Dipstick, [PATH, http://www.path.org; produced locally in Thailand]) and a standard protocol [21,22]. All positive results and a 10% sample of negative results were confirmed using a plate EIA (Abbott Third-Generation HIV-1/HIV-2 EIA [http://www.abbott.com] or Genelavia MIXT HIV-1/HIV-2 [Sanofi Diagnostics Pasteur, Marnes La Coquette, France]). At follow-up, a similar protocol was followed. Only the samples from those participants recorded as being HIV seronegative at baseline were tested at follow-up, again using a dot EIA (ICL-HIV-1/HIV-2 Dipstick, [PATH, produced locally in India]). Where seroconversion was indicated, the frozen stored baseline sample was retested to confirm the original negative result using the same dot EIA test. Where the baseline result remained negative, the Abbott EIA test was used to confirm both baseline and follow-up results. The change in place of manufacture of the dot EIA and the exclusive use of Abbott test kits to confirm positive sera at follow-up was due only to changes in the supply of test reagents, and not to perceived changes in sensitivity or specificity [23]. Apart from the principal investigators (based in Harare, London and Oxford) and those nurses given permission by participants requesting voluntary counselling and testing (VCT), all research personnel remained blind to the HIV-1 status of individual participants. Secondary outcomes, measured at the community and individual level, were self-reported genital ulcers and urethral or vaginal discharge in the past year (STI cases), STI treatment effectiveness (self-reported cessation of symptoms), indicators of sexual and health-seeking behaviour change, and HIV/AIDS knowledge. The behaviour-change variables assessed were sexual debut, sexual partner change in the past year, non-regular partnerships in the past month, and unprotected sex with regular and casual partners in the past 3 y. The data on sexual partnerships and condom use were collected using the Informal Confidential Voting Interview method for 75% of respondents selected at random in the first round of the survey. This method includes procedures to build rapport, ensure a non-judgemental interview approach, and provide reassurance that there are no right or wrong answers to questions of a personal nature, and uses a simple secret voting-box system to reduce embarrassment and guarantee confidentiality in low-development settings [18]. Its use has been shown to be associated with greater disclosure of socially proscribed behaviour in the study population [24]. Process indicators examined comprised changes in knowledge and psychosocial status and indicators of programme coverage and quality.\n\nBODY.METHODS.SAMPLE-SIZE CALCULATIONS:\nInitial sample-size calculations assumed 20% HIV-1 prevalence at baseline, 30% loss to follow-up after 2 y, and 80% power to detect a 40% reduction in HIV-1 incidence in the intervention communities compared with control communities, assuming a background yearly incidence of 2%. Based on six pairs of communities and a co-efficient of variation between communities of 0.15, the required sample size in each community was 1,000. Funding constraints and slower than anticipated implementation of intervention activities led to revisions of the sample size for each community to 800 and the length of follow-up to 3 y, respectively. Assuming a proportionate increase in loss to follow-up to 41%, these arrangements also yielded 80% power to detect a 40% reduction in HIV-1 incidence.\n\nBODY.METHODS.STATISTICAL METHODS:\nTo test the randomisation with small numbers of communities, HIV-1 prevalence, STI history, and socio-demographic characteristics were compared at baseline for study participants in the intervention and control communities, together with uptake of STI treatment and VCT services offered at baseline. Outcome and process indicators were compared for intervention versus control communities. Analysis of the primary outcome was on an intention-to-treat basis. Incident events and person-years at risk of seroconversion were used to calculate HIV-1 incidence rates and unadjusted and adjusted incidence rate ratios (IRR) with 95% confidence intervals (CIs) for each pair of communities. Adjustment was made for sex, 3-y age group, and community-level baseline HIV prevalence. The overall IRRs (unadjusted and adjusted) were taken to be the geometric means of the IRRs for the six pairs of communities. We calculated 95% CIs for each geometric mean as geometric mean ± 1.96 × standard error of the geometric mean. Paired student t-tests on the logarithms of the pair-specific IRRs were used to test whether these differed significantly from unity [25]. The coefficient of variation between communities was calculated based on baseline HIV prevalence using a standard procedure for pair-matched studies [26]. Analyses of prevalence for secondary outcome and process variables were conducted separately for male and female respondents seen at both survey rounds by fitting logistic regression models to the individual-level data and adjusting for community pair and, where available, value of variable at baseline. Since most programme activities were targeted and overall coverage of programme activities was therefore limited, sub-group analyses, adjusted for community pair, were done for HIV-1 incidence and behavioural outcomes to assess the individual-level effects of attendance at programme meetings. Data were entered and validated using SPSS-PC (http://calcnet.mth.cmich.edu/org/spss/index.htm) and data analysis was conducted in Stata version 7 (http://www.stata.com). Statistical tests were double-sided and results were taken to be significant at the 5% level.\n\nBODY.METHODS.ETHICAL APPROVAL:\nAll study participants in the intervention and control communities were offered free VCT for HIV-1, an information sheet on HIV/AIDS, results from a diagnostic test for Trichomonas vaginalis [27] (done at baseline only), and free treatment for T. vaginalis and other STIs from a research nurse. Testing and treatment for T. vaginalis was provided because the prevalence of other curable STIs was low in the study areas [22]. Antibodies reactive with T. vaginalis were detected in DBS eluates following a previously described procedure [27,28]. Written informed consent was sought as a condition of enrolment and continuation in the study. Prior ethical approval was obtained from the Research Council of Zimbabwe, number 02187; the Applied and Qualitative Research Ethics Committee in Oxford, United Kingdom, N97.039; and the UNAIDS Research Ethics Committee, ERC 98/03.\n\nBODY.RESULTS.PARTICIPANT FLOW:\nIn round 1 of the census (July 1998 to February 2000), 5,943 and 6,037 eligible individuals in the intervention (total population size 18,104) and control (18,633) communities, respectively, were selected for recruitment into the study cohort (Figure 2). In round 2, 3 y later (July 2001 to February 2003), 1,044 (23%) and 1,144 (26%) of baseline respondents who were still alive had migrated away from the intervention and control communities, respectively, and were therefore lost to follow-up (Figure 2). At both baseline and follow-up, migrants and non-migrants had similar risks of HIV-1 infection and associated behaviour [29]. Of those still resident in the intervention and control communities, 2,664 (75%) and 2,564 (77%), respectively, were interviewed and blood samples taken for a second time. Temporary absence from the usual place of residence was the main reason for non-participation in the intervention (n = 794, 95%) and control (n = 698, 94%) communities. The overall proportions of baseline respondents followed up at the end of the study were 55% and 56% in the intervention and control communities, respectively. The median follow-up of communities was 3.0 y (range of median within communities, 3.0–3.1). Figure 2Flow-Chart Comparing Participation and Follow-Up Rates in the Intervention and Control CommunitiesIndividuals enrolled in round 1 and still resident in the study communities were considered eligible for participation in round 2.\n\nBODY.RESULTS.BASELINE DATA:\nHIV-1 prevalence was higher in the intervention communities than in the control communities (24% versus 21%, risk ratio 1.13 [95% CI 1.05–1.22], p = 0.001). T. vaginalis infection, secondary school education, and spatial mobility were more common in the control communities, whilst history of genital discharge and uptake of STI treatment and VCT services offered in the survey were low overall but more frequent in the intervention communities (Table 1). However, the differences in each case were small and were unlikely to be clinically meaningful. Table 1 Baseline Characteristics of the Study Populations \n\nBODY.RESULTS.OUTCOMES AND ESTIMATION:\nMedian follow-up per person was 2.9 y (range 1.4–3.9) and 3.0 y (range 1.5–4.1) in the intervention and control communities, respectively. In total, 4,052 individuals had 212 incident events of HIV-1 during 12,009 person-years at risk, giving an HIV-1 incidence rate of 1.77 per 100 person-years at risk. HIV-1 incidence was higher in communities with higher baseline HIV prevalence (IRR 11.49 [95% CI 1.80–73.40], p = 0.010), but this difference disappeared after adjustment for stratification by community type (p = 0.8). HIV-1 incidence was higher in the intervention communities than in the control communities overall, and in each community type, except in the forestry plantations where it was almost identical (Table 2). The difference was not significant after adjustment for sex, age group, and baseline HIV prevalence (IRR 1.27 [95% CI 0.92–1.75], p = 0.012). The observed coefficient of between-community variation was 0.14. Table 2 HIV Prevalence at Baseline and HIV Incidence and IRRs for Intervention Versus Control Communities Looking at outcome indicators for community members (rather than for communities—the unit of randomisation), self-reported STI symptoms were similar in both sets of communities (Table 3). Treatment for STI symptoms in males was effective more frequently in the intervention communities, with men in the intervention community in five of the six matched pairs reporting reduced symptom recurrence. However, more young women in the intervention than in the control communities had started sex, and reports of unprotected sex with a casual partner in the study period were more common in the intervention communities. No differences were observed in consistent condom use with regular partners between the two sets of communities. In the intervention communities, knowledge about HIV/AIDS was enhanced amongst men, and more respondents reported a close relative or family member with AIDS (sex- and age-adjusted prevalence odds ratio 1.22 [95% CI 1.05–1.42], p = 0.009). Slightly more women in the intervention communities reported that condom use within marriage was becoming acceptable, but a greater proportion of men agreed with the statement that \"condoms reduce the pleasure of sex\". Table 3 Biomedical, Sexual Behaviour, and Psychological Outcomes at Follow-up by Residence in the Intervention and Control Communities A total of 63,261 peer-education meetings were held, and 6.8 million condoms were distributed by the programme in the intervention communities (Table 4). Outputs increased over time as new communities entered the programme. However, owing to high inflation and economic decline, the micro-credit income-generating projects proved impossible to implement. We were able to obtain data on STI episodes treated at clinics in the 11 out of 12 study communities that reported cases to the administrative districts of Mutasa and Makoni. In the three intervention communities each in Mutasa and Makoni, STI cases fell by 66% and 51%, respectively, over the 3-y study period. Similar declines of 67% and 52% occurred at clinics in the four control communities in Mutasa and the one control community in Makoni. Coverage of training in syndromic STI management and systemic counselling for nursing staff was high (Table 4). Table 4 Summary of Service Statistics on Programme Output Most of the activities were targeted at high-risk groups. In the general population sample interviewed in the follow-up survey, 1,779 (35%) and 647 (13%) of 5,098 respondents reported attending an HIV/AIDS meeting and a programme meeting, respectively (Table 5). More respondents in the intervention communities than in the control communities attended an HIV/AIDS meeting (41% versus 28%, prevalence rate ratio 1.44 [95% CI 1.33–1.56], p < 0.001) and a programme meeting (20% versus 5%, 4.27 [95% CI 3.52–5.17], p < 0.001), and participation was higher among men than women (prevalence rate ratio 1.32 [95% CI 1.14–1.53], p = 0.002). Fewer women in the intervention communities had heard about HIV/AIDS from external sources or believed that STI drugs were available at their local clinics. Sixty-two (2%) out of 2,528 respondents in the control communities reported spending at least 1 d in the past month in the intervention communities; the equivalent number for respondents in the intervention communities visiting control communities was 70 (3%) out of 2,683. Table 5 Intervention Coverage \n\nBODY.RESULTS.ANCILLARY ANALYSES:\nIn exploratory analysis to assess where the intervention failed, we found that HIV-1 incidence was reduced in males (IRR 0.48 [95% CI 0.24–0.98], p = 0.044) who reported attending programme meetings, after adjustment for the targeting of activities to groups with high-risk behaviour (Table 6). Amongst men who reported one or more casual sexual partners in the past 3 y, fewer of those who attended meetings reported unprotected sex with these partners (prevalence odds ratio 0.45 [95% CI 0.27–0.75], p = 0.002). HIV-1 incidence was not associated with programme participation in women. Table 6 HIV Incidence and IRRs by Meeting Attendance and Sex \n\nBODY.DISCUSSION.INTERPRETATION:\nWe conducted a scientific trial of the feasibility and impact of an integrated community- and clinic-based HIV-1–prevention intervention. The income-generating projects apart, the intervention activities were feasible. The outputs of the programme were extensive with more than 63,000 meetings being conducted and almost 7 million condoms distributed by trained peer educators. Programme messages were considered relevant and realistic. Local STI treatment and counselling services were strengthened and promoted in accordance with the intervention protocol. For male participants, these activities improved HIV/AIDS knowledge, increased the effectiveness of STI treatment, increased consistent condom use with casual partners, and reduced HIV-1 incidence. However, the cluster-RCT results clearly show that the intervention had no positive impact at the community level and suggest possible detrimental effects on the onset of female sexual activity and condom use with casual partners over a 3-y timeframe. Did the cluster-RCT design fail to capture the true effect of the intervention? There are three possibilities: (1) inadequate statistical power; (2) insufficient follow-up; and (3) contamination of intervention within control communities. The study design provided adequate statistical power to detect a meaningful average reduction (40%) in HIV-1 incidence in the intervention versus the control communities over a 3-y observation period. In hindsight, an effect size of 40% was too optimistic and the study had insufficient power to detect a smaller effect. However, there was no trend in the results towards reduced HIV-1 incidence in the intervention communities. Largely due to migration, attrition was close to that anticipated in the study design and was comparable to other recent cohort studies [6,10,9,30]. Migrants had similar characteristics and sexual behaviour to non-migrants [29]. The results of the exploratory sub-group analysis generate the hypothesis that high-risk behaviour was reduced in males attending programme meetings but did not translate into a wider impact on HIV-1 incidence at the population level. Changes in core and bridge populations may take more time to reflect in the general population than was observed in the trial. However, a longer period of follow-up would have increased attrition, and the finding of a possible adverse effect at the population level meant that it would not have been ethical to continue with the same intervention. Future trials of behaviour-change interventions may need to include multiple rounds with phased recruitment and (where interim results are favourable) may need to consider phased intervention implementation. We minimised intervention contamination by selecting physically separated study communities, and movements between intervention and control communities were rare. However, a similar peer-education programme was implemented in one control community (small town), and HIV-1–prevention activity was considerable in all control communities that also had greater access to information from external sources. In some cases, programme messages (e.g., promotion of condom use) conflicted with those of other agencies working in the intervention communities. The effects of these other programmes could have limited our ability to detect a reduction in HIV-1 incidence caused by the current intervention. The absence of an observed effect of the intervention was not explained by differences in HIV-1 prevalence, sexual behaviour, STI cofactors, mobility, or socio-demographic composition at baseline. The earlier sexual debut in females and greater unprotected sex with casual partners seen in the intervention communities during the study period were not present at baseline but could reflect increased willingness to report high-risk behaviours in settings where there was more open discourse about HIV and AIDS. The peer-education programme could have had some effect for male but not for unmarried female participants. Preliminary findings from subsequent qualitative investigations indicate that, in the predominantly rural communities in which the study was conducted, poverty and the associated failure of income-generating projects meant that some peer educators were unable to maintain safer behaviours. Given their increased visibility within the community—intended to enhance their status and self-esteem and, thus, to reinforce their commitment to and role as models for behaviour change—they may, inadvertently, have served as negative role models and, thereby, may have contributed to the greater female early-age sexual activity. Free distribution of condoms by women still engaging in unprotected commercial sex led to their being poorly valued and reinforced their association with promiscuity.\n\nBODY.DISCUSSION.GENERALISABILITY OF FINDINGS:\nEpidemiological context can affect the impact of interventions [31], and structural obstacles can limit the pace and extent to which activities are implemented and the quality of these activities [32]. The HIV-1 epidemic stabilised in eastern Zimbabwe during the study period, with HIV-1 prevalence declining by 40%–50% in young adults [23]. This decline was accompanied by delayed sexual debut, reduced sexual partner change, and consistent condom use with casual partners [33,23]. Prevalence of syphilis, gonorrhoea, and Chlamydia is low, but non-curable herpes simplex virus type 2 remains common [22]. Risk reduction makes transmission more fragile, and an intervention could have a larger effect when set against secular behavioural changes [2]. Mathematical model simulations suggest that there would also be a greater chance of detecting a significant effect of the intervention even though there would be fewer seroconversions to power the calculation [34,35]. Structural obstacles to intervention implementation included HIV/AIDS mortality which disrupted the programme by claiming the lives of two programme coordinators and several of the nursing staff and peer-educators. Economic decline made the income-generating projects unfeasible and reduced the effectiveness of other components of the intervention. We believe that the coverage of the peer-education programme was satisfactory, given the focus on highly sexually active individuals. Meeting coverage could have been under-estimated in the survey since one-to-one discussions and activities at beer halls and other public places may not have been recognised as meetings by those present. However, the high level of spatial mobility limited the number of people who were reached at the required level of intensity and consistency, whilst national shortages of foreign currency restricted fuel and drug supplies, hampered attempts to extend community activities into the more remote rural areas, and disrupted the STI treatment programme in both the intervention and control communities. The intervention that we evaluated could have greater effect where an HIV-1 epidemic is younger, HIV-1 incidence is greater, local sexual networks are less diffuse, background STI control is weak, herpes simplex virus type 2 is less common, population mobility is lower, and/or the socio-economic climate is stable. We cannot rule out an effect of peer education in the urban intervention community since similar activities were implemented in the control community. Targeted peer education may work better in towns where bar-based sex work is more extensive. The absence of reduced HIV-1 incidence in farming estates reinforces doubts raised by the Harare factory workers study [8] concerning the efficacy of workplace peer education.\n\nBODY.DISCUSSION.OVERALL EVIDENCE:\nThese findings are important since the strategies evaluated—i.e., peer education, condom distribution, and syndromic STI management—are theory-based, have the potential for independent effects [11], and are widely promoted [36,37]. Syndromic STI management was effective in a nascent epidemic [6]. However, our disappointing findings echo those from recent trials [9,12] and emphasise the need for alternative strategies of behaviour-change promotion. Social marketing of condoms [14], larger poverty-alleviation programmes to reduce women's reliance on sex work—based on skills training and careful market research rather than on small-scale income-generating projects—and strategies which reach beyond high-activity core groups, such as the Popular Opinion Leader programme [38,39], and client-centred counselling [40], could be more viable and effective in reducing HIV-1 transmission in rural areas. Given the necessary economic conditions, unmarried women may still play a useful role in bar-based programmes since beer halls remain foci for high-risk behaviour [41,15].\n\nBODY.SUPPORTING INFORMATION.TRIAL REGISTRATION:\nThis trial has the registration number ISRNCT00390949 in the International Standard Randomized Controlled Trial Number Register. Found at: http://www.clinicaltrials.gov/ct/show/NCT00390949?order=1\n Protocol S1Protocol(35 KB DOC)Click here for additional data file. Protocol S2Revisions to Protocol(35 KB DOC)Click here for additional data file. Text S1CONSORT Checklist(48 KB DOC)Click here for additional data file. Text S2Ethical Approval, Information Letter, and Consent Forms(2.8 MB PDF)Click here for additional data file.\n\n**Question:** Compared to Baseline communities that received standard Government services what was the result of Baseline communities that received additional education and preventive measures on HIV/AIDS meeting attendance?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
334
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Formoterol DPI 9 μg what was the result of Budesonide/formoterol pMDI 320/9 μg on Baseline-adjusted average 12-hour FEV1 at end of treatment?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
438
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Treatment of osteoarthritis of the knee with a topical diclofenac solution: a randomised controlled, 6-week trial [ISRCTN53366886]\n\n ABSTRACT.BACKGROUND:\nTopical NSAIDs have been proven to relieve the symptoms of osteoarthritis (OA) in short-term studies (2 weeks). To justify its chronic use, efficacy of a topical NSAID over a longer term of study should be demonstrated. The efficacy and safety of a topical diclofenac solution over a 6-week treatment course in symptomatic primary OA of the knee was investigated.\n\nABSTRACT.METHODS:\n216 men and women, age 40–85 years, with radiologically confirmed primary OA of the knee and a flare of pain at baseline following discontinuation of prior therapy were enrolled into this double-blind study. Participants applied either a topical diclofenac solution (Pennsaid®) or vehicle control solution (carrier with no diclofenac); 40 drops 4 times daily directly to the painful knee(s), without massage, for 6 weeks. Pre-planned primary efficacy outcome measures included the core continuous variables pain relief and improved physical function measured by the Western Ontario and McMaster Universities (WOMAC) LK3.1 OA Index, and improved patient global assessment (PGA). Secondary efficacy measure was reduced stiffness. Safety assessments included adverse events and vital signs.\n\nABSTRACT.RESULTS:\nThe topical diclofenac group had a significantly greater mean change in score (final minus baseline) compared to the vehicle control group for pain (-5.2 vs. -3.3, p = 0.003), physical function (-13.4 vs. -6.9, p = 0.001), PGA (-1.3 vs. -0.7, p = 0.0001) and stiffness (-1.8 vs. -0.9, p = 0.002). The mean difference between treatment arms (95% confidence interval [CI]) was 1.9 (0.7 to 3.2), 6.5 (2.5 to 10.5), 0.6 (0.2 to 0.9), and 0.9 (0.3 to 1.4), respectively. Safety analyses showed that topical diclofenac caused skin irritation, mostly minor local skin dryness, in 42/107 (39%), leading to discontinuation of treatment in 5/107 (5%) participants.\n\nABSTRACT.CONCLUSION:\nThis topical diclofenac solution demonstrated relief at 6 weeks of the symptoms of primary osteoarthritis of the knee.\n\nBODY.BACKGROUND:\nMeta-analysis of previous trials of topical non-steroidal anti-inflammatory drugs (NSAIDs) concluded that they effectively treat the pain of acute soft tissue injuries [1] and chronic musculoskeletal conditions [2,3]. Current evidence-based recommendations for the management of osteoarthritis (OA) support the use of topical NSAIDs and rubefacients [4-6] as a therapeutic option potentially with fewer gastrointestinal risks than oral NSAIDs [7]. However, a recent critical meta-analysis concluded that claims of pain relief in OA by currently available topical NSAIDs are supported by only a limited number of randomised controlled trials of small size and brief duration, with no data demonstrating efficacy beyond 2 weeks [8]. In this report, we present the efficacy and safety results from a 6-week controlled trial using a newer topical diclofenac solution in knee OA. Effect size data and number-needed-to-treat (NNT) are presented, facilitating comparison with the previously reviewed data.\n\nBODY.METHODS.PARTICIPANTS AND INCLUSION/EXCLUSION CRITERIA:\nThis study was conducted from November 1999 to August 2000, at 17 medical centres across central Canada, following approval by a central ethics review board (Integrated Research Incorporated, Ethics Review Committee, Montreal, QC). Participants were recruited from the physician's private practice or the surrounding community. At the screening visit, after providing written, informed consent, each participant underwent a screening interview and was eligible to proceed to washout if all inclusion criteria and no exclusion criteria were met. Inclusion criteria specified men and non-pregnant women, age 40–85 years, with primary OA of at least one knee, and a flare of pain after withdrawal of prior therapy with either an oral NSAID or acetaminophen (used at least 3 days per week during the previous month). Primary OA was defined by deterioration and abrasion of articular cartilage (joint space narrowing) or formation of new bone (osteophytes) at the joint surface of the knee (medial tibio-femoral, lateral tibio-femoral or patello-femoral), demonstrated on a radiological examination carried out within the previous 3 months [9]. Pain was measured by the Western Ontario and McMaster Universities LK3.1 OA Index (WOMAC) 5-item pain subscale, each item scored on a 5-point Likert scale (none = 0; mild = 1; moderate = 2; severe = 3; extreme = 4) [10]. Pain was scored at the screening visit, following which prior therapy was withdrawn. The patient scored the pain again at the baseline visit. A flare was defined as an increase in total pain subscale score of at least 2 and at least 25%, with a baseline total pain score of at least 6 (out of a possible 20), and a score of ≥2 (out of a possible 4) on at least one of the 5 items in the WOMAC pain subscale. Participants were excluded if they had secondary arthritis related to systemic inflammatory arthritis (including rheumatoid arthritis, psoriatic arthritis, post-infectious arthritis and metabolic arthritis, traumatic arthritis or surgical joint replacement); corticosteroid use: (a) oral corticosteroid within the previous 14 days, or (b) intramuscular corticosteroid within 30 days, or (c) intra-articular corticosteroid into the study knee within 90 days, or (d) intra-articular corticosteroid into any other joint within 30 days, or (e) topical corticosteroid at the site of application within 14 days; intra-articular viscosupplementation (e.g., Synvisc®) into the study knee in the preceding 90 days; ongoing use of prohibited medication including NSAID, other oral analgesic, muscle relaxant, or low-dose antidepressant for any chronic pain management; ongoing use of glucosamine or chondroitin (unless used continuously for 90 days prior to study entry); sensitivity to diclofenac, acetylsalicylic acid (ASA) or any other NSAID, acetaminophen, dimethyl sulphoxide, propylene glycol, glycerine or ethanol; clinically-active renal, hepatic or peptic ulcer disease; history of alcohol or drug abuse; lactation; concomitant skin disease at the application site; current application for disability benefits on the basis of knee osteoarthritis; fibromyalgia; other painful or disabling condition affecting the knee; or participation in another investigational drug trial in the previous 30 days.\n\nBODY.METHODS.INTERVENTIONS:\nAt the baseline visit, all patients that met the final entry criterion of a flare of pain were randomly assigned to receive one of two treatments: (a) topical diclofenac solution (Pennsaid®; Dimethaid Research Inc.), consisting of 1.5% (w/w) diclofenac sodium in a patented carrier containing dimethyl sulphoxide (45.5%, w/w), propylene glycol, glycerine, ethanol and water, or (b) vehicle control solution, consisting of the complete carrier (including dimethyl sulphoxide, 45.5% w/w) but no diclofenac. Participants applied a dose of 40 drops of study solution (about 1.3 mL) to the affected knee 4 times daily for up to 6 weeks. The participant was instructed to apply 10 drops of solution to each side of the knee (front, back, medial and lateral) either dripped directly onto the knee or first into the hand, and then spread over the site without massage. Compliance was verified by weighing the solution bottles at each visit. If the other knee was painful at any time during the study, it was treated and evaluated for safety, but efficacy analysis was performed on only the study knee – the one with the greater baseline pain score (or the dominant knee if both had the same score). Consumption of acetaminophen (up to four 325-mg tablets per day) was permitted for residual knee or other body pain throughout the treatment period, but not during the washout period prior to baseline assessment or during the week prior to final assessment at week 6. ASA (≤ 325 mg/day) was permitted for cardiovascular prophylaxis.\n\nBODY.METHODS.OUTCOME MEASURES:\nThe primary outcome measures were defined as the change from baseline to final assessment of the study knee in the 3 core continuous variables [11] pain and physical function, assessed using the WOMAC subscales, and patient global assessment (PGA). There was no intermediate assessment of efficacy. The WOMAC is a validated questionnaire [12] consisting of 24 questions (5 on pain, 17 on physical function and 2 on stiffness), each scored on a 5-point Likert scale (see Participants). The PGA question asked: \"How has the osteoarthritis in your study joint been over the last 48 hours?\" and was scored on a Likert scale (very good = 0; good = 1; fair = 2; poor = 3; very poor = 4). This question focuses on the treated site, unlike a PGA in an oral NSAID trial that can probe the non-signal joints. Secondary measure was change in stiffness. Ancillary measures defined a posteriori were pain on walking – the first question of the WOMAC pain subscale (referred to as 'use-related pain' [13]) – and the following dichotomous variables: 50% improvement in pain [3]; final PGA score of \"good\" or \"very good\" [3]; and response based on OMERACT-OARSI responder criteria [14] (a responder is defined as a participant with ≥ 50% improvement in pain or function that was ≥ 20% of the scale, or ≥ 20% improvement in at least two of pain, function or PGA that was ≥ 10% of the scale).\n\nBODY.METHODS.SAFETY ANALYSES:\nSafety was assessed during all clinic visits (weeks 3 and 6) and telephone 'visits' (weeks 1 and 5). Safety variables included adverse events, application-site dermatological reactions and vital signs. Adverse events were identified using open-ended questions and a checklist covering common oral NSAID side effects. Dermatological assessment of the knee was based on a standard scale [15] and any abnormality was recorded as an adverse event. All adverse events were categorised according to Coding Symbols for Thesaurus of Adverse Reaction Terms (COSTART) [16]. Laboratory assessment was not done.\n\nBODY.METHODS.SAMPLE SIZE:\nBased on a power of 80% and a Type I error rate of α = 0.052-tailed, a sample size of 80 participants per group was required to detect an estimated important difference of 2 between the treatment arms, in the change in WOMAC pain dimension score from baseline to final (with standard deviation of 4.5). A total sample size of 200 participants (100 per treatment group) was specified in the protocol, which allowed for a non-evaluable rate of up to 20%.\n\nBODY.METHODS.RANDOMISATION AND BLINDING:\nThe study kits were prepared, labelled and numbered according to a computer-generated randomisation schedule created by an outside consultant using a randomly chosen block size of 4 or 6. They were shipped to the sites in multiples of complete blocks to ensure that a balanced number of participants was assigned to the two treatment arms within each site. As a participant qualified for study entry at the baseline visit, the investigator assigned him/her the next randomisation number in a sequential manner. The randomisation schedule was concealed from the investigators, their support staff, study participants and the sponsor's clinical research personnel, until final data lock. Except for the individual participant identification number on the label, the two study solutions were identical clear, colourless liquids packaged in opaque bottles.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nSafety analyses were performed on all randomised participants who received at least one dose of study solution. There was no imputation of missing safety data. Efficacy analyses were performed on an intent-to-treat (ITT) group, defined as a subset of all randomised participants who met critical inclusion criteria (primary OA by history, an abnormal radiological study, and any degree of knee pain), as per ICH guidelines [17]. For any missing efficacy data in the ITT analysis, the last observation was carried forward. A per-protocol group was defined based on stricter adherence to study conduct, including requirement for a moderate flare of knee pain (see Participants) and treatment continuing for at least 40 days. Baseline demographic and clinical variables were analysed by Chi-square or Student's t-Test. Adverse event incidence was analysed by Chi-square or Fisher's Exact Test. Continuous variables (WOMAC dimensions, PGA and pain on walking) were analysed by ANCOVA with baseline score as the covariate without adjustment for testing secondary/alternative objectives. The dichotomous variables were analysed by Chi-square test. All statistical tests were two-sided and were performed at the 0.05 level of significance.\n\nBODY.RESULTS.PARTICIPANT FLOW:\nTwo hundred and sixteen participants were randomised to treatment with either topical diclofenac (n = 107) or vehicle control (n = 109). All participants received their allocated intervention. More participants in the topical diclofenac group (86 [80%]) completed the entire 6-week treatment period compared to the vehicle control group (70 [64%]; p = 0.008). Discontinuation rate due to an adverse event was similar in both groups. Dropout due to lack of effect was lower for topical diclofenac (8 [7.5%]) compared to vehicle control (18 [16.5%]; p = 0.041). No participant was lost to follow-up (Fig. 1). Figure 1Flow of participants.\n\nBODY.RESULTS.BASELINE DEMOGRAPHIC AND CLINICAL CHARACTERISTICS:\nNo significant difference was found between treatment groups in baseline demographic and clinical characteristics (Table 1). The mean (SD) screening and baseline pain scores were 8.2 (2.7) and 13.0 (3.2) in the topical diclofenac group versus 8.3 (3.0) and 12.8 (3.1) in the vehicle control group (12.9 [3.2] overall). Most participants treated both knees, either from baseline or by the end of the trial. Table 1 Baseline demographic and clinical characteristics of treatment groups Topical diclofenac (n = 107) Vehicle control (n = 109) Age (years) 65.0 (11.0) 64.6 (10.9) Women, number (%) 56 (52.3) 66 (60.6) Race/ethnicity, number (%) White 88 (82.2) 91 (83.5) Black 8 (7.5) 3 (2.8) Oriental 3 (2.8) 2 (1.8) Other 8 (7.5) 13 (11.9) Weight (kg) 89.9 (18.1) 86.5 (17.3) Height (m) 1.65 (0.11) 1.65 (0.10) Heart rate (bpm) 74.1 (10.0) 74.3 (9.1) Systolic blood pressure (mm Hg) 137.6 (16.3) 133.6 (15.6) Diastolic blood pressure (mm Hg) 81.4 (9.1) 79.7 (8.7) Total x-ray score* 7.7 (5.4) 7.0 (5.0) Screening pain score 8.2 (2.7) 8.3 (3.0) Baseline † pain score 13.0 (3.2) 12.8 (3.1) Baseline † physical function score 40.7 (11.9) 40.4 (11.2) Baseline † stiffness score 5.2 (1.5) 5.2 (1.5) Patient global assessment score‡ 3.1 (0.8) 3.2 (0.8) Participants treating two knees at baseline, number (%) 64 (59.8) 70 (64.2) Participants treating two knees at final, number (%) 84 (78.5) 89 (81.7) Data are presented as mean (SD) unless otherwise indicated. *Total score of joint space narrowing, marginal osteophytes formation and subchondrial sclerosis for each knee compartment (medial, lateral, patello-femoral); maximum score possible was 27. †After washout of prior therapy; pain scale ranged from 0 (no pain) to 20 (extreme pain); physical function scale ranged from 0 (no difficulty) to 68 (extreme difficulty); stiffness scale ranged from 0 (no stiffness) to 8 (extreme stiffness). ‡Patient global assessment was measured using a Likert scale, ranging from 0 (very good) to 4 (very poor). Mean (SD) duration of treatment in the topical diclofenac group was 38.2 (9.9) days versus 34.4 (12.5) days in the vehicle control group (p = 0.013). Compliance with the dosing regime was 83.1 % and 84.5% for the topical diclofenac and vehicle control groups, respectively. No significant difference was noted in the mean (SD) consumption of rescue acetaminophen tablets per day between the topical diclofenac (0.9 [0.9]) and vehicle control groups (1.1 [1.0]; p = 0.079).\n\nBODY.RESULTS.EFFICACY ANALYSES:\nFour of 216 randomized participants were not included in the ITT analysis group because they violated major entry criteria: 2 participants lacked radiological confirmation of OA (no radiological examination for one participant and a normal examination for the other), and 2 participants had secondary OA (related to osteochondroma). Inclusion of these participants yielded the same results in a subsequent re-analysis (data not shown).\n\nBODY.RESULTS.EFFICACY ANALYSES.PLANNED ANALYSES:\nThere was a significantly greater improvement in score with topical diclofenac compared to vehicle control (Table 2) for pain (-5.2 vs. -3.3; p = 0.003,), physical function (-13.4 vs. -6.9; p = 0.001), PGA (-1.3 vs. -0.7; p = 0.0001) and stiffness (-1.8 vs. -0. 9; p = 0.002) Analysis of the per protocol group of 128 participants confirmed the statistical superiority of topical diclofenac over vehicle control for the primary and secondary outcome measures (p < 0.01; data not shown). Table 2 Efficacy evaluation of the continuous variables Efficacy variable Treatment group N Baseline score, mean (SD) Change in score mean (SD) Mean difference in change (95% CI) P-value Effect size (95% CI) Pain Topical diclofenac 105 13.0 (3.1) -5.2 (5.0) 1.9 (0.7 to 3.2) 0.003 0.41 (0.14 to 0.68) Vehicle control 107 12.7 (3.2) -3.3 (4.3) Physical function Topical diclofenac 105 40.9 (11.9) -13.4 (16.3) 6.5 (2.5 to 10.5) 0.001 0.44 (0.16 to 0.71) Vehicle control 107 40.3 (11.3) -6.9 (13.2) Patient global assessment Topical diclofenac 105 3.1 (0.8) -1.3 (1.3) 0.6 (0.2 to 0.9) 0.0001 0.47 (0.19 to 0.74) Vehicle control 107 3.2 (0.7) -0.7 (1.1) Stiffness Topical diclofenac 105 5.3 (1.4) -1.8 (2.1) 0.9 (0.3 to 1.4) 0.002 0.43 (0.15 to 0.70) Vehicle control 107 5.2 (1.5) -0.9 (2.0) Pain on walking Topical diclofenac 105 2.7 (0.8) -1.2 (1.2) 0.4 (0.1 to 0.7) 0.014 0.34 (0.07 to 0.61) Vehicle control 107 2.7 (0.8) -0.8 (1.1) \n\nBODY.RESULTS.EFFICACY ANALYSES.A POSTERIORI ANALYSES:\nThere was a significantly greater improvement in score with topical diclofenac compared to vehicle control (Table 2) for pain on walking (-1.2 vs. -0.8; p = 0.014). The response rate for at least a 50% reduction in pain (Table 3) was significantly greater following topical diclofenac treatment compared to vehicle control (46/105 [43.8%] vs. 27/107 [25.2%]; p = 0.004). The topical diclofenac group had a significantly greater number of participants with good or very good PGA response (43.8% vs. 16.8%; p <0.0001) compared to the vehicle control group and of OMERACT-OARSI responders (65.7% vs. 49.5%; p = 0.017). Table 3 Efficacy evaluation of the dichotomous variables Efficacy variables Treatment group N Number (%) of participants p-value Number-needed-to-treat (95% CI) 50% reduction in pain Topical diclofenac 105 46 (43.8) 0.004 5 (3–17) Vehicle control 107 27 (25.2) OMERACT-OARSI responder* Topical diclofenac 105 69 (65.7) 0.017 6 (3–33) Vehicle control 107 53 (49.5) Good or very good PGA response Topical diclofenac 105 46 (43.8) <0.0001 4 (3–7) Vehicle control 107 18 (16.8) *A responder is defined as a participant with ≥ 50% improvement in pain or function that was ≥ 20% of the scale, or ≥ 20% improvement in at least two of pain, function or patient global assessment that was ≥ 10% of the scale. \n\nBODY.RESULTS.ADVERSE EVENTS:\nThe major adverse effect reported was dry skin at the application site, occurring in 42/107 (39.3%) and 23/109 (21.1%; p = 0.004) of topical diclofenac and vehicle control participants, respectively (Table 4). A skin-related adverse event led to discontinuation of only 5 participants in the topical diclofenac group. All skin reactions resolved promptly upon withdrawal of treatment. Abdominal pain and dyspepsia each were reported in 4 [3.7%] participants in the topical diclofenac group compared to 1 [0.9%] participant in the vehicle control group, but this difference was not significant (p = 0.21). Table 4 Number (%) of adverse events Adverse Event Topical diclofenac (n = 107) Vehicle control (n = 109) Gastrointestinal reaction Abdominal pain 4 (3.7) 1 (0.9) Constipation 1 (0.9) 1 (0.9) Diarrhea 1 (0.9) 0 Dyspepsia 4 (3.7) 1 (0.9) Gastritis 1 (0.9) 0 Melena 0 1 (0.9) Nausea 1 (0.9) 2 (1.8) Application-site skin reaction Dry skin 42 (39.3)* 23 (21.1) Rash 2 (1.9) 4 (3.7) Paresthesia 2 (1.9) 2 (1.8) Pruritus 0 2 (1.8) Other reaction Headache 6 (5.6) 10 (9.2) Halitosis 2 (1.9) 0 Taste Perversion 4 (3.7) 2 (1.8) *p < 0.01 vs. vehicle control \n\nBODY.DISCUSSION:\nPublished guidelines have incorporated topical NSAIDs as recommended treatment for OA of the knee [4-6]. However, there has been controversy surrounding the adequacy of data supporting their benefit beyond 2 weeks [2,3,8,18]. Moreover, the studies identified in these meta-analyses generally did not conform to current standards for OA trial design [11,19]. In contrast, the present trial utilized standardized radiological and clinical entry criteria and measured efficacy with validated outcome measures. Baseline pain score was substantial; mean (SD) score was 12.9 (3.2) out of a maximum of 20, indicating a flare of pain following withdrawal of prior therapy. Analysis of all of the primary and secondary measures demonstrated that treatment with this topical diclofenac solution relieved the symptoms of primary knee OA at 6 weeks in this study population. Two other recently published trials using this topical diclofenac solution showed it to be superior to vehicle control and/or placebo; a 4-week, non-flare trial of 248 participants [20] and a 12-week, flare trial of 326 participants [21]. As with most NSAID trials, the subject population in this study was selected by the inclusion criterion of a flare of pain, which demonstrates the potential to respond to NSAID/analgesic. In clinical practice, an individual not taking an analgesic may have considered previous NSAID therapy ineffective, in which case s/he would not be expected to respond to topical diclofenac. However, where an individual is intolerant to oral NSAID, one may consider topical diclofenac as a treatment option. Comparison of efficacy results from independent trials with various treatments is facilitated by the introduction of benchmark determinants that are mathematically derived from the experimental raw data, such as effect size [22] for improvement of a continuous variable (e.g. \"How much did the patient's pain improve, relative to placebo?\"). We calculated an effect size (95% CI) of 0.41 (0.14 to 0.68) for pain relief, 0.44 (0.16 to 0.71) for improved physical function and 0.34–0.47 for improved measures of PGA, stiffness and pain on walking (Table 2). In contrast, Lin et al. [8] calculated a pooled effect size for pain relief of 0.04 (essentially no effect) in 3 placebo-controlled topical NSAID trials of 4 weeks duration. A meta-analysis of 23 oral NSAID trials for OA knee, lasting 2–13 weeks, reported a pooled effect size of 0.32 for pain reduction and 0.29 for improving physical function [23]. Another meta-analysis of 14 OA trials found a pooled effect size of 0.37 for pain reduction with oral NSAIDs and 0.44 for coxibs [24]. Zhang et al. [25], using data from 2 oral NSAID studies of 6–12 weeks duration, calculated a pooled effect size for OA pain reduction of 0.34. Efficacy of a treatment is being expressed increasingly as a dichotomous result, e.g. \"Did the patient's pain improve by 50%; yes or no?\". We derived the response rate for each dichotomous variable from our raw data, and demonstrated the superiority of topical diclofenac over vehicle control for 50% reduction in pain, achieving a good or very good final PGA response, and 'response' by OMERACT-OARSI criteria (Table 3). The benchmark determinant for comparing dichotomous efficacy results of various treatments is the number-needed-to-treat (NNT) [26]. We calculated a NNT between 4 and 6, depending upon the variable (Table 3). In their meta-analysis of topical NSAIDs, Mason et al. [3] cited 5 placebo-controlled trials of short duration for OA knee pain – 8 days (1 trial), 14 days (3 trials), and 28 days (1 trial). Their definition of clinical success, representing approximately a 50% reduction of pain, was estimated using patient or physician global assessment as the outcome measure (4 trials and 1 trial, respectively). They calculated a NNT of 5.3. Few oral NSAID studies have reported dichotomous data. Osiri et al. [26] reported a NNT for pain improvement of 4.4 with etodolac and 3.8 with tenoxicam. Defining improvement as an increase of at least 2 grades (on a 0–5 scale) in the patient's global rating of arthritis, Edwards et al. [27] reported a NNT of 11–13 for valdecoxib treatment of OA. The OMERACT-OARSI initiative used a consensus approach to derive dichotomous 'responder' criteria [14]. Through their vast meta-analysis of suitable trials, the authors found that for trials of oral NSAIDs vs. placebo the responder rates were 65.4% and 45.9% respectively. Responder rates of 60–65% have been reported for 13-week treatment of OA with celecoxib and lumiracoxib, with placebo responder rates of 49–53% [28,29]. The OMERACT-OARSI initiative did not look at topicals but we applied its criteria to this study and found a responder rate for topical diclofenac of 65.7% with a placebo responder rate of 49.5%, similar to their oral NSAID data. A caveat in the application of the mathematical benchmarks, effect size and NNT, is the influence of trial design, outcome measures and patient population on the apparent magnitude of response to a given treatment. Because the trials with topical diclofenac were designed according to the OARSI guidelines, like most recent NSAID and cyclooxygenase-2 (COX-2) inhibitor studies, such comparison of results is reasonable [19]. Although the data observed for topical diclofenac in this trial are comparable to other NSAID trials, a direct head-to-head comparison trial is required to prove equivalency of two treatments. A previously published 12-week comparative trial of 622 participants with OA knee confirmed the clinical equivalence between topical diclofenac solution and oral diclofenac [30]. Safety analysis revealed no serious clinical adverse effects and only minor application-site skin reactions, mostly skin dryness, following treatment with topical diclofenac. While dimethyl sulphoxide in the carrier acts as a penetrant [31], it also dissolves normal surface oils and leaves the skin dry. Common skin lubricants may prevent most application site reactions and any related discontinued therapy, but such products were not permitted in this trial in order to detect the maximum potential side effect profile of the study solutions. The low dropout rate due to skin reactions (5/107 [4.7%] for topical diclofenac) suggests patient acceptance of the overall topical treatment regime. The use of a checklist to prompt the patient about possible adverse events likely yielded a high estimate of the true incidence of gastrointestinal adverse reactions caused by topical diclofenac. The report of abdominal pain and dyspepsia each in 3.7% of patients is consistent with what was seen in other published trials of this topical diclofenac [20,21] and much lower than commonly experienced with oral NSAIDs or COX-2s [30]. Those other trials included results of laboratory testing and found minor abnormality of liver enzymes in 2–5%, creatinine in 1% and haemoglobin in 2% of patients, significantly lower than with oral diclofenac [30]. This safety profile can be predicted from the low systemic availability of topically applied diclofenac. Although the patient applies a daily dose (40 drops, 4 times a day) of 86 mg of diclofenac to the knee, the blood level is only 12 ng/mL [31]. The level reported after oral administration of 50 mg Voltaren® is 1500 ng/mL [32]. Similar improved safety with topical NSAIDs has been reported previously [33].\n\nBODY.CONCLUSION:\nTopical diclofenac solution provides 6-week relief of the symptoms of knee OA. The data in this and previous reports provide substantial evidence for the efficacy and safety of topical diclofenac solution in chronic OA.\n\nBODY.COMPETING INTERESTS:\nLMT and ZS are employees of Dimethaid Research Inc. PAB was a principal investigator in the trial, and was remunerated for his participation.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nPAB was a major investigator in the trial and was involved in data interpretation. LMT was involved in analysis and interpretation of the data and writing of the manuscript. ZS was involved in trial design and conduct, data review and writing of the manuscript. All authors reviewed and approved the final draft of the manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here:\n\n**Question:** Compared to vehicle control solution (carrier with no diclofenac) what was the result of topical diclofenac solution (Pennsaid®) on good or very good PGA response and OMERACT-OARSI responder?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
358
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Placebo what was the result of Budesonide/formoterol pMDI 160/9 μg on Sleep score improvement?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
371
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Formoterol DPI 9 μg what was the result of Budesonide/formoterol pMDI 320/9 μg on Sleep score improvement?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
409
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pentobarbital versus thiopental in the treatment of refractory intracranial hypertension in patients with traumatic brain injury: a randomized controlled trial\n\n ABSTRACT.INTRODUCTION:\nExperimental research has demonstrated that the level of neuroprotection conferred by the various barbiturates is not equal. Until now no controlled studies have been conducted to compare their effectiveness, even though the Brain Trauma Foundation Guidelines recommend that such studies be undertaken. The objectives of the present study were to assess the effectiveness of pentobarbital and thiopental in terms of controlling refractory intracranial hypertension in patients with severe traumatic brain injury, and to evaluate the adverse effects of treatment.\n\nABSTRACT.METHODS:\nThis was a prospective, randomized, cohort study comparing two treatments: pentobarbital and thiopental. Patients who had suffered a severe traumatic brain injury (Glasgow Coma Scale score after resuscitation ≤ 8 points or neurological deterioration during the first week after trauma) and with refractory intracranial hypertension (intracranial pressure > 20 mmHg) first-tier measures, in accordance with the Brain Trauma Foundation Guidelines.\n\nABSTRACT.RESULTS:\nA total of 44 patients (22 in each group) were included over a 5-year period. There were no statistically significant differences in ' baseline characteristics, except for admission computed cranial tomography characteristics, using the Traumatic Coma Data Bank classification. Uncontrollable intracranial pressure occurred in 11 patients (50%) in the thiopental treatment group and in 18 patients (82%) in the pentobarbital group (P = 0.03). Under logistic regression analysis – undertaken in an effort to adjust for the cranial tomography characteristics, which were unfavourable for pentobarbital – thiopental was more effective than pentobarbital in terms of controlling intracranial pressure (odds ratio = 5.1, 95% confidence interval 1.2 to 21.9; P = 0.027). There were no significant differences between the two groups with respect to the incidence of arterial hypotension or infection.\n\nABSTRACT.CONCLUSIONS:\nThiopental appeared to be more effective than pentobarbital in controlling intracranial hypertension refractory to first-tier measures. These findings should be interpreted with caution because of the imbalance in cranial tomography characteristics and the different dosages employed in the two arms of the study. The incidence of adverse effects was similar in both groups.\n\nABSTRACT.TRIAL REGISTRATION:\n(Trial registration: US Clinical Trials registry NCT00622570.)\n\nBODY.INTRODUCTION:\nHigh dosages of barbiturates are used in patients with severe traumatic brain injury (TBI) who present with refractory intracranial hypertension (ICH) after medical and surgical treatment. This practice is recommended in the Brain Trauma Foundation (BTF) Guidelines, because this is the only second-level measure for which there is class II evidence that it can reduce intracranial pressure (ICP) [1]. Nevertheless, its effect on outcome is unproven [2], mainly because of severe medical complications. Within the family of barbiturates the oxibarbiturates and thiobarbiturates stand out, their primary representatives being pentobarbital and thiopental. Until now no controlled studies have been reported that compare the effectiveness of pentobarbital and thiopental in controlling ICH. At the experimental level, research has demonstrated that mechanisms of action and levels of neuroprotection differ between these agents [3-6]. For this reason, research is needed to compare the effectiveness of these two drugs in terms of controlling refractory ICH in patients with severe TBI. Based on various studies conducted in laboratory animals [3-6], suggesting that the neuroprotective capacity of thiopental is superior, our working hypothesis was that thiopental is more effective than pentobarbital in controlling ICP in patients with severe TBI, with a similar incidence of adverse side effects. In support of our work in the present study, the BTF Guidelines recommend that studies be undertaken to compare the effectiveness of the different barbiturates that are currently used in TBI patients [1].\n\nBODY.MATERIALS AND METHODS:\nWe conducted a prospective, randomized cohort study comparing two treatments: pentobarbital and thiopental. Our primary objective was to compare the effectiveness of these agents in controlling refractory ICH in patients with severe TBI. Secondary objectives were to compare the incidence of secondary effects, especially arterial hypotension, which was defined as the presence of mean arterial pressure (MAP) under 80 mmHg at any point during barbiturate therapy. This study was conducted at Son Dureta University Hospital (Palma de Mallorca, Spain) and was approved by the Ethics Committee of the Balearic Islands on 31 March 2002. It is registered with the US Clinical Trials Registry, with the number NCT00622570. In all cases, the patient's closest relative, legal representative, or guardian gave written informed consent for their inclusion in the study.\n\nBODY.MATERIALS AND METHODS.INCLUSION CRITERIA:\nPatients admitted to our intensive care unit (ICU) between May 2002 and July 2007 with a severe TBI (Glasgow Coma Scale [GCS] score after nonsurgical resuscitation ≤ 8) and presenting with refractory ICH (ICP > 20 mmHg), and who underwent first-level measures in accordance with the BTF Guidelines [7], were included. Refractory ICH was defined as follows: ICP 21 to 29 mmHg for 30 minutes or more, ICP of 30 to 39 mmHg for 15 minutes or more, or ICP greater than 40 mmHg for more than 1 minute, in the absence of external interventions. Included patients were required to be haemodynamically stable at the point of inclusion in the study; haemodynamic stability was defined as systolic blood pressure of 100 mmHg or greater.\n\nBODY.MATERIALS AND METHODS.EXCLUSION CRITERIA:\nWe did not include in the study patients who were younger than 15 or older than 76 years; patients with a GCS score of 3 upon admission and neurological signs of brain death (bilateral arreactive midryasis and loss of brainstem reflexes); and patients who were pregnant, had barbiturate allergy or intolerance, or had a history of severe cardiac ventricular dysfunction with an ejection fraction under 35%.\n\nBODY.MATERIALS AND METHODS.GENERAL THERAPEUTIC PROTOCOL:\nAll patients with severe TBI underwent cranial computed tomography (CT) upon admission and were categorized in accordance with the classification proposed by the Traumatic Coma Data Bank [8]. We also recorded findings of CTs conducted before inclusion of the patients in the study. The CT findings on inclusion were regarded to be the worst of the hospital stay; the prognostic value of such CT findings have been described by other authors [9]. CTs were independently reviewed and categorized by two neurosurgeons (JI and MB) who were unaware of the treatment group to which the patients had been assigned. In cases of disagreement between these investigators, a third investigator reviewed the CT images. All patients' ICP was monitored using an intraparenchymal Camino catheter (Integra Neurosciences, Plainsboro, NJ, USA). The ICP catheter was placed in the frontal region of the hemisphere with more radiological lesions on the CT. The systemic monitoring of these patients included invasive blood pressure, pulse oximetry, and a pulmonary artery thermodilution catheter. The ICP, MAP and cerebral perfusion pressure data were gathered on an hourly basis (one value every full hour) throughout the study using the Care Vue® clinical monitoring system (Phillips, Eindhoven, The Netherlands). The general treatment objectives in patients with severe TBI were to maintain MAP above 80 mmHg, ICP below 20 mmHg, and cerebral perfusion pressure above 60 mmHg. To achieve these objectives, we used liquids and/or vasoactive support with norepinephrine (noradrenaline). In patients with ICP greater than 20 mmHg, initial treatment included elevation of the head of the bed, keeping the neck straight, appropriate sedation, muscular paralysis, ventricular drainage (if the patient had visible ventricles on the CT), 20% mannitol (0.25 to 0.75 mg/kg), 7.5% hypertonic saline (2 ml/kg) and moderate hyperventilation (partial carbon dioxide tension of 30 to 35 mmHg). Neurosurgical interventions were undertaken when necessary to evacuate surgical lesions. This approach can be considered conventional treatment and is included in the BTF Guidelines as first-tier therapy [7]. Patients whose ICP remained high with conventional treatment were included in the study. Before randomization of the patient to a study group, we required that patient to have received maximal medical treatment (first-level measures). In addition, we required a CT to have been conducted within 24 hours before inclusion of the patient in the study; intravenous administration of 0.7 g/kg mannitol 1 hour before randomization; or a plasmatic osmolarity measurement above 320 mOsm/kg, in order to ensure that hyperosmolar therapy had been optimized before inclusion.\n\nBODY.MATERIALS AND METHODS.RANDOMISATION:\nRandomization was based on a computer-generated list that intercollated the two drugs. Allocation was done by the intensive care unit physician who was on duty, once the patient had been found to meet the inclusion criteria and none of the exclusion criteria. Data collection and patient follow up were conducted by the same investigator (JPB).\n\nBODY.MATERIALS AND METHODS.BLINDING OF TREATMENT GROUPS:\nThe study was not blinded because it was difficult for us to mask treatment; thiopental is liophylized for administration and pentobarbital is not.\n\nBODY.MATERIALS AND METHODS.ADMINISTRATION OF BARBITURATES AND MONITORING OF EFFECTS:\nPentobarbital was administered in accordance with the protocol established by Eisenberg and coworkers [10], using a loading dose of 10 mg/kg over 30 minutes followed by a continuous perfusion of 5 mg/kg per hour for 3 hours. This was followed by a maintenance dosage of 1 mg/kg per hour. Thiopental was administered in the form of a 2 mg/kg bolus administered over 20 seconds. If the ICP was not lowered to below 20 mmHg, then the protocol permitted a second bolus of 3 mg/kg, which could be readministered at 5 mg/kg if necessary to reduce persistently elevated ICP. The maintenance dosage was an infusion of thiopental at a rate of 3 mg/kg per hour. In both treatment groups, for cases in which the maintenance dosage did not achieve the reduction in ICP to below the 20 mmHg threshold, the maintenance dosage for both drugs could be increased by 1 mg/kg per hour, while looking for electroencephalographic burst suppression or even the flat pattern, in order to ensure that different doses of the two barbiturates were equipotent. Electroencephalography was conducted daily in a noncontinuous manner (Nicolet; Viasys Healthcare, Verona Road, Madison, WI, USA). Results were analyzed by an experienced neurologist who was blinded to the treatment of the patients. In those patients in whom barbiturate coma did not control ICP, we used decompressive craniotomy and/or external lumbar drainage, in accordance with the Munch criteria, as life-saving measures [11,12].\n\nBODY.MATERIALS AND METHODS.EFFECTIVENESS CRITERIA:\nAdequate response to treatment was defined as a decrease in ICP to below 20 mmHg, and maintenance below this threshold for at least 48 hours. To describe the ICP, we also followed the criteria previously employed by Stocchetti and coworkers [13]; the arithmetic mean of ICP data recorded during every 24-hour period, after filtering to exclude inaccurate readings, was calculated and expressed as 'mean ICP'. Three ICP blocks were considered for further analysis: less than 20 mmHg, 20 to 30 mmHg, and more than 30 mmHg. Uncontrollable ICP was defined as follows: ICP of 21 to 35 mmHg for 4 hours, ICP of 36 to 40 mmHg for 1 hour, or ICP above 41 mmHg for 5 minutes, in the absence of external interventions. We also defined as unresponsive to treatment those cases in which, because of refractory ICP, the patient needed some other treatment (surgery and/or lumbar drainage) and cases in which the patient progressed to brain death. Although it was not a main objective of the study, patients were evaluated 6 months after injury using the Glasgow Outcome Scale [14].\n\nBODY.MATERIALS AND METHODS.WITHDRAWAL OF TREATMENT:\nWhen ICP was controlled (<20 mmHg for 48 hours), we conducted a step-wise reduction in the barbiturate coma in steps that reduced the dosage by 50% every 24 hours until the infusion was suspended. In the event of ICP values rising to the study's inclusion values during the withdrawal of barbiturate treatment, the perfusion dosage was once again increased to achieve control of the patient's ICP.\n\nBODY.MATERIALS AND METHODS.SAMPLE SIZE:\nAccepting an α error of 0.05 and a β error of 0.2 in a bilateral hypothesis contrast, we estimated that 47 patients were needed in each group to detect differences of 30% or greater in the control of ICH. To calculate sample size, we assumed that the therapeutic response rate in the pentobarbital group would be 50%, excluding patients lost to follow up.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nQuantitative variables are expressed as the mean and standard deviation from the mean (SD) in normal distributions, and as median and interquartile range in cases that were not normally distributed. Qualitative variables are expressed as percentages, along with 95% confidence interval (CI). To determine whether variables followed a normal distribution, we used the Shapiro Wilks test. For the comparison of quantitative variables, Student's t-test was used if the variable followed a normal distribution. In other cases, we used the Mann-Whitney U-test. For the comparison of qualitative variables, we used χ2 or Fisher's exact test, as appropriate. Given that the randomization did not create groups that were similar in terms of types of intracranial lesions shown on the CT results, which is a prognostic variable that influences the effectiveness of barbiturate treatment in controlling ICP, we conducted a multivariate analysis using binary logistic regression, so that we would include the prognostic variables with the most plausible association with the dependent variable 'uncontrollable ICP'. These are variables such as age, GCS score at admission, and the worst CT obtained within 24 hours before inclusion of the patient in the study, as well as the type of barbiturate administered. To achieve this multivariate analysis, and given the small number of cases in each of the five groups in Marshall's classification, the CT data were grouped into focal and diffuse lesions. We also included in the model the minimum daily MAP during barbiturate treatment, given that in the second and third days of treatment there were statistically significant differences between the groups in the univariate analysis. The significant variables identified by the 'likelihood ratio' ≤ 0.1 test were used, along with those whose inclusion affected the calculation of the effect of the 'treatment group' variable. Both treatment groups were very similar in terms of other known prognostic variables, such as the presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them, so these were not included in the multivariate analysis. To analyze the variable ICP, which was determined on an hourly basis, we calculated the area under the curve (AUC) at 24, 48 and 72 hours, and also standardized by time [15]. For all comparisons, we considered statistical significance to have been achieved if the two-tailed α error probability was 5% or less (P ≤ 0.05). Statistical analyses were conducted using SPSS version 15 (SPSS Inc., Chicago, IL, USA).\n\nBODY.RESULTS:\nPreliminary results for the first 20 patients have already been published elsewhere [16]. From May 2002 to July 2007, 480 TBI patients were admitted to the intensive care unit of the Son Dureta University Hospital. Of these 480 patients, 71 (14.8%) presented with ICH refractory to first-level measures, of whom 44 were included in the study. The study was concluded prematurely because of the unexpected and slow inclusion rate; this could have modified some uncontrollable environmental factors that may affect results. The reasons for not including the remaining 27 refractory ICH cases were as follows: 13 patients were included in other studies, six were older than 76 years, five were admitted with nonreacting midriatic pupils and with clinical evidence of brain death, two presented with haemodynamic instability at the time of randomization, and one patient was transferred to a different hospital during the first 24 hours of admission, which excluded that patient from follow-up analysis. On average, the barbiturate coma was initiated in the thiopental group at 89 ± 15.5 hours after admission and in the pentobarbital group at 61 ± 14.3 hours after admission (P = 0.33). The baseline characteristics of the 44 patients included in the study, 22 randomized to each group, are presented in Table 1. There were no statistically significant differences with respect to epidemiological data, co-morbidity (data not shown) or lesions associated with TBI, although there were differences in the CT classification. Table 1 Baseline characteristics of patient population Characteristic Thiopental (n = 22) Pentobarbital (n = 22) P Sex (male; n) 19 19 1 Age (years) 26 (20 to 41) 32 (22 to 43) 0.45 ISS 25 (24 to 34) 25 (25 to 38) 0.77 SAPS II 42 (28 to 54) 43 (38 to 46) 0.95 APACHE II 23 (15 to 25) 20 (18 to 26) 0.27 APACHE III 60 (38 to 73) 52 (32 to 76) 0.41 Associated lesion (n) Thoracic injury 7 2 0.13 Abdominal injury 4 1 0.34 Extremities injury 9 5 0.20 Admission CT (n) Diffuse injury without brain swelling 12 4 0.046 Diffuse bilateral brain swelling 6 12 Diffuse unilateral brain swelling with midline shift 1 0 Any mass lesion > 25 ml 3 6 Age, ISS, SAPS II, APACHE II and APACHE III are expressed as median and interquartile range. APACHE, Acute Physiology and Chronic Health Evaluation; admission CT, admission computed tomography (according to the Traumatic Coma Data Bank); ISS, Injury Severity Score; SAPS, Simplified Acute Physiology. The summary of prognostic variables for the 44 patients is shown in Table 2. As in Table 1 the characteristics of the worst CT conducted before inclusion in the study differed between the two groups. Table 2 Prognostic variables of patient population Variable Thiopental (n = 22) Pentobarbital (n = 22) P Admission GCS score 6.5 (3.0 to 7.2) 7 (4.7 to 10.0) 0.38 Out-of-hospital hypoxia (n) 5 7 0.63 Out-of-hospital hypotension (n) 5 4 1 Pupillary reactivity (n) a One reacting 3 5 0.66 Both reacting b 12 14 Pre-enrolment CT (n) Diffuse injury without brain swelling 8 5 0.04 Diffuse bilateral brain swelling 1 8 Diffuse injury unilateral brain swelling with midline shift 5 1 Any mass lesion evacuated 7 5 Nonevacuated mass lesion 1 3 Admission GCS is expressed as median (interquartile range). a Pupillary reactivity at hospital admission. b Miotic pupils were considered as reactive. CT, computed tomography; GCS, Glasgow Coma Scale. \n\nBODY.RESULTS.EFFECTIVENESS CRITERION: CONTROL OF INTRACRANIAL PRESSURE:\nThe distribution of the ICP during the first 3 days of treatment, according to Stocchetti's criteria, is summarized in Table 3. The missing cases during these 3 days were due to brain deaths or to receipt of rescue treatment for uncontrollable ICP. Finally ICP was uncontrollable in 11 cases (50%) in the thiopental group and in 18 patients (82%) in the pentobarbital group (P = 0.03). In nonresponding patients, we chose to place a lumbar drainage in five, in three we opted for surgical treatment, and in three other patients we combined both treatments, drainage and surgery. Surgical decompression was conducted in four patients in the thiopental group and in two of the patients in the pentobarbital group. The number of hyperosmolar treatments administered (manitol and/or hypertonic saline) during the barbiturate coma was similar in both groups: 16.5 (8.0 to 24.2) in the thiopental group and 16.5 (3.0 to 21.5) in the pentobarbital group (P = 0.9). The mean ± SD duration of the barbiturate coma was 156 ± 60 hours for thiopental and 108 ± 100 hours for pentobarbital (P = 0.06). Seven (31.8%) patients presented an ICP rebound with thiopental and six (27.3%) with pentobarbital (P = 0.74) during treatment withdrawal. Table 3 Mean ICP recorded per day during the first 3 days of barbiturate coma Drug Day Mean ICP (n[%]) <20 mmHg 20 to 30 mmHg >30 mmHg Thiopental 1 10 46 11 50 1 5 2 15 71 4 19 2 10 3 12 63 6 32 1 5 Pentobarbital 1 9 41 8 36 5 23 2 8 38 9 43 4 19 3 6 43 8 57 0 0 Mean intracranial pressure (ICP) is the arithmetic mean of ICP data recorded during every 24-hour period, according to Stocchetti's criteria [ 13 ]. Data are presented as number of cases and as a percentage of the total number of cases each day. Figure 1 presents the AUC for ICP above 20 mmHg, standardized over time, as follows. The ICP value of AUC0–24 h was 458.00 mmHg·hour (95% CI = 421.84 to 494.16) in the thiopental group and 550.63 mmHg·hour (95% CI = 411.31 to 689.95) in the pentobarbital group. The AUC0–48 h was 913.18 mmHg·hour (95% CI = 814.08 to 1,012.27) in the thiopental group and 997.27 mmHg·hour (95% CI = 757.10 to 1,237.43) in the pentobarbital group. The AUC0–72 h in the thiopental group was 1,291.69 mmHg·hour (95% CI = 1,172.27 to 1,411.12) and 1,399.73 mmHg·hour (95% CI = 1,291.11 to 1,508.35) in the pentobarbital group. Standardized over time, the AUC per hour in the thiopental group was 23.90 mmHg (95% CI = 22.00 to 25.81) and in the pentobarbital group it was 29.39 mmHg (95% CI = 23.20 to 35.59). Figure 1AUC of ICP data. Presented are areas under the curve (AUCs) of the intracranial pressure (ICP) data, standardized by time, with a base value of 20 mmHg. Both treatment groups were similar in terms of known prognostic variables, such as presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them. Therefore, these were not included in the multivariate analysis. The logistic regression analysis showed that, after adjusting for the worst CT and the type of barbiturate used, thiopental was five times more likely than pentobarbital to control ICP (odds ratio = 5.1, 95% CI = 1.2 to 21.9; P = 0.027). The Hosmer-Lemeshow test indicated that the fit of the model was good (P = 0.799). The association of focal lesions in the pre-inclusion CT with ICP control was 3.6 times higher than that for the diffuse lesions. The relative risk for good control of ICP in the thiopental versus pentobarbital group was 2.26 for patients with focal lesions and 3.52 for those who presented with diffuse lesions. The other variables analyzed did not exhibit a significant relationship to ICP control, and did not modify the effect of the barbiturate treatment, including the third day minimum MAP, which was significantly different between the two treatments (data not shown).\n\nBODY.RESULTS.ADVERSE SIDE EFFECTS DURING THE BARBITURATE COMA:\nThe secondary effects during the barbiturate coma are presented in Table 4. In both groups almost all patients presented with at least one MAP measurement below 80 mmHg. There were no differences between groups with respect to the incidence of infections, Sepsis related Organ-Failure Assessment (SOFA) scores before initiation of treatment, or the maximum SOFA value [17] during the entire period of barbiturate coma. Table 4 Adverse events during barbiturate coma Adverse event Thiopental (n = 22) Pentobarbital (n = 22) P Hypotension a 21 20 1 Respiratory infection b 18 17 1 Urinary infection c 0 2 0.49 Positive blood culture 4 1 0.34 ICP catheter colonization 7 5 0.5 CNS infection (CSF) d 3 0 0.23 SOFA pre e 7 (4.5 to 9.5) 8.0 (5.5 to 9.0) 0.57 SOFA maximum f 11 (10 to 12) 11 (10 to 12) 0.94 a Hypotension is defined as detection of a medium arterial blood pressure below 80 mmHg at any time during barbiturate coma. b Respiratory infection: presence of a positive sputum culture. c Urinary infection: presence of a positive urine culture. d Central nervous system infection (CNS) infection (cerebrospinal fluid [CSF]): infection of the CNS with a positive culture in the CSF. e SOFA pre: value of the Sepsis related Organ-Failure Assessment (SOFA) score before the beginning of the barbiturate coma. f SOFA maximum: maximum value of the SOFA during the barbiturate coma, according the indication by Moreno and coworkers [ 16 ]. A thermodilution catheter was placed in 42 patients to facilitate haemodynamic control. The haemodynamic changes produced during the barbiturate coma are presented in Table 5. Differences of note include the minimum MAP, the pulmonary wedge pressure value, and the maximum norepinephrine dosage on days 2 and 3. Table 5 Systemic changes during barbiturate coma Parameter Pretreatment 1st day 2nd day 3rd day 4rd day Cardiac output (l/minute) a Thiopental 6.8 ± 1.4 6.4 ± 1.5 6.0 ± 1.4 6.7 ± 1.5 6.6 ± 1.8 Pentobarbital 7.4 ± 2.2 7.1 ± 1.9 6.5 ± 2.0 7 ± 1.4 6.1 ± 1.3 Cardiac index (l/minute per m 2 ) Thiopental 3.6 ± 0.6 3.4 ± 0.6 3.1 ± 0.6 3.6 ± 1.6 3.5 ± 0.9 Pentobarbital 3.8 ± 1.2 3.8 ± 0.8 3.4 ± 0.8 3.6 ± 0.7 3.2 ± 0.6 Peripheral venous resistance (dines/m 2 ) Thiopental 1,015 ± 325 1,022 ± 347 1,140 ± 429 1,089 ± 289 1,029 ± 253 Pentobarbital 952 ± 257 893 ± 210 1,003 ± 322 939 ± 261 914 ± 188 Pulmonary artery wedge pressure (mmHg) Thiopental 10.4 ± 4.5 9.6 ± 3.6 10.1 ± 4.1* 10.9 ± 4.6* 11.4 ± 3.5* Pentobarbital 11.6 ± 4.0 11.4 ± 3.1 12.8 ± 3.1 13.2 ± 2.1 13.9 ± 3.1 mBP (mmHg) b Thiopental 92 ± 11 75 ± 7 76 ± 9* 76 ± 6* 76 ± 8 Pentobarbital 94 ± 10 74 ± 1 68 ± 10 70 ± 1 70 ± 10 NAD (μg/kg per minute) c Thiopental 0.18 ± 0.33 0.28 ± 0.27 0.37 ± 0.3* 0.46 ± 0.39 0.56 ± 0.63 Pentobarbital 0.19 ± 0.18 0.55 ± 0.68 0.73 ± 0.69 0.60 ± 0.44 0.96 ± 0.79 P O 2 /Fi O 2 d Thiopental 284 ± 130 300 ± 139 293 ± 132 285 ± 138 254 ± 119 Pentobarbital 317 ± 127 304 ± 116 262 ± 125 211 ± 77 184 ± 92 Haemoglobin Thiopental 10.9 ± 1.6 10.7 ± 1.3 11 ± 1.2 10.8 ± 0.9 10.7 ± 1.4 Pentobarbital 10.6 ± 1.2 10.1 ± 1.0 10.4 ± 1.1 10.5 ± 1.1 10.2 ± 1.2 Temperature (°C) e Thiopental 35.8 ± 0.5 34.6 ± 1.3 34.6 ± 3.4 34.9 ± 1.0 34.9 ± 1.0 Pentobarbital 35.7 ± 1.0 34.6 ± 1.2 34.3 ± 1.3 34.4 ± 1.3 34.2 ± 1.1 a Cardiac output, cardiac index, peripheral venous resistance and pulmonary artery wedge pressure: the values are the mean values over 24 hours. b mBP: minimum value of the medium blood pressure during the day. c NAD: maximum dose of Noradrenaline bitartrate during the day. d P O 2 /Fis O 2 : ratio of partial oxygen tension to inspired fractional oxygen tension at 8:00 am. e Temperature: value of the minimum central temperature. * P < 0.05. \n\nBODY.RESULTS.SIX-MONTH OUTCOMES:\nIn the thiopental group, the neurological outcomes at 6 months (in accordance with Glasgow Outcome Scale score) were as follows: death in nine patients, vegetative state in two, severe disability in two, moderate disability in four and good recovery in four. In the pentobarbital group, the 6-month outcome was death in 16 patients, vegetative state in one, moderate disability in two and good recovery in two. In both groups one case was missing from the 6-month follow up analysis\n\nBODY.DISCUSSION:\nThe results of this study indicate that thiopental is five times more effective than pentobarbital in controlling refractory ICH. However, these findings must be interpreted with caution, given the small sample size and the fact that the study was unable to mask assignment to treatment groups. Barbiturate coma is at present the only therapy for which we have class II evidence, under BTF Guidelines [1], of efficacy in treating refractory ICH. Hence, it is perhaps the case that barbiturate coma is the most used second-level measure, with a usage frequency reported in the literature that varies from 13% to 56% [18,19]. Therefore, it is important to test the effectiveness of the various barbiturates available for controlling ICP refractory to first-level measures.\n\nBODY.DISCUSSION.DIFFERENCES BETWEEN OXIBARBITURATES AND THIOBARBITURATES:\nThe pharmacokinetic characteristics of thiopental and pentobarbital are different because their protein binding, distribution volume and clearance differ [20]. Nevertheless, the mean half life (thiopental 6 to 46 hours and pentobarbital 15 and 48 hours), which is the fundamental pharmacological parameter, differs little between the two agents. It therefore does not appear that these pharmacokinetic differences have clinical repercussions. One difference between these two groups of barbiturates is the presence of active metabolites. Thiopental has five metabolites, of which four are inactive and one (pentobarbital, or pentobarbitone) is active. Therefore, pentobarbital is an active metabolite of thiopental. This fact, along with the great intra-individual and inter-individual variability in the metabolism of these agents (caused by the existence of enzymatic induction phenomena associated with hepatic cytochrome P450), results in a weak correlation between serum concentrations and pharmacological effect. For this reason, monitoring this treatment with electroencephalography is strongly recommended. At the experimental level, various studies have compared these two medications. Hatano and coworkers [21], in a study conducted in a dog model, concluded that thiobarbiturates provoke cerebral vasoconstriction, which could help to redistribute cerebral blood flow toward ischaemic zones. Cole and colleagues [4] demonstrated that thiopental reduced the size of the ischaemic area more than did pentobarbital, even though both drugs achieved electroencephalographic burst suppression patterns. Shibuta [5] observed that thiopental, but not pentobarbital, was capable of limiting the cytotoxic damage caused by nitric oxide. Almaas and coworkers [3] observed that the different barbiturates had different neuroprotective effects with respect to oxygen and glucose deprivation in a model using human neurone cultures. Thiopental exhibited a neuroprotective effect at all the dosages studied, whereas pentobarbital was neuroprotective only at elevated dosages. Finally, in an in vitro study, Smith and colleagues [6] demonstrated that although thiopental provoked 96% inhibition of lipid peroxidation, pentobarbital had almost no effect. These experimental studies demonstrate that not all barbiturates are equal and that their neuroprotective capacity and effectiveness may differ [22]. Therefore, despite the unavoidable methodological limitations of the present study, we believe that our results may have clinical relevance.\n\nBODY.DISCUSSION.SECONDARY EFFECTS OF BARBITURATE COMA:\nThe most frequently detected secondary effect in our study, as might be expected, was arterial hypotension, which occurred in 21 patients in the thiopental group and 20 patients in the pentobarbital group. Although this incidence may be greater than that in previous studies [10], we attribute this to the definition of hypotension used (detection at any time in the barbiturate coma of MAP < 80 mmHg), which did not take the 'time' variable into account. For that reason, we collected data on other variables, such as maximum daily norepinephrine dosage and minimum daily MAP. Nearly all patients were monitored using a pulmonary artery thermodilution catheter, and arterial hypotension episodes were rigorously managed with fluid therapy and vasoactive drugs. We would note that the changes produced by pentobarbital at the cardiac and respiratory level were, in general terms, greater than those produced by thiopental. This is because (as shown in Table 5) cardiac output, cardiac index, and partial oxygen tension/fraction of inspired oxygen ratio exhibited greater changes during treatment with pentobarbital than with thiopental. This observation contrasts with the findings of previous experimental studies [23], in which it appeared that at high doses pentobarbital was safer and better tolerated than thiopental. Other complications (mostly infections) and the incidence of multiple organ dysfunction (identified using maximum SOFA) were similar in the two groups.\n\nBODY.DISCUSSION.LIMITATIONS OF THE STUDY:\nAs previously noted, this study has two important limitations. First, it was not a blinded study because the pentobarbital was not liophylized and thiopental was. Second, the sample size was small, so that small changes in the principal variable studied, namely ICP control, could significantly affect the statistical analysis. The classical view is that ICP response to barbiturates varies from 30% to 50%, and so it is possible that part of the difference found between drugs is due to poor response by the pentobarbital group as a result of any confounding bias. The randomization process is a potent mechanism that tends to eliminate bias by randomly distributing the values of all of the variables to the experimental groups. Nonetheless, the tool is not perfect and the groups frequently exhibit an imbalance in some confounding variable, especially when working with samples that are not very large. For this reason, in this study we used logistic regression analysis to eliminate any possible bias, and separate, independent analyses of the CT data were also conducted by two investigators who did not know the experimental group to which the patients belonged. Another limitation is that the dosages in the two groups were not the same. This leaves the possibility that the reason for the difference between agents that we identified is inadequate pentobarbital dose. Although in the two groups barbiturates were used with the end-point of ICP control, in this type of patient we also employ daily noncontinuous electroencephalographic monitoring. In this way, we believe that – despite different doses – the effect of the two barbiturates can be considered as equipotent because we looked for burst suppression or even the flat electroencephalographic pattern if the ICP was not controlled and the patients remained haemodynamically stable.\n\nBODY.CONCLUSION:\nIn this patient sample, thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-level measures, according to the BTF Guidelines. Nevertheless, these findings should be interpreted with caution because of the imbalance in CT characteristics and the different dosages employed in the two arms of the study. However, the present study is useful as a hypothesis testing exercise and will help to inform the design of future studies. These findings corroborate experimental evidence suggesting that there are differences in the neuroprotective mechanism between the two treatments, and this study may be a first step toward translating evidence from animal models to clinical disease. The incidence of secondary effects during treatment was similar between groups.\n\nBODY.KEY MESSAGES:\n• High doses of barbiturates are used in those patients with severe TBI who present with refractory ICH, and this recommendation is included in the BTF Guidelines. • Until now no controlled studies have been conducted to compare the effectiveness of pentobarbital and thiopental in controlling refractory ICH. Nevertheless, at the experimental level, research has demonstrated that their mechanisms and levels of neuroprotection differ. • Thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-tier measures, although these results should be interpreted with caution because of the imbalance in CT characteristics and other limitations of the study.\n\nBODY.ABBREVIATIONS:\nAUC: area under the curve; BTF: Brain Trauma Foundation; CI: confidence interval; ICH: intracranial hypertension; ICP: intracranial pressure; MAP: mean arterial pressure; SD: standard deviation; SOFA: Sepsis related Organ-Failure Assessment; TBI: traumatic brain injury.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nJPB was responsible for study design, acquisition of data, analysis and interpretation of data, and writing of the manuscript. JALP was responsible for acquisition of data and patient randomization. JH acquired data and conducted patient randomization. JMA acquired data and conducted patient randomization. JMR conducted statistical analyses. GF conducted statistical analyses. MB was responsible for designing the study and reviewing CT findings. JI was responsible for designing the study and reviewing CT findings. JI revised the article critically and gave final approval to the version to be published.\n\n**Question:** Compared to Pentobarbital what was the result of Thiopental on Intracranial pressure control?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
413
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pentobarbital versus thiopental in the treatment of refractory intracranial hypertension in patients with traumatic brain injury: a randomized controlled trial\n\n ABSTRACT.INTRODUCTION:\nExperimental research has demonstrated that the level of neuroprotection conferred by the various barbiturates is not equal. Until now no controlled studies have been conducted to compare their effectiveness, even though the Brain Trauma Foundation Guidelines recommend that such studies be undertaken. The objectives of the present study were to assess the effectiveness of pentobarbital and thiopental in terms of controlling refractory intracranial hypertension in patients with severe traumatic brain injury, and to evaluate the adverse effects of treatment.\n\nABSTRACT.METHODS:\nThis was a prospective, randomized, cohort study comparing two treatments: pentobarbital and thiopental. Patients who had suffered a severe traumatic brain injury (Glasgow Coma Scale score after resuscitation ≤ 8 points or neurological deterioration during the first week after trauma) and with refractory intracranial hypertension (intracranial pressure > 20 mmHg) first-tier measures, in accordance with the Brain Trauma Foundation Guidelines.\n\nABSTRACT.RESULTS:\nA total of 44 patients (22 in each group) were included over a 5-year period. There were no statistically significant differences in ' baseline characteristics, except for admission computed cranial tomography characteristics, using the Traumatic Coma Data Bank classification. Uncontrollable intracranial pressure occurred in 11 patients (50%) in the thiopental treatment group and in 18 patients (82%) in the pentobarbital group (P = 0.03). Under logistic regression analysis – undertaken in an effort to adjust for the cranial tomography characteristics, which were unfavourable for pentobarbital – thiopental was more effective than pentobarbital in terms of controlling intracranial pressure (odds ratio = 5.1, 95% confidence interval 1.2 to 21.9; P = 0.027). There were no significant differences between the two groups with respect to the incidence of arterial hypotension or infection.\n\nABSTRACT.CONCLUSIONS:\nThiopental appeared to be more effective than pentobarbital in controlling intracranial hypertension refractory to first-tier measures. These findings should be interpreted with caution because of the imbalance in cranial tomography characteristics and the different dosages employed in the two arms of the study. The incidence of adverse effects was similar in both groups.\n\nABSTRACT.TRIAL REGISTRATION:\n(Trial registration: US Clinical Trials registry NCT00622570.)\n\nBODY.INTRODUCTION:\nHigh dosages of barbiturates are used in patients with severe traumatic brain injury (TBI) who present with refractory intracranial hypertension (ICH) after medical and surgical treatment. This practice is recommended in the Brain Trauma Foundation (BTF) Guidelines, because this is the only second-level measure for which there is class II evidence that it can reduce intracranial pressure (ICP) [1]. Nevertheless, its effect on outcome is unproven [2], mainly because of severe medical complications. Within the family of barbiturates the oxibarbiturates and thiobarbiturates stand out, their primary representatives being pentobarbital and thiopental. Until now no controlled studies have been reported that compare the effectiveness of pentobarbital and thiopental in controlling ICH. At the experimental level, research has demonstrated that mechanisms of action and levels of neuroprotection differ between these agents [3-6]. For this reason, research is needed to compare the effectiveness of these two drugs in terms of controlling refractory ICH in patients with severe TBI. Based on various studies conducted in laboratory animals [3-6], suggesting that the neuroprotective capacity of thiopental is superior, our working hypothesis was that thiopental is more effective than pentobarbital in controlling ICP in patients with severe TBI, with a similar incidence of adverse side effects. In support of our work in the present study, the BTF Guidelines recommend that studies be undertaken to compare the effectiveness of the different barbiturates that are currently used in TBI patients [1].\n\nBODY.MATERIALS AND METHODS:\nWe conducted a prospective, randomized cohort study comparing two treatments: pentobarbital and thiopental. Our primary objective was to compare the effectiveness of these agents in controlling refractory ICH in patients with severe TBI. Secondary objectives were to compare the incidence of secondary effects, especially arterial hypotension, which was defined as the presence of mean arterial pressure (MAP) under 80 mmHg at any point during barbiturate therapy. This study was conducted at Son Dureta University Hospital (Palma de Mallorca, Spain) and was approved by the Ethics Committee of the Balearic Islands on 31 March 2002. It is registered with the US Clinical Trials Registry, with the number NCT00622570. In all cases, the patient's closest relative, legal representative, or guardian gave written informed consent for their inclusion in the study.\n\nBODY.MATERIALS AND METHODS.INCLUSION CRITERIA:\nPatients admitted to our intensive care unit (ICU) between May 2002 and July 2007 with a severe TBI (Glasgow Coma Scale [GCS] score after nonsurgical resuscitation ≤ 8) and presenting with refractory ICH (ICP > 20 mmHg), and who underwent first-level measures in accordance with the BTF Guidelines [7], were included. Refractory ICH was defined as follows: ICP 21 to 29 mmHg for 30 minutes or more, ICP of 30 to 39 mmHg for 15 minutes or more, or ICP greater than 40 mmHg for more than 1 minute, in the absence of external interventions. Included patients were required to be haemodynamically stable at the point of inclusion in the study; haemodynamic stability was defined as systolic blood pressure of 100 mmHg or greater.\n\nBODY.MATERIALS AND METHODS.EXCLUSION CRITERIA:\nWe did not include in the study patients who were younger than 15 or older than 76 years; patients with a GCS score of 3 upon admission and neurological signs of brain death (bilateral arreactive midryasis and loss of brainstem reflexes); and patients who were pregnant, had barbiturate allergy or intolerance, or had a history of severe cardiac ventricular dysfunction with an ejection fraction under 35%.\n\nBODY.MATERIALS AND METHODS.GENERAL THERAPEUTIC PROTOCOL:\nAll patients with severe TBI underwent cranial computed tomography (CT) upon admission and were categorized in accordance with the classification proposed by the Traumatic Coma Data Bank [8]. We also recorded findings of CTs conducted before inclusion of the patients in the study. The CT findings on inclusion were regarded to be the worst of the hospital stay; the prognostic value of such CT findings have been described by other authors [9]. CTs were independently reviewed and categorized by two neurosurgeons (JI and MB) who were unaware of the treatment group to which the patients had been assigned. In cases of disagreement between these investigators, a third investigator reviewed the CT images. All patients' ICP was monitored using an intraparenchymal Camino catheter (Integra Neurosciences, Plainsboro, NJ, USA). The ICP catheter was placed in the frontal region of the hemisphere with more radiological lesions on the CT. The systemic monitoring of these patients included invasive blood pressure, pulse oximetry, and a pulmonary artery thermodilution catheter. The ICP, MAP and cerebral perfusion pressure data were gathered on an hourly basis (one value every full hour) throughout the study using the Care Vue® clinical monitoring system (Phillips, Eindhoven, The Netherlands). The general treatment objectives in patients with severe TBI were to maintain MAP above 80 mmHg, ICP below 20 mmHg, and cerebral perfusion pressure above 60 mmHg. To achieve these objectives, we used liquids and/or vasoactive support with norepinephrine (noradrenaline). In patients with ICP greater than 20 mmHg, initial treatment included elevation of the head of the bed, keeping the neck straight, appropriate sedation, muscular paralysis, ventricular drainage (if the patient had visible ventricles on the CT), 20% mannitol (0.25 to 0.75 mg/kg), 7.5% hypertonic saline (2 ml/kg) and moderate hyperventilation (partial carbon dioxide tension of 30 to 35 mmHg). Neurosurgical interventions were undertaken when necessary to evacuate surgical lesions. This approach can be considered conventional treatment and is included in the BTF Guidelines as first-tier therapy [7]. Patients whose ICP remained high with conventional treatment were included in the study. Before randomization of the patient to a study group, we required that patient to have received maximal medical treatment (first-level measures). In addition, we required a CT to have been conducted within 24 hours before inclusion of the patient in the study; intravenous administration of 0.7 g/kg mannitol 1 hour before randomization; or a plasmatic osmolarity measurement above 320 mOsm/kg, in order to ensure that hyperosmolar therapy had been optimized before inclusion.\n\nBODY.MATERIALS AND METHODS.RANDOMISATION:\nRandomization was based on a computer-generated list that intercollated the two drugs. Allocation was done by the intensive care unit physician who was on duty, once the patient had been found to meet the inclusion criteria and none of the exclusion criteria. Data collection and patient follow up were conducted by the same investigator (JPB).\n\nBODY.MATERIALS AND METHODS.BLINDING OF TREATMENT GROUPS:\nThe study was not blinded because it was difficult for us to mask treatment; thiopental is liophylized for administration and pentobarbital is not.\n\nBODY.MATERIALS AND METHODS.ADMINISTRATION OF BARBITURATES AND MONITORING OF EFFECTS:\nPentobarbital was administered in accordance with the protocol established by Eisenberg and coworkers [10], using a loading dose of 10 mg/kg over 30 minutes followed by a continuous perfusion of 5 mg/kg per hour for 3 hours. This was followed by a maintenance dosage of 1 mg/kg per hour. Thiopental was administered in the form of a 2 mg/kg bolus administered over 20 seconds. If the ICP was not lowered to below 20 mmHg, then the protocol permitted a second bolus of 3 mg/kg, which could be readministered at 5 mg/kg if necessary to reduce persistently elevated ICP. The maintenance dosage was an infusion of thiopental at a rate of 3 mg/kg per hour. In both treatment groups, for cases in which the maintenance dosage did not achieve the reduction in ICP to below the 20 mmHg threshold, the maintenance dosage for both drugs could be increased by 1 mg/kg per hour, while looking for electroencephalographic burst suppression or even the flat pattern, in order to ensure that different doses of the two barbiturates were equipotent. Electroencephalography was conducted daily in a noncontinuous manner (Nicolet; Viasys Healthcare, Verona Road, Madison, WI, USA). Results were analyzed by an experienced neurologist who was blinded to the treatment of the patients. In those patients in whom barbiturate coma did not control ICP, we used decompressive craniotomy and/or external lumbar drainage, in accordance with the Munch criteria, as life-saving measures [11,12].\n\nBODY.MATERIALS AND METHODS.EFFECTIVENESS CRITERIA:\nAdequate response to treatment was defined as a decrease in ICP to below 20 mmHg, and maintenance below this threshold for at least 48 hours. To describe the ICP, we also followed the criteria previously employed by Stocchetti and coworkers [13]; the arithmetic mean of ICP data recorded during every 24-hour period, after filtering to exclude inaccurate readings, was calculated and expressed as 'mean ICP'. Three ICP blocks were considered for further analysis: less than 20 mmHg, 20 to 30 mmHg, and more than 30 mmHg. Uncontrollable ICP was defined as follows: ICP of 21 to 35 mmHg for 4 hours, ICP of 36 to 40 mmHg for 1 hour, or ICP above 41 mmHg for 5 minutes, in the absence of external interventions. We also defined as unresponsive to treatment those cases in which, because of refractory ICP, the patient needed some other treatment (surgery and/or lumbar drainage) and cases in which the patient progressed to brain death. Although it was not a main objective of the study, patients were evaluated 6 months after injury using the Glasgow Outcome Scale [14].\n\nBODY.MATERIALS AND METHODS.WITHDRAWAL OF TREATMENT:\nWhen ICP was controlled (<20 mmHg for 48 hours), we conducted a step-wise reduction in the barbiturate coma in steps that reduced the dosage by 50% every 24 hours until the infusion was suspended. In the event of ICP values rising to the study's inclusion values during the withdrawal of barbiturate treatment, the perfusion dosage was once again increased to achieve control of the patient's ICP.\n\nBODY.MATERIALS AND METHODS.SAMPLE SIZE:\nAccepting an α error of 0.05 and a β error of 0.2 in a bilateral hypothesis contrast, we estimated that 47 patients were needed in each group to detect differences of 30% or greater in the control of ICH. To calculate sample size, we assumed that the therapeutic response rate in the pentobarbital group would be 50%, excluding patients lost to follow up.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nQuantitative variables are expressed as the mean and standard deviation from the mean (SD) in normal distributions, and as median and interquartile range in cases that were not normally distributed. Qualitative variables are expressed as percentages, along with 95% confidence interval (CI). To determine whether variables followed a normal distribution, we used the Shapiro Wilks test. For the comparison of quantitative variables, Student's t-test was used if the variable followed a normal distribution. In other cases, we used the Mann-Whitney U-test. For the comparison of qualitative variables, we used χ2 or Fisher's exact test, as appropriate. Given that the randomization did not create groups that were similar in terms of types of intracranial lesions shown on the CT results, which is a prognostic variable that influences the effectiveness of barbiturate treatment in controlling ICP, we conducted a multivariate analysis using binary logistic regression, so that we would include the prognostic variables with the most plausible association with the dependent variable 'uncontrollable ICP'. These are variables such as age, GCS score at admission, and the worst CT obtained within 24 hours before inclusion of the patient in the study, as well as the type of barbiturate administered. To achieve this multivariate analysis, and given the small number of cases in each of the five groups in Marshall's classification, the CT data were grouped into focal and diffuse lesions. We also included in the model the minimum daily MAP during barbiturate treatment, given that in the second and third days of treatment there were statistically significant differences between the groups in the univariate analysis. The significant variables identified by the 'likelihood ratio' ≤ 0.1 test were used, along with those whose inclusion affected the calculation of the effect of the 'treatment group' variable. Both treatment groups were very similar in terms of other known prognostic variables, such as the presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them, so these were not included in the multivariate analysis. To analyze the variable ICP, which was determined on an hourly basis, we calculated the area under the curve (AUC) at 24, 48 and 72 hours, and also standardized by time [15]. For all comparisons, we considered statistical significance to have been achieved if the two-tailed α error probability was 5% or less (P ≤ 0.05). Statistical analyses were conducted using SPSS version 15 (SPSS Inc., Chicago, IL, USA).\n\nBODY.RESULTS:\nPreliminary results for the first 20 patients have already been published elsewhere [16]. From May 2002 to July 2007, 480 TBI patients were admitted to the intensive care unit of the Son Dureta University Hospital. Of these 480 patients, 71 (14.8%) presented with ICH refractory to first-level measures, of whom 44 were included in the study. The study was concluded prematurely because of the unexpected and slow inclusion rate; this could have modified some uncontrollable environmental factors that may affect results. The reasons for not including the remaining 27 refractory ICH cases were as follows: 13 patients were included in other studies, six were older than 76 years, five were admitted with nonreacting midriatic pupils and with clinical evidence of brain death, two presented with haemodynamic instability at the time of randomization, and one patient was transferred to a different hospital during the first 24 hours of admission, which excluded that patient from follow-up analysis. On average, the barbiturate coma was initiated in the thiopental group at 89 ± 15.5 hours after admission and in the pentobarbital group at 61 ± 14.3 hours after admission (P = 0.33). The baseline characteristics of the 44 patients included in the study, 22 randomized to each group, are presented in Table 1. There were no statistically significant differences with respect to epidemiological data, co-morbidity (data not shown) or lesions associated with TBI, although there were differences in the CT classification. Table 1 Baseline characteristics of patient population Characteristic Thiopental (n = 22) Pentobarbital (n = 22) P Sex (male; n) 19 19 1 Age (years) 26 (20 to 41) 32 (22 to 43) 0.45 ISS 25 (24 to 34) 25 (25 to 38) 0.77 SAPS II 42 (28 to 54) 43 (38 to 46) 0.95 APACHE II 23 (15 to 25) 20 (18 to 26) 0.27 APACHE III 60 (38 to 73) 52 (32 to 76) 0.41 Associated lesion (n) Thoracic injury 7 2 0.13 Abdominal injury 4 1 0.34 Extremities injury 9 5 0.20 Admission CT (n) Diffuse injury without brain swelling 12 4 0.046 Diffuse bilateral brain swelling 6 12 Diffuse unilateral brain swelling with midline shift 1 0 Any mass lesion > 25 ml 3 6 Age, ISS, SAPS II, APACHE II and APACHE III are expressed as median and interquartile range. APACHE, Acute Physiology and Chronic Health Evaluation; admission CT, admission computed tomography (according to the Traumatic Coma Data Bank); ISS, Injury Severity Score; SAPS, Simplified Acute Physiology. The summary of prognostic variables for the 44 patients is shown in Table 2. As in Table 1 the characteristics of the worst CT conducted before inclusion in the study differed between the two groups. Table 2 Prognostic variables of patient population Variable Thiopental (n = 22) Pentobarbital (n = 22) P Admission GCS score 6.5 (3.0 to 7.2) 7 (4.7 to 10.0) 0.38 Out-of-hospital hypoxia (n) 5 7 0.63 Out-of-hospital hypotension (n) 5 4 1 Pupillary reactivity (n) a One reacting 3 5 0.66 Both reacting b 12 14 Pre-enrolment CT (n) Diffuse injury without brain swelling 8 5 0.04 Diffuse bilateral brain swelling 1 8 Diffuse injury unilateral brain swelling with midline shift 5 1 Any mass lesion evacuated 7 5 Nonevacuated mass lesion 1 3 Admission GCS is expressed as median (interquartile range). a Pupillary reactivity at hospital admission. b Miotic pupils were considered as reactive. CT, computed tomography; GCS, Glasgow Coma Scale. \n\nBODY.RESULTS.EFFECTIVENESS CRITERION: CONTROL OF INTRACRANIAL PRESSURE:\nThe distribution of the ICP during the first 3 days of treatment, according to Stocchetti's criteria, is summarized in Table 3. The missing cases during these 3 days were due to brain deaths or to receipt of rescue treatment for uncontrollable ICP. Finally ICP was uncontrollable in 11 cases (50%) in the thiopental group and in 18 patients (82%) in the pentobarbital group (P = 0.03). In nonresponding patients, we chose to place a lumbar drainage in five, in three we opted for surgical treatment, and in three other patients we combined both treatments, drainage and surgery. Surgical decompression was conducted in four patients in the thiopental group and in two of the patients in the pentobarbital group. The number of hyperosmolar treatments administered (manitol and/or hypertonic saline) during the barbiturate coma was similar in both groups: 16.5 (8.0 to 24.2) in the thiopental group and 16.5 (3.0 to 21.5) in the pentobarbital group (P = 0.9). The mean ± SD duration of the barbiturate coma was 156 ± 60 hours for thiopental and 108 ± 100 hours for pentobarbital (P = 0.06). Seven (31.8%) patients presented an ICP rebound with thiopental and six (27.3%) with pentobarbital (P = 0.74) during treatment withdrawal. Table 3 Mean ICP recorded per day during the first 3 days of barbiturate coma Drug Day Mean ICP (n[%]) <20 mmHg 20 to 30 mmHg >30 mmHg Thiopental 1 10 46 11 50 1 5 2 15 71 4 19 2 10 3 12 63 6 32 1 5 Pentobarbital 1 9 41 8 36 5 23 2 8 38 9 43 4 19 3 6 43 8 57 0 0 Mean intracranial pressure (ICP) is the arithmetic mean of ICP data recorded during every 24-hour period, according to Stocchetti's criteria [ 13 ]. Data are presented as number of cases and as a percentage of the total number of cases each day. Figure 1 presents the AUC for ICP above 20 mmHg, standardized over time, as follows. The ICP value of AUC0–24 h was 458.00 mmHg·hour (95% CI = 421.84 to 494.16) in the thiopental group and 550.63 mmHg·hour (95% CI = 411.31 to 689.95) in the pentobarbital group. The AUC0–48 h was 913.18 mmHg·hour (95% CI = 814.08 to 1,012.27) in the thiopental group and 997.27 mmHg·hour (95% CI = 757.10 to 1,237.43) in the pentobarbital group. The AUC0–72 h in the thiopental group was 1,291.69 mmHg·hour (95% CI = 1,172.27 to 1,411.12) and 1,399.73 mmHg·hour (95% CI = 1,291.11 to 1,508.35) in the pentobarbital group. Standardized over time, the AUC per hour in the thiopental group was 23.90 mmHg (95% CI = 22.00 to 25.81) and in the pentobarbital group it was 29.39 mmHg (95% CI = 23.20 to 35.59). Figure 1AUC of ICP data. Presented are areas under the curve (AUCs) of the intracranial pressure (ICP) data, standardized by time, with a base value of 20 mmHg. Both treatment groups were similar in terms of known prognostic variables, such as presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them. Therefore, these were not included in the multivariate analysis. The logistic regression analysis showed that, after adjusting for the worst CT and the type of barbiturate used, thiopental was five times more likely than pentobarbital to control ICP (odds ratio = 5.1, 95% CI = 1.2 to 21.9; P = 0.027). The Hosmer-Lemeshow test indicated that the fit of the model was good (P = 0.799). The association of focal lesions in the pre-inclusion CT with ICP control was 3.6 times higher than that for the diffuse lesions. The relative risk for good control of ICP in the thiopental versus pentobarbital group was 2.26 for patients with focal lesions and 3.52 for those who presented with diffuse lesions. The other variables analyzed did not exhibit a significant relationship to ICP control, and did not modify the effect of the barbiturate treatment, including the third day minimum MAP, which was significantly different between the two treatments (data not shown).\n\nBODY.RESULTS.ADVERSE SIDE EFFECTS DURING THE BARBITURATE COMA:\nThe secondary effects during the barbiturate coma are presented in Table 4. In both groups almost all patients presented with at least one MAP measurement below 80 mmHg. There were no differences between groups with respect to the incidence of infections, Sepsis related Organ-Failure Assessment (SOFA) scores before initiation of treatment, or the maximum SOFA value [17] during the entire period of barbiturate coma. Table 4 Adverse events during barbiturate coma Adverse event Thiopental (n = 22) Pentobarbital (n = 22) P Hypotension a 21 20 1 Respiratory infection b 18 17 1 Urinary infection c 0 2 0.49 Positive blood culture 4 1 0.34 ICP catheter colonization 7 5 0.5 CNS infection (CSF) d 3 0 0.23 SOFA pre e 7 (4.5 to 9.5) 8.0 (5.5 to 9.0) 0.57 SOFA maximum f 11 (10 to 12) 11 (10 to 12) 0.94 a Hypotension is defined as detection of a medium arterial blood pressure below 80 mmHg at any time during barbiturate coma. b Respiratory infection: presence of a positive sputum culture. c Urinary infection: presence of a positive urine culture. d Central nervous system infection (CNS) infection (cerebrospinal fluid [CSF]): infection of the CNS with a positive culture in the CSF. e SOFA pre: value of the Sepsis related Organ-Failure Assessment (SOFA) score before the beginning of the barbiturate coma. f SOFA maximum: maximum value of the SOFA during the barbiturate coma, according the indication by Moreno and coworkers [ 16 ]. A thermodilution catheter was placed in 42 patients to facilitate haemodynamic control. The haemodynamic changes produced during the barbiturate coma are presented in Table 5. Differences of note include the minimum MAP, the pulmonary wedge pressure value, and the maximum norepinephrine dosage on days 2 and 3. Table 5 Systemic changes during barbiturate coma Parameter Pretreatment 1st day 2nd day 3rd day 4rd day Cardiac output (l/minute) a Thiopental 6.8 ± 1.4 6.4 ± 1.5 6.0 ± 1.4 6.7 ± 1.5 6.6 ± 1.8 Pentobarbital 7.4 ± 2.2 7.1 ± 1.9 6.5 ± 2.0 7 ± 1.4 6.1 ± 1.3 Cardiac index (l/minute per m 2 ) Thiopental 3.6 ± 0.6 3.4 ± 0.6 3.1 ± 0.6 3.6 ± 1.6 3.5 ± 0.9 Pentobarbital 3.8 ± 1.2 3.8 ± 0.8 3.4 ± 0.8 3.6 ± 0.7 3.2 ± 0.6 Peripheral venous resistance (dines/m 2 ) Thiopental 1,015 ± 325 1,022 ± 347 1,140 ± 429 1,089 ± 289 1,029 ± 253 Pentobarbital 952 ± 257 893 ± 210 1,003 ± 322 939 ± 261 914 ± 188 Pulmonary artery wedge pressure (mmHg) Thiopental 10.4 ± 4.5 9.6 ± 3.6 10.1 ± 4.1* 10.9 ± 4.6* 11.4 ± 3.5* Pentobarbital 11.6 ± 4.0 11.4 ± 3.1 12.8 ± 3.1 13.2 ± 2.1 13.9 ± 3.1 mBP (mmHg) b Thiopental 92 ± 11 75 ± 7 76 ± 9* 76 ± 6* 76 ± 8 Pentobarbital 94 ± 10 74 ± 1 68 ± 10 70 ± 1 70 ± 10 NAD (μg/kg per minute) c Thiopental 0.18 ± 0.33 0.28 ± 0.27 0.37 ± 0.3* 0.46 ± 0.39 0.56 ± 0.63 Pentobarbital 0.19 ± 0.18 0.55 ± 0.68 0.73 ± 0.69 0.60 ± 0.44 0.96 ± 0.79 P O 2 /Fi O 2 d Thiopental 284 ± 130 300 ± 139 293 ± 132 285 ± 138 254 ± 119 Pentobarbital 317 ± 127 304 ± 116 262 ± 125 211 ± 77 184 ± 92 Haemoglobin Thiopental 10.9 ± 1.6 10.7 ± 1.3 11 ± 1.2 10.8 ± 0.9 10.7 ± 1.4 Pentobarbital 10.6 ± 1.2 10.1 ± 1.0 10.4 ± 1.1 10.5 ± 1.1 10.2 ± 1.2 Temperature (°C) e Thiopental 35.8 ± 0.5 34.6 ± 1.3 34.6 ± 3.4 34.9 ± 1.0 34.9 ± 1.0 Pentobarbital 35.7 ± 1.0 34.6 ± 1.2 34.3 ± 1.3 34.4 ± 1.3 34.2 ± 1.1 a Cardiac output, cardiac index, peripheral venous resistance and pulmonary artery wedge pressure: the values are the mean values over 24 hours. b mBP: minimum value of the medium blood pressure during the day. c NAD: maximum dose of Noradrenaline bitartrate during the day. d P O 2 /Fis O 2 : ratio of partial oxygen tension to inspired fractional oxygen tension at 8:00 am. e Temperature: value of the minimum central temperature. * P < 0.05. \n\nBODY.RESULTS.SIX-MONTH OUTCOMES:\nIn the thiopental group, the neurological outcomes at 6 months (in accordance with Glasgow Outcome Scale score) were as follows: death in nine patients, vegetative state in two, severe disability in two, moderate disability in four and good recovery in four. In the pentobarbital group, the 6-month outcome was death in 16 patients, vegetative state in one, moderate disability in two and good recovery in two. In both groups one case was missing from the 6-month follow up analysis\n\nBODY.DISCUSSION:\nThe results of this study indicate that thiopental is five times more effective than pentobarbital in controlling refractory ICH. However, these findings must be interpreted with caution, given the small sample size and the fact that the study was unable to mask assignment to treatment groups. Barbiturate coma is at present the only therapy for which we have class II evidence, under BTF Guidelines [1], of efficacy in treating refractory ICH. Hence, it is perhaps the case that barbiturate coma is the most used second-level measure, with a usage frequency reported in the literature that varies from 13% to 56% [18,19]. Therefore, it is important to test the effectiveness of the various barbiturates available for controlling ICP refractory to first-level measures.\n\nBODY.DISCUSSION.DIFFERENCES BETWEEN OXIBARBITURATES AND THIOBARBITURATES:\nThe pharmacokinetic characteristics of thiopental and pentobarbital are different because their protein binding, distribution volume and clearance differ [20]. Nevertheless, the mean half life (thiopental 6 to 46 hours and pentobarbital 15 and 48 hours), which is the fundamental pharmacological parameter, differs little between the two agents. It therefore does not appear that these pharmacokinetic differences have clinical repercussions. One difference between these two groups of barbiturates is the presence of active metabolites. Thiopental has five metabolites, of which four are inactive and one (pentobarbital, or pentobarbitone) is active. Therefore, pentobarbital is an active metabolite of thiopental. This fact, along with the great intra-individual and inter-individual variability in the metabolism of these agents (caused by the existence of enzymatic induction phenomena associated with hepatic cytochrome P450), results in a weak correlation between serum concentrations and pharmacological effect. For this reason, monitoring this treatment with electroencephalography is strongly recommended. At the experimental level, various studies have compared these two medications. Hatano and coworkers [21], in a study conducted in a dog model, concluded that thiobarbiturates provoke cerebral vasoconstriction, which could help to redistribute cerebral blood flow toward ischaemic zones. Cole and colleagues [4] demonstrated that thiopental reduced the size of the ischaemic area more than did pentobarbital, even though both drugs achieved electroencephalographic burst suppression patterns. Shibuta [5] observed that thiopental, but not pentobarbital, was capable of limiting the cytotoxic damage caused by nitric oxide. Almaas and coworkers [3] observed that the different barbiturates had different neuroprotective effects with respect to oxygen and glucose deprivation in a model using human neurone cultures. Thiopental exhibited a neuroprotective effect at all the dosages studied, whereas pentobarbital was neuroprotective only at elevated dosages. Finally, in an in vitro study, Smith and colleagues [6] demonstrated that although thiopental provoked 96% inhibition of lipid peroxidation, pentobarbital had almost no effect. These experimental studies demonstrate that not all barbiturates are equal and that their neuroprotective capacity and effectiveness may differ [22]. Therefore, despite the unavoidable methodological limitations of the present study, we believe that our results may have clinical relevance.\n\nBODY.DISCUSSION.SECONDARY EFFECTS OF BARBITURATE COMA:\nThe most frequently detected secondary effect in our study, as might be expected, was arterial hypotension, which occurred in 21 patients in the thiopental group and 20 patients in the pentobarbital group. Although this incidence may be greater than that in previous studies [10], we attribute this to the definition of hypotension used (detection at any time in the barbiturate coma of MAP < 80 mmHg), which did not take the 'time' variable into account. For that reason, we collected data on other variables, such as maximum daily norepinephrine dosage and minimum daily MAP. Nearly all patients were monitored using a pulmonary artery thermodilution catheter, and arterial hypotension episodes were rigorously managed with fluid therapy and vasoactive drugs. We would note that the changes produced by pentobarbital at the cardiac and respiratory level were, in general terms, greater than those produced by thiopental. This is because (as shown in Table 5) cardiac output, cardiac index, and partial oxygen tension/fraction of inspired oxygen ratio exhibited greater changes during treatment with pentobarbital than with thiopental. This observation contrasts with the findings of previous experimental studies [23], in which it appeared that at high doses pentobarbital was safer and better tolerated than thiopental. Other complications (mostly infections) and the incidence of multiple organ dysfunction (identified using maximum SOFA) were similar in the two groups.\n\nBODY.DISCUSSION.LIMITATIONS OF THE STUDY:\nAs previously noted, this study has two important limitations. First, it was not a blinded study because the pentobarbital was not liophylized and thiopental was. Second, the sample size was small, so that small changes in the principal variable studied, namely ICP control, could significantly affect the statistical analysis. The classical view is that ICP response to barbiturates varies from 30% to 50%, and so it is possible that part of the difference found between drugs is due to poor response by the pentobarbital group as a result of any confounding bias. The randomization process is a potent mechanism that tends to eliminate bias by randomly distributing the values of all of the variables to the experimental groups. Nonetheless, the tool is not perfect and the groups frequently exhibit an imbalance in some confounding variable, especially when working with samples that are not very large. For this reason, in this study we used logistic regression analysis to eliminate any possible bias, and separate, independent analyses of the CT data were also conducted by two investigators who did not know the experimental group to which the patients belonged. Another limitation is that the dosages in the two groups were not the same. This leaves the possibility that the reason for the difference between agents that we identified is inadequate pentobarbital dose. Although in the two groups barbiturates were used with the end-point of ICP control, in this type of patient we also employ daily noncontinuous electroencephalographic monitoring. In this way, we believe that – despite different doses – the effect of the two barbiturates can be considered as equipotent because we looked for burst suppression or even the flat electroencephalographic pattern if the ICP was not controlled and the patients remained haemodynamically stable.\n\nBODY.CONCLUSION:\nIn this patient sample, thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-level measures, according to the BTF Guidelines. Nevertheless, these findings should be interpreted with caution because of the imbalance in CT characteristics and the different dosages employed in the two arms of the study. However, the present study is useful as a hypothesis testing exercise and will help to inform the design of future studies. These findings corroborate experimental evidence suggesting that there are differences in the neuroprotective mechanism between the two treatments, and this study may be a first step toward translating evidence from animal models to clinical disease. The incidence of secondary effects during treatment was similar between groups.\n\nBODY.KEY MESSAGES:\n• High doses of barbiturates are used in those patients with severe TBI who present with refractory ICH, and this recommendation is included in the BTF Guidelines. • Until now no controlled studies have been conducted to compare the effectiveness of pentobarbital and thiopental in controlling refractory ICH. Nevertheless, at the experimental level, research has demonstrated that their mechanisms and levels of neuroprotection differ. • Thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-tier measures, although these results should be interpreted with caution because of the imbalance in CT characteristics and other limitations of the study.\n\nBODY.ABBREVIATIONS:\nAUC: area under the curve; BTF: Brain Trauma Foundation; CI: confidence interval; ICH: intracranial hypertension; ICP: intracranial pressure; MAP: mean arterial pressure; SD: standard deviation; SOFA: Sepsis related Organ-Failure Assessment; TBI: traumatic brain injury.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nJPB was responsible for study design, acquisition of data, analysis and interpretation of data, and writing of the manuscript. JALP was responsible for acquisition of data and patient randomization. JH acquired data and conducted patient randomization. JMA acquired data and conducted patient randomization. JMR conducted statistical analyses. GF conducted statistical analyses. MB was responsible for designing the study and reviewing CT findings. JI was responsible for designing the study and reviewing CT findings. JI revised the article critically and gave final approval to the version to be published.\n\n**Question:** Compared to Pentobarbital what was the result of Thiopental on Mean barbiturate coma length?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
373
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Formoterol DPI 9 μg what was the result of Budesonide/formoterol pMDI 160/9 μg on Cough score improvement?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
471
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: An Open Label, Randomised Trial of Artesunate+Amodiaquine, Artesunate+Chlorproguanil-Dapsone and Artemether-Lumefantrine for the Treatment of Uncomplicated Malaria\n\n ABSTRACT.BACKGROUND:\nArtesunate+amodiaquine (AS+AQ) and artemether-lumefantrine (AL) are now the most frequently recommended first line treatments for uncomplicated malaria in Africa. Artesunate+chlorproguanil-dapsone (AS+CD) was a potential alternative for treatment of uncomplicated malaria. A comparison of the efficacy and safety of these three drug combinations was necessary to make evidence based drug treatment policies.\n\nABSTRACT.METHODS:\nFive hundred and thirty-four, glucose-6-phosphate dehydrogenase (G6PD) normal children were randomised in blocks of 15 to the AS+AQ, AL or AS+CD groups. Administration of study drugs was supervised by project staff and the children were followed up at r home on days 1,2,3,7,14 and 28 post treatment. Parasitological and clinical failures and adverse events were compared between the study groups.\n\nABSTRACT.MAIN FINDINGS:\nIn a per-protocol analysis, the parasitological and clinical failure rate at day 28 post treatment (PCF28) was lower in the AS+AQ group compared to the AL or AS+CD groups (corrected for re-infections: 6.6% vs 13.8% and 13.8% respectively, p = 0.08; uncorrected: 14.6% vs 27.6% and 28.1% respectively, p = 0.005). In the intention to treat analysis, the rate of early treatment failure was high in all three groups (AS+AQ 13.3%; AL 15.2%; and AS+CD 9.3%, p = 0.2) primarily due to vomiting. However, the PCF28 corrected for re-infection was lower, though not significantly, in the AS+AQ group compared to the AL or the AS+CD groups (AS+AQ 18.3%; AL 24.2%; AS+CD 20.8%, p = 0.4) The incidence of adverse events was comparable between the groups.\n\nABSTRACT.CONCLUSIONS:\nAS+AQ is an appropriate first line treatment for uncomplicated malaria in Ghana and possibly in the neighbouring countries in West Africa. The effectiveness of AL in routine programme conditions needs to be studied further in West Africa.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov NCT00119145\n\n\nBODY.INTRODUCTION:\nThere is now widespread acceptance that combination therapy (≥2 antimalarial drugs with different modes of action) is a better option than monotherapy for the treatment of uncomplicated malaria and artemisinin based combination therapy (ACT) is advocated as a way forward.[1] The WHO recommends artesunate+amodiaquine (AS+AQ), artemether-lumefantrine (AL) or artesunate+sulphadoxine-pyremethamine (AS+SP) as the first line treatment for uncomplicated malaria in Africa.[2] By November 2006, most malaria endemic countries in Africa (33/42) had adopted ACT as the first line treatment for uncomplicated malaria.[3] In 2002, Ghana adopted AS+AQ as first line treatment based on the evidence of its efficacy and safety observed elsewhere in Africa and on account of its potential for production by local manufacturers.[4] Randomised controlled efficacy trials in Zanzibar,[5] Uganda[6] and Angola[7] had shown that polymerase chain reaction ( PCR) corrected adequate clinical response rates at day 28 post treatment (ACPR28) were very high for both AS+AQ (94–100%) and AL (97–100%). In 2003, a four arm comparative efficacy trial in Ghana showed that the ACPR28 was 100% (n = 51) for AL and 97.5% (n = 54) for AS+AQ.[8] However, a randomised trial of the effectiveness of AS+AQ and AL in Tanzania showed that the parasitological failure at day 28 was 2.6 fold (95% CI 1.9–3.4) higher in the AS+AQ group (40%) compared to the AL group (21%).[9] Artesunate+chlorproguanil-dapsone (AS+CD) is another potential alternative for AS+AQ because chlorproguanil-dapsone has been shown to be efficacious in areas with high SP and chloroquine resistance.[10] Clinical trials of AS+CD have been carried out in several countries in Africa (www.ispub.com/ostia/index.phpxmlFilePathjournals/ijid/vol4n2/cda.xml) but the development of AS+CD was abandoned recently due to safety concerns in glucose-6-phosphate dehydrogenase (G6PD) deficient subjects. There has been no comparative studies of the efficacy and safety of AS+CD versus AS+AQ or AL. Even though most countries in Africa have adopted ACT as first line treatment, antimalarial monotherapy is still common and this can undermine the efficacy of ACT. Furthermore high levels of resistance to AQ already exists in many parts of Africa.[9] Thus, it is important to evaluate the efficacy of ACTs particularly that of AS+AQ periodically. In this paper, we report the results of a randomised trial that compared the efficacy and safety of AS+AQ, AL and AS+CD in children in Ghana.\n\nBODY.METHODS:\nThe protocol for this trial and supporting CONSORT checklist are available as supporting information; see checklist S1 and Protocol S1.\n\nBODY.METHODS.PARTICIPANTS:\nThe study was conducted in Kintampo district hospital, Brong-Ahafo region, Ghana. Malaria transmission in this forest region of Ghana is perennial but peaks in July–August and the entomological inoculation rate is high, about 270 infective bites per person per year. Although the study area has high transmission, malaria is common in older children and therefore the study included children up to 10 years of age. From June 2005 to May 2006, 1718 children aged 6 months to 10 years who attended the study hospital's outpatient department with a history of fever or an axillary temperature ≥37.5°C were examined for malaria parasitaemia and screened for their eligibility for enrolment in this study after written, informed consent had been obtained from their caretakers (Figure 1). Children who had a body weight ≤5 kg, Hb <7 g/dL, malaria parasitaemia <2000 or >200000 parasites/μL, danger signs (unable to drink, history of repeated vomiting, convulsions or other signs of severe malaria, or any other concomitant febrile disease were excluded from the study but offered standard care according to Ministry of Health guidelines. Children were screened for glucose-6-phosphate dehydrogenase (G6PD) deficiency before randomisation (the G6PD test took about 1hour). A total of 630 children were eligible; 534 were G6PD normal and 96 were G6PD deficient. The G6PD normal children were randomly assigned to the AL, AS+AQ, or AS+CD groups. The G6PD deficient children were randomised to the AS+AQ or AL group only because the Ghana Ministry of Health Ethical Committee expressed concern about the possibility of haemolysis associated with chlorproguanil-dapsone treatment in G6PD deficient children. 10.1371/journal.pone.0002530.g001Figure 1Enrolment and Follow up profile.\n\nBODY.METHODS.PROCEDURES:\nAdministration of the first dose of study drugs was supervised by a study nurse and the administration of subsequent doses was supervised by study field workers. All children were given iron along with antimalarials according to national treatment guidelines. Caretakers of children in the AL group were told about the need to give a fatty meal along with the drug. Children were actively followed up at their homes by 10 field workers on days 1, 2, 3, 7, 14 and 28 post treatment to solicit adverse events. Finger prick blood samples for parasitological observations were obtained on days 3, 7, 14, 28, for haematological measurements on days 1, 2, 3, 7, 28 and for biochemical assessments on days 2, 7, 28 (0.7ml of capillary blood) after the start of treatment. Blood samples were collected from children who attended the study clinic for suspected malaria on any other day outside the scheduled days of follow up. There were 77 unscheduled visits and those who had a positive blood slide on these unscheduled visits (n = 15) were treated with quinine and classified as treatment failures.\n\nBODY.METHODS.RANDOMISATION:\nRandomisation was done using Microsoft Excel 2003© randomisation generator. G6PD normal children were randomised in blocks of 15 to the AL, AS-AQ, or AS+CD group. G6PD deficient children were randomised in blocks of 10 to AL or AS-AQ group. Co-blistered packs of artesunate and amodiaquine (Arsucam,® Sanofi-Aventis), artemether-lumefantrine (Coartem,© Novartis) and chlorproguanil-dapsone (Lapdap,TM GlaxoSmithKline) were obtained from the respective local suppliers.\n\nBODY.METHODS.STATISTICAL METHODS:\nData were double-entered, and validated using Visual Foxpro© 6.0.and the analysis was done using StataTM 9.1. Per protocol analysis included patients who were properly randomised, had received the study drugs according to the protocol, and for whom data were available on the primary end point (ACPR28). Intention to treat (ITT) analysis involved all randomised patients irrespective of how many doses of the study drugs had been given but excluded all major day 0 protocol violations. All statistical tests were two-sided and an α-level <0.05 was considered a statistically significant result. For comparisons of continuous variables between groups, the t-test was used and for comparisons between more than two groups, one-way analysis of variance was used after assuring normality and homogeneity of variances assumptions were satisfied. For comparison of categorical variables, the chi-square test was used with the exact extension invoked when there were small numbers in the cells. A survival analysis using the life table method was done on the cumulative proportion of children having treatment failure at different time points during the post treatment period in each of the arms of the study. The end points were any of the following: failure to take the drug on any of the first three days, parasitaemia on day 2 greater than that on day 0, presence of parasitaemia on day 7, diagnosis of severe malaria at any point after day 0, recurrent parasitaemia after day 7 up to day 28. The likelihood-ratio test statistic of homogeneity and the logrank tests of homogeneity of arm were also carried out.\n\nBODY.METHODS.SAMPLE SIZE:\nThe primary endpoint was PCR corrected ACPR by day 28. A sample size of 510 children was chosen on the basis of the following assumptions: (1) the efficacy of AL would be 95%; (2) the study would have 80% power at 95% significance level to detect a 10% difference in efficacy as measured by the parasitological failure at day 28 post-treatment in the AS+AQ, and AS+CD groups compared with the AL group; (3) loss to follow up by day 28 post treatment would be <5%.\n\nBODY.METHODS.LABORATORY PROCEDURES:\nAt least 200 oil immersion fields of thick blood films stained with Giemsa stain were examined for malaria parasites before a blood film was considered negative. The parasite density per micro-litre was estimated by multiplying the number of parasites per 200 leukocytes by a factor of 40, assuming a white blood cell count of 8,000/μl. Each blood slide was read by two microscopists. If the difference in the parasite density estimated by the two microscopists was <50%, the mean of the two readings was defined as the true parasite density. If the disagreement between the two readings was ≥50%, a third microscopist examined the slide and the mean of the two closest readings was deemed to be the true parasite density. To distinguish between recrudescent and new infections, parasites identified on Days 14 and 28 were compared to those identified at enrolment using PCR amplification of msp2 P. falciparum genes. Full blood count and biochemical tests were done by calibrated automated ABX MICROS 60 (Horiba ABX, France) and Selectra E Clinical Chemistry Analyzer (Vital Scientific N.V, Netherlands) respectively. Quantitative G6PD phenotype analysis was conducted using Randox method with Humalyser Junior (Human, Germany). Plasma ALT, AST, Total Bilirubin, Creatinine and Urea were measured on the Selectra E Clinical Chemistry analyzer (Vital Scientific, The Netherlands) using reagents from Elitech Diagnostics (Sees, France). ALT and AST were measured using the kinetic, UV, IFCC method without pyridoxal phosphate, total bilirubin with the modified Evelyn-Malloy method, creatinine with the kinetic Jaffe method and urea with the kinetic urease method. Glucose-6-phosphate dehydrogenase (G6PD) activity was measured using a quantitative UV G6PD kit from Randox (Antrium, UK). The enzyme activity was determined by the measurement of the rate of absorbance change at 340 nm due to the reduction of NADP+.\n\nBODY.METHODS.ETHICS:\nThe study protocol was approved by the ethics committees of the Kintmapo Health Research Centre, Ghana Ministry of Health and the London School of Hygiene & Tropical Medicine. The study is registered at the United States National Institute of Health clinical trials register; the registration number is NCT00119145 and the URL:https://clinicaltrials.gov/ct2/show/NCT00119145/\n\n\nBODY.RESULTS.G6PD NORMAL CHILDREN:\nThere were no statistically significant differences in the demographic or baseline haematological characteristics between the three treatment groups at enrolment (Table 1). 10.1371/journal.pone.0002530.t001 Table 1 Demographic and haematological characteristics at enrolment in G6PD normal children. Characteristics AS+AQ [N = 178] AL [N = 177] AS+CD [N = 178] P n (%) n (%) n (%) \n Age (months) \n 6–11 26 (14.6) 25 (14.0) 22 (12.4) 1.0 12–59 119 (66.9) 120 (67.4) 122 (68.5) 60+ 32 (18.0) 33 (18.5) 34 (19.1) Mean (SD) 37.6 (24.3) 36.8 (26.2) 39.4 (25.0) 0.6 \n Gender \n Male 83 (46.9) 94 (52.8) 92 (51.7) 0.5 Female 94 (52.8) 84 (47.2) 86 (48.3) \n Weight (Kg) \n <9.9 50 (28.1) 54 (30.3) 46 (25.8) 0.8 10.0–19.9 117 (65.7) 112 (62.9) 118 (66.3) 20.0+ 10 (5.6) 12 (6.7) 14 (7.9) Mean (SD) 12.6 (4.3) 12.4 (4.5) 12.6 (4.3) 0.9 \n Temperature (°C) \n ≥37.5 106 (59.6) 107 (60.1) 97 (54.5) 0.5 Mean (SD) 37.9 (1.1) 39.9 (1.1) 37.7 (1.1) 0.3 \n Parasite Density/μL \n <2500 39 (21.9) 31 (17.4) 32 (18.0) 0.2 2500-<10000 42 (23.6) 28 (15.7) 36 (20.2) ≥10000 96 (53.9) 119 (66.9) 110 (61.8) Geometric mean (range) 12507 (1000, 198520) 16521 (1000, 197360) 13820 (1000,199280) Gametocytaemia 10 (5.6) 11 (6.2) 16 (9.0) 0.4 \n Haemoglobin (g/dL) \n 6-<11 163 (91.6) 167 (93.8) 165 (92.7) 0.8 11+ 14 (7.9) 11 (6.2) 13 (7.3) Mean (SD) 9.1 (1.4) 8.9 (1.3) 8.9 (1.4) 0.3 AS = artesunate; AQ = amodiaquine; AL = artemether-lumefantrine; CD = chlorproguanil-dapsone In the per-protocol (PP) analyses there were no statistically significant differences in the rates of early treatment, late treatment, parasitological or clinical failures at day 14 between the three groups (Table 2). Survival analysis showed that there was no statistically significant differences in treatment failure at different time points during the 28 day post treatment period between the three groups (Figure 2). However, the parasitological and clinical failure rate at day 28 (PCF28) uncorrected for re-infections was significantly lower in the AS+AQ group (14.6%) compared to the AL (27.6%) or AS+CD (28.1%) groups (Table 2). The PCF28 corrected for re-infection was also lower in the AS+AQ group (6.6%) than in the AL (13.8%) or AS+CD (13.8%) groups but this difference was not statistically significant. PCF28 uncorrected for re-infection was nearly 50% less in the AS+AQ group compared to AL and AS+CD groups (Table 3). PCF28 corrected for new infections was significantly lower in the AS+AQ group compared to AS+CD group (RR 0.43; 95% CI 0.20, 0.89). There was no significant difference in the PCF28 between AL and AS+CD groups (Table 3). 10.1371/journal.pone.0002530.g002Figure 2Proportion of children having treatment failures at different time points during the post treatment period Per protocol analysis of G6PD normal children. 10.1371/journal.pone.0002530.t002 Table 2 Treatment outcomes (per protocol analysis). Outcomes AS+AQ [N = 151] AL [N = 152] AS+CD [N = 160] P * \n n (%) n (%) n (%) Early treatment failure 1 (0.7) 5 (3.3) 3 (1.9) 0.257 Late treatment failure 6 (4.0) 7 (4.6) 7 (4.4) 0.960 Parasitological or clinical failure by day 14 8 (5.3) 13 (8.6) 13 (8.1) 0.482 Parasitological or clinical failure by day 28 (PCR uncorrected) 22 (14.6) 42 (27.6) 45 (28.1) 0.005 Parasitological or clinical failure by day 28 (PCR corrected) 10 (6.6) 21 (13.8) 22 (13.8) 0.083 Missing PCR by day 28 (excluded) 3 (2.0) 9 (5.9) 13 (8.1) - Gametocytaemia by day 7 3 (2.0) 0 (0) 6 (3.8) 0.043 AS = artesunate; AQ = amodiaquine; AL = artemether-lumefantrine; CD = chlorproguanil-dapsone * \n exact P values \n 10.1371/journal.pone.0002530.t003 Table 3 Comparison of treatment outcomes between groups (per protocol analysis). Outcomes AS+AQ vs AL P * \n AS+AQ vs AS+CD P * \n AS+CD vs AL P * \n RR (95% CI) RR (95% CI) RR (95% CI) Parasitological or clinical failure by day 14 0.69 (0.28,1.63) 0.4 0.67 (0.27,1.55) 0.4 1.08 (0.49,2.22) 0.8 Parasitological of clinical failure by day 28 (PCR uncorrected) 0.53 (0.32,0.85) 0.007 0.51 (0.30,0.81) 0.004 1.01 (0.68,1.41) 1.0 Parasitological of clinical failure by day 28 (PCR corrected) 0.48 (0.23,0.98) 0.044 0.43 (0.20,0.89) 0.023 1.03 (0.57,1.47) 0.9 AS = artesunate; AQ = amodiaquine; AL = artemether-lumefantrine; CD = chlorproguanil-dapsone * \n since there are three comparisons Bonfferroni correction is applied; the P value has to <0.017 to be statistically significant \n In the intention to treat analyses, the rate of early treatment failure was high in all three groups (13.3% in AS+AQ, 15.2% in AL, and 9.3% in AS+CD groups respectively) but this was primarily due to vomiting twice or more within half an hour of administration of the study drugs. Among the early treatment failures, 22/23 in AS+AQ, 22/27 in AL, and 13/16 in AS+CD groups were due to repeated vomiting of study drugs. In the intention to treat analyses the relative risk (RR) of parasitological and clinical failure by day 28 corrected for reinfection was lower, though not statistically significantly, in the AS+AQ group compared to the AL group (RR 0.75; 95% CI 0.48, 1.14) or to the AS+CD group (RR 0.81; 95% CI 0.5, 1.27). The relative risk of parasitological and clinical failure corrected for reinfection was lower in the AS+AQ group compared to the AL (RR 0.68, 95% CI 0.47, 0.94) or AS+CD group (RR 0.72, 95% CI 0.49, 1.01). There was a drop in mean Hb concentration on day 2 post treatment compared to day 0 in each of the three groups (Table 4). The mean drop in Hb on day 2 ranged from 0.8 g/dl in the AS+CD group to 0.4 g/dl in the AL group. By day 7 post treatment, the mean Hb concentration had recovered to the day 0 levels in the AS+AQ and AL groups and by day 28 the mean Hb was higher than the day 0 in all three groups. The rate of recovery of Hb was slightly slower in the AS+CD group compared to the other two groups. 10.1371/journal.pone.0002530.t004 Table 4 Haemoglobin concentration during the post treatment period in the study groups. Post treatment day AS+AQ (n = 151) AL (n = 152) AS+CD (n = 160) P * \n Mean Hb g/dl (SD) Mean Hb g/dl (SD) Mean Hb g/dl (SD) 0 9.0 (1.3) 9.2 (1.4) 8.9 (1.3) 0.2 1 8.5 (1.6) 8.7 (1.6) 8.3 (1.4) 0.08 2 8.3 (1.7) 8.8 (1.7) 8.1 (1.6) 0.002 3 8.8 (1.8) 8.9 (1.6) 8.4 (1.5) 0.045 7 9.0 (1.7) 9.3 (1.6) 8.6 (1.5) 0.001 28 9.9 (1.7) 10.0 (1.6) 9.7 (1.6) 0.3 AS = artesunate; AQ = amodiaquine; AL = artemether-lumefantrine; CD = chlorproguanil-dapsone SD = standard deviation * \n since there are five time points compared against the baseline (day 0), Bonfferroni correction is applied; the P value has to <0.008 to be statistically significant \n The reported incidences of solicited adverse events during the 7 days post treatment are shown in Table 5. The incidence of solicited adverse events was comparable between the three groups. A history of body pain was more frequent in the AS+AQ group than the other two groups (Table 5). 10.1371/journal.pone.0002530.t005 Table 5 Distribution of solicited adverse events during the 7-day post treatment period. Reported symptoms AS+AQ (n = 178) AL (n = 177) AS+CD (n = 178) P * \n (Adverse events) n (%) n (%) n (%) Unable to suck/drink 8 (4.5) 5 (2.8) 2 (1.1) 0.11 Fever 0 (0) 0 (0) 0 (0) - Runny nose 29 (16.3) 30 (17.0) 14 (7.9) 0.03 Cough 33 (18.5) 23 (13.0) 21(11.8) 0.30 Difficulty in breathing 3 (1.7) 4 (2.3) 2 (1.1) 0.48 Diarrhoea 13 (7.3) 19(10.7) 11(6.2) 0.44 Vomiting 8(4.5) 6(3.4) 12 (6.7) 0.58 Itching/pruritus 13 (7.3) 10 (5.7) 10 (5.6) 0.93 Loss of appetite 61 (34.3) 44 (24.9) 50 (28.1) 0.29 Nausea 2 (1.1) 0 (0.0) 5 (2.8) 0.17 Abdominal pain 31 (17.4) 19 (10.7) 28 (15.7) 0.34 Body pain 25 (14.0) 10 (5.7) 9 (5.1) 0.01 Difficulty in sleeping 2 (12.4) 23 (13.0) 16 (9.0) 0.75 Joint pain 4 (2.3) 1 (0.6) 0 (0.0) 0.28 Palpitation 3 (1.7) 4 (2.6) 5 (2.8) 0.89 Rash 2 (1.1) 3 (1.7) 2 (1.1) 0.97 Ulcers in mouth/tongue 15 (8.4) 12 (6.8) 10 (5.6) 0.82 Yellow eyes 4 (2.3) 3 (1.7) 4 (2.3) 1.00 AS = artesunate; AQ = amodiaquine; AL = artemether-lumefantrine; CD = chlorproguanil-dapsone * \n exact P values \n \n\nBODY.RESULTS.G6PD DEFICIENT CHILDREN:\nThere was no statistically significant differences in the parasitological or clinical failure rates by day 14 or day 28 between the AS+AQ and AL groups (Table 6). The drop in mean Hb by day 3 post treatment and the recovery in Hb by day 28 were comparable between AS+AQ and AL groups and there was no apparent difference in the distribution of Hb concentrations following treatment between the G6PD normal and deficient children (data not shown). 10.1371/journal.pone.0002530.t006 Table 6 Treatment outcomes in G6PD deficient children (Per protocol analysis) Outcomes AS+AQ [N = 44] AL [N = 42] P * \n n (%) n (%) Early treatment failure 1 (2.3) 0 (0.0) 0.3 Late treatment failure 1 (2.3) 2 (4.8) 0.5 Parasitological or clinical failure by day 14 3 (6.8) 2 (4.8) 0.7 Parasitological or clinical failure by day 28 (PCR uncorrected) 11 (25.0) 11 (26.2) 0.9 Parasitological or clinical failure by day 28 (PCR corrected) 6/43 (14.0) 4/42 (9.5) 0.5 Missing PCR by day 28 (excluded) 1 (2.3) 0 0.3 AS = artesunate; AQ = amodiaquine; AL = artemether-lumefantrine; CD = chlorproguanil-dapsone * \n exact P values \n \n\nBODY.DISCUSSION:\nIn our study population, the parasitological and clinical failure at day 28 was lower in the AS+AQ group than in AL group. Our PCR corrected parasitological failure rate at day 28 is higher than that previously reported from Ghana[8] for AS+AQ (6.6% vs 2.5%) and remarkably higher for AL (13.8% vs 0%). The reason for the substantially higher parasitological failure at day 28 for AL compared to the results of a previous study in Ghana[8] and elsewhere[9] is unclear. Dietary differences between our population and the previously studied populations is a possible explanation for this difference; poor absorption of AL leading to a higher parasitological failure compared to that reported from elsewhere. We did not follow the recommended practice of administering AL with a fatty diet in a clinical trial; instead we only advised caretakers to give fatty food at the time of drug administration. This was a pragmatic decision because in routine health care setting one can only advise a caretaker to administer AL with a fatty meal. Thus, the observed higher treatment failure of AL observed in our study compared with others may have been due to the lack of intake of fat along with AL, as is likely to happen frequently in routine clinical practice. Although there was a significant difference in the parasitological failure rate (both recrudescence and re-infections) at day 28 between AL and AS+AQ, there was no difference in the clinical failure between the two groups, perhaps because both combinations contain a fast acting artemisinin. The parasitological or clinical failure of AS+CD by day 14 was 8% and by day 28 (PCR corrected) was 13.8% in our study population. There are no other published studies of efficacy of AS+CD with which to compare these results. An earlier multicountry trial of CD monotherapy showed a parasitological or clinical failure rate of 5% by day 14 in Nigeria.[10] Our study suggests that adding AS to CD may have little value in West Africa given that the PCR corrected failure rate by day 28 has already reached 13.8%. Surprisingly, the PCR corrected failure rate by day 28 for AL was also 13.8% and this suggests that introducing AL as a replacement for AS+AQ needs to considered with caution. More evidence on the efficacy of AL in Ghana is needed urgently. In the AL group, all children who had gametocytes on day 0 (n = 11) had cleared gametocytes by day 3 post treatment; gametocytes appeared in the blood of two children between day 14 and 28. In children in the AS+AQ group who had gametocytes on day 0 (n = 10) only one child had gametocytes on day 3 and 7. Two more children developed gametocytaemia by day 7 but all children cleared gametocytes by day 14. In children in the AS+CD group who had gametocytes on day 0 (n = 16) 4 children had gametocytes on day 3 and one child had gametocytes on day 7 Gametocytes appeared in a further child by day 7 but all children had cleared gametocytes by day 14; two children had developed gametocytes between day 14 an 28. It appears that all three ACTs tested in this study are effective at clearing gametocytes and this property of ACTs should have an effect on the transmission of malaria. A slight reduction in the Hb concentration occured during the early post treatment period in all three treatment groups. Although differences were not remarkable, the recovery of Hb was slowest following treatment with AS+CD. There was no difference in the risk of haemolysis between the three ACTs in G6PD normal children. However, we cannot comment about the potential risk of haemolysis associated with AS+CD in an unselected population because G6PD deficient children were not included in the AS+CD arm. Results from recently completed multicentre trials indicate that coformulated AS+CD can cause serious haemolysis in children who are G6PD deficient so further development of this drug combination has been halted. Our study results supports the current policy of AS+AQ as first line treatment for uncomplicated malaria in Ghana. However, the slightly higher incidence of adverse events, particularly vomiting and body pain, associated with use of AS+AQ is a concern. If these adverse events are common in adults as well then they might reduce adherence to a full course of the treatment. There were some reports of adverse events of AQ in the Ghanaian mass media and this has lead to the general public being reluctant to accept AS+AQ combination therapy. Although the overall incidence of adverse events related to AS+AQ group is reasonable, in order to achieve a good compliance an appropriate communication strategy is needed in addition to the introduction of the new fixed combinations of artesunate plus amodiaquine that are currently being developed. We conclude that AS+AQ is an appropriate first line treatment for uncomplicated malaria in Ghana and possibly in neighbouring countries in West Africa. However, the deployment of AS+AQ should be linked to a clear information strategy regarding the potential mild adverse events for health care providers and the general public. The efficacy and safety of AL when given in the context of routine care need to be further studied in Ghana and elsewhere in West Africa.\n\nBODY.SUPPORTING INFORMATION:\nProtocol S1Trial Protocol.(0.29 MB DOC)Click here for additional data file. Checklist S1CONSORT Checklist.(0.06 MB DOC)Click here for additional data file.\n\n**Question:** Compared to artemether-lumefantrine (AL) what was the result of Artesunate+amodiaquine (AS+AQ) on parasitological or clinical failure rates by day 14 or day 28 in G6PD deficient children?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
416
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pentobarbital versus thiopental in the treatment of refractory intracranial hypertension in patients with traumatic brain injury: a randomized controlled trial\n\n ABSTRACT.INTRODUCTION:\nExperimental research has demonstrated that the level of neuroprotection conferred by the various barbiturates is not equal. Until now no controlled studies have been conducted to compare their effectiveness, even though the Brain Trauma Foundation Guidelines recommend that such studies be undertaken. The objectives of the present study were to assess the effectiveness of pentobarbital and thiopental in terms of controlling refractory intracranial hypertension in patients with severe traumatic brain injury, and to evaluate the adverse effects of treatment.\n\nABSTRACT.METHODS:\nThis was a prospective, randomized, cohort study comparing two treatments: pentobarbital and thiopental. Patients who had suffered a severe traumatic brain injury (Glasgow Coma Scale score after resuscitation ≤ 8 points or neurological deterioration during the first week after trauma) and with refractory intracranial hypertension (intracranial pressure > 20 mmHg) first-tier measures, in accordance with the Brain Trauma Foundation Guidelines.\n\nABSTRACT.RESULTS:\nA total of 44 patients (22 in each group) were included over a 5-year period. There were no statistically significant differences in ' baseline characteristics, except for admission computed cranial tomography characteristics, using the Traumatic Coma Data Bank classification. Uncontrollable intracranial pressure occurred in 11 patients (50%) in the thiopental treatment group and in 18 patients (82%) in the pentobarbital group (P = 0.03). Under logistic regression analysis – undertaken in an effort to adjust for the cranial tomography characteristics, which were unfavourable for pentobarbital – thiopental was more effective than pentobarbital in terms of controlling intracranial pressure (odds ratio = 5.1, 95% confidence interval 1.2 to 21.9; P = 0.027). There were no significant differences between the two groups with respect to the incidence of arterial hypotension or infection.\n\nABSTRACT.CONCLUSIONS:\nThiopental appeared to be more effective than pentobarbital in controlling intracranial hypertension refractory to first-tier measures. These findings should be interpreted with caution because of the imbalance in cranial tomography characteristics and the different dosages employed in the two arms of the study. The incidence of adverse effects was similar in both groups.\n\nABSTRACT.TRIAL REGISTRATION:\n(Trial registration: US Clinical Trials registry NCT00622570.)\n\nBODY.INTRODUCTION:\nHigh dosages of barbiturates are used in patients with severe traumatic brain injury (TBI) who present with refractory intracranial hypertension (ICH) after medical and surgical treatment. This practice is recommended in the Brain Trauma Foundation (BTF) Guidelines, because this is the only second-level measure for which there is class II evidence that it can reduce intracranial pressure (ICP) [1]. Nevertheless, its effect on outcome is unproven [2], mainly because of severe medical complications. Within the family of barbiturates the oxibarbiturates and thiobarbiturates stand out, their primary representatives being pentobarbital and thiopental. Until now no controlled studies have been reported that compare the effectiveness of pentobarbital and thiopental in controlling ICH. At the experimental level, research has demonstrated that mechanisms of action and levels of neuroprotection differ between these agents [3-6]. For this reason, research is needed to compare the effectiveness of these two drugs in terms of controlling refractory ICH in patients with severe TBI. Based on various studies conducted in laboratory animals [3-6], suggesting that the neuroprotective capacity of thiopental is superior, our working hypothesis was that thiopental is more effective than pentobarbital in controlling ICP in patients with severe TBI, with a similar incidence of adverse side effects. In support of our work in the present study, the BTF Guidelines recommend that studies be undertaken to compare the effectiveness of the different barbiturates that are currently used in TBI patients [1].\n\nBODY.MATERIALS AND METHODS:\nWe conducted a prospective, randomized cohort study comparing two treatments: pentobarbital and thiopental. Our primary objective was to compare the effectiveness of these agents in controlling refractory ICH in patients with severe TBI. Secondary objectives were to compare the incidence of secondary effects, especially arterial hypotension, which was defined as the presence of mean arterial pressure (MAP) under 80 mmHg at any point during barbiturate therapy. This study was conducted at Son Dureta University Hospital (Palma de Mallorca, Spain) and was approved by the Ethics Committee of the Balearic Islands on 31 March 2002. It is registered with the US Clinical Trials Registry, with the number NCT00622570. In all cases, the patient's closest relative, legal representative, or guardian gave written informed consent for their inclusion in the study.\n\nBODY.MATERIALS AND METHODS.INCLUSION CRITERIA:\nPatients admitted to our intensive care unit (ICU) between May 2002 and July 2007 with a severe TBI (Glasgow Coma Scale [GCS] score after nonsurgical resuscitation ≤ 8) and presenting with refractory ICH (ICP > 20 mmHg), and who underwent first-level measures in accordance with the BTF Guidelines [7], were included. Refractory ICH was defined as follows: ICP 21 to 29 mmHg for 30 minutes or more, ICP of 30 to 39 mmHg for 15 minutes or more, or ICP greater than 40 mmHg for more than 1 minute, in the absence of external interventions. Included patients were required to be haemodynamically stable at the point of inclusion in the study; haemodynamic stability was defined as systolic blood pressure of 100 mmHg or greater.\n\nBODY.MATERIALS AND METHODS.EXCLUSION CRITERIA:\nWe did not include in the study patients who were younger than 15 or older than 76 years; patients with a GCS score of 3 upon admission and neurological signs of brain death (bilateral arreactive midryasis and loss of brainstem reflexes); and patients who were pregnant, had barbiturate allergy or intolerance, or had a history of severe cardiac ventricular dysfunction with an ejection fraction under 35%.\n\nBODY.MATERIALS AND METHODS.GENERAL THERAPEUTIC PROTOCOL:\nAll patients with severe TBI underwent cranial computed tomography (CT) upon admission and were categorized in accordance with the classification proposed by the Traumatic Coma Data Bank [8]. We also recorded findings of CTs conducted before inclusion of the patients in the study. The CT findings on inclusion were regarded to be the worst of the hospital stay; the prognostic value of such CT findings have been described by other authors [9]. CTs were independently reviewed and categorized by two neurosurgeons (JI and MB) who were unaware of the treatment group to which the patients had been assigned. In cases of disagreement between these investigators, a third investigator reviewed the CT images. All patients' ICP was monitored using an intraparenchymal Camino catheter (Integra Neurosciences, Plainsboro, NJ, USA). The ICP catheter was placed in the frontal region of the hemisphere with more radiological lesions on the CT. The systemic monitoring of these patients included invasive blood pressure, pulse oximetry, and a pulmonary artery thermodilution catheter. The ICP, MAP and cerebral perfusion pressure data were gathered on an hourly basis (one value every full hour) throughout the study using the Care Vue® clinical monitoring system (Phillips, Eindhoven, The Netherlands). The general treatment objectives in patients with severe TBI were to maintain MAP above 80 mmHg, ICP below 20 mmHg, and cerebral perfusion pressure above 60 mmHg. To achieve these objectives, we used liquids and/or vasoactive support with norepinephrine (noradrenaline). In patients with ICP greater than 20 mmHg, initial treatment included elevation of the head of the bed, keeping the neck straight, appropriate sedation, muscular paralysis, ventricular drainage (if the patient had visible ventricles on the CT), 20% mannitol (0.25 to 0.75 mg/kg), 7.5% hypertonic saline (2 ml/kg) and moderate hyperventilation (partial carbon dioxide tension of 30 to 35 mmHg). Neurosurgical interventions were undertaken when necessary to evacuate surgical lesions. This approach can be considered conventional treatment and is included in the BTF Guidelines as first-tier therapy [7]. Patients whose ICP remained high with conventional treatment were included in the study. Before randomization of the patient to a study group, we required that patient to have received maximal medical treatment (first-level measures). In addition, we required a CT to have been conducted within 24 hours before inclusion of the patient in the study; intravenous administration of 0.7 g/kg mannitol 1 hour before randomization; or a plasmatic osmolarity measurement above 320 mOsm/kg, in order to ensure that hyperosmolar therapy had been optimized before inclusion.\n\nBODY.MATERIALS AND METHODS.RANDOMISATION:\nRandomization was based on a computer-generated list that intercollated the two drugs. Allocation was done by the intensive care unit physician who was on duty, once the patient had been found to meet the inclusion criteria and none of the exclusion criteria. Data collection and patient follow up were conducted by the same investigator (JPB).\n\nBODY.MATERIALS AND METHODS.BLINDING OF TREATMENT GROUPS:\nThe study was not blinded because it was difficult for us to mask treatment; thiopental is liophylized for administration and pentobarbital is not.\n\nBODY.MATERIALS AND METHODS.ADMINISTRATION OF BARBITURATES AND MONITORING OF EFFECTS:\nPentobarbital was administered in accordance with the protocol established by Eisenberg and coworkers [10], using a loading dose of 10 mg/kg over 30 minutes followed by a continuous perfusion of 5 mg/kg per hour for 3 hours. This was followed by a maintenance dosage of 1 mg/kg per hour. Thiopental was administered in the form of a 2 mg/kg bolus administered over 20 seconds. If the ICP was not lowered to below 20 mmHg, then the protocol permitted a second bolus of 3 mg/kg, which could be readministered at 5 mg/kg if necessary to reduce persistently elevated ICP. The maintenance dosage was an infusion of thiopental at a rate of 3 mg/kg per hour. In both treatment groups, for cases in which the maintenance dosage did not achieve the reduction in ICP to below the 20 mmHg threshold, the maintenance dosage for both drugs could be increased by 1 mg/kg per hour, while looking for electroencephalographic burst suppression or even the flat pattern, in order to ensure that different doses of the two barbiturates were equipotent. Electroencephalography was conducted daily in a noncontinuous manner (Nicolet; Viasys Healthcare, Verona Road, Madison, WI, USA). Results were analyzed by an experienced neurologist who was blinded to the treatment of the patients. In those patients in whom barbiturate coma did not control ICP, we used decompressive craniotomy and/or external lumbar drainage, in accordance with the Munch criteria, as life-saving measures [11,12].\n\nBODY.MATERIALS AND METHODS.EFFECTIVENESS CRITERIA:\nAdequate response to treatment was defined as a decrease in ICP to below 20 mmHg, and maintenance below this threshold for at least 48 hours. To describe the ICP, we also followed the criteria previously employed by Stocchetti and coworkers [13]; the arithmetic mean of ICP data recorded during every 24-hour period, after filtering to exclude inaccurate readings, was calculated and expressed as 'mean ICP'. Three ICP blocks were considered for further analysis: less than 20 mmHg, 20 to 30 mmHg, and more than 30 mmHg. Uncontrollable ICP was defined as follows: ICP of 21 to 35 mmHg for 4 hours, ICP of 36 to 40 mmHg for 1 hour, or ICP above 41 mmHg for 5 minutes, in the absence of external interventions. We also defined as unresponsive to treatment those cases in which, because of refractory ICP, the patient needed some other treatment (surgery and/or lumbar drainage) and cases in which the patient progressed to brain death. Although it was not a main objective of the study, patients were evaluated 6 months after injury using the Glasgow Outcome Scale [14].\n\nBODY.MATERIALS AND METHODS.WITHDRAWAL OF TREATMENT:\nWhen ICP was controlled (<20 mmHg for 48 hours), we conducted a step-wise reduction in the barbiturate coma in steps that reduced the dosage by 50% every 24 hours until the infusion was suspended. In the event of ICP values rising to the study's inclusion values during the withdrawal of barbiturate treatment, the perfusion dosage was once again increased to achieve control of the patient's ICP.\n\nBODY.MATERIALS AND METHODS.SAMPLE SIZE:\nAccepting an α error of 0.05 and a β error of 0.2 in a bilateral hypothesis contrast, we estimated that 47 patients were needed in each group to detect differences of 30% or greater in the control of ICH. To calculate sample size, we assumed that the therapeutic response rate in the pentobarbital group would be 50%, excluding patients lost to follow up.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nQuantitative variables are expressed as the mean and standard deviation from the mean (SD) in normal distributions, and as median and interquartile range in cases that were not normally distributed. Qualitative variables are expressed as percentages, along with 95% confidence interval (CI). To determine whether variables followed a normal distribution, we used the Shapiro Wilks test. For the comparison of quantitative variables, Student's t-test was used if the variable followed a normal distribution. In other cases, we used the Mann-Whitney U-test. For the comparison of qualitative variables, we used χ2 or Fisher's exact test, as appropriate. Given that the randomization did not create groups that were similar in terms of types of intracranial lesions shown on the CT results, which is a prognostic variable that influences the effectiveness of barbiturate treatment in controlling ICP, we conducted a multivariate analysis using binary logistic regression, so that we would include the prognostic variables with the most plausible association with the dependent variable 'uncontrollable ICP'. These are variables such as age, GCS score at admission, and the worst CT obtained within 24 hours before inclusion of the patient in the study, as well as the type of barbiturate administered. To achieve this multivariate analysis, and given the small number of cases in each of the five groups in Marshall's classification, the CT data were grouped into focal and diffuse lesions. We also included in the model the minimum daily MAP during barbiturate treatment, given that in the second and third days of treatment there were statistically significant differences between the groups in the univariate analysis. The significant variables identified by the 'likelihood ratio' ≤ 0.1 test were used, along with those whose inclusion affected the calculation of the effect of the 'treatment group' variable. Both treatment groups were very similar in terms of other known prognostic variables, such as the presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them, so these were not included in the multivariate analysis. To analyze the variable ICP, which was determined on an hourly basis, we calculated the area under the curve (AUC) at 24, 48 and 72 hours, and also standardized by time [15]. For all comparisons, we considered statistical significance to have been achieved if the two-tailed α error probability was 5% or less (P ≤ 0.05). Statistical analyses were conducted using SPSS version 15 (SPSS Inc., Chicago, IL, USA).\n\nBODY.RESULTS:\nPreliminary results for the first 20 patients have already been published elsewhere [16]. From May 2002 to July 2007, 480 TBI patients were admitted to the intensive care unit of the Son Dureta University Hospital. Of these 480 patients, 71 (14.8%) presented with ICH refractory to first-level measures, of whom 44 were included in the study. The study was concluded prematurely because of the unexpected and slow inclusion rate; this could have modified some uncontrollable environmental factors that may affect results. The reasons for not including the remaining 27 refractory ICH cases were as follows: 13 patients were included in other studies, six were older than 76 years, five were admitted with nonreacting midriatic pupils and with clinical evidence of brain death, two presented with haemodynamic instability at the time of randomization, and one patient was transferred to a different hospital during the first 24 hours of admission, which excluded that patient from follow-up analysis. On average, the barbiturate coma was initiated in the thiopental group at 89 ± 15.5 hours after admission and in the pentobarbital group at 61 ± 14.3 hours after admission (P = 0.33). The baseline characteristics of the 44 patients included in the study, 22 randomized to each group, are presented in Table 1. There were no statistically significant differences with respect to epidemiological data, co-morbidity (data not shown) or lesions associated with TBI, although there were differences in the CT classification. Table 1 Baseline characteristics of patient population Characteristic Thiopental (n = 22) Pentobarbital (n = 22) P Sex (male; n) 19 19 1 Age (years) 26 (20 to 41) 32 (22 to 43) 0.45 ISS 25 (24 to 34) 25 (25 to 38) 0.77 SAPS II 42 (28 to 54) 43 (38 to 46) 0.95 APACHE II 23 (15 to 25) 20 (18 to 26) 0.27 APACHE III 60 (38 to 73) 52 (32 to 76) 0.41 Associated lesion (n) Thoracic injury 7 2 0.13 Abdominal injury 4 1 0.34 Extremities injury 9 5 0.20 Admission CT (n) Diffuse injury without brain swelling 12 4 0.046 Diffuse bilateral brain swelling 6 12 Diffuse unilateral brain swelling with midline shift 1 0 Any mass lesion > 25 ml 3 6 Age, ISS, SAPS II, APACHE II and APACHE III are expressed as median and interquartile range. APACHE, Acute Physiology and Chronic Health Evaluation; admission CT, admission computed tomography (according to the Traumatic Coma Data Bank); ISS, Injury Severity Score; SAPS, Simplified Acute Physiology. The summary of prognostic variables for the 44 patients is shown in Table 2. As in Table 1 the characteristics of the worst CT conducted before inclusion in the study differed between the two groups. Table 2 Prognostic variables of patient population Variable Thiopental (n = 22) Pentobarbital (n = 22) P Admission GCS score 6.5 (3.0 to 7.2) 7 (4.7 to 10.0) 0.38 Out-of-hospital hypoxia (n) 5 7 0.63 Out-of-hospital hypotension (n) 5 4 1 Pupillary reactivity (n) a One reacting 3 5 0.66 Both reacting b 12 14 Pre-enrolment CT (n) Diffuse injury without brain swelling 8 5 0.04 Diffuse bilateral brain swelling 1 8 Diffuse injury unilateral brain swelling with midline shift 5 1 Any mass lesion evacuated 7 5 Nonevacuated mass lesion 1 3 Admission GCS is expressed as median (interquartile range). a Pupillary reactivity at hospital admission. b Miotic pupils were considered as reactive. CT, computed tomography; GCS, Glasgow Coma Scale. \n\nBODY.RESULTS.EFFECTIVENESS CRITERION: CONTROL OF INTRACRANIAL PRESSURE:\nThe distribution of the ICP during the first 3 days of treatment, according to Stocchetti's criteria, is summarized in Table 3. The missing cases during these 3 days were due to brain deaths or to receipt of rescue treatment for uncontrollable ICP. Finally ICP was uncontrollable in 11 cases (50%) in the thiopental group and in 18 patients (82%) in the pentobarbital group (P = 0.03). In nonresponding patients, we chose to place a lumbar drainage in five, in three we opted for surgical treatment, and in three other patients we combined both treatments, drainage and surgery. Surgical decompression was conducted in four patients in the thiopental group and in two of the patients in the pentobarbital group. The number of hyperosmolar treatments administered (manitol and/or hypertonic saline) during the barbiturate coma was similar in both groups: 16.5 (8.0 to 24.2) in the thiopental group and 16.5 (3.0 to 21.5) in the pentobarbital group (P = 0.9). The mean ± SD duration of the barbiturate coma was 156 ± 60 hours for thiopental and 108 ± 100 hours for pentobarbital (P = 0.06). Seven (31.8%) patients presented an ICP rebound with thiopental and six (27.3%) with pentobarbital (P = 0.74) during treatment withdrawal. Table 3 Mean ICP recorded per day during the first 3 days of barbiturate coma Drug Day Mean ICP (n[%]) <20 mmHg 20 to 30 mmHg >30 mmHg Thiopental 1 10 46 11 50 1 5 2 15 71 4 19 2 10 3 12 63 6 32 1 5 Pentobarbital 1 9 41 8 36 5 23 2 8 38 9 43 4 19 3 6 43 8 57 0 0 Mean intracranial pressure (ICP) is the arithmetic mean of ICP data recorded during every 24-hour period, according to Stocchetti's criteria [ 13 ]. Data are presented as number of cases and as a percentage of the total number of cases each day. Figure 1 presents the AUC for ICP above 20 mmHg, standardized over time, as follows. The ICP value of AUC0–24 h was 458.00 mmHg·hour (95% CI = 421.84 to 494.16) in the thiopental group and 550.63 mmHg·hour (95% CI = 411.31 to 689.95) in the pentobarbital group. The AUC0–48 h was 913.18 mmHg·hour (95% CI = 814.08 to 1,012.27) in the thiopental group and 997.27 mmHg·hour (95% CI = 757.10 to 1,237.43) in the pentobarbital group. The AUC0–72 h in the thiopental group was 1,291.69 mmHg·hour (95% CI = 1,172.27 to 1,411.12) and 1,399.73 mmHg·hour (95% CI = 1,291.11 to 1,508.35) in the pentobarbital group. Standardized over time, the AUC per hour in the thiopental group was 23.90 mmHg (95% CI = 22.00 to 25.81) and in the pentobarbital group it was 29.39 mmHg (95% CI = 23.20 to 35.59). Figure 1AUC of ICP data. Presented are areas under the curve (AUCs) of the intracranial pressure (ICP) data, standardized by time, with a base value of 20 mmHg. Both treatment groups were similar in terms of known prognostic variables, such as presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them. Therefore, these were not included in the multivariate analysis. The logistic regression analysis showed that, after adjusting for the worst CT and the type of barbiturate used, thiopental was five times more likely than pentobarbital to control ICP (odds ratio = 5.1, 95% CI = 1.2 to 21.9; P = 0.027). The Hosmer-Lemeshow test indicated that the fit of the model was good (P = 0.799). The association of focal lesions in the pre-inclusion CT with ICP control was 3.6 times higher than that for the diffuse lesions. The relative risk for good control of ICP in the thiopental versus pentobarbital group was 2.26 for patients with focal lesions and 3.52 for those who presented with diffuse lesions. The other variables analyzed did not exhibit a significant relationship to ICP control, and did not modify the effect of the barbiturate treatment, including the third day minimum MAP, which was significantly different between the two treatments (data not shown).\n\nBODY.RESULTS.ADVERSE SIDE EFFECTS DURING THE BARBITURATE COMA:\nThe secondary effects during the barbiturate coma are presented in Table 4. In both groups almost all patients presented with at least one MAP measurement below 80 mmHg. There were no differences between groups with respect to the incidence of infections, Sepsis related Organ-Failure Assessment (SOFA) scores before initiation of treatment, or the maximum SOFA value [17] during the entire period of barbiturate coma. Table 4 Adverse events during barbiturate coma Adverse event Thiopental (n = 22) Pentobarbital (n = 22) P Hypotension a 21 20 1 Respiratory infection b 18 17 1 Urinary infection c 0 2 0.49 Positive blood culture 4 1 0.34 ICP catheter colonization 7 5 0.5 CNS infection (CSF) d 3 0 0.23 SOFA pre e 7 (4.5 to 9.5) 8.0 (5.5 to 9.0) 0.57 SOFA maximum f 11 (10 to 12) 11 (10 to 12) 0.94 a Hypotension is defined as detection of a medium arterial blood pressure below 80 mmHg at any time during barbiturate coma. b Respiratory infection: presence of a positive sputum culture. c Urinary infection: presence of a positive urine culture. d Central nervous system infection (CNS) infection (cerebrospinal fluid [CSF]): infection of the CNS with a positive culture in the CSF. e SOFA pre: value of the Sepsis related Organ-Failure Assessment (SOFA) score before the beginning of the barbiturate coma. f SOFA maximum: maximum value of the SOFA during the barbiturate coma, according the indication by Moreno and coworkers [ 16 ]. A thermodilution catheter was placed in 42 patients to facilitate haemodynamic control. The haemodynamic changes produced during the barbiturate coma are presented in Table 5. Differences of note include the minimum MAP, the pulmonary wedge pressure value, and the maximum norepinephrine dosage on days 2 and 3. Table 5 Systemic changes during barbiturate coma Parameter Pretreatment 1st day 2nd day 3rd day 4rd day Cardiac output (l/minute) a Thiopental 6.8 ± 1.4 6.4 ± 1.5 6.0 ± 1.4 6.7 ± 1.5 6.6 ± 1.8 Pentobarbital 7.4 ± 2.2 7.1 ± 1.9 6.5 ± 2.0 7 ± 1.4 6.1 ± 1.3 Cardiac index (l/minute per m 2 ) Thiopental 3.6 ± 0.6 3.4 ± 0.6 3.1 ± 0.6 3.6 ± 1.6 3.5 ± 0.9 Pentobarbital 3.8 ± 1.2 3.8 ± 0.8 3.4 ± 0.8 3.6 ± 0.7 3.2 ± 0.6 Peripheral venous resistance (dines/m 2 ) Thiopental 1,015 ± 325 1,022 ± 347 1,140 ± 429 1,089 ± 289 1,029 ± 253 Pentobarbital 952 ± 257 893 ± 210 1,003 ± 322 939 ± 261 914 ± 188 Pulmonary artery wedge pressure (mmHg) Thiopental 10.4 ± 4.5 9.6 ± 3.6 10.1 ± 4.1* 10.9 ± 4.6* 11.4 ± 3.5* Pentobarbital 11.6 ± 4.0 11.4 ± 3.1 12.8 ± 3.1 13.2 ± 2.1 13.9 ± 3.1 mBP (mmHg) b Thiopental 92 ± 11 75 ± 7 76 ± 9* 76 ± 6* 76 ± 8 Pentobarbital 94 ± 10 74 ± 1 68 ± 10 70 ± 1 70 ± 10 NAD (μg/kg per minute) c Thiopental 0.18 ± 0.33 0.28 ± 0.27 0.37 ± 0.3* 0.46 ± 0.39 0.56 ± 0.63 Pentobarbital 0.19 ± 0.18 0.55 ± 0.68 0.73 ± 0.69 0.60 ± 0.44 0.96 ± 0.79 P O 2 /Fi O 2 d Thiopental 284 ± 130 300 ± 139 293 ± 132 285 ± 138 254 ± 119 Pentobarbital 317 ± 127 304 ± 116 262 ± 125 211 ± 77 184 ± 92 Haemoglobin Thiopental 10.9 ± 1.6 10.7 ± 1.3 11 ± 1.2 10.8 ± 0.9 10.7 ± 1.4 Pentobarbital 10.6 ± 1.2 10.1 ± 1.0 10.4 ± 1.1 10.5 ± 1.1 10.2 ± 1.2 Temperature (°C) e Thiopental 35.8 ± 0.5 34.6 ± 1.3 34.6 ± 3.4 34.9 ± 1.0 34.9 ± 1.0 Pentobarbital 35.7 ± 1.0 34.6 ± 1.2 34.3 ± 1.3 34.4 ± 1.3 34.2 ± 1.1 a Cardiac output, cardiac index, peripheral venous resistance and pulmonary artery wedge pressure: the values are the mean values over 24 hours. b mBP: minimum value of the medium blood pressure during the day. c NAD: maximum dose of Noradrenaline bitartrate during the day. d P O 2 /Fis O 2 : ratio of partial oxygen tension to inspired fractional oxygen tension at 8:00 am. e Temperature: value of the minimum central temperature. * P < 0.05. \n\nBODY.RESULTS.SIX-MONTH OUTCOMES:\nIn the thiopental group, the neurological outcomes at 6 months (in accordance with Glasgow Outcome Scale score) were as follows: death in nine patients, vegetative state in two, severe disability in two, moderate disability in four and good recovery in four. In the pentobarbital group, the 6-month outcome was death in 16 patients, vegetative state in one, moderate disability in two and good recovery in two. In both groups one case was missing from the 6-month follow up analysis\n\nBODY.DISCUSSION:\nThe results of this study indicate that thiopental is five times more effective than pentobarbital in controlling refractory ICH. However, these findings must be interpreted with caution, given the small sample size and the fact that the study was unable to mask assignment to treatment groups. Barbiturate coma is at present the only therapy for which we have class II evidence, under BTF Guidelines [1], of efficacy in treating refractory ICH. Hence, it is perhaps the case that barbiturate coma is the most used second-level measure, with a usage frequency reported in the literature that varies from 13% to 56% [18,19]. Therefore, it is important to test the effectiveness of the various barbiturates available for controlling ICP refractory to first-level measures.\n\nBODY.DISCUSSION.DIFFERENCES BETWEEN OXIBARBITURATES AND THIOBARBITURATES:\nThe pharmacokinetic characteristics of thiopental and pentobarbital are different because their protein binding, distribution volume and clearance differ [20]. Nevertheless, the mean half life (thiopental 6 to 46 hours and pentobarbital 15 and 48 hours), which is the fundamental pharmacological parameter, differs little between the two agents. It therefore does not appear that these pharmacokinetic differences have clinical repercussions. One difference between these two groups of barbiturates is the presence of active metabolites. Thiopental has five metabolites, of which four are inactive and one (pentobarbital, or pentobarbitone) is active. Therefore, pentobarbital is an active metabolite of thiopental. This fact, along with the great intra-individual and inter-individual variability in the metabolism of these agents (caused by the existence of enzymatic induction phenomena associated with hepatic cytochrome P450), results in a weak correlation between serum concentrations and pharmacological effect. For this reason, monitoring this treatment with electroencephalography is strongly recommended. At the experimental level, various studies have compared these two medications. Hatano and coworkers [21], in a study conducted in a dog model, concluded that thiobarbiturates provoke cerebral vasoconstriction, which could help to redistribute cerebral blood flow toward ischaemic zones. Cole and colleagues [4] demonstrated that thiopental reduced the size of the ischaemic area more than did pentobarbital, even though both drugs achieved electroencephalographic burst suppression patterns. Shibuta [5] observed that thiopental, but not pentobarbital, was capable of limiting the cytotoxic damage caused by nitric oxide. Almaas and coworkers [3] observed that the different barbiturates had different neuroprotective effects with respect to oxygen and glucose deprivation in a model using human neurone cultures. Thiopental exhibited a neuroprotective effect at all the dosages studied, whereas pentobarbital was neuroprotective only at elevated dosages. Finally, in an in vitro study, Smith and colleagues [6] demonstrated that although thiopental provoked 96% inhibition of lipid peroxidation, pentobarbital had almost no effect. These experimental studies demonstrate that not all barbiturates are equal and that their neuroprotective capacity and effectiveness may differ [22]. Therefore, despite the unavoidable methodological limitations of the present study, we believe that our results may have clinical relevance.\n\nBODY.DISCUSSION.SECONDARY EFFECTS OF BARBITURATE COMA:\nThe most frequently detected secondary effect in our study, as might be expected, was arterial hypotension, which occurred in 21 patients in the thiopental group and 20 patients in the pentobarbital group. Although this incidence may be greater than that in previous studies [10], we attribute this to the definition of hypotension used (detection at any time in the barbiturate coma of MAP < 80 mmHg), which did not take the 'time' variable into account. For that reason, we collected data on other variables, such as maximum daily norepinephrine dosage and minimum daily MAP. Nearly all patients were monitored using a pulmonary artery thermodilution catheter, and arterial hypotension episodes were rigorously managed with fluid therapy and vasoactive drugs. We would note that the changes produced by pentobarbital at the cardiac and respiratory level were, in general terms, greater than those produced by thiopental. This is because (as shown in Table 5) cardiac output, cardiac index, and partial oxygen tension/fraction of inspired oxygen ratio exhibited greater changes during treatment with pentobarbital than with thiopental. This observation contrasts with the findings of previous experimental studies [23], in which it appeared that at high doses pentobarbital was safer and better tolerated than thiopental. Other complications (mostly infections) and the incidence of multiple organ dysfunction (identified using maximum SOFA) were similar in the two groups.\n\nBODY.DISCUSSION.LIMITATIONS OF THE STUDY:\nAs previously noted, this study has two important limitations. First, it was not a blinded study because the pentobarbital was not liophylized and thiopental was. Second, the sample size was small, so that small changes in the principal variable studied, namely ICP control, could significantly affect the statistical analysis. The classical view is that ICP response to barbiturates varies from 30% to 50%, and so it is possible that part of the difference found between drugs is due to poor response by the pentobarbital group as a result of any confounding bias. The randomization process is a potent mechanism that tends to eliminate bias by randomly distributing the values of all of the variables to the experimental groups. Nonetheless, the tool is not perfect and the groups frequently exhibit an imbalance in some confounding variable, especially when working with samples that are not very large. For this reason, in this study we used logistic regression analysis to eliminate any possible bias, and separate, independent analyses of the CT data were also conducted by two investigators who did not know the experimental group to which the patients belonged. Another limitation is that the dosages in the two groups were not the same. This leaves the possibility that the reason for the difference between agents that we identified is inadequate pentobarbital dose. Although in the two groups barbiturates were used with the end-point of ICP control, in this type of patient we also employ daily noncontinuous electroencephalographic monitoring. In this way, we believe that – despite different doses – the effect of the two barbiturates can be considered as equipotent because we looked for burst suppression or even the flat electroencephalographic pattern if the ICP was not controlled and the patients remained haemodynamically stable.\n\nBODY.CONCLUSION:\nIn this patient sample, thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-level measures, according to the BTF Guidelines. Nevertheless, these findings should be interpreted with caution because of the imbalance in CT characteristics and the different dosages employed in the two arms of the study. However, the present study is useful as a hypothesis testing exercise and will help to inform the design of future studies. These findings corroborate experimental evidence suggesting that there are differences in the neuroprotective mechanism between the two treatments, and this study may be a first step toward translating evidence from animal models to clinical disease. The incidence of secondary effects during treatment was similar between groups.\n\nBODY.KEY MESSAGES:\n• High doses of barbiturates are used in those patients with severe TBI who present with refractory ICH, and this recommendation is included in the BTF Guidelines. • Until now no controlled studies have been conducted to compare the effectiveness of pentobarbital and thiopental in controlling refractory ICH. Nevertheless, at the experimental level, research has demonstrated that their mechanisms and levels of neuroprotection differ. • Thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-tier measures, although these results should be interpreted with caution because of the imbalance in CT characteristics and other limitations of the study.\n\nBODY.ABBREVIATIONS:\nAUC: area under the curve; BTF: Brain Trauma Foundation; CI: confidence interval; ICH: intracranial hypertension; ICP: intracranial pressure; MAP: mean arterial pressure; SD: standard deviation; SOFA: Sepsis related Organ-Failure Assessment; TBI: traumatic brain injury.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nJPB was responsible for study design, acquisition of data, analysis and interpretation of data, and writing of the manuscript. JALP was responsible for acquisition of data and patient randomization. JH acquired data and conducted patient randomization. JMA acquired data and conducted patient randomization. JMR conducted statistical analyses. GF conducted statistical analyses. MB was responsible for designing the study and reviewing CT findings. JI was responsible for designing the study and reviewing CT findings. JI revised the article critically and gave final approval to the version to be published.\n\n**Question:** Compared to Pentobarbital what was the result of Thiopental on Sepsis related Organ-Failure Assessment (SOFA) maximum score during treatment?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
313
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Formoterol DPI 9 μg what was the result of Budesonide/formoterol pMDI 320/9 μg on Pre-dose FEV1 improvement?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
353
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and Tolerability of Budesonide/Formoterol in One Hydrofluoroalkane Pressurized Metered-Dose Inhaler in Patients with Chronic Obstructive Pulmonary Disease\n\n ABSTRACT:\nBackground: Combination therapy with a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended in patients with chronic obstructive pulmonary disease (COPD) who have frequent exacerbations. The efficacy and tolerability of the combination of budesonide/formoterol have been demonstrated in patients with COPD when administered via the dry powder inhaler (DPI) in a 1-year study and when administered via the hydrofluoroalkane (HFA) pressurized metered-dose inhaler (pMDI) in a 6-month study. Objective: This study assessed the long-term efficacy and tolerability of budesonide/formoterol HFA pMDI in patients with moderate to very severe COPD. Methods: This was a 12-month, randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre study (NCT00206167) of 1964 patients aged ≥40 years with moderate to very severe COPD conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. After 2 weeks of treatment based on previous therapy (ICSs, short-acting bronchodilators allowed), patients received one of the following treatments twice daily: budesonide/formoterol pMDI 160/4.5 μg × two inhalations (320/9 μg); budesonide/formoterol pMDI 80/4.5 μg × two inhalations (160/9 μg); formoterol DPI 4.5 μg × two inhalations (9 μg); or placebo. Main outcome measures: The co-primary efficacy variables were pre-dose forced expiratory volume in 1 second (FEV1) and 1-hour post-dose FEV1. Results: Budesonide/formoterol 320/9 μg demonstrated greater improvements in pre-dose FEV1 versus formoterol (p = 0.008), and both budesonide/formoterol doses demonstrated greater improvements in 1-hour post-dose FEV1 versus placebo (p < 0.001). The rate of COPD exacerbations was lower in both budesonide/formoterol groups compared with formoterol and placebo (p ≤ 0.004). Both budesonide/formoterol doses were more effective than placebo (p ≤ 0.006) for controlling dyspnoea and improving health status (St George's Respiratory Questionnaire). All treatments were generally well tolerated. The incidence of pneumonia was not different for active (3.4–4.0%) and placebo (5.0%) groups. Conclusions: Budesonide/formoterol pMDI (320/9 μg and 160/9 μg) improved pulmonary function and reduced symptoms and exacerbations over 1 year in patients with moderate to very severe COPD. Only budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy for both co-primary variables compared with formoterol DPI 9 μg. Both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol and placebo.\n\nABSTRACT.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material is available for this article at 10.2165/00003495-200969050-00004 and is accessible for authorized users.\n\nBODY.BACKGROUND:\nIn patients with chronic obstructive pulmonary disease (COPD) and frequent exacerbations, the combination of a long-acting bronchodilator and an inhaled corticosteroid (ICS) is recommended.[1] Budesonide and formoterol delivered via a single dry powder inhaler (DPI; Symbicort® Turbuhaler®; AstraZeneca, Lund, Sweden) have been shown to improve pulmonary function[2,3] and reduce COPD exacerbation rates.[2,3] Fixed-combination budesonide/formoterol is available in the US in a hydrofluoroalkane pressurized metered-dose inhaler (pMDI; Symbicort® Inhalation Aerosol; AstraZeneca LP, Wilmington, DE, USA). While most patients with COPD can benefit from either a pMDIor DPI, the pMDI formulation allows patients whomay have inadequate peak inspiratory flow for optimal delivery from a DPI to use the pMDI effectively. A recent 6-month study demonstrated the efficacy and tolerability of budesonide/formoterol pMDI in patients with moderate to very severe COPD.[4] Treatment with budesonide/formoterol pMDI resulted in significant improvements in pulmonary function, dyspnoea and health-related quality of life; however, the duration of the study was limiting with respect to the analysis of low-frequency events, such as COPD exacerbations, and precluded an assessment of safety outcomes with long-term exposure.[4] In this study, the long-term efficacy and tolerability of two dosage strengths of budesonide/formoterol pMDI were assessed over 12 months in patients with moderate to very severe COPD.\n\nBODY.PATIENTS AND METHODS.PATIENTS:\nThe inclusion criteria were designed to select a population with moderate to very severe COPD with previous exacerbations (i.e. appropriate candidates for combination ICS/long-acting β2-adrenoceptor agonist [LABA] therapy): age ≥40 years, diagnosis of symptomatic COPD for >2 years, ≥10 pack-year smoking history, prebronchodilator forced expiratory volume in 1 second (FEV1) of ≤50% of predicted normal and prebronchodilator FEV1/forced vital capacity (FVC) of <70%. Patients were to have a Modified Medical Research Council dyspnoea scale score of ≥2 and a history of at least one COPD exacerbation requiring oral corticosteroids or antibacterials within 1–12 months before the first study visit. Additional enrolment criteria were the same as those in a similar 6-month study by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.STUDY DESIGN:\nThis was a randomized, double-blind, double-dummy, parallel-group, active- and placebo-controlled, multicentre trial (ClinicalTrials.gov identifier: NCT00206167) conducted from 2005 to 2007 at 237 sites in the US, Europe and Mexico. The study protocol was approved by a local institutional review board and ethics committee, and written informed consent was obtained from patients. The study was designed to conform with the Declaration of Helsinki, and was consistent with the International Conference on Harmonisation and Good Clinical Practice and applicable regulatory requirements. After meeting eligibility criteria, patients entered a 2-week run-in period, during which they received ICS monotherapy if previously stable on ICS (alone or in combination) and ipratropium bromide at a fixed dose if previously receiving anticholinergics. Albuterol (salbutamol) was permitted for rescue use throughout the study. At randomization, all previous ICSs were discontinued and patients were randomized to one of four treatments (figure 1). Patients who were treated with ipratropium bromide during the run-in period were allowed to continue on it throughout the study period. Other allowed and disallowed concomitant medications were the same as those reported in the study by Tashkin et al.[4]\nFig. 1Study design. To maintain blinding, patients received both a pressurized metered-dose inhaler (pMDI) and a dry powder inhaler (DPI) containing either active treatment or double-dummy placebo (PL) as appropriate. This study used formoterol (FM) DPI (Oxis® Turbuhaler®, AstraZeneca, Lund, Sweden) as the FM comparator because FM is not available as a hydrofluoroalkane pMDI in the US. A previous study in asthma patients reported equivalent FM-related bronchodilatory effects when FM was administered in combination with budesonide (BUD) via pMDI or alone via DPI.[5] Patients were asked to return to the clinic for follow-up visits 3–8 at the end of months 1, 2, 4, 6, 9 and 12, and received a telephone call 4 weeks after the last clinic visit. bid = twice daily; R = randomization.\n\nBODY.PATIENTS AND METHODS.EFFICACY EVALUATIONS:\nThe co-primary efficacy variables, measured at all clinic visits, were pre-dose FEV1 and 1-hour post-dose FEV1. Additional pulmonary function variables included pre-dose and 1-hour post-dose FVC measured at all clinic visits, and morning and evening peak expiratory flow (PEF) recorded daily in patient diaries. In a subset of patients (n = 491 of 1964; 25%) who agreed to undergo spirometry testing, 12-hour serial spirometry was performed and pre-dose and 1-hour post-dose inspiratory capacity (IC) were collected at randomization and months 6 and 12. FEV1 was measured pre-dose and at 5, 15, 30, 60, 120, 180, 240, 360, 480, 600 and 720 minutes post-dose. Baseline-adjusted average 12-hour FEV1 was calculated as the area between the 12-hour post-dose FEV1-over-time curve and the baseline pre-dose FEV1, divided by observation time. Spirometry was performed according to American Thoracic Society guidelines.[6] Crapo-predicted normals for FEV1 were used.[7] Secondary efficacy endpoints included COPD exacerbations, dyspnoea (separate and composite scores) and health status, all assessed as previously described.[4] A COPD exacerbation was defined as worsening of COPD requiring an oral corticosteroid or hospitalization.[4] Dyspnoea was assessed daily before the evening dose of study medication using the Breathlessness Diary, a validated single-item component of the Breathlessness Cough and Sputum Scale (BCSS).[8] Health status was assessed at months 1, 2, 6 and 12 using the St George's Respiratory Questionnaire (SGRQ).[9,10] Sleep score, percentage of awakening-free nights (sleep score of 0) and study rescue medication use were assessed as previously described by Tashkin et al.[4]\n\nBODY.PATIENTS AND METHODS.SAFETY EVALUATIONS:\nSafety was assessed by adverse event (AE) reporting. Pneumonia events were reported by physicians based on the Medical Dictionary for Regulatory Activities (version 10.0) pneumonia-related preferred terms (pneumonia, bronchopneumonia, lobar pneumonia or pneumonia staphylococcal). Vital signs and 12-lead ECGs were evaluated as previously described by Tashkin et al.[4] Subsets of patients were assessed for 24-hour urinary cortisol (n = 179), 24-hour Holter monitoring (n = 520), bone mineral density (BMD) at the hip and spine regions (n = 326), and ophthalmological assessments (n = 461), including intraocular pressure and progression of lenticular opacities. In all patients, blood and urine samples were collected, and comprehensive physical examinations were carried out at the time of screening and at the end of month 12. Blood and urine samples were analysed by a central laboratory (Quest Diagnostics Clinical Laboratories, Van Nuys, CA, USA). Vital signs, including heart rate and blood pressure, were measured at all study visits. Samples to assess 24-hour urinary cortisol levels were collected in a subset of patients at or before randomization and within 1 week before the 6- and 12-month visits, and analysed by Quest Diagnostics. 24-Hour Holter monitoring was performed at screening and months 1 and 4, BMD assessments (two sets of dual energy x-ray absorptiometry scans in the hip and spine regions) were performed at screening and the end of month 12, and ophthalmology assessments (intraocular pressure and lenticular opacities) were performed at screening and the end of months 6 and 12.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSES:\nThe efficacy analysis set (i.e. intent-to-treat population) included all randomized patients who received at least one dose of randomized study medication and contributed sufficient data for at least one co-primary or secondary efficacy endpoint to be calculated during the randomized treatment period. The safety analysis population included all randomized patients who received at least one dose of randomized study medication and from whom any post-randomization data were available. For the subsets of patients who underwent serial spirometry, 24-hour urinary cortisol, BMD, 24-hour Holter monitoring and ophthalmological analyses, analysis sets were defined as those patients who received at least one dose of randomized study medication and had baseline and on-treatment values for the variable being assessed. Patients who discontinued prematurely completed final visit (month 12) assessments at the time of discontinuation, followed by the 4-week follow-up. A sample size of approximately 400 patients per treatment group was calculated to allow 90% power to detect a reduction in the number of COPD exacerbations of approximately 30%, adjusting for overdispersion of 2.3. This sample size ensured >95% power to detect a difference of 0.10L in FEV1, given an estimated standard deviation of 0.3 L. All tests were two-sided, with p ≤ 0.05 considered significant. The prespecified primary comparators were formoterol DPI for pre-dose FEV1 to demonstrate the contribution of budesonide and placebo for 1-hour post-dose FEV1. To address issues of multiplicity relating to multiple-dose comparisons and multiple variables of interest, a fixed-sequence testing procedure was adopted. The primary comparisons were prespecified as budesonide/formoterol pMDI 320/9 μg compared with (i) placebo for pre-dose FEV1 and 1-hour post-dose FEV1; and (ii) formoterol DPI 9 μg for pre-dose FEV1. If significant differences were obtained, comparisons continued with budesonide/formoterol pMDI 320/9 μg compared with placebo for (i) dyspnoea; (ii) SGRQ total score; and (iii) number of exacerbations. If significant differences were obtained for each of these key secondary variables, the lower dose of budesonide/formoterol pMDI was tested on the co-primary variables, as previously described, and, if significant differences were obtained, testing continued with number of exacerbations, dyspnoea and SGRQ total score compared with placebo. For all secondary efficacy variables, the primary comparison was budesonide/formoterol pMDI versus placebo. Primary and secondary variables were assessed as the change from baseline to the average over the randomized treatment period except for average 12-hour FEV1, mean FEV1 at 12 hours and SGRQ at end of treatment. Changes from baseline in the co-primary efficacy variables were analysed via analysis of co-variance (ANCOVA), adjusting for treatment, country and baseline value. The following three key secondary efficacy variables were identified: (i) dyspnoea; (ii) SGRQ total score; and (iii) exacerbations. Secondary variables were analysed similar to the co-primary efficacy variables; however, exacerbation rate (number/patient-treatment year) was analysed using a Poisson regression model, adjusted for country and differential randomization time, and time to first COPD exacerbation was described via Kaplan-Meier plot and analysed using the log-rank test. The number and percentage of patients experiencing clinically meaningful changes (based on a prespecified minimal important difference) in dyspnoea were analysed using the Cochran-Mantel-Haenszel test, adjusting for country. Geometric mean 24-hour urinary cortisol levels at end of treatment were compared between treatment groups using a multiplicative ANCOVA model. Mean changes from baseline to the average during the randomized treatment period in 12-lead ECG, and Holter variables and ophthalmology variables were analysed using a model similar to that used for the co-primary variables. BMD variables (natural logarithm of the analysis timepoint minus the natural logarithm of the respective baseline value for hip and spine) were analysed using an ANCOVA model adjusting for country, treatment and natural logarithm of the baseline value. Other safety data were summarized using descriptive statistics. No formal hypothesis testing of the safety data was performed.\n\nBODY.RESULTS.PATIENTS:\nOf 1964 randomized patients, 1355 completed the study (figure 2). Discontinuation was greater with placebo versus budesonide/formoterol and formoterol driven by withdrawal of consent. Time to discontinuation was significantly (p ≤ 0.004) prolonged in both budesonide/formoterol groups versus placebo. AE was the most common reason for study discontinuation, with a similar incidence across treatments (12.1–13.5%). Approximately 60% of patients had documented use of an ICS, either alone or in combination before entering the study. The percentage of patients who discontinued from the study in the formoterol and placebo groups was slightly higher in patients previously treated with ICS (34.9% and 38.0%, respectively) compared with those not previously receiving ICS before the study (26.8% and 33.9%, respectively). In contrast, patients in the budesonide/formoterol 320/9-μg group previously receiving ICS had a lower discontinuation rate compared with those not previously receiving ICS (23.1% vs 34.1%, respectively). In the budesonide/formoterol 160/9-μg group, the percentage of patients who discontinued the study was similar for those who were previously receiving an ICS (29.5%) and those who were not (28.2%).\nFig. 2Patient disposition. AE = adverse event; bid = twice daily; BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; med = medication; PL = placebo; pMDI = pressurized metered-dose inhaler. Most demographic and disease characteristics at baseline were similar across treatments (table I). However, in the serial spirometry subset (n = 491), mean percentage reversibility was greater in the budesonide/formoterol 320/9 μg (19.9%), budesonide/formoterol 160/9 μg (20.7%) and placebo (19.5%) groups versus formoterol (16.9%). COPD severity[1] was moderate in 17.8%, severe in 60.4% and very severe in 21.5% of patients. Common co-morbid conditions included hypertension (41.6%), lipid profile abnormalities (22.0%), cardiac disease (17.7%), diabetes mellitus (11.0%), osteoporosis (10.5%), cataracts (5.2%), atrial fibrillation/arrhythmia (4.3%) and congestive cardiac failure (2.9%).\nTable IPatient demographic and baseline clinical characteristics of randomized patients\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.CO-PRIMARY ASSESSMENTS:\nImprovements in pre-dose FEV1 were significantly greater for budesonide/formoterol 320/9 μg compared with formoterol (primary comparison; p = 0.008) and for both budesonide/formoterol dosages compared with placebo (p < 0.001) [figure 3a]. Although improvements in 1-hour post-dose FEV1 were significantly greater for both budesonide/formoterol dosages compared with placebo (primary comparison; p < 0.001), budesonide/formoterol 320/9 μg also resulted in significantly greater improvements compared with formoterol (p = 0.023) [figure 3b]. Improvements from baseline were apparent at the first assessment (pre-dose FEV1 at end of month 1; 1-hour post-dose FEV1 at day of randomization) and overall maintained over the 12-month treatment period for both budesonide/formoterol dosages (figure 3a and b).\nFig. 3Co-primary efficacy endpoints. Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose forced expiratory volume in 1 second (FEV1) and (b) 1-hour post-dose FEV1. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p ≤ 0.023 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.PULMONARY FUNCTION.SECONDARY ASSESSMENTS:\nMorning and evening PEF improved significantly for all active treatments compared with placebo (p ≤ 0.012) and for both budesonide/formoterol dosages compared with formoterol (p ≤ 0.017) [table II]. Results for pre-dose and 1-hour post-dose FVC are presented in the online supplement (see figures S1a and b in the supplementary material ['ArticlePlus'] at http://links.adisonline.com/DGZ/A5).\nTable IIMean (SD) changes from baseline in additional pulmonary function assessments In the serial spirometry subset, a ≥15% improvement in FEV1 was observed at 5 minutes after dose administration (first assessment) with all active treatments on the day of randomization (budesonide/formoterol 320/9 μg, 17.7%; budesonide/formoterol 160/9 μg, 20.3%; formoterol 9 μg, 16.5%) and at end of treatment (budesonide/formoterol 320/9 μg, 21.8%; budesonide/formoterol 160/9 μg, 22.4%; formoterol 9 μg, 15.0%) [figures 4a, b and c]. There was no evidence of a diminished effect at end of treatment over the 12-hour period in the budesonide/formoterol groups. Mean FEV1 at 12 hours and baseline-adjusted average 12-hour FEV1 were significantly improved with both budesonide/formoterol dosages compared with placebo on the day of randomization and at end of treatment (p ≤ 0.002) [table II]. Although both budesonide/formoterol dosages demonstrated significant improvements in mean FEV1 at 12 hours and in baseline-adjusted average 12-hour FEV1 compared with formoterol on the day of randomization (p ≤ 0.029), only budesonide/formoterol 320/9 μg demonstrated this effect at the end of treatment (p ≤ 0.004) [table II].\nFig. 4Mean percentage change from baseline in forced expiratory volume in 1 second (FEV1) over 12 hours at randomization and end of treatment (EOT) for (a) budesonide (BUD)/formoterol (FM) 320/9 μg twice daily (bid) vs placebo, (b) BUD/FM 160/9 μg bid vs placebo and (c) FM 9 μg bid vs placebo. DOR = day of randomization; DPI = dry powder inhaler; pMDI = pressurized metered-dose inhaler. No significant differences in pre-dose IC were observed among the treatment groups (figure 5a). Improvements from baseline to the average over the randomized treatment period in 1-hour post-dose IC were significantly greater with both budesonide/formoterol dosages compared with placebo (p < 0.001) and formoterol (p ≤ 0.018) [figure 5b]. Both dosages of budesonide/formoterol resulted in a 350 mL (≈25%) improvement from baseline to the average over the randomized treatment period in 1-hour post-dose IC, and formoterol resulted in a 210 mL (17%) improvement in 1-hour post-dose IC.\nFig. 5Least squares mean change from baseline by study visit over the randomized treatment period in (a) pre-dose inspiratory capacity (IC) and (b) 1-hour post-dose IC. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p < 0.001 vs placebo; † p = 0.01 vs FM; ‡ p < 0.05 vs FM; § p < 0.01 vs placebo.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.CHRONIC OBSTRUCTIVE PULMONARY DISEASE (COPD) EXACERBATIONS:\nTime to first COPD exacerbation was significantly prolonged with both budesonide/formoterol dosages compared with placebo (p ≤ 0.004) and with budesonide/formoterol 320/9 μg compared with formoterol (p = 0.026) [figure 6]. In addition, significant reductions in the overall number of exacerbations per patient-treatment year were observed with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37% and 41%, respectively; p < 0.001) and formoterol (25% and 29%, respectively; p ≤ 0.004) [see figure S2 in the supplementary material]. These reductions were driven by exacerbations treated with oral corticosteroids, the rate of which was reduced with budesonide/formoterol 320/9 μg and 160/9 μg versus placebo (37.5% and 42.9%, respectively) and formoterol (24.1% and 30.6%, respectively) [p ≤ 0.006]. In addition, the percentage of patients in the budesonide/formoterol 320/9 μg, budesonide/formoterol 160/9 μg, formoterol and placebo groups who experienced an exacerbation was greater in those receiving ICS therapy either alone or in combination before the study (33.7%, 38.2%, 39.9% and 40.1%, respectively) compared with those not previously receiving ICS (25.8%, 24.9%, 29.4% and 32.8%, respectively).\nFig. 6Kaplan-Meier probability curve for the time to first chronic obstructive pulmonary disease exacerbation during randomized treatment. BUD = budesonide; DPI = dry powder inhaler; FM = formoterol; pMDI = pressurized metered-dose inhaler. * p ≤ 0.004 vs placebo; † p = 0.026 vs FM.\n\nBODY.RESULTS.EFFICACY EVALUATIONS.HEALTH STATUS AND COPD SYMPTOMS:\nImprovements in SGRQ total score were significantly greater for both budesonide/formoterol dosages compared with placebo (p ≤ 0.006) and for budesonide/formoterol 160/9 μg compared with formoterol (p = 0.006; table III). The improvements from baseline in SGRQ total score in the active treatment groups were not clinically meaningful versus placebo (i.e. decrease of ≥4 points). Significantly greater improvements in COPD symptom variables were observed for both budesonide/formoterol dosages versus placebo for all variables (BCSS, dyspnoea score, cough score, sputum score, sleep score, percentage of awakening-free nights and total daily rescue medication use) [p ≤ 0.003]. Compared with formoterol, mean improvements were significantly greater with budesonide/formoterol 320/9 μg (p ≤ 0.038) for all COPD symptom variables except sputum score and percentage of awakening-free nights, and with budesonide/formoterol 160/9 μg (p ≤ 0.047) for all COPD symptom variables except BCSS, dyspnoea and sputum score (table IV).\nTable IIIMean changes (SD) in SGRQ total and domain scores from baselinea to end of treatmentbTable IVMean (SD) changes in chronic obstructive pulmonary disease (COPD) symptom variables from baselinea to the average over the randomized treatment period Improvements (i.e. reductions) in dyspnoea scores were significantly greater for all active treatments versus placebo (p ≤ 0.003) and for budesonide/formoterol 320/9 μg versus formoterol (p = 0.032; table IV). All active treatment arms demonstrated ≥0.2 points (minimal important difference) change from baseline, but only budesonide/formoterol 320/9 μg had an increase of ≥0.2 points over placebo. A significantly (p < 0.001) greater percentage of patients in both budesonide/formoterol groups and in the formoterol group experienced clinically meaningful improvements in dyspnoea versus placebo (see figure S3 in the supplementary material).\n\nBODY.RESULTS.SAFETY EVALUATIONS:\nMean treatment exposure was lowest for placebo (270 days) compared with budesonide/formoterol 320/9 μg (305 days), budesonide/formoterol 160/9 μg (299 days) and formoterol (289 days). The most commonly reported AE (irrespective of causality) was COPD, which had a lower incidence with budesonide/formoterol 320/9 μg versus placebo and a slightly higher incidence with budesonide/formoterol 160/9 μg versus placebo (table V). AEs considered by the investigator to be related to study medication were generally similar among treatment groups with the most commonly reported being oral candidiasis, COPD and dysphonia (see table SI in the supplementary material).\nTable VOverall adverse events (AEs) [irrespective of relationship to study medication] reported by ≥3% of patients The total incidence of pneumonia-related AEs (pneumonia, bronchopneumonia, lobar pneumonia and pneumonia staphylococcal) was similar for budesonide/formoterol 320/9 μg and 160/9 μg (4.0% and 3.4%, respectively) compared with formoterol (3.4%) and placebo (5.0%) [see table SII in the supplementary material]. For potential lung infections other than pneumonia, the incidence was slightly higher in the active treatment groups versus placebo, which was driven largely by bronchitis (see table SII in the supplementary material). AEs typically or potentially associated with local and systemic effects of inhaled corticosteroids (local effects: aphonia, dysphonia, oral candidiasis and candidiasis; systemic effects: weight gain, adrenal suppression, ocular effects, skin effects, psychiatric disorder, diabetes control, thirst, taste effects and bone effects) were more frequent with budesonide/formoterol 320/9 μg (10.3% and 4.0%, respectively) and budesonide/formoterol 160/9 μg (5.7% and 4.5%, respectively) than formoterol (0.6% and 2.6%, respectively) and placebo (2.5% and 2.7%, respectively). The overall incidence of LABA class effects (i.e. tremor, palpitation, tachycardia, potassium changes, glucose changes, headache, agitation, anxiety, sleep effects and muscle cramp) was low, but higher among active treatment groups (budesonide/formoterol 320/9 μg [9.5%], budesonide/formoterol 160/9 μg [8.9%] and formoterol [6.5%]) versus placebo (4.8%). The incidence of cardiac-related AEs was higher for all active treatments (10.5–11.3%) versus placebo (6.9%). The most common cardiac-related AEs were hypertension and angina pectoris (budesonide/formoterol 320/9 μg [2.4% and 1.2%, respectively], budesonide/formoterol 160/9 μg [1.6% and 0.8%, respectively], formoterol [2.6% and 1.8%, respectively] and placebo [2.1% and 1.0%, respectively]). Although the number of atrial fibrillation AEs was low, all cases occurred within the active treatment groups. Discontinuations due to AEs (DAEs) occurred in 238 patients, with a similar incidence observed across treatment groups (range 11.3–12.5%) [see table SIII in the supplementary material]. The most common DAE was COPD, which was highest in the formoterol group (7.3%) and lowest in the budesonide/formoterol 320/9 μg group (4.0%); the incidence was similar in the budesonide/formoterol 160/9 μg (6.1%) and placebo (6.0%) groups (see table SIII in the supplementary material). The overall incidence of non-fatal serious adverse events (SAEs) was highest with formoterol (17.8%) compared with the other treatment groups and higher with budesonide/formoterol 320/9 μg (15.6%) and budesonide/formoterol 160/9 μg (13.6%) versus placebo (12.1%) [see table SIV in the supplementary material]. The most common non-fatal SAEs (occurring in five or more patients [all treatment groups combined]) were COPD (6.8%), pneumonia (1.5%), atrial fibrillation (0.5%), angina pectoris (0.3%), bronchitis (0.3%) and coronary artery disease (0.3%). These non-fatal SAEs occurred at a similar incidence in all treatment groups, except for COPD, which was slightly more common in the active treatment groups (budesonide/formoterol 320/9 μg [7.1%], budesonide/formoterol 160/9 μg [6.7%] and formoterol [7.9%]) versus placebo (5.6%). Fifteen patients died during the randomized treatment period with no imbalance across treatments: three in the budesonide/formoterol 320/9 μg group; six in the budesonide/formoterol 160/9 μg group; two in the formoterol group; and four in the placebo group. Fifteen patients died after the randomized treatment period (≥2 days after stopping study treatment) with no imbalance across treatments: five in the budesonide/formoterol 320/9 μg group; two in the budesonide/formoterol 160/9 μg group; four in the formoterol group; and four in the placebo group. None of the deaths were considered drug related by the investigator. Clinically significant changes in vital signs, 24-hour urinary cortisol, and 12-lead ECGs, QT interval and Holter assessments were rare. The geometric mean values of 24-hour urinary cortisol at 6 months and end of treatment were lower in both budesonide/formoterol dosage groups compared with formoterol and placebo (see table SV in the supplementary material). Significant differences in 24-hour urinary cortisol were observed between the budesonide/formoterol 320/9 μg and placebo groups (p = 0.035) at month 6 and between the budesonide/formoterol 320/9 μg and formoterol groups (p = 0.044) at end of treatment. Corrected QT (QTc) intervals ≥450 msec were experienced by similar percentages of patients across all treatment groups, whereas few patients experienced QTc intervals ≥500 msec or a QTc change ≥60 msec (see table SVI in the supplementary material). Data from ECG and Holter recordings showed a similar incidence of new onset atrial fibrillation in the active and placebo groups. BMD was stable over the 1-year study period in all treatment groups, with small but statistically significant differences in changes from baseline observed for budesonide/formoterol 320/9 μg compared with all other treatments for total lumbar spine BMD (p ≤ 0.037) and for budesonide/formoterol 320/9 μg versus formoterol for total hip BMD (p = 0.012) [see table SVII in the supplementary material]. The differences between the treatment groups in changes from baseline in BMD were of unclear clinical relevance, as the geometric least squares mean ratios for these treatment group comparisons were close to 1 (range 0.98–0.99). Minor increases in lenticular opacities and intraocular pressure were noted across all treatment groups in the ophthalmological analysis subset; the magnitude of these changes was similar among the treatment groups (see table SVIII in the supplementary material). Small but significant differences were observed for the change from baseline in posterior subcapsular score between the budesonide/formoterol groups (p = 0.022). Clinically significant changes in ophthalmological assessment were infrequent.\n\nBODY.DISCUSSION:\nIn this study, both budesonide/formoterol dosage strengths resulted in significant improvements from baseline over the randomized treatment period in pulmonary function, health status and COPD symptoms, as measured by dyspnoea, cough and sputum production, and a clinically significant reduction in COPD exacerbation rate compared with placebo. In addition, both budesonide/formoterol pMDI dosages were well tolerated relative to formoterol alone and placebo. The results of this 12-month study confirm those from the earlier related 6-month study by Tashkin et al.[4] and are consistent with those from studies of budesonide/formoterol DPI.[2,3] Taken together, the results demonstrate that this ICS/LABA combination provides benefits beyond formoterol alone in the treatment of COPD. The contribution of budesonide to improvements from baseline in pulmonary function and COPD symptoms was demonstrated by the greater efficacy of budesonide/formoterol 320/9 μg compared with formoterol alone for the co-primary variables of pre-dose FEV1 and 1-hour post-dose FEV1, and for dyspnoea and total BCSS scores, supporting use of the higher-dose combination for COPD symptoms. Both budesonide/formoterol dosage strengths demonstrated greater improvements from baseline compared with formoterol alone in morning and evening PEF, 12-hour FEV1, symptom scores and rescue medication use. In addition, the 25–29% reduction in exacerbation rate observed with both budesonide/formoterol dosage strengths beyond the substantial reduction achieved with formoterol alone further demonstrates the important contribution of budesonide to the combination product. The magnitude of the reduction in exacerbation rates reported in this study is similar to that reported previously for fixed-dose regimens of budesonide/formoterol 320/9 μg twice daily[2–4] and fluticasone propionate/salmeterol[11–13] relative to LABA alone. A key difference between this 12-month study and the 6-month study of similar design reported by Tashkin et al.[4] is that this study was powered to show a difference in exacerbations, while the 6-month study was not. This study demonstrated a significant reduction in exacerbation rates in patients treated with budesonide/formoterol 320/9 μg and 160/9 μg compared with those receiving formoterol or placebo. The fact that a greater percentage of patients in the formoterol and placebo groups who previously received ICS therapy, either alone or in combination, experienced exacerbations compared with those who did not previously receive ICS therapy may result in a skewing of the data; however, a similar response was observed in combination budesonide/formoterol patients with a greater percentage of patients who previously received ICS experiencing exacerbations compared with patients who were not previously treated with ICS therapy. Similarly, a greater percentage of patients who previously received ICS therapy discontinued in the formoterol and placebo groups than those who did not previously receive ICS therapy; however, this trend was reversed in the combination budesonide/formoterol groups. The long-term nature of this study allowed for a more thorough assessment of tolerability compared with the 6-month study.[4] No differences in pneumonia incidence were observed among treatment groups in this study or in the 6-month study, despite a shorter exposure time in the placebo group.[4] These results contrast with previous COPD studies that showed an increased incidence of pneumonia with fluticasone propionate/salmeterol treatment.[11–14] However, in this study and the 6-month study,[4] the incidence of potential lung infections other than pneumonia was slightly higher in all active treatments compared with placebo; these differences were largely driven by an increased incidence of bronchitis. The incidence of SAEs, including COPD SAEs, was slightly higher in both budesonide/formoterol groups compared with placebo. This finding may be attributed to the earlier discontinuation in the placebo group, which resulted in a shorter study drug exposure (35 and 29 fewer days vs budesonide/formoterol 320/9 μg and 160/9 μg, respectively). Although the overall incidence of atrial fibrillation, a known LABA class effect, was small (1.1%), an imbalance was noted between the formoterol-containing arms and placebo. However, no differences in new-onset atrial fibrillation were apparent among groups based on 24-hour Holter monitoring or ECG data collected at repeated visits during the randomized treatment period. Overall, the safety profile of budesonide/formoterol pMDI in this 12-month study was similar to that reported in the 6-month study by Tashkin et al.,[4] suggesting no increase in safety concerns with a longer duration of treatment.\n\nBODY.CONCLUSIONS:\nBoth dosage strengths of budesonide/formoterol pMDI (320/9 μg and 160/9 μg) were effective and well tolerated over 1 year of treatment in this population of patients with moderate to very severe COPD. In addition, budesonide/formoterol pMDI 320/9 μg demonstrated greater efficacy compared with formoterol for pre-dose FEV1, suggesting that the higher dosage strength containing twice the daily dose of budesonide is appropriate in this patient population.\n\nBODY.ELECTRONIC SUPPLEMENTARY MATERIAL:\nSupplementary material, approximately 247 KB.\n\n**Question:** Compared to Formoterol DPI 9 μg what was the result of Budesonide/formoterol pMDI 160/9 μg on Improvements in St. George's Respiratory Questionnaire overall score?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
466
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Comparison of intravenous immunoglobulin and plasma exchange in treatment of mechanically ventilated children with Guillain Barré syndrome: a randomized study\n\n ABSTRACT.INTRODUCTION:\nRespiratory failure is a life threatening complication of Guillain Barré syndrome (GBS). There is no consensus on the specific treatment for this subset of children with GBS.\n\nABSTRACT.METHODS:\nThis was a prospective randomized study to compare the outcome of intravenous immunoglobulin (IVIG) and plasma exchange (PE) treatment in children with GBS requiring mechanical ventilation. Forty-one children with GBS requiring endotracheal mechanical ventilation (MV) within 14 days from disease onset were included. The ages of the children ranged from 49 to 143 months. Randomly, 20 children received a five-day course of IVIG (0.4 g/kg/day) and 21 children received a five-day course of one volume PE daily. Lumbar puncture (LP) was performed in 36 patients (18 in each group).\n\nABSTRACT.RESULTS:\nBoth groups had comparable age (p = 0.764), weight (p = 0.764), duration of illness prior to MV (p = 0.854), preceding diarrhea (p = 0.751), cranial nerve involvement (p = 0.756), muscle power using Medical Research Council (MRC) sum score (p = 0.266) and cerebrospinal fluid (CSF) protein (p = 0.606). Children in the PE group had a shorter period of MV (median 11 days, IQR 11.0 to 13.0) compared to IVIG group (median 13 days, IQR 11.3 to 14.5) with p = 0.037. Those in the PE group had a tendency for a shorter Pediatric Intensive Care Unit (PICU) stay (p = 0.094). A total of 20/21 (95.2%) and 18/20 (90%) children in the PE and IVIG groups respectively could walk unaided within four weeks after PICU discharge (p = 0.606). There was a negative correlation between CSF protein and duration of mechanical ventilation in the PE group (p = 0.037), but not in the IVIG group (p = 0.132).\n\nABSTRACT.CONCLUSIONS:\nIn children with GBS requiring MV, PE is superior to IVIG regarding the duration of MV but not PICU stay or the short term neurological outcome. The negative correlation between CSF protein values and duration of MV in PE group requires further evaluation of its clinical usefulness.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicaltrials.gov Identifier NCT01306578\n\nBODY.INTRODUCTION:\nGuillain-Barré syndrome (GBS) is, currently, the most common cause of acute flaccid paralysis following the worldwide decline in incidence of poliomyelitis. Incidence varies according to age, geographic areas and diagnostic criteria used for inclusion. Annual incidence in western countries varies from 1.1 to 1.8/100,000 population per year [1-5] with a considerably lower annual incidence of 0.66/100,000 population per year in each of Taiwan [6] and China [7]. GBS usually follows infection by a number of bacterial and viral agents with Campylobacter jejuni representing the most common preceding infection [8-11]. The syndrome is also reported to rarely temporally follow vaccination with measles vaccine [12,13], tetanus toxoid [14], rabies vaccine [15], oral polio vaccine [16], polysaccharide meningococcal vaccine [17], measles-rubella vaccine [18], flu vaccine [19] and hepatitis B vaccine [19]. Since the publishing of the first report of the condition by Guillain, Barré, and Strohl in 1916, GBS has remained a clinically-diagnosed disorder. The condition is a polyneuropathy involving mainly motor but sometimes also sensory and autonomic nerves. It starts with rapidly progressive bilateral and relatively symmetric weakness in the lower limbs with diminished or absent deep tendon reflexes. Paralysis follows an ascending pattern involving trunk, upper limb and, finally, bulbar muscles. There can be numbness, parathesia and muscle pain and tenderness. Labile blood pressure with postural hypotension and labile heart rate with episodes of bradycardia up to asystole rarely occur denoting autonomic neuropathy. van Doorn et al. categorize diagnostic features of the condition into features required for diagnosis, including progressive weakness in both arms and legs, and areflexia or hyporeflexia, and features that strongly support the diagnosis, including progression of symptoms to a nadir over days to four weeks, relative symmetry of symptoms, mild sensory symptoms or signs, cranial nerve involvement, autonomic dysfunction, pain, a high concentration of protein in CSF without increase in cells and typical electro-diagnostic features [20]. A common, yet not an early, feature of GBS is increased cerebrospinal fluid (CSF) protein (> 45 mg/dL) without CSF pleocytosis (< 10 cells/mm3), often referred to as cytoalbuminous dissociation [21]. Electromyography may be used to confirm the diagnosis in the small subset of patients where the diagnosis is not straightforward. It is also useful to sub-classify patients into motor axonal neuropathy and acute inflammatory demyelinating polyneuropathy [22]. A recent study conducted in Egypt on children with GBS found that acute inflammatory demyelinating polyneuropathy, was the most common type (76%) while, acute motor axonal neuropathy, acute motor sensory axonal neuropathy and unclassified forms represented 8% each [23]. Respiratory failure is one of the most serious complications of GBS. It affects 15% of children with the condition [24]. The ability to predict the occurrence of respiratory failure and need for mechanical ventilation (MV) among patients with GBS has long been a target for neurologists and intensivists alike. Some bedside indicators of the likelihood of requiring MV are rapid disease progression, bulbar dysfunction, bilateral facial weakness, or dysautonomia, inability to stand, inability to lift the elbows or head, elevated liver enzymes and abnormal pulmonary function test [25-27]. Electrophysiological evidence of demyelination was also suggested to predict the need for endotracheal MV [28]. Treatment of GBS is a multidisciplinary effort. The general care of the child with muscle weakness includes regular monitoring of pulmonary and cardiovascular function for possible involvement of respiratory muscles and autonomic neuropathy respectively, prevention of infection and deep vein thrombosis, pain management, early physiotherapy, early rehabilitation once muscle power improvement starts and psychosocial support for the affected children and their families [20]. Specific treatment of severely affected children comprises intravenous immunoglobulin (IVIG) or plasma exchange (PE). Performed on more than 200 patients each, two large trials in the mid-1980s confirmed the beneficial role of PE in treatment of patients with GBS compared to the conventional treatment of the time [29,30]. The routine use of IVIG as the first line of treatment in GBS followed the publication of a randomized controlled trial (RCT) in 1992 showing a similar, if not a superior, effect of IVIG compared to PE [31]. A recent systematic review of heterogeneous study populations showed there was no evidence for a better outcome with either of the two modalities of treatment. There is also no evidence of a beneficial effect of adding corticosteroids to the treatment [32]. The objective of this study is to compare PE and IVIG as a first line treatment for children with severe GBS requiring MV regarding the duration of MV, PICU stay and short term neurological outcome.\n\nBODY.MATERIALS AND METHODS:\nChildren with GBS admitted to the Pediatric Intensive Care Unit (PICU) at Mansoura University Children Hospital, Mansoura, Egypt, with the need for MV were prospectively enrolled in the study. Cases were diagnosed to have GBS according to clinical criteria by van Doorn et al. [20]. Patients were eligible for inclusion if they required MV based on the indications listed below, and if the duration of muscle weakness did not exceed 14 days on enrollment. Children were not eligible for inclusion if they had muscle weakness for longer than 14 days before requiring MV and if IVIG or PE was started prior to enrollment. All patients were ventilated using endotracheal MV. Children were intubated if they were unable to protect their airway, had increased work of breathing (WOB), had PaO2 less than 70 mmHg in room air requiring increasing FiO2, or showed CO2 retention. When children were able to trigger spontaneous breathing, they were changed to a pressure-support spontaneous ventilation mode with continuous positive airway pressure of 5 cm H2O. Pressure support was gradually weaned to 10 cm H2O. If secretions were manageable and airway reflexes intact, a daily spontaneous breathing trial (SBT) was performed using a T-piece for two hours. Patients were extubated if SBT was successful. An SBT was deemed successful if there was no diaphoresis, increased WOB or apnea, tachycardia (defined by increase in the heart rate of 40 bpm or more) and if SpO2, pH, PaO2 and PaCO2 remained close to pre-SBT values. The decisions to initiate, wean and terminate MV were made independently by the attending consultant in accordance with and in strict adherence to the unit guidelines as above. Over a period of three years, from January 2007 to December 2009, 44 children were admitted with GBS requiring MV; 41 children fulfilled inclusion criteria and were randomized to receive either IVIG (20 children) or PE (21 children) for initial treatment. Randomization was done by computer-generated random tables. IVIG was administered in a dose of 0.4 g/kg/day for five days. Patients in the PE group received a daily one-volume PE for five consecutive days. The sample size yields a study power of 86.9%. On admission, the muscle power was recorded using the Medical Research Council (MRC) sum score [33]. Lumbar puncture (LP) was performed in the second week of illness in 36 out of the 41 children (18 in each group). LP was performed at the discretion of the attending consultant. The primary outcome measure was the duration of mechanical ventilation and secondary outcome measures were length of PICU stay and ability to walk unaided within four weeks of PICU discharge. Institutional research ethics committee approval was granted and an informed consent was obtained from legal guardians of children included in the study. Statistical analysis was performed using Statistical Package for the Social Sciences, Version 17 (SPSS, Inc., Chicago, IL, USA). p-value was considered significant if less than .05.\n\nBODY.RESULTS:\nChildren in the two treatment groups were comparable as regards base line characteristics, such as age, weight, duration of illness prior to requiring mechanical ventilation, presence or absence of preceding diarrhea, cranial nerve affection, severity of muscle weakness on PICU admission and CSF protein when available (Table 1). Table 1 Comparison of IVIG and PE groups regarding base line variables IVIG group ( n = 20) PE group ( n = 21) p- value Age (months) 106.0 ± 22.8 (74.3 to 113.5) 96.0 ± 32.8 (65.5 to 135.0) 0.764 1 Weight (kg) 32.5 ± 7.0 (23.0 to 34.8) 29.0 ± 10.1 (20.0 to 41.5) 0.764 1 DOI (days) 9.0 ± 2.7 (7.0 to 12.0) 9.0 ± 2.8 (6.5 to 11.5) 0.854 1 Diarrhea (%) Yes 13 (65%) 12 (57.1%) 0.751 2 No 7 (35%) 9 (42.9%) Cranial nerve affection (%) Yes 8 (40%) 10 (47.6%) 0.756 2 No 12 (60%) 11 (52.4%) MRC sum score 12.0 ± 4.8 (8.5 to 15.5) 12.0 ± 5.9 (4.0 to 12.0) 0.266 1 CSF protein (mg/dL) 152.1 ± 55.7 (88.3 to 173.6) 148.4 ± 43.0 (117.5 to 166.5) 0.606 1 IVIG, intravenous immunoglobulin; PE, plasma exchange; DOI, Duration of illness prior to requiring mechanical ventilation; MRC, Medical Research Council score. Data presented as median ± SD (interquartile range) 1 Mann Whitney test 2 Chi square test. There was a statistically insignificant better outcome in the PE group compared to the IVIG group. Favorable outcome was defined as the child's ability to walk independently for 10 meters (Grade 2 on GBS disability score) [34] within four weeks from PICU discharge. The post discharge management and physiotherapy were standardized for children in the two groups. In the IVIG group, favorable outcome was observed in 90% (18/20) of children compared to 95.2% (20/21) in the PE group (Table 2). Table 2 Comparison of PICU stay and duration of mechanical ventilation in the IVIG and PE groups PICU stay (days) Mechanical ventilation (Days) Favorable outcome (%) Yes No IVIG group 16.5 ± 2.1 (15.3 to 18.8) 13.0 ± 2.1 (11.3 to 14.5) 18 (90%) 2 (10%) PE group 15.0 ± 2.6 (13.0 to 17.0) 11.0 ± 1.5 (11.0 to 13.0) 20 (95.2%) 1 (4.8%) p- value .094 1 0.037 1 0.606 2 IVIG, intravenous immunoglobulin; PE, plasma exchange. Data presented as median ± SD (interquartile range) 1 Mann Whitney test 2 Chi square test. Children receiving PE had a significantly shorter period of mechanical ventilation compared to those receiving IVIG. The hospital stay was shorter in the PE group without statistical significance (Table 2). For all patients, there was a statistically significant negative correlation between CSF protein and duration of mechanical ventilation (p = .024). Examining the treatment groups separately, the significant negative correlation remained for the PE group (p-value = 0.037) and not for the IVIG group (p-value 0.132) (Table 3). Table 3 Correlation between CSF protein and duration of mechanical ventilation All patients IVIG group PE group CSF protein (mg/dL) 149.3 ± 49.0 (110.5 to 169.0) 152.1 ± 55.7 (88.3 to 173.6) 148.4 ± 43.0 (117.5 to 166.5) Mechanical ventilation (days) 12.0 ± 1.9 (11.0 to 13.0) 13.0 ± 2.1 (11.3 to 14.5) 11.0 ± 1.5 (11.0 to 13.0) p -value 0.024 1 0.132 1 0.037 1 CSF, cerebrospinal fluid; IVIG, intravenous immunoglobulin; PE, plasma exchange. Data presented as median ± SD (interquartile range) 1 Pearson test. There was no significant side effect attributable to any of the treatment modalities in any of the studied patients.\n\nBODY.DISCUSSION:\nRespiratory failure among children with GBS is a serious complication requiring intensive supportive treatment in addition to the specific treatment. The two treatment groups had no significant complications attributable to treatment intervention apart from minor hypotension episodes responding to fluid boluses in the PE group. This confirms the safety of both IVIG and PE for treating children with GBS. The results of this study suggest that PE is more useful than IVIG as a specific treatment for the subset of children with severe rapidly progressive GBS requiring MV. PE is believed to act by removal of circulating autoantibodies [35,36], while IVIG, among other mechanisms, is thought to work through blocking antibody production both in vivo [37] and in vitro [38,39]. Removal of autoantibodies, by PE, creates a concentration gradient between the lowered blood level and the extravascular space forcing antibody movement from the extra to the intra vascular space to be removed during the subsequent session [40]. Specific anti-ganglioside antibody levels were recently found to be associated with disease severity [41]. Children with severe, rapidly progressive GBS, as those included in this study, most likely have an intense autoantibody production with a high percentage of these antibodies already bound to nerves on development of respiratory failure. This might provide an explanation of why this subset of patients preferentially benefit from removal of already bound antibodies, PE, in comparison to blocking antibody production, IVIG. The clinical usefulness of this relatively small difference in the duration of mechanical ventilation between PE and IVIG groups waits to be confirmed in a larger, probably multi-center, study. CSF protein was elevated in all patients (Table 3) with no statistically significant difference between the two treatment groups (Table 1). On post hoc analysis, there was, however, a negative correlation between CSF protein level and duration of MV in PE but not IVIG group. This finding supports the above explanation of a shorter duration of MV in the PE group especially in view of a RCT showing CSF filtration to be at least as effective as PE for treatment of GBS [42] and the suggestion of a blood-CSF barrier dysfunction in adults and children with GBS [43]. PE group had a tendency for a shorter PICU stay, p = 0.094 with a comparable ability of children to walk unaided within four weeks from PICU discharge (Table 2). So, despite a shorter duration of MV, there was no difference between PE and IVIG groups regarding PICU stay or short term neurological outcome. To our knowledge, this is the first randomized controlled study comparing PE and IVIG for treatment of children with rapidly progressive GBS requiring MV. An RCT conducted in adults with GBS showed no difference in the duration of MV in PE, IVIG and combined treatment groups [44]. This difference can be accounted for by differences in the age and PE protocol used. It would have been more informative to perform an electrophysiological study for the study children to confirm homogeneity of the study population. It would also add to the understanding of these results to study kinetics of autoantibodies in future research with a similar design.\n\nBODY.CONCLUSIONS:\nRapidly progressive GBS necessitating MV in children responds favorably to both IVIG and PE, with PE being superior in regard to the duration of MV but not PICU stay or short term neurological outcome. The finding of a negative correlation between CSF protein values and duration of MV in the PE group might serve as a basis for future research aiming at a better understanding of autoantibody kinetics during treatment of GBS.\n\nBODY.KEY MESSAGES:\n• Children with GBS requiring MV respond favorably to both IVIG and PE. • Using a weaning and extubation protocol, children receiving PE had a shorter duration of MV.\n\nBODY.ABBREVIATIONS:\nCSF: cerebrospinal fluid; DOI: duration of Illness; GBS: Guillain-Barré syndrome; IVIG: intravenous immunoglobulin; LP: lumbar puncture; MRC: Medical Research Council; MV: mechanical ventilation; PE: plasma exchange; PICU: pediatric intensive care unit; SBT: spontaneous breathing trial; WOB: work of breathing.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nMAE formulated the research idea, designed the plan, performed statistical analysis and proofread the draft. AME co-designed the plan and supervised the plasma exchange making sure of uniformity of the procedure in all studied subjects and proofread the draft. AMA followed up patients on PICU, made sure the plan was followed, and helped MAE in performing statistical analysis. ME followed up patients on PICU, drafted the manuscript, and designed statistical methodology. AAA co-formulated the research idea, co-designed the plan, followed up patients on PICU, and generated and was responsible for the random assignment of the groups. HME followed up patients on PICU, co-drafted the manuscript with ME and made sure PICU management of patients complied with the unit guidelines. All authors read and approved the final manuscript.\n\nBODY.AUTHORS' INFORMATION:\nHME is one of the founding members and the current president of the ESPIC (Egyptian Society of Pediatric Intensive Care). MAE is a member of the Board of Directors of WFPICCS (World Federation of Pediatric Intensive Care Societies) and the ambassador of WFPICCS in Egypt. An abstract of this article has been presented by MAE as an oral presentation at the 6th World Congress of Pediatric Intensive Care, Sydney, 2011.\n\n**Question:** Compared to intravenous immunoglobulin (IVIG) what was the result of plasma exchange (PE) on could walk unaided within four weeks after PICU discharge?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
392
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Incisional hernia after upper abdominal surgery: a randomised controlled trial of midline versus transverse incision\n\n ABSTRACT.OBJECTIVES:\nTo determine whether a transverse incision is an alternative to a midline incision in terms of incisional hernia incidence, surgical site infection, postoperative pain, hospital stay and cosmetics in cholecystectomy.\n\nABSTRACT.SUMMARY BACKGROUND DATA:\nIncisional hernias after midline incision are commonly underestimated but probably complicate between 2 and 20% of all abdominal wall closures. The midline incision is the preferred incision for surgery of the upper abdomen despite evidence that alternatives, such as the lateral paramedian and transverse incision, exist and might reduce the rate of incisional hernia. A RCT was preformed in the pre-laparoscopic cholecystectomy era the data of which were never published.\n\nABSTRACT.METHODS:\nOne hundred and fifty female patients were randomly allocated to cholecystectomy through midline or transverse incision. Early complications, the duration to discharge and the in-hospital use of analgesics was noted. Patients returned to the surgical outpatient clinic for evaluation of the cosmetic results of the scar and to evaluate possible complications such as fistula, wound dehiscence and incisional hernia after a minimum of 12 months follow-up.\n\nABSTRACT.RESULTS:\nTwo percent (1/60) of patients that had undergone the procedure through a transverse incision presented with an incisional hernia as opposed to 14% (9/63) of patients from the midline incision group (P = 0.017). Transverse incisions were found to be significantly shorter than midline incisions and associated with more pleasing appearance. More patients having undergone a midline incision, reported pain on day one, two and three postoperatively than patients from the transverse group. The use of analgesics did not differ between the two groups.\n\nABSTRACT.CONCLUSIONS:\nIn light of our results a transverse incision should, if possible, be considered as the preferred incision in acute and elective surgery of the upper abdomen when laparoscopic surgery is not an option.\n\nBODY.INTRODUCTION:\nThe rate of incisional hernia after midline incision is commonly underestimated but probably lies between 2 and 20% [1–5]. Thus, incisional hernia is a major postoperative problem. The treatment of incisional hernia is complicated by high rates of recurrences. Recently, in a randomised controlled trial published by Burger et al. [6], midline incisional hernia repair has been shown to be associated with a 10-year cumulative recurrence rate of 63 and 32% for suture and mesh repair, respectively. The midline incision is the preferred incision for surgery of the upper abdomen, despite evidence that alternatives, such as the lateral paramedian and transverse incision, exist and might reduce the rate of incisional hernia [7]. Various approaches to opening the abdomen have been advocated over time. The choice for a certain incision is dependent on the exposure necessary for the desired procedure to succeed. A midline incision, be it supraumbilical, infraumbilical or both, is an approach especially suited for emergency and exploratory surgery because of the quick and generous exposure that can be achieved within a few minutes [8, 9]. The avascular nature of the linea alba minimises blood loss during this procedure. A supraumbilical transverse incision may be utilised in case exposure of the upper abdomen is desired. During this incision, the damage inflicted to the segmental arteries and nerves is previously described as being minimal [10]. Previously, only one randomised controlled trial, comparing transverse and true midline incisions, has been published specifically addressing incisional hernia incidence [11]. To determine whether the use of a transverse incision is an alternative to a midline incision for open cholecystectomy in terms of incisional hernia incidence, surgical site infection, postoperative pain and hospital stay, this randomised controlled trial was performed. This trial was conducted in an era when laparoscopic cholecystectomy was not yet available. The possibility of low incisional hernia rates after transverse incisions and the fact that little is known about potential advantages incited us to publish the relevant results of this randomised controlled trial which has been performed in the past and has only been reported in a Dutch thesis by one of the authors (H.L.). The primary endpoint of this study was the incisional hernia incidence after 12 months of follow-up. Secondary endpoints included pain and cosmetic appearance.\n\nBODY.METHODS.PROTOCOL:\nSome 150 consecutive female patients were randomly assigned to a midline or transverse incision as an approach for elective cholecystectomy or combined cholecystectomy and cholangiography (with or without consecutive choledochotomy) (75 and 75 patients, respectively). Emergency procedures were excluded from participation. The sample size is based on an incisional hernia rate reduction from 20 to 6% at a power of 80% and an error rate of 5%. Obtaining informed consent was conducted in accordance with the ethical standards of the Helsinki Declaration of 1975. The investigation reported was performed with informed consent from all of the patients and followed the guidelines for experimental investigation with human subjects and was approved by the medical ethics committee. An independent statistician prepared closed, tamper-proof envelopes containing the random allocation (Fig. 1). Patients were randomised for one of the procedures in theatre through the opening of the envelopes.Fig. 1Flow chart of patient inclusion and follow-up Patient-related factors that were recorded were age, body mass and length and date of operation. Operation-related factors that were recorded were the exact nature of the operation, length of the incision, the thickness of the subcutaneous fat, surgeon performing the procedure, as well as the duration of the operation (skin-to-skin time). In the immediate postoperative period, the use, dose and type of analgesics was recorded and a pain score was administered. The use of analgesics (morphine 7.5 mg intra-muscular injection, 4 h minimum interval between consecutive injections) was monitored for 48 h after surgery; the pain score was administered for the first 6 days after surgery. In patients assigned to surgery through a midline incision, the skin was incised from just below the xyphoid process to just above the umbilicus. The abdominal wall was opened in the midline by incising the linea alba. A Collin type (two-bladed) self-retaining retractor was used to maintain exposure. The abdominal wall was closed in one layer using single polygalactin 910 sutures (Vicryl; Ethicon, Amersfoort, The Netherlands). The skin was consequently closed using running monofilament nylon sutures (Ethilon; Ethicon, Amersfoort, The Netherlands). Patients randomised for a transverse incision received a right-sided unilateral transverse incision between 3 and 4 cm below the costal margin. The rectus muscle was incised. The fibres of the external and internal obliques and the transverse muscles were separated in the direction of their course. Exposure was achieved through the use of a manually held single-bladed retractor. Closure of the abdominal wall was achieved by closure of the peritoneum and the posterior rectus fascia using a continuous, polygalactin 910 suture (Vicryl; Ethicon, Amersfoort, The Netherlands). The anterior rectus sheath and the fascia of the internal and external transverses were closed using simple interrupted polygalactin 910 sutures (Vicryl; Ethicon, Amersfoort, The Netherlands). Towards the end of both procedures, a Redon low-vacuum drain catheter was placed, which was guided outside the abdominal cavity approximately 5 cm from the incision. The skin was consequently closed using continuous monofilament nylon suture (Ethilon; Ethicon, Amersfoort, The Netherlands). All patients received a dose of 5,000 IU of sodium–heparin on the morning of the procedure as thrombosis prophylaxis.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nThe Pearson χ2 test was used for comparing percentages. In case of small expected numbers, a Fisher's exact test was performed. Continuous variables were analysed using the Mann–Whitney test. A P-value of 0.05 or less (two-sided) was considered to be statistically significant. Means and medians are expressed ±standard deviation (SD).\n\nBODY.METHODS.FOLLOW-UP:\nPatients returned to the surgical outpatient clinic for evaluation of the cosmetic results of the scar and to evaluate possible complications, such as fistula, wound dehiscence and incisional hernia, after a minimum of 12 months follow-up. The patient and the surgeon evaluated the cosmetic results independently and were asked to rate the scar as unsatisfactory, satisfactory or fine. Furthermore, the length and width of the scar was measured.\n\nBODY.RESULTS.STUDY GROUP:\nSome 150 consecutive patients were randomised for participation in this study during an inclusion period from April 1977 until July 1979. Seventy-five patients received a transverse incision and 75 patients a midline incision (Fig. 1). One patient was withdrawn from further follow-up after developing peritonitis and consequent acute respiratory distress syndrome (ARDS) not related to the closure of the abdominal wall 2 days after surgery (transverse incision group). The patients' average age was 51.9 and 51.4 years for the midline and the transverse incision groups, respectively. Furthermore, no differences were found in the body mass and average length between the two groups (Table 1). A cholecystectomy was performed using a transverse incision in 52 patients and utilising a midline incision in 52 patients also. Fifteen and 16 patients, respectively, underwent a combined cholangiography/cholecystectomy. A further 7 and 6 patients, respectively, were treated with a cholangiography/cholecystectomy plus additional choledochotomy and the postexploratory placement of a T-tube.Table 1Baseline characteristics of the patients undergoing surgery, according to study groupVariableMidline incisionTransverse incisionn = 75n = 74Average age (years) ± SD51.9 ± 14.851.4 ± 13.8Average weight (kg) ± SD71.3 ± 14.568 ± 14.3Average length (cm) ± SD163.5 ± 7.8164 ± 7.3\n\nBODY.RESULTS.SURGEON:\nStaff surgeons performed 17% (13/75 patients) of all procedures performed through a midline incision. The remainder of the procedures through a midline incision was carried out under staff surgeon supervision. Staff surgeons performed 14% of all procedures in the transverse incisions study group (10/74 patients) and supervised the remainder. No statistically significant difference was found between the two randomised groups (P = 0.65).\n\nBODY.RESULTS.DURATION OF SURGERY:\nNo significant difference was noted in the skin-to-skin time (in min) for the two different incisions (Table 2). Surgery utilising midline and transverse incision took 56.9 ± 29.3 and 53.2 ± 26.8 min, respectively (P = 0.35). The total duration of the procedures until extubation (in min) did not differ between the midline and transverse incisions (71.0 ± 30.5 and 67.0 ± 27.3, respectively, P = 0.34).Table 2Length of incision, thickness of subcutaneous fat and skin-to-skin time, according to study groupVariableMidline incisionTransverse incisionP-valueLength of incision (mm) ± SDa164 ± 28140 ± 24<0.0001Thickness of subcutaneous fat (mm) ± SDa34.5 ± 13.030.3 ± 12.40.05Skin-to-skin time (min) ± SDa56.9 ± 29.353.2 ± 26.80.40Width of scar (mm) ± SDb8.3 ± 1.43.3 ± 1.2<0.0001aMeasured during surgery in 75 midline and 74 transverse incisionsbMeasured at follow-up in 63 and 60 midline and transverse incisions, respectively\n\nBODY.RESULTS.PAIN AND ANALGESICS:\nSignificantly more patients, having undergone a midline incision, reported pain on day one, two and three postoperatively (P < 0.0001, Table 3). In the midline incision group, 28/75 patients required no or only one dose of analgesics; the remainder required two or more doses. Thirty-one patients operated through a transverse incision required no analgesics or only one dose; 43 patients (the remainder) required two or more. No significant difference in the use of analgesics was found between the groups (P = 0.69).Table 3Postoperatively reported pain, according to study group, shown as the number of patients reporting pain at the time points indicated (percentage), with the remainder of patients reporting no painTime point after surgeryMidline incision n = 75Transverse incision n = 74P-valuePatients reporting pain, n (%)Patients reporting pain, n (%)3–4 h68 (91)60 (81)0.09First day64 (85)39 (53)<0.0001Second day57 (76)23 (31)<0.0001Third day28 (37)9 (12)<0.0001Fourth day5 (7)3 (4)0.72Fifth day0 (0)1 (1)0.50Sixth day0 (0)1 (1)0.50\n\nBODY.RESULTS.COMPLICATIONS:\nPostoperative complications (Table 4) were seen in 16 out of 75 patients (21%) from the midline incision group and in 15% from the transverse incision group (11 patients) (P = 0.30). Briefly, one patient in each group developed cardiac complications; 8 and 6 patients developed urinary retention after the midline and transverse incisions, respectively (P = 0.59). Surgical site infections were diagnosed in 7 and 3 patients, respectively (P = 0.33).Table 4Rate of complications after surgery, according to study group, shown as the number of patients diagnosed with complications (percentage)ComplicationMidline incisionTransverse incisionP-valuen = 75 n (%)n = 75 n (%)Cardiac1 (1)1 (1)1Urinary retention8 (12)6 (8)0.59ARDS01 (1)0.50Surgical site infection7 (9)3 (4)0.33Haemorrhage1 (1)00.50Pneumonia01 (1)0.50Total17 (23)12 (16)0.30\n\nBODY.RESULTS.DISCHARGE:\nForty-five (60%) and 42 (57%) patients from the patients having undergone a midline or a transverse incision, respectively, were discharged on day 6 or 7 postoperatively. The remaining patients from each group left hospital care on day 8 or later. The duration of hospital admission did not differ between the two types of incision (P = 0.74).\n\nBODY.RESULTS.COSMETICS:\nThe width and length of all incisions was measured during the follow-up visit (Table 2). The mean width of the scar after the healing of the midline incisions was found to be 8.3 ± 1.4 mm. The mean width of the scar after the healing of the transverse incisions was measured to be 3.3 ± 1.2 mm. This observed difference is significant (P < 0.0001). The length of the incisions was 140 ± 24 mm and 164 ± 28 mm for the transverse and the midline incisions, respectively. The difference in scar length was found to be significant (P < 0.0001).\n\nBODY.FOLLOW-UP:\nEighty-one percent of all patients operated through a transverse incision were seen during the follow-up examination (n = 60). Of the patients operated through a midline incision, 63 out of 75 were seen at the outpatient clinic (84%). The patients that were lost to follow-up could either not be traced or had deceased (Fig. 1). The minimum follow-up for the evaluation of cosmetic results and hernia incidence was 12 months and the maximum was 36 months.\n\nBODY.FOLLOW-UP.INCISIONAL HERNIA:\nFrom the patients that had undergone the procedure through a transverse incision, one (1/60; 2%) presented with an incisional hernia as opposed to 9 patients from the midline incision group (9/63; 14%); 95% confidence interval (CI) 7.5–25.4%. This difference in hernia incidence is significant (P = 0.017). No significant correlation was found between the incisional hernia rate and surgical site infection (P = 0.07).\n\nBODY.FOLLOW-UP.SUBJECTIVE COSMETICS:\nPatients and surgeons alike were asked to rate the appearance of the scar during the postoperative follow-up outpatient clinic visit. Both the surgeons and the patients found the scar resulting from the transverse incision to be more cosmetically pleasing (P < 0.0001 and P = 0.03, respectively, Table 5).Table 5Number of patients and surgeons rating the cosmetics of a scar at follow-upScoreMidline incision (n = 63)Transverse incision (n = 60)Patients, n (%)Surgeons, n (%)Patients, n (%)Surgeons, n (%)Unsatisfactory6 (10)25 (40)2 (3)6 (10)Satisfactory16 (25)27 (43)9 (15)12 (20)Fine41 (65)11 (17)49 (82)42 (70)Total63636060Difference between type of incision: patients P = 0.03; surgeons P < 0.0001\n\nBODY.DISCUSSION:\nThis prospective randomised study of transverse and midline incisions for open cholecystectomy shows that a significant reduction of incisional hernia incidence can be achieved through the use of a transverse incision. Only one other study (published in 1980) reported the incidence of incisional hernia after upper abdominal midline and unilateral transverse incision in a randomised trial. No difference between the two techniques (8 and 6% incisional hernia, respectively) was found, but the relatively short follow-up of 6 months, however, may be held accountable for this finding [11]. Three retrospective studies showed rates of incisional hernia of 3.2, 5.4 and 16.5% for midline incision and 1.3, 6.7 and 13.4% for transverse incision without statistically significant differences [12–14]. The possible reason for the rather high incidence of incisional hernia in the midline incision group (14%) may lie in the use of resorbable 910 polygalactin sutures. Nevertheless, the use of the same type of resorbable suture in the closure of the transverse incisions resulted in a 2% hernia rate. There is evidence for the importance of proper technique and choice of incision as a means to reduce incisional hernia being more important than the use of suture material [7]. Furthermore, as mentioned above, it is known that the incidence of incisional hernia in the case of a midline incision lies between 2 and 20%. From our data, the NNT (numbers needed to treat) is calculated to be 8 (95% CI 5–30) and the RRR (relative risk reduction) is 88% (95% CI 23–100%). Luijendijk et al. [15] have published a hernia rate of 2% after Pfannenstiel incisions closed using 910 polygalactin, which is in agreement with our findings in the patients randomised for a transverse incision, emphasising the importance of the incision over the choice of suture material. In our study, significantly fewer patients reported pain on day 1, 2 and 3 after transverse incisions, a result that was also described by other authors [16, 17]. Greenall et al. [18] published a contradictory report (in 1980) in which no significant difference in postoperative pain was found between midline and transverse incisions. The previously mentioned study, however, only analysed 46 out of 572 patients (8%) with regard to pain, which may explain the finding. In the same way, Lacy et al. suspended visual analogue pain scoring in a study comparing midline and transverse incisions for abdominal aortic surgery. Remarkably, the two groups in our study did not differ in terms of postoperative analgesia, a finding that is also reported by Lindgren et al. [17] and Donati et al. [19]. In our study, surgeons as well as patients were significantly more satisfied with the aesthetic appearance after a transverse in comparison with a midline incision. The scars after transverse incisions were found to be significantly shorter and less wide than the midline incisions, which may account for the observed difference. A possible reason for this is that a transverse incision is executed parallel to the prevailing direction of the skin lines on the abdomen and, therefore, the tension on the wound and consequent scar is low. Cholecystectomy has come a long way since this trial. The introduction and widespread acceptance of laparoscopic technique as the treatment of choice has rendered open cholecystectomy to be an operation for exceptional, and perhaps surgically difficult, circumstances. Nowadays, the study reported is hardly feasible, yet, the results are still applicable and very relevant for other surgical procedures in the (upper) abdomen. Knowledge of the favourable results of a transverse incision may aid surgeons in their choice when finding themselves in the unfortunate position of needing conversion to open cholecystectomy. In conclusion, this investigation on transverse incisions might be helpful in reducing the incidence of incisional hernia in patients after open cholecystectomy. The midline incision is a preferred manner to achieve exposure of the abdominal cavity and is considered to be easily performed and quick. Although the midline incision is generally accepted, the incidence of incisional hernias is surprisingly high [1–5]. The choice for a particular incision should not only be based on exposure, but also on hernia incidence reduction, especially since recurrence rates after hernia repair are reported to be very high. Furthermore, the recurrence rate after incisional hernia repair is a disappointing 63 and 32% for suture and mesh repair, respectively [6]. In the light of these results, incisional hernia prevention is warranted. In this investigation, it is shown that a significant reduction (from 14.5 to 1.7%) of incisional hernia incidence was achieved by using a transverse incision. Hence, a transverse incision should be considered as the preferred incision in acute and elective surgery of the upper abdomen in which laparoscopic surgery is not an option. Full exposure of two quadrants is feasible through the use of a unilateral transverse incision in, for example, biliary, bariatric, liver and colonic surgery. The transverse incision should be part of the abdominal surgeon's armamentarium and is a preferable incision to prevent the high incidence of incisional hernia after abdominal surgery.\n\n**Question:** Compared to Midline incision what was the result of Transverse incision on Pain on day two after surgery?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
412
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pentobarbital versus thiopental in the treatment of refractory intracranial hypertension in patients with traumatic brain injury: a randomized controlled trial\n\n ABSTRACT.INTRODUCTION:\nExperimental research has demonstrated that the level of neuroprotection conferred by the various barbiturates is not equal. Until now no controlled studies have been conducted to compare their effectiveness, even though the Brain Trauma Foundation Guidelines recommend that such studies be undertaken. The objectives of the present study were to assess the effectiveness of pentobarbital and thiopental in terms of controlling refractory intracranial hypertension in patients with severe traumatic brain injury, and to evaluate the adverse effects of treatment.\n\nABSTRACT.METHODS:\nThis was a prospective, randomized, cohort study comparing two treatments: pentobarbital and thiopental. Patients who had suffered a severe traumatic brain injury (Glasgow Coma Scale score after resuscitation ≤ 8 points or neurological deterioration during the first week after trauma) and with refractory intracranial hypertension (intracranial pressure > 20 mmHg) first-tier measures, in accordance with the Brain Trauma Foundation Guidelines.\n\nABSTRACT.RESULTS:\nA total of 44 patients (22 in each group) were included over a 5-year period. There were no statistically significant differences in ' baseline characteristics, except for admission computed cranial tomography characteristics, using the Traumatic Coma Data Bank classification. Uncontrollable intracranial pressure occurred in 11 patients (50%) in the thiopental treatment group and in 18 patients (82%) in the pentobarbital group (P = 0.03). Under logistic regression analysis – undertaken in an effort to adjust for the cranial tomography characteristics, which were unfavourable for pentobarbital – thiopental was more effective than pentobarbital in terms of controlling intracranial pressure (odds ratio = 5.1, 95% confidence interval 1.2 to 21.9; P = 0.027). There were no significant differences between the two groups with respect to the incidence of arterial hypotension or infection.\n\nABSTRACT.CONCLUSIONS:\nThiopental appeared to be more effective than pentobarbital in controlling intracranial hypertension refractory to first-tier measures. These findings should be interpreted with caution because of the imbalance in cranial tomography characteristics and the different dosages employed in the two arms of the study. The incidence of adverse effects was similar in both groups.\n\nABSTRACT.TRIAL REGISTRATION:\n(Trial registration: US Clinical Trials registry NCT00622570.)\n\nBODY.INTRODUCTION:\nHigh dosages of barbiturates are used in patients with severe traumatic brain injury (TBI) who present with refractory intracranial hypertension (ICH) after medical and surgical treatment. This practice is recommended in the Brain Trauma Foundation (BTF) Guidelines, because this is the only second-level measure for which there is class II evidence that it can reduce intracranial pressure (ICP) [1]. Nevertheless, its effect on outcome is unproven [2], mainly because of severe medical complications. Within the family of barbiturates the oxibarbiturates and thiobarbiturates stand out, their primary representatives being pentobarbital and thiopental. Until now no controlled studies have been reported that compare the effectiveness of pentobarbital and thiopental in controlling ICH. At the experimental level, research has demonstrated that mechanisms of action and levels of neuroprotection differ between these agents [3-6]. For this reason, research is needed to compare the effectiveness of these two drugs in terms of controlling refractory ICH in patients with severe TBI. Based on various studies conducted in laboratory animals [3-6], suggesting that the neuroprotective capacity of thiopental is superior, our working hypothesis was that thiopental is more effective than pentobarbital in controlling ICP in patients with severe TBI, with a similar incidence of adverse side effects. In support of our work in the present study, the BTF Guidelines recommend that studies be undertaken to compare the effectiveness of the different barbiturates that are currently used in TBI patients [1].\n\nBODY.MATERIALS AND METHODS:\nWe conducted a prospective, randomized cohort study comparing two treatments: pentobarbital and thiopental. Our primary objective was to compare the effectiveness of these agents in controlling refractory ICH in patients with severe TBI. Secondary objectives were to compare the incidence of secondary effects, especially arterial hypotension, which was defined as the presence of mean arterial pressure (MAP) under 80 mmHg at any point during barbiturate therapy. This study was conducted at Son Dureta University Hospital (Palma de Mallorca, Spain) and was approved by the Ethics Committee of the Balearic Islands on 31 March 2002. It is registered with the US Clinical Trials Registry, with the number NCT00622570. In all cases, the patient's closest relative, legal representative, or guardian gave written informed consent for their inclusion in the study.\n\nBODY.MATERIALS AND METHODS.INCLUSION CRITERIA:\nPatients admitted to our intensive care unit (ICU) between May 2002 and July 2007 with a severe TBI (Glasgow Coma Scale [GCS] score after nonsurgical resuscitation ≤ 8) and presenting with refractory ICH (ICP > 20 mmHg), and who underwent first-level measures in accordance with the BTF Guidelines [7], were included. Refractory ICH was defined as follows: ICP 21 to 29 mmHg for 30 minutes or more, ICP of 30 to 39 mmHg for 15 minutes or more, or ICP greater than 40 mmHg for more than 1 minute, in the absence of external interventions. Included patients were required to be haemodynamically stable at the point of inclusion in the study; haemodynamic stability was defined as systolic blood pressure of 100 mmHg or greater.\n\nBODY.MATERIALS AND METHODS.EXCLUSION CRITERIA:\nWe did not include in the study patients who were younger than 15 or older than 76 years; patients with a GCS score of 3 upon admission and neurological signs of brain death (bilateral arreactive midryasis and loss of brainstem reflexes); and patients who were pregnant, had barbiturate allergy or intolerance, or had a history of severe cardiac ventricular dysfunction with an ejection fraction under 35%.\n\nBODY.MATERIALS AND METHODS.GENERAL THERAPEUTIC PROTOCOL:\nAll patients with severe TBI underwent cranial computed tomography (CT) upon admission and were categorized in accordance with the classification proposed by the Traumatic Coma Data Bank [8]. We also recorded findings of CTs conducted before inclusion of the patients in the study. The CT findings on inclusion were regarded to be the worst of the hospital stay; the prognostic value of such CT findings have been described by other authors [9]. CTs were independently reviewed and categorized by two neurosurgeons (JI and MB) who were unaware of the treatment group to which the patients had been assigned. In cases of disagreement between these investigators, a third investigator reviewed the CT images. All patients' ICP was monitored using an intraparenchymal Camino catheter (Integra Neurosciences, Plainsboro, NJ, USA). The ICP catheter was placed in the frontal region of the hemisphere with more radiological lesions on the CT. The systemic monitoring of these patients included invasive blood pressure, pulse oximetry, and a pulmonary artery thermodilution catheter. The ICP, MAP and cerebral perfusion pressure data were gathered on an hourly basis (one value every full hour) throughout the study using the Care Vue® clinical monitoring system (Phillips, Eindhoven, The Netherlands). The general treatment objectives in patients with severe TBI were to maintain MAP above 80 mmHg, ICP below 20 mmHg, and cerebral perfusion pressure above 60 mmHg. To achieve these objectives, we used liquids and/or vasoactive support with norepinephrine (noradrenaline). In patients with ICP greater than 20 mmHg, initial treatment included elevation of the head of the bed, keeping the neck straight, appropriate sedation, muscular paralysis, ventricular drainage (if the patient had visible ventricles on the CT), 20% mannitol (0.25 to 0.75 mg/kg), 7.5% hypertonic saline (2 ml/kg) and moderate hyperventilation (partial carbon dioxide tension of 30 to 35 mmHg). Neurosurgical interventions were undertaken when necessary to evacuate surgical lesions. This approach can be considered conventional treatment and is included in the BTF Guidelines as first-tier therapy [7]. Patients whose ICP remained high with conventional treatment were included in the study. Before randomization of the patient to a study group, we required that patient to have received maximal medical treatment (first-level measures). In addition, we required a CT to have been conducted within 24 hours before inclusion of the patient in the study; intravenous administration of 0.7 g/kg mannitol 1 hour before randomization; or a plasmatic osmolarity measurement above 320 mOsm/kg, in order to ensure that hyperosmolar therapy had been optimized before inclusion.\n\nBODY.MATERIALS AND METHODS.RANDOMISATION:\nRandomization was based on a computer-generated list that intercollated the two drugs. Allocation was done by the intensive care unit physician who was on duty, once the patient had been found to meet the inclusion criteria and none of the exclusion criteria. Data collection and patient follow up were conducted by the same investigator (JPB).\n\nBODY.MATERIALS AND METHODS.BLINDING OF TREATMENT GROUPS:\nThe study was not blinded because it was difficult for us to mask treatment; thiopental is liophylized for administration and pentobarbital is not.\n\nBODY.MATERIALS AND METHODS.ADMINISTRATION OF BARBITURATES AND MONITORING OF EFFECTS:\nPentobarbital was administered in accordance with the protocol established by Eisenberg and coworkers [10], using a loading dose of 10 mg/kg over 30 minutes followed by a continuous perfusion of 5 mg/kg per hour for 3 hours. This was followed by a maintenance dosage of 1 mg/kg per hour. Thiopental was administered in the form of a 2 mg/kg bolus administered over 20 seconds. If the ICP was not lowered to below 20 mmHg, then the protocol permitted a second bolus of 3 mg/kg, which could be readministered at 5 mg/kg if necessary to reduce persistently elevated ICP. The maintenance dosage was an infusion of thiopental at a rate of 3 mg/kg per hour. In both treatment groups, for cases in which the maintenance dosage did not achieve the reduction in ICP to below the 20 mmHg threshold, the maintenance dosage for both drugs could be increased by 1 mg/kg per hour, while looking for electroencephalographic burst suppression or even the flat pattern, in order to ensure that different doses of the two barbiturates were equipotent. Electroencephalography was conducted daily in a noncontinuous manner (Nicolet; Viasys Healthcare, Verona Road, Madison, WI, USA). Results were analyzed by an experienced neurologist who was blinded to the treatment of the patients. In those patients in whom barbiturate coma did not control ICP, we used decompressive craniotomy and/or external lumbar drainage, in accordance with the Munch criteria, as life-saving measures [11,12].\n\nBODY.MATERIALS AND METHODS.EFFECTIVENESS CRITERIA:\nAdequate response to treatment was defined as a decrease in ICP to below 20 mmHg, and maintenance below this threshold for at least 48 hours. To describe the ICP, we also followed the criteria previously employed by Stocchetti and coworkers [13]; the arithmetic mean of ICP data recorded during every 24-hour period, after filtering to exclude inaccurate readings, was calculated and expressed as 'mean ICP'. Three ICP blocks were considered for further analysis: less than 20 mmHg, 20 to 30 mmHg, and more than 30 mmHg. Uncontrollable ICP was defined as follows: ICP of 21 to 35 mmHg for 4 hours, ICP of 36 to 40 mmHg for 1 hour, or ICP above 41 mmHg for 5 minutes, in the absence of external interventions. We also defined as unresponsive to treatment those cases in which, because of refractory ICP, the patient needed some other treatment (surgery and/or lumbar drainage) and cases in which the patient progressed to brain death. Although it was not a main objective of the study, patients were evaluated 6 months after injury using the Glasgow Outcome Scale [14].\n\nBODY.MATERIALS AND METHODS.WITHDRAWAL OF TREATMENT:\nWhen ICP was controlled (<20 mmHg for 48 hours), we conducted a step-wise reduction in the barbiturate coma in steps that reduced the dosage by 50% every 24 hours until the infusion was suspended. In the event of ICP values rising to the study's inclusion values during the withdrawal of barbiturate treatment, the perfusion dosage was once again increased to achieve control of the patient's ICP.\n\nBODY.MATERIALS AND METHODS.SAMPLE SIZE:\nAccepting an α error of 0.05 and a β error of 0.2 in a bilateral hypothesis contrast, we estimated that 47 patients were needed in each group to detect differences of 30% or greater in the control of ICH. To calculate sample size, we assumed that the therapeutic response rate in the pentobarbital group would be 50%, excluding patients lost to follow up.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nQuantitative variables are expressed as the mean and standard deviation from the mean (SD) in normal distributions, and as median and interquartile range in cases that were not normally distributed. Qualitative variables are expressed as percentages, along with 95% confidence interval (CI). To determine whether variables followed a normal distribution, we used the Shapiro Wilks test. For the comparison of quantitative variables, Student's t-test was used if the variable followed a normal distribution. In other cases, we used the Mann-Whitney U-test. For the comparison of qualitative variables, we used χ2 or Fisher's exact test, as appropriate. Given that the randomization did not create groups that were similar in terms of types of intracranial lesions shown on the CT results, which is a prognostic variable that influences the effectiveness of barbiturate treatment in controlling ICP, we conducted a multivariate analysis using binary logistic regression, so that we would include the prognostic variables with the most plausible association with the dependent variable 'uncontrollable ICP'. These are variables such as age, GCS score at admission, and the worst CT obtained within 24 hours before inclusion of the patient in the study, as well as the type of barbiturate administered. To achieve this multivariate analysis, and given the small number of cases in each of the five groups in Marshall's classification, the CT data were grouped into focal and diffuse lesions. We also included in the model the minimum daily MAP during barbiturate treatment, given that in the second and third days of treatment there were statistically significant differences between the groups in the univariate analysis. The significant variables identified by the 'likelihood ratio' ≤ 0.1 test were used, along with those whose inclusion affected the calculation of the effect of the 'treatment group' variable. Both treatment groups were very similar in terms of other known prognostic variables, such as the presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them, so these were not included in the multivariate analysis. To analyze the variable ICP, which was determined on an hourly basis, we calculated the area under the curve (AUC) at 24, 48 and 72 hours, and also standardized by time [15]. For all comparisons, we considered statistical significance to have been achieved if the two-tailed α error probability was 5% or less (P ≤ 0.05). Statistical analyses were conducted using SPSS version 15 (SPSS Inc., Chicago, IL, USA).\n\nBODY.RESULTS:\nPreliminary results for the first 20 patients have already been published elsewhere [16]. From May 2002 to July 2007, 480 TBI patients were admitted to the intensive care unit of the Son Dureta University Hospital. Of these 480 patients, 71 (14.8%) presented with ICH refractory to first-level measures, of whom 44 were included in the study. The study was concluded prematurely because of the unexpected and slow inclusion rate; this could have modified some uncontrollable environmental factors that may affect results. The reasons for not including the remaining 27 refractory ICH cases were as follows: 13 patients were included in other studies, six were older than 76 years, five were admitted with nonreacting midriatic pupils and with clinical evidence of brain death, two presented with haemodynamic instability at the time of randomization, and one patient was transferred to a different hospital during the first 24 hours of admission, which excluded that patient from follow-up analysis. On average, the barbiturate coma was initiated in the thiopental group at 89 ± 15.5 hours after admission and in the pentobarbital group at 61 ± 14.3 hours after admission (P = 0.33). The baseline characteristics of the 44 patients included in the study, 22 randomized to each group, are presented in Table 1. There were no statistically significant differences with respect to epidemiological data, co-morbidity (data not shown) or lesions associated with TBI, although there were differences in the CT classification. Table 1 Baseline characteristics of patient population Characteristic Thiopental (n = 22) Pentobarbital (n = 22) P Sex (male; n) 19 19 1 Age (years) 26 (20 to 41) 32 (22 to 43) 0.45 ISS 25 (24 to 34) 25 (25 to 38) 0.77 SAPS II 42 (28 to 54) 43 (38 to 46) 0.95 APACHE II 23 (15 to 25) 20 (18 to 26) 0.27 APACHE III 60 (38 to 73) 52 (32 to 76) 0.41 Associated lesion (n) Thoracic injury 7 2 0.13 Abdominal injury 4 1 0.34 Extremities injury 9 5 0.20 Admission CT (n) Diffuse injury without brain swelling 12 4 0.046 Diffuse bilateral brain swelling 6 12 Diffuse unilateral brain swelling with midline shift 1 0 Any mass lesion > 25 ml 3 6 Age, ISS, SAPS II, APACHE II and APACHE III are expressed as median and interquartile range. APACHE, Acute Physiology and Chronic Health Evaluation; admission CT, admission computed tomography (according to the Traumatic Coma Data Bank); ISS, Injury Severity Score; SAPS, Simplified Acute Physiology. The summary of prognostic variables for the 44 patients is shown in Table 2. As in Table 1 the characteristics of the worst CT conducted before inclusion in the study differed between the two groups. Table 2 Prognostic variables of patient population Variable Thiopental (n = 22) Pentobarbital (n = 22) P Admission GCS score 6.5 (3.0 to 7.2) 7 (4.7 to 10.0) 0.38 Out-of-hospital hypoxia (n) 5 7 0.63 Out-of-hospital hypotension (n) 5 4 1 Pupillary reactivity (n) a One reacting 3 5 0.66 Both reacting b 12 14 Pre-enrolment CT (n) Diffuse injury without brain swelling 8 5 0.04 Diffuse bilateral brain swelling 1 8 Diffuse injury unilateral brain swelling with midline shift 5 1 Any mass lesion evacuated 7 5 Nonevacuated mass lesion 1 3 Admission GCS is expressed as median (interquartile range). a Pupillary reactivity at hospital admission. b Miotic pupils were considered as reactive. CT, computed tomography; GCS, Glasgow Coma Scale. \n\nBODY.RESULTS.EFFECTIVENESS CRITERION: CONTROL OF INTRACRANIAL PRESSURE:\nThe distribution of the ICP during the first 3 days of treatment, according to Stocchetti's criteria, is summarized in Table 3. The missing cases during these 3 days were due to brain deaths or to receipt of rescue treatment for uncontrollable ICP. Finally ICP was uncontrollable in 11 cases (50%) in the thiopental group and in 18 patients (82%) in the pentobarbital group (P = 0.03). In nonresponding patients, we chose to place a lumbar drainage in five, in three we opted for surgical treatment, and in three other patients we combined both treatments, drainage and surgery. Surgical decompression was conducted in four patients in the thiopental group and in two of the patients in the pentobarbital group. The number of hyperosmolar treatments administered (manitol and/or hypertonic saline) during the barbiturate coma was similar in both groups: 16.5 (8.0 to 24.2) in the thiopental group and 16.5 (3.0 to 21.5) in the pentobarbital group (P = 0.9). The mean ± SD duration of the barbiturate coma was 156 ± 60 hours for thiopental and 108 ± 100 hours for pentobarbital (P = 0.06). Seven (31.8%) patients presented an ICP rebound with thiopental and six (27.3%) with pentobarbital (P = 0.74) during treatment withdrawal. Table 3 Mean ICP recorded per day during the first 3 days of barbiturate coma Drug Day Mean ICP (n[%]) <20 mmHg 20 to 30 mmHg >30 mmHg Thiopental 1 10 46 11 50 1 5 2 15 71 4 19 2 10 3 12 63 6 32 1 5 Pentobarbital 1 9 41 8 36 5 23 2 8 38 9 43 4 19 3 6 43 8 57 0 0 Mean intracranial pressure (ICP) is the arithmetic mean of ICP data recorded during every 24-hour period, according to Stocchetti's criteria [ 13 ]. Data are presented as number of cases and as a percentage of the total number of cases each day. Figure 1 presents the AUC for ICP above 20 mmHg, standardized over time, as follows. The ICP value of AUC0–24 h was 458.00 mmHg·hour (95% CI = 421.84 to 494.16) in the thiopental group and 550.63 mmHg·hour (95% CI = 411.31 to 689.95) in the pentobarbital group. The AUC0–48 h was 913.18 mmHg·hour (95% CI = 814.08 to 1,012.27) in the thiopental group and 997.27 mmHg·hour (95% CI = 757.10 to 1,237.43) in the pentobarbital group. The AUC0–72 h in the thiopental group was 1,291.69 mmHg·hour (95% CI = 1,172.27 to 1,411.12) and 1,399.73 mmHg·hour (95% CI = 1,291.11 to 1,508.35) in the pentobarbital group. Standardized over time, the AUC per hour in the thiopental group was 23.90 mmHg (95% CI = 22.00 to 25.81) and in the pentobarbital group it was 29.39 mmHg (95% CI = 23.20 to 35.59). Figure 1AUC of ICP data. Presented are areas under the curve (AUCs) of the intracranial pressure (ICP) data, standardized by time, with a base value of 20 mmHg. Both treatment groups were similar in terms of known prognostic variables, such as presence of hypoxia, hypotension before hospital admission and pupil reactivity, and the univariate analysis did not identify differences between them. Therefore, these were not included in the multivariate analysis. The logistic regression analysis showed that, after adjusting for the worst CT and the type of barbiturate used, thiopental was five times more likely than pentobarbital to control ICP (odds ratio = 5.1, 95% CI = 1.2 to 21.9; P = 0.027). The Hosmer-Lemeshow test indicated that the fit of the model was good (P = 0.799). The association of focal lesions in the pre-inclusion CT with ICP control was 3.6 times higher than that for the diffuse lesions. The relative risk for good control of ICP in the thiopental versus pentobarbital group was 2.26 for patients with focal lesions and 3.52 for those who presented with diffuse lesions. The other variables analyzed did not exhibit a significant relationship to ICP control, and did not modify the effect of the barbiturate treatment, including the third day minimum MAP, which was significantly different between the two treatments (data not shown).\n\nBODY.RESULTS.ADVERSE SIDE EFFECTS DURING THE BARBITURATE COMA:\nThe secondary effects during the barbiturate coma are presented in Table 4. In both groups almost all patients presented with at least one MAP measurement below 80 mmHg. There were no differences between groups with respect to the incidence of infections, Sepsis related Organ-Failure Assessment (SOFA) scores before initiation of treatment, or the maximum SOFA value [17] during the entire period of barbiturate coma. Table 4 Adverse events during barbiturate coma Adverse event Thiopental (n = 22) Pentobarbital (n = 22) P Hypotension a 21 20 1 Respiratory infection b 18 17 1 Urinary infection c 0 2 0.49 Positive blood culture 4 1 0.34 ICP catheter colonization 7 5 0.5 CNS infection (CSF) d 3 0 0.23 SOFA pre e 7 (4.5 to 9.5) 8.0 (5.5 to 9.0) 0.57 SOFA maximum f 11 (10 to 12) 11 (10 to 12) 0.94 a Hypotension is defined as detection of a medium arterial blood pressure below 80 mmHg at any time during barbiturate coma. b Respiratory infection: presence of a positive sputum culture. c Urinary infection: presence of a positive urine culture. d Central nervous system infection (CNS) infection (cerebrospinal fluid [CSF]): infection of the CNS with a positive culture in the CSF. e SOFA pre: value of the Sepsis related Organ-Failure Assessment (SOFA) score before the beginning of the barbiturate coma. f SOFA maximum: maximum value of the SOFA during the barbiturate coma, according the indication by Moreno and coworkers [ 16 ]. A thermodilution catheter was placed in 42 patients to facilitate haemodynamic control. The haemodynamic changes produced during the barbiturate coma are presented in Table 5. Differences of note include the minimum MAP, the pulmonary wedge pressure value, and the maximum norepinephrine dosage on days 2 and 3. Table 5 Systemic changes during barbiturate coma Parameter Pretreatment 1st day 2nd day 3rd day 4rd day Cardiac output (l/minute) a Thiopental 6.8 ± 1.4 6.4 ± 1.5 6.0 ± 1.4 6.7 ± 1.5 6.6 ± 1.8 Pentobarbital 7.4 ± 2.2 7.1 ± 1.9 6.5 ± 2.0 7 ± 1.4 6.1 ± 1.3 Cardiac index (l/minute per m 2 ) Thiopental 3.6 ± 0.6 3.4 ± 0.6 3.1 ± 0.6 3.6 ± 1.6 3.5 ± 0.9 Pentobarbital 3.8 ± 1.2 3.8 ± 0.8 3.4 ± 0.8 3.6 ± 0.7 3.2 ± 0.6 Peripheral venous resistance (dines/m 2 ) Thiopental 1,015 ± 325 1,022 ± 347 1,140 ± 429 1,089 ± 289 1,029 ± 253 Pentobarbital 952 ± 257 893 ± 210 1,003 ± 322 939 ± 261 914 ± 188 Pulmonary artery wedge pressure (mmHg) Thiopental 10.4 ± 4.5 9.6 ± 3.6 10.1 ± 4.1* 10.9 ± 4.6* 11.4 ± 3.5* Pentobarbital 11.6 ± 4.0 11.4 ± 3.1 12.8 ± 3.1 13.2 ± 2.1 13.9 ± 3.1 mBP (mmHg) b Thiopental 92 ± 11 75 ± 7 76 ± 9* 76 ± 6* 76 ± 8 Pentobarbital 94 ± 10 74 ± 1 68 ± 10 70 ± 1 70 ± 10 NAD (μg/kg per minute) c Thiopental 0.18 ± 0.33 0.28 ± 0.27 0.37 ± 0.3* 0.46 ± 0.39 0.56 ± 0.63 Pentobarbital 0.19 ± 0.18 0.55 ± 0.68 0.73 ± 0.69 0.60 ± 0.44 0.96 ± 0.79 P O 2 /Fi O 2 d Thiopental 284 ± 130 300 ± 139 293 ± 132 285 ± 138 254 ± 119 Pentobarbital 317 ± 127 304 ± 116 262 ± 125 211 ± 77 184 ± 92 Haemoglobin Thiopental 10.9 ± 1.6 10.7 ± 1.3 11 ± 1.2 10.8 ± 0.9 10.7 ± 1.4 Pentobarbital 10.6 ± 1.2 10.1 ± 1.0 10.4 ± 1.1 10.5 ± 1.1 10.2 ± 1.2 Temperature (°C) e Thiopental 35.8 ± 0.5 34.6 ± 1.3 34.6 ± 3.4 34.9 ± 1.0 34.9 ± 1.0 Pentobarbital 35.7 ± 1.0 34.6 ± 1.2 34.3 ± 1.3 34.4 ± 1.3 34.2 ± 1.1 a Cardiac output, cardiac index, peripheral venous resistance and pulmonary artery wedge pressure: the values are the mean values over 24 hours. b mBP: minimum value of the medium blood pressure during the day. c NAD: maximum dose of Noradrenaline bitartrate during the day. d P O 2 /Fis O 2 : ratio of partial oxygen tension to inspired fractional oxygen tension at 8:00 am. e Temperature: value of the minimum central temperature. * P < 0.05. \n\nBODY.RESULTS.SIX-MONTH OUTCOMES:\nIn the thiopental group, the neurological outcomes at 6 months (in accordance with Glasgow Outcome Scale score) were as follows: death in nine patients, vegetative state in two, severe disability in two, moderate disability in four and good recovery in four. In the pentobarbital group, the 6-month outcome was death in 16 patients, vegetative state in one, moderate disability in two and good recovery in two. In both groups one case was missing from the 6-month follow up analysis\n\nBODY.DISCUSSION:\nThe results of this study indicate that thiopental is five times more effective than pentobarbital in controlling refractory ICH. However, these findings must be interpreted with caution, given the small sample size and the fact that the study was unable to mask assignment to treatment groups. Barbiturate coma is at present the only therapy for which we have class II evidence, under BTF Guidelines [1], of efficacy in treating refractory ICH. Hence, it is perhaps the case that barbiturate coma is the most used second-level measure, with a usage frequency reported in the literature that varies from 13% to 56% [18,19]. Therefore, it is important to test the effectiveness of the various barbiturates available for controlling ICP refractory to first-level measures.\n\nBODY.DISCUSSION.DIFFERENCES BETWEEN OXIBARBITURATES AND THIOBARBITURATES:\nThe pharmacokinetic characteristics of thiopental and pentobarbital are different because their protein binding, distribution volume and clearance differ [20]. Nevertheless, the mean half life (thiopental 6 to 46 hours and pentobarbital 15 and 48 hours), which is the fundamental pharmacological parameter, differs little between the two agents. It therefore does not appear that these pharmacokinetic differences have clinical repercussions. One difference between these two groups of barbiturates is the presence of active metabolites. Thiopental has five metabolites, of which four are inactive and one (pentobarbital, or pentobarbitone) is active. Therefore, pentobarbital is an active metabolite of thiopental. This fact, along with the great intra-individual and inter-individual variability in the metabolism of these agents (caused by the existence of enzymatic induction phenomena associated with hepatic cytochrome P450), results in a weak correlation between serum concentrations and pharmacological effect. For this reason, monitoring this treatment with electroencephalography is strongly recommended. At the experimental level, various studies have compared these two medications. Hatano and coworkers [21], in a study conducted in a dog model, concluded that thiobarbiturates provoke cerebral vasoconstriction, which could help to redistribute cerebral blood flow toward ischaemic zones. Cole and colleagues [4] demonstrated that thiopental reduced the size of the ischaemic area more than did pentobarbital, even though both drugs achieved electroencephalographic burst suppression patterns. Shibuta [5] observed that thiopental, but not pentobarbital, was capable of limiting the cytotoxic damage caused by nitric oxide. Almaas and coworkers [3] observed that the different barbiturates had different neuroprotective effects with respect to oxygen and glucose deprivation in a model using human neurone cultures. Thiopental exhibited a neuroprotective effect at all the dosages studied, whereas pentobarbital was neuroprotective only at elevated dosages. Finally, in an in vitro study, Smith and colleagues [6] demonstrated that although thiopental provoked 96% inhibition of lipid peroxidation, pentobarbital had almost no effect. These experimental studies demonstrate that not all barbiturates are equal and that their neuroprotective capacity and effectiveness may differ [22]. Therefore, despite the unavoidable methodological limitations of the present study, we believe that our results may have clinical relevance.\n\nBODY.DISCUSSION.SECONDARY EFFECTS OF BARBITURATE COMA:\nThe most frequently detected secondary effect in our study, as might be expected, was arterial hypotension, which occurred in 21 patients in the thiopental group and 20 patients in the pentobarbital group. Although this incidence may be greater than that in previous studies [10], we attribute this to the definition of hypotension used (detection at any time in the barbiturate coma of MAP < 80 mmHg), which did not take the 'time' variable into account. For that reason, we collected data on other variables, such as maximum daily norepinephrine dosage and minimum daily MAP. Nearly all patients were monitored using a pulmonary artery thermodilution catheter, and arterial hypotension episodes were rigorously managed with fluid therapy and vasoactive drugs. We would note that the changes produced by pentobarbital at the cardiac and respiratory level were, in general terms, greater than those produced by thiopental. This is because (as shown in Table 5) cardiac output, cardiac index, and partial oxygen tension/fraction of inspired oxygen ratio exhibited greater changes during treatment with pentobarbital than with thiopental. This observation contrasts with the findings of previous experimental studies [23], in which it appeared that at high doses pentobarbital was safer and better tolerated than thiopental. Other complications (mostly infections) and the incidence of multiple organ dysfunction (identified using maximum SOFA) were similar in the two groups.\n\nBODY.DISCUSSION.LIMITATIONS OF THE STUDY:\nAs previously noted, this study has two important limitations. First, it was not a blinded study because the pentobarbital was not liophylized and thiopental was. Second, the sample size was small, so that small changes in the principal variable studied, namely ICP control, could significantly affect the statistical analysis. The classical view is that ICP response to barbiturates varies from 30% to 50%, and so it is possible that part of the difference found between drugs is due to poor response by the pentobarbital group as a result of any confounding bias. The randomization process is a potent mechanism that tends to eliminate bias by randomly distributing the values of all of the variables to the experimental groups. Nonetheless, the tool is not perfect and the groups frequently exhibit an imbalance in some confounding variable, especially when working with samples that are not very large. For this reason, in this study we used logistic regression analysis to eliminate any possible bias, and separate, independent analyses of the CT data were also conducted by two investigators who did not know the experimental group to which the patients belonged. Another limitation is that the dosages in the two groups were not the same. This leaves the possibility that the reason for the difference between agents that we identified is inadequate pentobarbital dose. Although in the two groups barbiturates were used with the end-point of ICP control, in this type of patient we also employ daily noncontinuous electroencephalographic monitoring. In this way, we believe that – despite different doses – the effect of the two barbiturates can be considered as equipotent because we looked for burst suppression or even the flat electroencephalographic pattern if the ICP was not controlled and the patients remained haemodynamically stable.\n\nBODY.CONCLUSION:\nIn this patient sample, thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-level measures, according to the BTF Guidelines. Nevertheless, these findings should be interpreted with caution because of the imbalance in CT characteristics and the different dosages employed in the two arms of the study. However, the present study is useful as a hypothesis testing exercise and will help to inform the design of future studies. These findings corroborate experimental evidence suggesting that there are differences in the neuroprotective mechanism between the two treatments, and this study may be a first step toward translating evidence from animal models to clinical disease. The incidence of secondary effects during treatment was similar between groups.\n\nBODY.KEY MESSAGES:\n• High doses of barbiturates are used in those patients with severe TBI who present with refractory ICH, and this recommendation is included in the BTF Guidelines. • Until now no controlled studies have been conducted to compare the effectiveness of pentobarbital and thiopental in controlling refractory ICH. Nevertheless, at the experimental level, research has demonstrated that their mechanisms and levels of neuroprotection differ. • Thiopental appeared to be more effective than pentobarbital in controlling ICH refractory to first-tier measures, although these results should be interpreted with caution because of the imbalance in CT characteristics and other limitations of the study.\n\nBODY.ABBREVIATIONS:\nAUC: area under the curve; BTF: Brain Trauma Foundation; CI: confidence interval; ICH: intracranial hypertension; ICP: intracranial pressure; MAP: mean arterial pressure; SD: standard deviation; SOFA: Sepsis related Organ-Failure Assessment; TBI: traumatic brain injury.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nJPB was responsible for study design, acquisition of data, analysis and interpretation of data, and writing of the manuscript. JALP was responsible for acquisition of data and patient randomization. JH acquired data and conducted patient randomization. JMA acquired data and conducted patient randomization. JMR conducted statistical analyses. GF conducted statistical analyses. MB was responsible for designing the study and reviewing CT findings. JI was responsible for designing the study and reviewing CT findings. JI revised the article critically and gave final approval to the version to be published.\n\n**Question:** Compared to Pentobarbital what was the result of Thiopental on Administration of hyperosmolar treatments?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
514
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Comparative Study of Low Doses of Rosuvastatin and Atorvastatin on Lipid and Glycemic Control in Patients with Metabolic Syndrome and Hypercholesterolemia\n\n ABSTRACT.BACKGROUND/AIMS:\nThis multicenter, open-labeled, randomized trial was performed to compare the effects of rosuvastatin 10 mg and atorvastatin 10 mg on lipid and glycemic control in Korean patients with nondiabetic metabolic syndrome.\n\nABSTRACT.METHODS:\nIn total, 351 patients who met the modified National Cholesterol Education Program Adult Treatment Panel III (NCEP ATP III) criteria for metabolic syndrome with low-density lipoprotein cholesterol (LDL-C) levels ≥ 130 mg/dL were randomized to receive either rosuvastatin 10 mg (n = 173) or atorvastatin 10 mg (n = 178) for over 6 weeks.\n\nABSTRACT.RESULTS:\nAfter 6 weeks of treatment, greater reductions in total cholesterol (- 35.94 ± 11.38 vs. - 30.07 ± 10.46%, p < 0.001), LDL-C (48.04 ± 14.45 vs. 39.52 ± 14.42%, p < 0.001), non-high-density lipoprotein cholesterol (- 42.93 ± 13.15 vs. - 35.52 ± 11.76%, p < 0.001), and apolipoprotein-B (- 38.7 ± 18.85 vs. - 32.57 ± 17.56%, p = 0.002) levels were observed in the rosuvastatin group as compared to the atorvastatin group. Overall, the percentage of patients attaining the NCEP ATP III goal was higher with rosuvastatin as compared to atorvastatin (87.64 vs. 69.88%, p < 0.001). Changes in glucose and insulin levels, and homeostasis model assessment of insulin resistance index were not significantly different between the two groups. The safety and tolerability of the two agents were similar.\n\nABSTRACT.CONCLUSIONS:\nRosuvastatin 10 mg was more effective than atorvastatin 10 mg in achieving NCEP ATP III LDL-C goals in patients with nondiabetic metabolic syndrome, especially in those with lower NCEP ATP III target level goals.\n\nBODY.INTRODUCTION:\nMetabolic syndrome consists of a group of cardiovascular risk factors, namely dyslipidemia, high blood pressure (BP), abdominal obesity, and insulin intolerance, whose concurrent appearance increases the risk of atherosclerotic cardiovascular disease [1]. Using the modified National Cholesterol Education Program (NCEP) Expert Panel on Detection, Evaluation, and Treatment of High Blood Cholesterol in Adults (Adult Treatment Panel III [ATP III]) criteria, the prevalence of atherosclerotic cardiovascular disease is estimated to be as high as 24.8% in Korea and is continuing to rapidly increase to epidemic proportions [2]. Elevated cholesterol levels have also been shown to be a strong risk factor for the development of coronary heart disease (CHD). This clustering of risk factors may interact synergistically to affect atherosclerosis and cardiovascular events [3]. Current guidelines for lipid management stress the importance of low-density lipoprotein cholesterol (LDL-C) levels as the primary goal of therapy [4]; however, a high proportion of patients, especially those having high lipid levels, do not achieve their target LDL-C levels despite lipid-lowering therapy [5,6]. Statins effectively lower blood cholesterol levels and reduce the risk of cardiovascular events in many patient types, and are therefore recommended as first-line agents for lowering LDL-C levels [4,7]. Statins also improve other aspects of the lipid profile, such as increasing high-density lipoprotein cholesterol (HDL-C) and lowering triglyceride levels to some extent. Rosuvastatin is a highly effective HMG-CoA reductase inhibitor, which was registered in 2002 in Korea. Rosuvastatin use has been previously shown in numerous studies to be associated with greater LDL-C level reductions as compared to atorvastatin, simvastatin, or pravastatin use [8-10]. The primary objective of the current trial was to compare the effects of rosuvastatin 10 mg with that of atorvastatin 10 mg, which are the lowest-dose tablets available, on the percentage of patients who reach the NCEP ATP III LDL-C goal and safety in subjects with nondiabetic metabolic syndrome after 6 weeks of treatment. The secondary objective was to compare the effects of rosuvastatin with that of atorvastatin on glucose control and insulin resistance.\n\nBODY.METHODS.STUDY DESIGN:\nThis 6-week, multicenter, randomized, open-label, parallel-group, single-dose trial (NCT00335699) was designed to compare the efficacy of a single dose of rosuvastatin and atorvastatin in patients having nondiabetic metabolic syndrome with dyslipidemia (Fig. 1). The study was conducted from August 2005 to January 2006 at 20 medical centers in Korea. The study included a 6-week dietary run-in period before randomization, followed by a 6-week treatment phase. Subjects entering the run-in period were asked to follow the NCEP Step I diet and required to discontinue any previous lipid lowering therapy. Following the dietary lead-in period, patients with fasting LDL-C levels ≥ 130 mg/dL to < 220 mg/dL were selected and randomly assigned to two parallel treatment groups. At baseline, eligible subjects were randomized 1 : 1 to receive either rosuvastatin (Astra-Zeneca Korea, Seoul, Korea) 10 mg or atorvastatin (Pfizer Pharmaceuticals Korea, Seoul, Korea) 10 mg once daily at bedtime for 6 weeks. The study drug was discontinued and subjects were removed from the study if they withdrew informed consent, became pregnant, or developed creatine kinase levels greater than 10 times the upper normal limit. The ethics committees and institutional review boards at each participating hospital approved the study protocol. All patients provided informed consent to participate in this study.\n\nBODY.METHODS.SUBJECTS:\nPatients were ≥ 18 years of age and had nondiabetic metabolic syndrome. Metabolic syndrome was defined according to the modified NCEP ATP III criteria [11], which requires at least three of the following: abdominal obesity (waist circumference): men > 90 cm (36 inches), women > 80 cm (32 inches); triglyceride levels ≥ 150 mg/dL (1.70 mmol/L); HDL-C levels: men < 40 mg/dL (1.04 mmol/L) and women < 50 mg/dL (1.3 mmol/L); BP ≥ 130 / ≥ 85 mmHg or subject receiving antihypertensive treatment; and fasting blood glucose 110 mg/dL (6.11 mmol/L) to 125 mg/dL (6.94 mmol/L). Patients were excluded if they were pregnant or had malignancy. Additional exclusion criteria included diabetes, and active arterial disease such as unstable angina, myocardial infarction, cerebrovascular accident, coronary artery bypass surgery, or angioplasty within 2 months prior to enrollment. After completing the 6-week dietary run-in period, fasting LDL-C concentrations were required to be ≥ 130 mg/dL (3.36 mmol/L) to < 220 mg/dL (5.69 mmol/L) and fasting triglyceride levels were required to be < 400 mg/dL (4.52 mmol/L).\n\nBODY.METHODS.ASSESSMENTS:\nSample analysis for efficacy endpoints was performed in the Green Cross Reference Laboratory, Yongin, Korea, which was certified by the American College of Pathology (LAP No. 6708401) and the National Committee for Clinical Laboratory Standards. Blood samples from patients who had fasted for 12 hours were collected at all investigational sites and delivered by courier to the central laboratory within 24 hours of blood draw. To assess the primary efficacy endpoint, lipid parameters such as total cholesterol, LDL-C, HDL-C, and triglyceride levels were measured during the dietary lead-in period, at randomization, and 6 weeks after treatment. Additionally, levels of apolipoprotein A-1 and B, high-sensitivity C-reactive protein (hsCRP), insulin, glucose, and hemoglobin A1c (HbA1c) were measured at randomization and at 6 weeks after treatment. LDL-C levels were calculated using the Friedewald equation (LDL-C = total cholesterol - (HDL-C + triglyceride/5). The insulin resistance index was estimated using the homeostasis model assessment (HOMA) for insulin resistance based on the following formula: fasting serum insulin (μU/mL) × fasting plasma glucose (mmol/L)/22.5. According to the NCEP ATP III guidelines, the goal LDL-C level for each patient and the proportion of patients achieving the goal in each group was assessed. Persons with CHD or CHD risk equivalent (Framingham 10-year CHD risk > 20%) had a LDL-C level goal of < 100 mg/dL. Those with multiple risk factors had a LDL cholesterol level goal of < 130 mg/dL and those with 0 - 1 risk factor (s) had a goal LDL cholesterol of < 160 mg/dL. Individual demographic data, physical findings, vital signs, and adverse events were evaluated and recorded in the given case record form. To evaluate adverse events, various laboratory assessments including blood counts, and hemoglobin, aspartate aminotransferase, alanine aminotransferase, creatine kinase, electrolyte, and creatinine levels were performed at each time point.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nOne-hundred and forty-three evaluable subjects per treatment group were required to achieve 95% power for detecting a clinically significant difference of 6% at the 5% two-sided level in percentage change from baseline in LDL-C levels at 6 weeks with an assumed standard deviation of 14% [12]. Assuming a dropout rate of 20% during the randomized treatment period, approximately 180 subjects were recruited to each active treatment group. To obtain the required number of randomized subjects (360 in total), approximately 900 subjects were assumed to be needed for screening based on a screening failure rate of 60%. The primary analysis population was the last observation carried forward on the intention-to-treat population. This included all subjects with a baseline and at least one post-baseline lipid level measurement. All numeric variables were expressed as the mean ± SEM (standard error of the mean). Efficacy endpoints were analyzed using the unpaired t-test for continuous variables and Pearson's chi-square test for frequencies with 95% confidence intervals. Multivariate logistic regression analysis was used to evaluate the predictors for reaching target NCEP ATP III LDL-C levels after treatment. Variables used for analysis included the statin used, presence of coronary artery disease and hypertension, body mass index, gender, age, waist circumference, and lipid parameters. On the basis of the actual treatment received, safety data were evaluated for all patients who received at least one dose of study medication.\n\nBODY.RESULTS.SUBJECT CHARACTERISTICS:\nIn total, 645 subjects were screened for participation in this study. Of them, 370 patients entered the dietary lead-in phase and 351 patients met the inclusion criteria and were randomly assigned to treatment with either rosuvastatin 10 mg or atorvastatin 10 mg (Fig. 1). One patient was lost to follow-up and had no safety assessment. Table 1 shows demographic data and baseline characteristics of all 350 subjects who took at least one dose of the study drug at baseline. In terms of demographic data and baseline characteristics, no statistically significant differences existed between the two treatment groups. Patients had a mean age of 60 years in the rosuvastatin group and 58 years in the atorvastatin group. Mean body weights were 66 kg in the rosuvastatin group and 66 kg in the atorvastatin group. Mean systolic and diastolic BP and waist circumstance were comparable between the two groups (Table 1). A total of five patients dropped out before efficacy assessment. Data from 346 patients were analyzed for efficacy in the intention-to-treat population defined as those who took at least one dose of study drug and had lipid levels checked at baseline and follow-up. Safety assessments were performed in 350 patients who were randomized and available for follow-up.\n\nBODY.RESULTS.CHANGES IN METABOLIC PARAMETERS:\nLipid levels, glucose levels, insulin resistance indices, and hsCRP levels at baseline and 6 weeks are shown in Table 2. In each group, atherogenic lipid parameters including total cholesterol, LDL-C, triglyceride, non-HDL-C, and apolipoprotein B had significantly decreased after 6 weeks of treatment (p < 0.001 vs. baseline). Only the atorvastatin treatment produced a modest decrease in HDL-C. Rosuvastatin treatment significantly increased HbA1c and the HOMA index; however, no significant change occurred in the atorvastatin group. Data from two groups were analyzed for an efficacy comparison in the intention-to-treat population. Baseline values of all parameters were similar between the two groups. At 6 weeks after treatment, rosuvastatin 10 mg produced a significantly greater reduction in total cholesterol, LDL-C, non-HDL-C, and apolipoprotein B levels. Otherwise, no significant differences were detected in HDL-C and apolipoprotein A-1 levels between the two groups. In addition, no significant differences were observed with respect to glucose, HbA1c, and hsCRP levels, and HOMA index between the rosuvastatin and atorvastatin groups at 6 weeks (Table 2). At 6 weeks, LDL-C absolute values decreased by 48.04 ± 14.45 mg/dL in the rosuvastatin group and by 39.52 ± 14.42 mg/dL in the atorvastatin group; the former reduction associated with rosuvastatin use was significantly larger than that with atorvastatin (p < 0.0001). Percent changes from baseline in lipid profiles after treatment for 6 weeks, including LDL-C, are shown in Fig. 2. Reductions in total cholesterol (- 35.94 ± 11.38 vs. - 30.07 ± 10.46%, p < 0.0001), non-HDL-C (- 42.93 ± 13.15 vs. - 35.52 ± 11.76%, p < 0.0001), and apolipoprotein B (- 38.7 ± 18.85 vs. - 32.57 ± 17.56%, p = 0.0019) levels were larger in the rosuvastatin group as compared to the atorvastatin group (Fig. 2).\n\nBODY.RESULTS.LDL-C TARGET ACHIEVEMENT:\nAccording to the reported CHD or/and CHD risk equivalents and/or number of risk factors and/or Framingham 10-year risk, the NCEP ATP III LDL-C target goal was determined in each patient and the success rate in reaching their target goal was analyzed after 6 weeks in each group. The percentage of patients who reached their ATP III LDL-C level goals was higher in the rosuvastatin group (87.6 vs. 69.9%, p < 0.001). Among them, patients having LDL-C target cholesterol level goals of < 100 mg and < 130 mg reached their LDL-C target level goals more frequently in the rosuvastatin group as compared to the atorvastatin group. In contrast, in patients with a LDL-C target level goal < 160 mg, more than 96% reached their target goal without a significant difference between the rosuvastatin- and atorvastatin-treated groups (Fig. 3). The overall achievement rate for NCEP non-HDL-C level target goals after 6 weeks of treatment was 76.08% in the rosuvastatin group and 58.92% in the atorvastatin group (p = 0.067).\n\nBODY.RESULTS.PERCENT CHANGES IN GLUCOSE LEVELS AND INSULIN RESISTANCE:\nPercent changes in glucose levels and insulin resistance at 6 weeks are summarized in Table 3. Changes in glucose and insulin levels were not significantly different between the two groups; however, HbA1c levels were slightly higher in the rosuvastatin group with marginal significance. To evaluate insulin resistance in the two groups, the HOMA index was calculated. At 6 weeks, the HOMA index increased in both groups and the difference between groups was not significant.\n\nBODY.RESULTS.SAFETY:\nBoth rosuvastatin 10 mg and atorvastatin 10 mg were well tolerated, with similar incidences of adverse events. During the treatment period, 13 subjects in the rosuvastatin group and 9 subjects in the atorvastatin group reported adverse events (Table 4). The most frequent adverse events in the rosuvastatin group were edema and dizziness, both with incidences of 1.16%. Only five adverse events were reported in the atorvastatin group as related to the study drug; myalgia was reported in one case (0.56%). All adverse events were mild, developed within 2 weeks after starting treatment, had no action taken, and resolved spontaneously. No drug-related adverse effects were observed in the rosuvastatin group. Also, no patient had an increase in alanine aminotransferase level > 3 times the upper limit of normal or rhabdomyolysis.\n\nBODY.RESULTS.PREDICTORS FOR LDL-C LEVEL GOAL ACHIEVEMENT AT 6 WEEKS:\nOverall, the percentage of patients who reached NCEP ATP III LDL-C target level goals was higher in the rosuvastatin group as compared to the atorvastatin group. Univariate analysis showed that patients with target LDL-C levels at 6 weeks tended to be rosuvastatin-treated and have coronary artery disease. Multivariate logistic regression analyses that included age, gender, statin, coronary artery disease, hypertension, body mass index, waist circumference, baseline total cholesterol levels, and triglyceride levels showed that rosuvastatin treatment, the presence of coronary artery disease, female gender, lower total cholesterol level, and lower LDL-C levels at baseline were independent predictors for achievement of target LDL-C levels at 6 weeks (Table 5).\n\nBODY.DISCUSSION:\nThis study evaluated the comparative efficacy of the lowest doses available for two effective statins, rosuvastatin and atorvastatin, in Korean patients with nondiabetic metabolic syndrome. Rosuvastatin 10 mg was more effective than atorvastatin 10 mg in reducing LDL-C levels in subjects with nondiabetic metabolic syndrome after 6 weeks of treatment. Consistent with the greater reductions in LDL-C levels, more patients in the rosuvastatin group achieved LDL-C level goals as compared to the atorvastatin group. Otherwise, no significant difference was observed in glucose levels and insulin resistance. Metabolic syndrome, especially in the presence of high LDL-C levels, is already known to increase the risk of cardiovascular mortality and morbidity [13]. Statins are effective in decreasing LDL-C levels in patients with dyslipidemia. Survey studies have demonstrated that in real-world settings, only 67% of patients with treated dyslipidemia reach their LDL-C target level goals [14]. In this study, rosuvastatin treatment was associated with reaching recommended LDL-C level goals in a higher percentage of patients overall as compared to atorvastatin (87.6 vs. 69.9%). In particular, rosuvastatin was more effective in patients requiring more intensive LDL-C level lowering to less than 100 or 130 mg/dL. In high-risk patients with stronger targets of LDL-C levels < 100 mg/dL, rosuvastatin brought 83% of patients in this trial to the ATP III LDL-C level goal, which was higher than achieved in other studies conducted in South-Asian (76%) and Hispanic-American (61%) patients [15,16]. Both statins, however, were effective in patients with high target LDL-C level goals < 160 mg/dL. These data highlight the importance of using highly effective statins in high-risk patients to enable them to achieve their lower NCEP ATP III LDL-C level goals. With respect to other elements of the lipid profile, improvements in total cholesterol, apolipoprotein B, and non-HDL-C levels were also significantly greater with rosuvastatin as compared to atorvastatin, whereas changes in HDL-C, triglyceride, and apolipoprotein A1 levels were similar in both treatment groups. Unlike other studies in which rosuvastatin effectively raised HDL-C levels [9,15], HDL-C levels in this study were not effectively improved in either group [9]. Metabolic syndrome is associated with an increased risk of both insulin resistance and diabetes [17]. Additionally, changes in the insulin resistance index were investigated by evaluating the HOMA index, which is a positive predictor of metabolic syndrome [18]. Studies in an animal model of insulin resistance suggest that rosuvastatin treatment increases whole-body and peripheral tissue insulin sensitivity via improved cellular insulin signal transduction [19]. In contrast, in our study conducted in nondiabetic subjects, a tendency was detected for an increased HOMA index in both treatment arms. Major changes in this parameter were attributable to high increases in insulin concentrations. The degrees of percent change in fasting glucose, insulin concentrations, and HOMA index were not significantly different between the rosuvastatin and atorvastatin treatment groups. Thus, further studies are needed to elucidate the effects of statins on glucose metabolism, insulin secretion, and insulin sensitivity under diabetic or nondiabetic conditions. A multivariate analysis was performed to determine independent predictors of LDL-C goal achievement at 6 weeks. Overall, sex, the presence of coronary artery disease, LDL-C levels, and rosuvastatin treatment were predictive of target LDL-C achievement. Among these factors, rosuvastatin was the strongest predictor, with an odds ratio of 3.26. Moreover, the presence of coronary artery disease was an independent predictor of achieving target LDL-C levels. These patients were assumed to have been more likely to take interest in diet control or exercise than patients without coronary artery disease. Although the findings of this study are provocative, this study has important limitations. Recently, intensive regimens with 80 mg of atorvastatin or 20 mg of rosuvastatin have become available in Korea and produce greater reductions in atherosclerotic lipoprotein levels, which is particularly useful in patients with established coronary artery disease or acute coronary syndrome. Further studies comparing statins across dose ranges in patients not reaching their target goal with low-dose statins are required. Additionally, although changes metabolic parameters were not the primary endpoint of this study, a trend toward differences in blood glucose levels was observed between the two statins. Further studies are needed to elucidate the metabolic effects of statins. In conclusion, this study demonstrated that rosuvastatin 10 mg is significantly more effective than atorvastatin 10 mg in reducing LDL-C levels in patients with nondiabetic metabolic syndrome, especially among those with lower NCEP ATP III target level goals. Both statins were well tolerated.\n\n**Question:** Compared to Atorvastatin what was the result of Rosuvastatin on Apolipoprotein-B levels after 6 weeks of treatment?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
515
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Comparative Study of Low Doses of Rosuvastatin and Atorvastatin on Lipid and Glycemic Control in Patients with Metabolic Syndrome and Hypercholesterolemia\n\n ABSTRACT.BACKGROUND/AIMS:\nThis multicenter, open-labeled, randomized trial was performed to compare the effects of rosuvastatin 10 mg and atorvastatin 10 mg on lipid and glycemic control in Korean patients with nondiabetic metabolic syndrome.\n\nABSTRACT.METHODS:\nIn total, 351 patients who met the modified National Cholesterol Education Program Adult Treatment Panel III (NCEP ATP III) criteria for metabolic syndrome with low-density lipoprotein cholesterol (LDL-C) levels ≥ 130 mg/dL were randomized to receive either rosuvastatin 10 mg (n = 173) or atorvastatin 10 mg (n = 178) for over 6 weeks.\n\nABSTRACT.RESULTS:\nAfter 6 weeks of treatment, greater reductions in total cholesterol (- 35.94 ± 11.38 vs. - 30.07 ± 10.46%, p < 0.001), LDL-C (48.04 ± 14.45 vs. 39.52 ± 14.42%, p < 0.001), non-high-density lipoprotein cholesterol (- 42.93 ± 13.15 vs. - 35.52 ± 11.76%, p < 0.001), and apolipoprotein-B (- 38.7 ± 18.85 vs. - 32.57 ± 17.56%, p = 0.002) levels were observed in the rosuvastatin group as compared to the atorvastatin group. Overall, the percentage of patients attaining the NCEP ATP III goal was higher with rosuvastatin as compared to atorvastatin (87.64 vs. 69.88%, p < 0.001). Changes in glucose and insulin levels, and homeostasis model assessment of insulin resistance index were not significantly different between the two groups. The safety and tolerability of the two agents were similar.\n\nABSTRACT.CONCLUSIONS:\nRosuvastatin 10 mg was more effective than atorvastatin 10 mg in achieving NCEP ATP III LDL-C goals in patients with nondiabetic metabolic syndrome, especially in those with lower NCEP ATP III target level goals.\n\nBODY.INTRODUCTION:\nMetabolic syndrome consists of a group of cardiovascular risk factors, namely dyslipidemia, high blood pressure (BP), abdominal obesity, and insulin intolerance, whose concurrent appearance increases the risk of atherosclerotic cardiovascular disease [1]. Using the modified National Cholesterol Education Program (NCEP) Expert Panel on Detection, Evaluation, and Treatment of High Blood Cholesterol in Adults (Adult Treatment Panel III [ATP III]) criteria, the prevalence of atherosclerotic cardiovascular disease is estimated to be as high as 24.8% in Korea and is continuing to rapidly increase to epidemic proportions [2]. Elevated cholesterol levels have also been shown to be a strong risk factor for the development of coronary heart disease (CHD). This clustering of risk factors may interact synergistically to affect atherosclerosis and cardiovascular events [3]. Current guidelines for lipid management stress the importance of low-density lipoprotein cholesterol (LDL-C) levels as the primary goal of therapy [4]; however, a high proportion of patients, especially those having high lipid levels, do not achieve their target LDL-C levels despite lipid-lowering therapy [5,6]. Statins effectively lower blood cholesterol levels and reduce the risk of cardiovascular events in many patient types, and are therefore recommended as first-line agents for lowering LDL-C levels [4,7]. Statins also improve other aspects of the lipid profile, such as increasing high-density lipoprotein cholesterol (HDL-C) and lowering triglyceride levels to some extent. Rosuvastatin is a highly effective HMG-CoA reductase inhibitor, which was registered in 2002 in Korea. Rosuvastatin use has been previously shown in numerous studies to be associated with greater LDL-C level reductions as compared to atorvastatin, simvastatin, or pravastatin use [8-10]. The primary objective of the current trial was to compare the effects of rosuvastatin 10 mg with that of atorvastatin 10 mg, which are the lowest-dose tablets available, on the percentage of patients who reach the NCEP ATP III LDL-C goal and safety in subjects with nondiabetic metabolic syndrome after 6 weeks of treatment. The secondary objective was to compare the effects of rosuvastatin with that of atorvastatin on glucose control and insulin resistance.\n\nBODY.METHODS.STUDY DESIGN:\nThis 6-week, multicenter, randomized, open-label, parallel-group, single-dose trial (NCT00335699) was designed to compare the efficacy of a single dose of rosuvastatin and atorvastatin in patients having nondiabetic metabolic syndrome with dyslipidemia (Fig. 1). The study was conducted from August 2005 to January 2006 at 20 medical centers in Korea. The study included a 6-week dietary run-in period before randomization, followed by a 6-week treatment phase. Subjects entering the run-in period were asked to follow the NCEP Step I diet and required to discontinue any previous lipid lowering therapy. Following the dietary lead-in period, patients with fasting LDL-C levels ≥ 130 mg/dL to < 220 mg/dL were selected and randomly assigned to two parallel treatment groups. At baseline, eligible subjects were randomized 1 : 1 to receive either rosuvastatin (Astra-Zeneca Korea, Seoul, Korea) 10 mg or atorvastatin (Pfizer Pharmaceuticals Korea, Seoul, Korea) 10 mg once daily at bedtime for 6 weeks. The study drug was discontinued and subjects were removed from the study if they withdrew informed consent, became pregnant, or developed creatine kinase levels greater than 10 times the upper normal limit. The ethics committees and institutional review boards at each participating hospital approved the study protocol. All patients provided informed consent to participate in this study.\n\nBODY.METHODS.SUBJECTS:\nPatients were ≥ 18 years of age and had nondiabetic metabolic syndrome. Metabolic syndrome was defined according to the modified NCEP ATP III criteria [11], which requires at least three of the following: abdominal obesity (waist circumference): men > 90 cm (36 inches), women > 80 cm (32 inches); triglyceride levels ≥ 150 mg/dL (1.70 mmol/L); HDL-C levels: men < 40 mg/dL (1.04 mmol/L) and women < 50 mg/dL (1.3 mmol/L); BP ≥ 130 / ≥ 85 mmHg or subject receiving antihypertensive treatment; and fasting blood glucose 110 mg/dL (6.11 mmol/L) to 125 mg/dL (6.94 mmol/L). Patients were excluded if they were pregnant or had malignancy. Additional exclusion criteria included diabetes, and active arterial disease such as unstable angina, myocardial infarction, cerebrovascular accident, coronary artery bypass surgery, or angioplasty within 2 months prior to enrollment. After completing the 6-week dietary run-in period, fasting LDL-C concentrations were required to be ≥ 130 mg/dL (3.36 mmol/L) to < 220 mg/dL (5.69 mmol/L) and fasting triglyceride levels were required to be < 400 mg/dL (4.52 mmol/L).\n\nBODY.METHODS.ASSESSMENTS:\nSample analysis for efficacy endpoints was performed in the Green Cross Reference Laboratory, Yongin, Korea, which was certified by the American College of Pathology (LAP No. 6708401) and the National Committee for Clinical Laboratory Standards. Blood samples from patients who had fasted for 12 hours were collected at all investigational sites and delivered by courier to the central laboratory within 24 hours of blood draw. To assess the primary efficacy endpoint, lipid parameters such as total cholesterol, LDL-C, HDL-C, and triglyceride levels were measured during the dietary lead-in period, at randomization, and 6 weeks after treatment. Additionally, levels of apolipoprotein A-1 and B, high-sensitivity C-reactive protein (hsCRP), insulin, glucose, and hemoglobin A1c (HbA1c) were measured at randomization and at 6 weeks after treatment. LDL-C levels were calculated using the Friedewald equation (LDL-C = total cholesterol - (HDL-C + triglyceride/5). The insulin resistance index was estimated using the homeostasis model assessment (HOMA) for insulin resistance based on the following formula: fasting serum insulin (μU/mL) × fasting plasma glucose (mmol/L)/22.5. According to the NCEP ATP III guidelines, the goal LDL-C level for each patient and the proportion of patients achieving the goal in each group was assessed. Persons with CHD or CHD risk equivalent (Framingham 10-year CHD risk > 20%) had a LDL-C level goal of < 100 mg/dL. Those with multiple risk factors had a LDL cholesterol level goal of < 130 mg/dL and those with 0 - 1 risk factor (s) had a goal LDL cholesterol of < 160 mg/dL. Individual demographic data, physical findings, vital signs, and adverse events were evaluated and recorded in the given case record form. To evaluate adverse events, various laboratory assessments including blood counts, and hemoglobin, aspartate aminotransferase, alanine aminotransferase, creatine kinase, electrolyte, and creatinine levels were performed at each time point.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nOne-hundred and forty-three evaluable subjects per treatment group were required to achieve 95% power for detecting a clinically significant difference of 6% at the 5% two-sided level in percentage change from baseline in LDL-C levels at 6 weeks with an assumed standard deviation of 14% [12]. Assuming a dropout rate of 20% during the randomized treatment period, approximately 180 subjects were recruited to each active treatment group. To obtain the required number of randomized subjects (360 in total), approximately 900 subjects were assumed to be needed for screening based on a screening failure rate of 60%. The primary analysis population was the last observation carried forward on the intention-to-treat population. This included all subjects with a baseline and at least one post-baseline lipid level measurement. All numeric variables were expressed as the mean ± SEM (standard error of the mean). Efficacy endpoints were analyzed using the unpaired t-test for continuous variables and Pearson's chi-square test for frequencies with 95% confidence intervals. Multivariate logistic regression analysis was used to evaluate the predictors for reaching target NCEP ATP III LDL-C levels after treatment. Variables used for analysis included the statin used, presence of coronary artery disease and hypertension, body mass index, gender, age, waist circumference, and lipid parameters. On the basis of the actual treatment received, safety data were evaluated for all patients who received at least one dose of study medication.\n\nBODY.RESULTS.SUBJECT CHARACTERISTICS:\nIn total, 645 subjects were screened for participation in this study. Of them, 370 patients entered the dietary lead-in phase and 351 patients met the inclusion criteria and were randomly assigned to treatment with either rosuvastatin 10 mg or atorvastatin 10 mg (Fig. 1). One patient was lost to follow-up and had no safety assessment. Table 1 shows demographic data and baseline characteristics of all 350 subjects who took at least one dose of the study drug at baseline. In terms of demographic data and baseline characteristics, no statistically significant differences existed between the two treatment groups. Patients had a mean age of 60 years in the rosuvastatin group and 58 years in the atorvastatin group. Mean body weights were 66 kg in the rosuvastatin group and 66 kg in the atorvastatin group. Mean systolic and diastolic BP and waist circumstance were comparable between the two groups (Table 1). A total of five patients dropped out before efficacy assessment. Data from 346 patients were analyzed for efficacy in the intention-to-treat population defined as those who took at least one dose of study drug and had lipid levels checked at baseline and follow-up. Safety assessments were performed in 350 patients who were randomized and available for follow-up.\n\nBODY.RESULTS.CHANGES IN METABOLIC PARAMETERS:\nLipid levels, glucose levels, insulin resistance indices, and hsCRP levels at baseline and 6 weeks are shown in Table 2. In each group, atherogenic lipid parameters including total cholesterol, LDL-C, triglyceride, non-HDL-C, and apolipoprotein B had significantly decreased after 6 weeks of treatment (p < 0.001 vs. baseline). Only the atorvastatin treatment produced a modest decrease in HDL-C. Rosuvastatin treatment significantly increased HbA1c and the HOMA index; however, no significant change occurred in the atorvastatin group. Data from two groups were analyzed for an efficacy comparison in the intention-to-treat population. Baseline values of all parameters were similar between the two groups. At 6 weeks after treatment, rosuvastatin 10 mg produced a significantly greater reduction in total cholesterol, LDL-C, non-HDL-C, and apolipoprotein B levels. Otherwise, no significant differences were detected in HDL-C and apolipoprotein A-1 levels between the two groups. In addition, no significant differences were observed with respect to glucose, HbA1c, and hsCRP levels, and HOMA index between the rosuvastatin and atorvastatin groups at 6 weeks (Table 2). At 6 weeks, LDL-C absolute values decreased by 48.04 ± 14.45 mg/dL in the rosuvastatin group and by 39.52 ± 14.42 mg/dL in the atorvastatin group; the former reduction associated with rosuvastatin use was significantly larger than that with atorvastatin (p < 0.0001). Percent changes from baseline in lipid profiles after treatment for 6 weeks, including LDL-C, are shown in Fig. 2. Reductions in total cholesterol (- 35.94 ± 11.38 vs. - 30.07 ± 10.46%, p < 0.0001), non-HDL-C (- 42.93 ± 13.15 vs. - 35.52 ± 11.76%, p < 0.0001), and apolipoprotein B (- 38.7 ± 18.85 vs. - 32.57 ± 17.56%, p = 0.0019) levels were larger in the rosuvastatin group as compared to the atorvastatin group (Fig. 2).\n\nBODY.RESULTS.LDL-C TARGET ACHIEVEMENT:\nAccording to the reported CHD or/and CHD risk equivalents and/or number of risk factors and/or Framingham 10-year risk, the NCEP ATP III LDL-C target goal was determined in each patient and the success rate in reaching their target goal was analyzed after 6 weeks in each group. The percentage of patients who reached their ATP III LDL-C level goals was higher in the rosuvastatin group (87.6 vs. 69.9%, p < 0.001). Among them, patients having LDL-C target cholesterol level goals of < 100 mg and < 130 mg reached their LDL-C target level goals more frequently in the rosuvastatin group as compared to the atorvastatin group. In contrast, in patients with a LDL-C target level goal < 160 mg, more than 96% reached their target goal without a significant difference between the rosuvastatin- and atorvastatin-treated groups (Fig. 3). The overall achievement rate for NCEP non-HDL-C level target goals after 6 weeks of treatment was 76.08% in the rosuvastatin group and 58.92% in the atorvastatin group (p = 0.067).\n\nBODY.RESULTS.PERCENT CHANGES IN GLUCOSE LEVELS AND INSULIN RESISTANCE:\nPercent changes in glucose levels and insulin resistance at 6 weeks are summarized in Table 3. Changes in glucose and insulin levels were not significantly different between the two groups; however, HbA1c levels were slightly higher in the rosuvastatin group with marginal significance. To evaluate insulin resistance in the two groups, the HOMA index was calculated. At 6 weeks, the HOMA index increased in both groups and the difference between groups was not significant.\n\nBODY.RESULTS.SAFETY:\nBoth rosuvastatin 10 mg and atorvastatin 10 mg were well tolerated, with similar incidences of adverse events. During the treatment period, 13 subjects in the rosuvastatin group and 9 subjects in the atorvastatin group reported adverse events (Table 4). The most frequent adverse events in the rosuvastatin group were edema and dizziness, both with incidences of 1.16%. Only five adverse events were reported in the atorvastatin group as related to the study drug; myalgia was reported in one case (0.56%). All adverse events were mild, developed within 2 weeks after starting treatment, had no action taken, and resolved spontaneously. No drug-related adverse effects were observed in the rosuvastatin group. Also, no patient had an increase in alanine aminotransferase level > 3 times the upper limit of normal or rhabdomyolysis.\n\nBODY.RESULTS.PREDICTORS FOR LDL-C LEVEL GOAL ACHIEVEMENT AT 6 WEEKS:\nOverall, the percentage of patients who reached NCEP ATP III LDL-C target level goals was higher in the rosuvastatin group as compared to the atorvastatin group. Univariate analysis showed that patients with target LDL-C levels at 6 weeks tended to be rosuvastatin-treated and have coronary artery disease. Multivariate logistic regression analyses that included age, gender, statin, coronary artery disease, hypertension, body mass index, waist circumference, baseline total cholesterol levels, and triglyceride levels showed that rosuvastatin treatment, the presence of coronary artery disease, female gender, lower total cholesterol level, and lower LDL-C levels at baseline were independent predictors for achievement of target LDL-C levels at 6 weeks (Table 5).\n\nBODY.DISCUSSION:\nThis study evaluated the comparative efficacy of the lowest doses available for two effective statins, rosuvastatin and atorvastatin, in Korean patients with nondiabetic metabolic syndrome. Rosuvastatin 10 mg was more effective than atorvastatin 10 mg in reducing LDL-C levels in subjects with nondiabetic metabolic syndrome after 6 weeks of treatment. Consistent with the greater reductions in LDL-C levels, more patients in the rosuvastatin group achieved LDL-C level goals as compared to the atorvastatin group. Otherwise, no significant difference was observed in glucose levels and insulin resistance. Metabolic syndrome, especially in the presence of high LDL-C levels, is already known to increase the risk of cardiovascular mortality and morbidity [13]. Statins are effective in decreasing LDL-C levels in patients with dyslipidemia. Survey studies have demonstrated that in real-world settings, only 67% of patients with treated dyslipidemia reach their LDL-C target level goals [14]. In this study, rosuvastatin treatment was associated with reaching recommended LDL-C level goals in a higher percentage of patients overall as compared to atorvastatin (87.6 vs. 69.9%). In particular, rosuvastatin was more effective in patients requiring more intensive LDL-C level lowering to less than 100 or 130 mg/dL. In high-risk patients with stronger targets of LDL-C levels < 100 mg/dL, rosuvastatin brought 83% of patients in this trial to the ATP III LDL-C level goal, which was higher than achieved in other studies conducted in South-Asian (76%) and Hispanic-American (61%) patients [15,16]. Both statins, however, were effective in patients with high target LDL-C level goals < 160 mg/dL. These data highlight the importance of using highly effective statins in high-risk patients to enable them to achieve their lower NCEP ATP III LDL-C level goals. With respect to other elements of the lipid profile, improvements in total cholesterol, apolipoprotein B, and non-HDL-C levels were also significantly greater with rosuvastatin as compared to atorvastatin, whereas changes in HDL-C, triglyceride, and apolipoprotein A1 levels were similar in both treatment groups. Unlike other studies in which rosuvastatin effectively raised HDL-C levels [9,15], HDL-C levels in this study were not effectively improved in either group [9]. Metabolic syndrome is associated with an increased risk of both insulin resistance and diabetes [17]. Additionally, changes in the insulin resistance index were investigated by evaluating the HOMA index, which is a positive predictor of metabolic syndrome [18]. Studies in an animal model of insulin resistance suggest that rosuvastatin treatment increases whole-body and peripheral tissue insulin sensitivity via improved cellular insulin signal transduction [19]. In contrast, in our study conducted in nondiabetic subjects, a tendency was detected for an increased HOMA index in both treatment arms. Major changes in this parameter were attributable to high increases in insulin concentrations. The degrees of percent change in fasting glucose, insulin concentrations, and HOMA index were not significantly different between the rosuvastatin and atorvastatin treatment groups. Thus, further studies are needed to elucidate the effects of statins on glucose metabolism, insulin secretion, and insulin sensitivity under diabetic or nondiabetic conditions. A multivariate analysis was performed to determine independent predictors of LDL-C goal achievement at 6 weeks. Overall, sex, the presence of coronary artery disease, LDL-C levels, and rosuvastatin treatment were predictive of target LDL-C achievement. Among these factors, rosuvastatin was the strongest predictor, with an odds ratio of 3.26. Moreover, the presence of coronary artery disease was an independent predictor of achieving target LDL-C levels. These patients were assumed to have been more likely to take interest in diet control or exercise than patients without coronary artery disease. Although the findings of this study are provocative, this study has important limitations. Recently, intensive regimens with 80 mg of atorvastatin or 20 mg of rosuvastatin have become available in Korea and produce greater reductions in atherosclerotic lipoprotein levels, which is particularly useful in patients with established coronary artery disease or acute coronary syndrome. Further studies comparing statins across dose ranges in patients not reaching their target goal with low-dose statins are required. Additionally, although changes metabolic parameters were not the primary endpoint of this study, a trend toward differences in blood glucose levels was observed between the two statins. Further studies are needed to elucidate the metabolic effects of statins. In conclusion, this study demonstrated that rosuvastatin 10 mg is significantly more effective than atorvastatin 10 mg in reducing LDL-C levels in patients with nondiabetic metabolic syndrome, especially among those with lower NCEP ATP III target level goals. Both statins were well tolerated.\n\n**Question:** Compared to Atorvastatin what was the result of Rosuvastatin on Patients attaining the NCEP ATP III goal?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
517
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: A randomized trial of artemether-lumefantrine \n\n ABSTRACT.BACKGROUND:\nThe use of antimalarial drug combinations with artemisinin derivatives is recommended to overcome drug resistance in Plasmodium falciparum. The fixed combination of oral artemether-lumefantrine, an artemisinin combination therapy (ACT) is highly effective and well tolerated. It is the only registered fixed combination containing an artemisinin. The trial presented here was conducted to monitor the efficacy of the six-dose regimen of artemether-lumefantrine (ALN) in an area of multi-drug resistance, along the Thai-Myanmar border.\n\nABSTRACT.METHODS:\nThe trial was an open-label, two-arm, randomized study comparing artemether-lumefantrine and mefloquine-artesunate for the treatment of uncomplicated falciparum malaria with 42 days of follow up. Parasite genotyping by polymerase chain reaction (PCR) was used to distinguish recrudescent from newly acquired P. falciparum infections. The PCR adjusted cure rates were evaluated by survival analysis.\n\nABSTRACT.RESULTS:\nIn 2001–2002 a total of 490 patients with slide confirmed uncomplicated P. falciparum malaria were randomly assigned to receive artemether-lumefantrine (n = 245) or artesunate and mefloquine (n = 245) and were followed for 42 days. All patients had rapid initial clinical and parasitological responses. In both groups, the PCR adjusted cure rates by day 42 were high: 98.8% (95% CI 96.4, 99.6%) for artemether-lumefantrine and 96.3% (95% CI 93.1, 98.0%) for artesunate-mefloquine. Both regimens were very well tolerated with no serious adverse events observed attributable to either combination.\n\nABSTRACT.CONCLUSION:\nOverall, this study confirms that these two artemisinin-based combinations remain highly effective and result in equivalent therapeutic responses in the treatment of highly drug-resistant falciparum malaria.\n\nBODY.INTRODUCTION:\nMulti-drug resistance of Plasmodium falciparum is a major health problem in many countries and the number of drugs available, effective and affordable is very limited [1]. Along the Thai-Myanmar border, P. falciparum has developed resistance to almost all available antimalarials [2]. As in tuberculosis and HIV where resistance to drugs is a serious issue, combination therapy has been applied to malaria treatment [3]. The use of antimalarial drug combinations with artemisinin derivatives has been advocated and is now implemented in many countries [4]. An extensive amount of information on efficacy and safety of mefloquine has been reported and reviewed [5]. Artemisinin or Qinghaosu is an extract of the medical plant Qinghao (Artemisia annua), which together with its derivatives, artesunate and artemether are the most active antimalarial compounds to date [6]. The artemisinin derivatives have a rapid onset of therapeutic effect, where a single dose can reduce the parasite biomass by a factor of approximately 104 every 48 hours. In addition, they have a very short terminal elimination half-life of less than 2 hours [7]. Previous studies showed that once-daily administration with artemisinin derivatives produced equivalent cure rates to more frequent administration [8]. A three-day course of artesunate combined with high dose mefloquine has become the standard treatment combination for P. falciparum infections in Thailand [9]. Oral artesunate-mefloquine is the most widely used combination. More recently, a fixed combination of oral artemether-lumefantrine (formerly known as benflumetol) has become available. Artemether is a methyl-ether derivative of artemisinin. Lumefantrine is a racemic fluorine derivative with high blood schizontocidal activity [10]. Both artemisinin combination therapies (ACT) are highly effective and well tolerated [11]. However, resistance to mefloquine and/or to lumefantrine, would compromise both combinations. Therefore it is important to monitor the therapeutic efficacy and thus provide advance warning in case of change. The trial presented here was conducted to monitor the efficacy of the six-dose regimen of artemether-lumefantrine combination given over three days for the treatment of uncomplicated P. falciparum infections in adults and children on the western border of Thailand.\n\nBODY.PATIENTS AND METHODS:\nThis study was conducted in the Maela and Mawker Tai malaria clinics of the Shoklo Malaria Research Unit (Mae Sot, Thailand)between July 2001 and June 2002. Patients were recruited from two populations: displaced people of the Karen ethnic minority and migrant workers living on the western border of Thailand. This is an area of low and unstable transmission of Plasmodium vivax and multi-drug-resistant P. falciparum [12]. The trial was an open-label, two-arm, randomized study comparing artemether-lumefantrine andmefloquine-artesunate. This study was approved by the Ethical and Scientific Committees of the Faculty of Tropical Medicine, Mahidol University.\n\nBODY.PATIENTS AND METHODS.PROCEDURES:\nPatients >10 kg in weight who had slide-confirmed acute P. falciparum malaria were included in the study, provided that they or their guardians gave fully informed written consent intheir own language, they were not pregnant, they had not received mefloquine in the previous 63 days and there were no other clinical or laboratory signs of severe illness and/or severe and complicated malaria [13]. If they gave written informed consent, they were allocated randomly to receive either the six-dose regimen of artemether-lumefantrine (Coartem® 20/120, Novartis Pharma AG, Basel, Switzerland) or mefloquine (Lariam®, Hoffman-La Roche, Basel, Switzerland) plus artesunate (Guilin Pharmaceutical Factory No.1, Guilin, China). At enrolment (Day 0), a medical history was obtained, a full physical examination was performed and blood was taken for quantitative parasite counts and routine haematology (finger prick blood sample for malaria smear and haematocrit). All information was recorded on a standard case record form. All patients were examined and blood smears were taken daily until they became aparasitaemic, and then weekly for 6 weeks. At each visit a questionnaire on adverse events was completed. A blood smear was also taken from any patient complaining of fever or symptoms compatible with malaria during the follow-up period. Parasite counts were determined on Giemsa-stained thick and thin blood films. The person-gametocyte-weeks were calculated per 1,000 person-weeks after excluding the episodes on admission and during treatment.\n\nBODY.PATIENTS AND METHODS.DRUG REGIMENS:\nComputerized randomization was in blocks of ten. Patients allocated to artemether-lumefantrine group (ALN) received the tablets at 0 and 8 hours and twice daily for the following 2 days. Artemether-lumefantrine was dispensed as a fixed dose combination tablet. Each tablet contained 20 mg of artemether and 120 mg of lumefantrine. The number of tablets was given according to the body weight. The minimum dosage for patients weighing less than 15 kg was one tablet per dose; patients between 15 and 24 kg received two tablets, those between 25 and 34 kg received three tablets and patients 35 kg and above were treated with four tablets per dose. Patients allocated to artesunate-mefloquine group (MAS3) received artesunate, 4 mg/kg oncedaily for 3 days (day 0 was the first day of treatment), plus mefloquine, 15 mg/kg on day 1 and 10 mg/kg on day 2. Each patient was given antipyretics and cooled by tepid sponging if the tympanic temperature was equal or above 37.5°C before drug administration. Drug administration was observed in all patients and if vomiting occurred in less than 30 min, administration of the full dose was repeated, if vomiting occurred between 30 and 60 min, half the dose was repeated. Patients treated with artemether-lumefantrine were given a glass of chocolate milk (200 ml) with each dose to increase absorption [14].\n\nBODY.PATIENTS AND METHODS.OUTCOME MEASURES:\nThe primary therapeutic outcome measure in this study was the incidence of microscopically and genotypically confirmedrecrudescent infections in both treatment groups by day 42. Parasite genotyping by the polymerase chain reaction (PCR) was used to distinguish recrudescent from newly acquired P. falciparum infections. P. falciparum infections were genotyped for allelic variation in three polymorphic antigen loci, merozoite surface proteins 1 and 2 (MSP-1 and MSP-2) and glutamate rich protein (GLURP), on admission and in case of parasite reappearance [15,16]. Secondary measures were the immediate treatment responses: parasite clearance, fever clearance, incidence of adverse events, and degree of anaemia. The sample size was calculated to detect a difference in failure rates of 7 % between the two regimens with 90% CI and 80 % power assuming a 20% drop out.\n\nBODY.PATIENTS AND METHODS.ADVERSE EVENTS:\nAdverse events were symptoms or signs that were not presenton admission and that developed after the start of treatment. All adverse events, including those probably related to malaria, were recording and compared among treatment groups. The rates of early vomiting (<1 h) after each dose and for each drug wererecorded and compared among the groups in the analysis.\n\nBODY.PATIENTS AND METHODS.MANAGEMENT OF RECRUDESCENT INFECTIONS:\nPatients with uncomplicated recrudescent infections were re-treated with artesunate, 2 mg/kg/day for 7 days; patients >8 years oldalso received doxycycline, 4 mg/kg/day for 7 days.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSIS:\nData were analysed using SPSS for Windows, version 11. Categorical data were compared using the Chi-square test with Yates' correction or by Fisher's exact test, as appropriate. Continuous variables conforming to a normal distribution were compared using Student's t test. Data not normally distributed were log-transformed or compared using the Mann-Whitney U test. The relative risks were calculated using cross-tabulations. The rates of adverse events at three different periods (days 1–2, days 3–7 and days 14–42) were compared among treatment groups. For each of the three periods, the events were counted only once (e.g., if a patient vomited on day one and day two, this was counted as one adverse event). The PCR-adjusted cure rates were evaluated by survival analysis and compared using the log-rank test. Patients for whom PCR genotyping was either inconclusive or missing were censored in the survival analysis on the day of parasite reappearance. For all statistical tests the significance level (p) was set at 0.05.\n\nBODY.RESULTS:\nFour hundred and ninety patients with uncomplicated P. falciparum infections were enrolled between July 2001 and May 2002. The artesunate-mefloquine and artemether-lumefantrine groups included 245 patients each, the age range for all patients was 2–72 years. Baseline characteristics were similar in both groups (Table 1). In total, 484 patients (242 each group) were included in the final evaluation. Six patients (three in each group) were excluded for the following reasons; withdrew consent (1), non-compliance e.g. failure to complete trial treatment course (4), failure to meet protocol criteria (1). Overall compliance was good; around 99% of the patients in the study (481 of 484) were seen at the day seven scheduled visit, 96.1% (465 patients) were seen at day 28 and 93.4% (452 patients) were seen at day 42. Table 1 Demographic and baseline characteristics ALN* (n = 245) MAS3** (n = 245) Maela 100 100 Mawker Tai 145 145 Males, no. (%) 172 (70) 164 (67) Age, years Mean (SD) 23.2 (14.6) 23.6 (15.1) Range 3–70 2–72 Age group, no. (%) <5 10 (4.1) 8 (3.3) 5–14 81 (33.1) 75 (30.6) >14 154 (62.9) 162 (66.1) Weight, kg Mean (SD) 42.4 (14.5) 42.3 (15.0) Range 10–77 10–78 Temperature, °C Mean (SD) 37.7 (1.0) 37.8 (1.1) Range 35.6–40.5 35.9–41.0 Fever a , no (%) 136 (55.5) 142 (58.0) Haematocrit, % Mean (SD) 36.7 (5.9) 36.4 (5.8) Range 21–52 20–51 Geometric mean (range) 8,047 7,570 parasite count (μl -1 ) (32–198,789) (16–198,789) Hepatomegaly, no (%) 48 (19.6) 50 (20.4) Splenomegaly, no (%) 70 (28.6) 57 (23.3) * ALN = artemether-lumefantrine, ** MAS3 = artesunate-mefloquine a Tympanic temperature ≥ 37.5°C \n\nBODY.RESULTS.CLINICAL AND PARASITOLOGICAL FINDINGS:\nThe initial responses to the two treatment groups were similar. None of the patients developed severe malaria. On admission, 55.0% (133/242) of the patients on ALN and 57.9% (140/242) of the patients in the MAS3 group had a tympanic temperature ≥ 37.5°C. All except three patients had a normal temperature on day 3 (2 in ALN and 1 in MAS3). There was no difference in fever clearance times between the two treatment groups (Figure 1). Parasite clearance times were short and most patients cleared their parasitaemia by day two. Figure 2 shows the percentage of patients with positive slide for asexual P. falciparum in both groups. By day three, four (1.8%) of 227 patients in the artemether-lumefantrine recipients and three (1.3%) of 238 artesunate-mefloquine recipients still had a positive blood film (P > 0.05). Overall, 12.3 % of patients were anaemic (haematocrit <30%) on admission, 10.8% in ALN group and 13.8% in MAS3 group (P = 0.33). The mean (SD) decrease in haematocrit value at day seven from baseline was greater in the group receiving MAS3 than in the ALN group: 9.3% (SD,11.5%; 95% CI, 7.7% to 10.9%) compared with 6.7% (SD, 11.4%; 95% CI, 5.1 to 8.3%) respectively (P = 0.023). Figure 1Percentage of patients with fever (temperature > 37.5°C). Figure 2Percentage of patients with positive slide for asexual P. falciparum forms. During the 42-day follow-up period, 27 new P. falciparum infections occurred among artemether-lumefantrine and 24 among artesunate-mefloquine recipients (P > 0.05) (Table 2). The PCR-adjusted cure rates by day 42 were 98.8% (95% CI, 96.4% to 99.6%) in the ALN group and 96.3% (95% CI, 93.1% to 98.0%) in the MAS3 group (P = 0.08). PCR confirmed treatment failures were more likely in children aged below 15 years than in adults (RR, 5.1; 95% CI, 1.4–18.7; P = 0.006). The mean age was 13.6 years (n = 12; SD = 8.5) in patients with treatment failure and 23.7 years (n = 438; SD = 15.2) in successfully treated patients. In this trial, only age group was independently associated with treatment failure, but not other factors e.g. higher parasitaemia (>10,000/μL); anaemia (haematocrit <30%); fever (tympanic temp ≥ 37.5°C) on admission; sites; treatment groups; early vomiting (within one hour following drug administration). The mediantime to recrudescence was comparable for MAS3 group (21 days; n = 9; range, 14–28 days) and ALN group (28 days; n = 3; range, 21–42 days; P > 0.05).\n\nBODY.RESULTS.OTHER PARASITOLOGICAL FINDINGS:\nOf 452 patients, 119 (26.3%) had P. vivax parasitaemia detected during follow up. There were significantly fewer cases of vivax malaria in the MAS3 group (29 of 227) than in the ALN group (90 of 225) (P < 0.001). The median time to appearance of P. vivax parasitaemia was longer in the MAS3 group (40 days; range, 13–43 days) than in the ALN group (28 days; range, 14–43 days; P < 0.001). Twenty patients (8.3%) in the artemether-lumefantrine group and 19 (7.9%) in the artesunate-mefloquine group had gametocytes detected during the first 3 days. All except one patient in ALN group cleared gametocytes within first week after start of treatment. After excluding these, gametocytes developed (between day 7 and 42) in 1.2% (3/241) of ALN group and 1.3 (3/240) of MAS3 group. The person-gametocyte weeks were low and similar: 2.7 (95% CI, 0.6–7.8) per 1000 person-weeks for both groups.\n\nBODY.RESULTS.ADVERSE EVENTS:\nBoth treatment regimens were well tolerated. No serious adverse events were reported. Overall, 5/242(2.1%) of the patients vomited one or more doses of medication in the ALN group and 2/242(0.8%) of the MAS3 treated patients (RR, 2.5; 95% CI, 0.5–12.7; P = 0.45). The rates of early vomiting (within one hour) of the drugs were very low (around 2%) and did not differ among groups (one in each group on day 2). The most commonly reported and possibly drug-related adverse events to both combination therapies were effects on the gastrointestinal (abdominal pain, anorexia, nausea, diarrhoea and late vomiting e.g. >1 h after administration of treatment) and central nervous system (headache, dizziness). Figure 3 shows the proportions of possibly drug-related adverse events of those who did not have those symptoms at admission during follow-up in both groups. Overall, there were less adverse events in ALN group compared to MAS3, though the differences were not statistically significant. Figure 3Possibly drug-related adverse events (day 1 – day 42).\n\nBODY.DISCUSSION:\nThe loss of affordable effective antimalarial drugs to resistance represents a major threat to the people of malaria endemic countries [1]. Using ineffective drugs with high failure rates kills many and is unacceptable. A clear treatment policy and readiness to use the new, more effective artemisinin-based combination therapies (ACT) are crucial [17]. Along the north-western border of Thailand, where highly multi-drug resistant isolates of P. falciparum are found, artesunate-mefloquine combination therapy (MAS3) is the standard treatment regimen for uncomplicated falciparum malaria [9]. Early diagnosis and treatment with an artemisinin-based drug combination of very high efficacy that reduces gametocyte carriage, has led to a marked decline in the incidence of falciparum malaria and a reversal of the previous trend toward increasing mefloquine resistance [18]. Artemisinin derivatives will ensure rapid clinical and parasitological responses and are remarkably effective, hence clinical deterioration is extremely unusual. To optimize therapy, combination with a slower-acting antimalarial drug is required. Systematic use of ACT would help to delay the emergence of resistance if the drug was used widely. However, the continued use of mefloquine monotherapy or with only 2 days of artesunate in this region, provides persistent selective pressure to continue the evolution of mefloquine resistance, which could diminish the efficacy of the artesunate-mefloquine combination and that of artemether-lumefantrine. Artemether-lumefantrine has been introduced recently for oral treatment of uncomplicated falciparum malaria. In Thailand, several trials have been conducted with this combination. The six-dose schedule provides sustained blood lumefantrine levels and thus improved cure rates [11]. Lumefantrine is highly lipophilic and the oral bioavailability varies considerably between individuals and increases greatly if the drug is administered after a meal rich in fat [19]. The present trial reconfirmed the efficacy of the six-dose regimen of artemether-lumefantrine given over three days [20]. Both treatments in this study cleared fever and parasitaemia promptly and reliably. Both treatments were well tolerated and highly effective. Importantly 2/3 less P. vivax infections and 12 days longer median time to appearance of P. vivax parasitaemia in the MAS3 group were most probably due to the longer terminal half-life of mefloquine compared to lumefantrine [21,22]. More data on the safety and efficacy of artemether-lumefantrine in very small children and pregnant women are needed.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nRH carried out the study and analyzed the data. RH, EAA, RMG, PS, TJ, NJW, FN conceived the study, participated in its design and co-ordination and contributed to draft the manuscript. LP, KLT assisted in collection of data. AB performed the PCR experiments. All authors read and approved the final manuscript. Table 2 Treatment response. Treatment group ALN* (n = 245) MAS3** (n = 245) Compliance, no. (%) Completed day 7 241 (99.6%) 240 (99.2%) Completed day 28 232 (95.9%) 233 (96.3%) Completed day 42 225 (93.0%) 227 (93.4%) Cumulative proportion of patients with clinical failure, no (%) Day 7 0 (0) 0 (0) Day 28 13 (5.6) 14 (6.0) Day 42 27 (12.0) 24 (10.6) PCR, no. Novel 23 14 Recrudescent 2 8 Novel + recrudescent 1 1 Indeterminate/missing 1 1 PCR-adjusted cure rates, no. (%) Day 7 0 (100) 0 (100) Day 28 2 (99.1) 9(96.1) Day 42 3 (98.8) 9 (96.3) * ALN = artemether-lumefantrine, ** MAS3 = artesunate-mefloquine\n\n**Question:** Compared to Mefloquine-artesunate what was the result of Artemether-lumefantrine on Adverse events?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
526
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Q-TWiST analysis to estimate overall benefit for patients with metastatic renal cell carcinoma treated in a phase III trial of sunitinib \n\n ABSTRACT.BACKGROUND:\nIn a randomised phase III trial of treatment-naive patients with metastatic renal cell carcinoma, sunitinib showed significant improvement in progression-free survival (PFS) compared with interferon (IFN)-α. We assessed between-treatment differences in overall benefit using a quality-adjusted Time Without Symptoms of disease progression or Toxicity of treatment (TWiST; Gelber and Goldhirsch) analysis.\n\nABSTRACT.METHODS:\nIn this analysis, in which only grade 3/4 treatment-related toxicities were included, overall survival was partitioned into three health states: toxicity (time with toxicity after randomisation and before progression), time without symptoms of disease progression or toxicity, and time from progression until death. Between-treatment differences in the mean duration of each state were calculated. A threshold utility analysis was used to assess quality-adjusted TWiST (Q-TWiST) outcomes.\n\nABSTRACT.RESULTS:\nQ-TWiST scores showed that quality-adjusted survival time was greater with sunitinib than with IFN-α, even though certain grade 3/4 toxicities occurred more frequently with sunitinib. For both treatments, the mean number of days with toxicity was small compared with PFS. This effect was more pronounced with sunitinib in which time spent without progression or toxicity was 151 days greater than with IFN-α.\n\nABSTRACT.CONCLUSION:\nPatients randomised to sunitinib had longer clinical benefit, defined as Q-TWiST scores, than patients randomised to IFN-α.\n\nBODY:\nTargeted treatment with antiangiogenic therapy has become standard of care for the treatment of most patients with metastatic clear cell renal cell carcinoma (mRCC) based upon improvements in progression-free survival (PFS) in several randomised phase III clinical trials (Escudier et al, 2007a, 2007b; Motzer et al, 2007; Sternberg et al, 2010). With more than one choice of therapy available for patients with mRCC, clinical decision making is more complex, and data on other outcomes in addition to efficacy, such as quality of life and safety, have become increasingly important. Most often, treatments are compared by a head-to-head analysis of each trial endpoint separately. For purposes of a primary analysis, this approach is reasonable. However, this approach may not be ideal if there are important tradeoffs between endpoints such as an increased time with side effects of treatment but longer time to progression in one arm compared with the other. One method that allows integration of both the quality and quantity of survival time is the Time Without Symptoms of disease progression or Toxicity of treatment or TWiST analysis, and its extension the quality-adjusted TWiST or Q-TWiST (Gelber and Goldhirsch, 1986; Goldhirsch et al, 1989). The primary hypothesis of these methods is that patients with no disease symptoms or treatment toxicity have better health-related quality of life than those who have disease symptoms and toxicity. Q-TWiST was first used to evaluate adjuvant therapy for breast cancer (Gelber et al, 1991), and has since been widely applied to other settings and cancers (Gelber et al, 1996; Rosendahl et al, 1999; Sherrill et al, 2008; Marcus et al, 2010; Zbrozek et al, 2010). In this paper, we report the results of a Q-TWiST analysis from a phase III randomised clinical trial comparing the oral antiangiogenic compound sunitinib (SUTENT; Pfizer, Inc; New York, NY, USA), with interferon-α (IFN-α) as first-line treatment for patients with mRCC (Motzer et al, 2007; Motzer et al, 2009). In this trial, sunitinib showed superior PFS compared with IFN-α (median PFS 11 vs 5 months, P<0.001); in addition, median overall survival with sunitinib was more than 2 years (26.4 months). In general, more adverse events of all grades were reported in the sunitinib arm than in the IFN-α arm, although the proportion of patients experiencing grade 3 or 4 toxicities was relatively low for both treatment groups. The Q-TWiST analysis was used to simultaneously compare the two treatments in terms of PFS, overall survival, and grade 3 or 4 toxicities.\n\nBODY.MATERIALS AND METHODS.PATIENTS AND STUDY DESIGN:\nThe design and main results of the randomised phase III clinical trial have been reported previously (Motzer et al, 2007; Motzer et al, 2009). In this trial, 750 patients with mRCC were randomised in a 1 : 1 ratio to receive either sunitinib or IFN-α. Key patient eligibility criteria included no previous systemic therapy for RCC, measurable disease, an Eastern Cooperative Oncology Group performance status of 0 or 1, as well as adequate hepatic, renal, and cardiac function. All patients provided signed informed consent. The primary endpoint was PFS. Sunitinib was administered orally at an initial dose of 50 mg per day for 4 weeks, followed by 2 weeks off treatment (Schedule 4/2). IFN-α was administered as a subcutaneous injection on three nonconsecutive days per week, starting at 3 million units (MU) for the first week, 6 MU for the second week, and 9 MU thereafter.\n\nBODY.MATERIALS AND METHODS.STATISTICAL METHODS AND ANALYSIS:\nThe Q-TWiST analysis considered three health states, TOX, TWiST, and REL, and the duration of each state was calculated for every patient. The TOX state comprised the total number of days after randomisation and before progression spent with toxicity, regardless of when the toxicity started or whether there were gaps between toxicities. All grade 3 or 4 toxicities attributable to the study drugs were included in the analysis, apart from those starting after progression. The model included only the more severe toxicities because they were the events considered most likely to have more effect on a patient's quality of life. The type, date of onset, and date of resolution of each toxicity were recorded prospectively as a part of the standard procedure in conducting a randomised phase III trial. Time spent with toxicities unresolved by progression was capped at the date of progression. There were 44 sunitinib and 34 IFN-α patients with unresolved toxicities at the time of progression. It is possible for a patient to have more than one type of toxicity during a period of time. Care was taken so that these overlapping toxicity intervals were not double counted. That is, if a patient had a toxicity that lasted from day 1 to day 5 and another toxicity that lasted from day 1 to day 10, the number of days spent with toxicity was 10 days. The TWiST state was defined as PFS time minus time with toxicities. Progression-free survival time was defined from randomisation to the last date of follow-up or progression. Patients without progression were censored at their last date of follow-up (median follow-up was similar in each treatment arm, being 853 days for sunitinib and 863 days for IFN-α). The duration of the relapse or REL state was defined as overall survival time minus PFS time, or the period of time from progression to death. Patients alive at the end of the study were censored for the overall survival endpoint. The mean time spent in each of the three health states was calculated for each treatment arm separately, and a 95% confidence interval for the difference by treatment was calculated using the nonparametric bootstrap method. Progression-free and overall survival curves were generated using Kaplan–Meier methods, which account for differential follow-up. These curves, along with a curve for time on toxicity, were overlaid on a single graph generated separately for each treatment. We used a threshold utility analysis to assess quality-adjusted or Q-TWiST outcomes, in which the TOX and REL health states are each weighted by utility scores or weights. These weights are represented by μTOX and μREL in the equation below: The utility weights reflect the relative value for the TOX and REL states and range from zero to one, with values closer to one discounting fewer days than those closer to zero for each state. A value of one represents a time period that is denoted by patients as a time of perfect health. Conversely, a value of zero represents a time period that is akin to death. Q-TWiST scores were calculated for a combination of utility weights increasing from zero to one by increments of 0.25.\n\nBODY.RESULTS:\nThere were more reported occurrences of most general adverse events of all grades in the sunitinib arm than in the IFN-α arm (Motzer et al, 2007). Figures 1A and B show survival times partitioned into the three health states over the follow-up period separately for sunitinib and IFN-α. In each graph, the overall survival curve (blue) is partitioned by the Kaplan–Meier curves for PFS (red) and time with treatment toxicity (green). The area between the Kaplan–Meier curves gives the average time spent in each of the three health states. The mean number of days spent with grade 3 or 4 toxicity (i.e., TOX) was 27 days higher among patients in the sunitinib arm than in patients from the IFN-α arm (95% CI: 18, 37; Table 1). However, the mean time spent without symptoms of disease progression or toxicity of treatment (i.e., TWiST) was 151 days higher in the sunitinib than in the IFN-α arm (95% CI: 118, 180; Table 1), and the mean time spent in relapse (i.e., REL) was 96 days lower among patients randomised to sunitinib (95% CI: −126, −56; Table 1). Results from a threshold utility analysis where the TOX and REL health states were weighted from 0 to 1 are provided in Table 2. The difference in Q-TWiST ranged from a maximum of 177 ((95% CI: 146, 212; Table 2) weight for TOX=1 and weight for REL=0) to a minimum of 56 ((95% CI: 16, 102; Table 2) weight for TOX=0 and weight for REL=1). The first scenario reflects the case when a patient's quality of life before progression is unaffected by toxicity, but quality of life after progression is severely affected. The second scenario is a reverse of this, when a patient's quality of life before progression is severely affected, but quality of life after progression is unaffected.\n\nBODY.DISCUSSION AND CONCLUSIONS:\nResults from this phase III trial of sunitinib vs IFN-α showed that sunitinib was superior to IFN-α, based on a longer duration of median PFS; overall survival was also longer with sunitinib than with IFN-α, although the difference did not reach statistical significance (Motzer et al, 2009). The results of exploratory analyses were consistent with the hypothesis that the overall survival endpoint was confounded by crossover treatment and use of alternate anticancer drugs after discontinuation. A total of 25 patients from the IFN-α group crossed over to receive sunitinib on study and one-third (117/359=33%) of the patients from the IFN-α group received post-study treatment with sunitinib. The rate of adverse events was low in both treatment groups, but occurred in more patients treated with sunitinib than with IFN-α. This is likely to be attributable to the much longer average duration of therapy with sunitinib than with IFN-α. Quality-of-life scores as measured by the FACT-G and FKSI questionnaires were higher among patients randomised to sunitinib than among those randomised to IFN-α, with minimal regional variation (Cella et al, 2008; Cella et al, 2010). In this Q-TWiST analysis, we integrated efficacy and safety endpoints, and found that patients on the sunitinib arm spent on average 27 more days with grade 3 or 4 treatment-related toxicity than patients on the IFN-α arm. For both treatment arms, the number of days during which a patient experienced toxicity was low compared with the time during which the average patient remained progression-free. This effect was more pronounced for the sunitinib arm; time spent without progression or toxicity was 151 days greater in the sunitinib than in the IFN-α arm. The Q-TWiST analysis provides a way by which we can compare PFS, overall survival, and time spent without toxicity in the two treatment arms in one metric. Patients can value time spent in relapse and time spent undergoing active therapy differently. For the Q-TWiST analysis, we assigned a range of utility weights to reflect 25 such scenarios. A utility weight of one discounts zero days from a health state, while a utility weight of zero discounts all days from a health state. In our analysis, all utility combinations resulted in positive Q-TWiST treatment differences (sunitinib Q-TWiST–IFN-α Q-TWiST). The difference in scores ranged from 177 to 56 days. Interpreted another way, sunitinib had higher quality-adjusted survival times than IFN-α across the entire range of utility combinations. Revicki et al (2006) recommended that differences in Q-TWiST equal to at least 10% of overall survival should be considered clinically meaningful. Based on the median overall survival of 26.4 months or ∼803 days in the sunitinib arm, a 10% or greater difference corresponds to 80 days or greater. In Table 2, Q-TWiST differences in all scenarios apart from five can be deemed as clinically important. Four of the five smallest differences occurred when time from progression to death or end of study was not discounted (REL weight=1), but time before progression was discounted (TOX weight <1). In this Q-TWiST analysis, we used overall utility weights to reflect the average value patients place on time spent in relapse and time spent experiencing toxicity. However, it is possible that there is heterogeneity in how a specific patient would value time spent with toxicity and time spent from progression to death or end of study. Another limitation of our analysis is that patients progressing on IFN-α were given the choice to crossover to the sunitinib arm. This resulted in 25 patients switching to sunitinib during the study and could affect estimation of the REL health state for the IFN-α arm. Q-TWiST methodology can provide useful advice on treatment choice when PFS differences are significant but overall survival differences are not, as is the case with the sunitinib vs IFN-α trial analysed herein. Applying Q-TWiST methodology to examine progression, overall survival, and toxicity as a single metric showed that sunitinib has a greater quality-adjusted survival time than IFN-α. For sunitinib patients, the greater amount of time spent with a toxicity is offset by far longer PFS. These results support the conclusion that sunitinib offers improved clinical and quality-of-life outcomes compared with IFN-α for mRCC patients.\n\n**Question:** Compared to Interferon (IFN)-α what was the result of Sunitinib on Quality-adjusted survival times?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
535
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: A Randomized Controlled Trial Investigating the Effects of a Low–Glycemic Index Diet on Pregnancy Outcomes in Gestational Diabetes Mellitus\n\n ABSTRACT.OBJECTIVE:\nThe prevalence of gestational diabetes mellitus (GDM) is rising. There is little evidence to demonstrate the effectiveness of one dietary therapy over another. We aimed to investigate the effect of a low–glycemic index (LGI) versus a conventional high-fiber diet on pregnancy outcomes, neonatal anthropometry, and maternal metabolic profile in GDM.\n\nABSTRACT.RESEARCH DESIGN AND METHODS:\nNinety-nine women (age 26–42 years; mean ± SD prepregnancy BMI 24 ± 5 kg/m2) diagnosed with GDM at 20–32 weeks' gestation were randomized to follow either an LGI (n = 50; target glycemic index [GI] ~50) or a high-fiber moderate-GI diet (HF) (n = 49; target GI ~60). Dietary intake was assessed by 3-day food records. Pregnancy outcomes were collected from medical records.\n\nABSTRACT.RESULTS:\nThe LGI group achieved a modestly lower GI than the HF group (mean ± SEM 47 ± 1 vs. 53 ± 1; P < 0.001). At birth, there was no significant difference in birth weight (LGI 3.3 ± 0.1 kg vs. HF 3.3 ± 0.1 kg; P = 0.619), birth weight centile (LGI 52.5 ± 4.3 vs. HF 52.2 ± 4.0; P = 0.969), prevalence of macrosomia (LGI 2.1% vs. HF 6.7%; P = 0.157), insulin treatment (LGI 53% vs. HF 65%; P = 0.251), or adverse pregnancy outcomes.\n\nABSTRACT.CONCLUSIONS:\nIn intensively monitored women with GDM, an LGI diet and a conventional HF diet produce similar pregnancy outcomes.\n\nBODY:\nGestational diabetes mellitus (GDM) is commonly defined as any degree of glucose intolerance with onset or first recognition during pregnancy (1). In developed nations, between 4 and 8% of pregnant women are presently affected (2–4), and the prevalence will rise dramatically if the guidelines of the new International Association of Diabetes in Pregnancy Study Groups (IADPSG) are adopted (3). The main adverse outcome of GDM is excessive fetal growth resulting in higher risk of large-for-gestational-age (LGA) infants (birth weight >90th centile). Higher birth weight has been linked with childhood obesity (5), cardiovascular disease (6), and diabetes (5) later in life. In the medical management of GDM, the primary goal is to maintain maternal blood glucose concentrations, especially postprandial levels, within an acceptable range (7). Interventions that reduce postprandial glucose levels, including dietary strategies such as carbohydrate restriction, have been shown to be effective in reducing LGA and later obesity in type 1 diabetic offspring (8). Postprandial glycemia can be reduced without carbohydrate restriction by slowing down the rate of carbohydrate digestion and absorption. Compared with moderate–or high–glycemic index (GI) foods containing similar amount of carbohydrates, low-GI (LGI) foods have been demonstrated to reduce postprandial glucose in healthy individuals (9). The GI of various foods has been shown to be the same in pregnancy as in the nonpregnant state (10). An LGI meal pattern may therefore represent an alternative strategy for reducing postprandial glycemia in GDM without restricting carbohydrate (11). The effect of an LGI eating pattern on obstetric outcomes in GDM has been little studied. Moses et al. (12) found that a significantly higher proportion of women in the higher-GI group met the criteria to commence insulin compared with women in the LGI group. In addition, 47% of the women in the high-GI group who met the criteria for insulin commencement avoided insulin by switching to an LGI diet. However, they found no significant differences in key fetal and obstetric outcomes. To our knowledge, this study is the first randomized controlled trial to determine the efficacy of an LGI diet versus a conventional healthy diet on pregnancy outcomes in GDM. Our hypothesis was that an LGI diet would reduce birth weight (primary end point), birth weight centile, ponderal index, and the prevalence of LGA infants.\n\nBODY.RESEARCH DESIGN AND METHODS:\nThis study was a two-arm parallel randomized controlled trial based at the Diabetes Antenatal Clinic of the Royal Prince Alfred Hospital, Camperdown, Australia. With the exception of the study dietitian (J.C.Y.L.), who provided the dietary education, all study personnel and participants were blinded to dietary assignment.\n\nBODY.RESEARCH DESIGN AND METHODS.SUBJECT RECRUITMENT, RANDOMIZATION, AND STRATIFICATION:\nWomen aged 18–45 years diagnosed with GDM by a 75-g oral glucose tolerance test at 20–32 weeks' gestation, with an otherwise healthy singleton pregnancy, were eligible for the study. GDM diagnosis was based on the modified Australasian Diabetes in Pregnancy Society (ADIPS) criteria: fasting blood glucose level (BGL) ≥5.5 mmol/L, 1-h BGL ≥10.0 mmol/L, or 2-h BGL ≥8.0 mmol/L. Most women were tested at 26–32 weeks, but testing occurred earlier in those at high risk. Women who had special dietary requirements (including vegetarianism/veganism), preexisting diabetes, or pregnancy achieved by assisted reproduction and those who smoked or consumed alcohol during pregnancy were excluded. A total of 482 women were approached between September 2008 and November 2010, of whom 99 met the inclusion criteria and agreed to participate. The enrolled subjects were centrally randomized to study diet by computer-generated random numbers, stratified by BMI (BMI <30 vs. ≥30 kg/m2) and weeks of gestation (<28 or ≥28 weeks). The allocation sequence was unpredictable and concealed from the recruiter. Participants received routine GDM care regardless of dietary assignment, including instructions to monitor BGL before breakfast and 1 h after meals. The treating endocrinologist (T.P.M. or N.P.) reviewed the subjects every 2–4 weeks prior to 36 weeks and then every week until delivery. Insulin treatment was commenced if the mean fasting BGL or 1-h postprandial BGL in the preceding week exceeded 5.2 and 7.5 mmol/L, respectively.\n\nBODY.RESEARCH DESIGN AND METHODS.DEMOGRAPHICS AND DIETARY ASSESSMENT:\nAt enrollment, demographic information, family history of diabetes, and ethnicity were recorded. Subjects were asked to recall their prepregnancy weight, were weighed, and were asked to complete a 3-day food record (including 2 weekdays and 1 weekend day) at baseline and again at 36–37 weeks' gestation. A two-dimensional food model booklet was provided to the subjects to assist in portion size estimation. Last recorded weight before delivery was obtained from the medical record.\n\nBODY.RESEARCH DESIGN AND METHODS.DIETARY INTERVENTIONS:\nSubjects were randomized to one of two healthy diets of similar protein (15–25%), fat (25–30%), and carbohydrate (40–45%) content—one with an LGI (target GI ≤50) and the other with a high-fiber content and moderate GI, similar to the Australian population average (HF) (target GI ∼60) (13–15). Both study diets provided all essential nutrients for pregnancy other than iron and iodine, which were supplemented as appropriate by the treating endocrinologist. The baseline 3-day food diary provided information on baseline dietary composition and served as the basis of individualized dietary counseling. Sample menus and their nutritional analyses are given in Supplementary Table A1. Subjects attended at least three face-to-face visits with the study dietitian, scheduled to coincide with regular antenatal visits. A 24-h recall of all food and drink intake was conducted during each session to assess compliance. In the case of noncompliance, suitable alternative foods were encouraged. Food sample baskets containing key foods for the assigned diet were provided to promote product recognition and dietary adherence. The content of the sample baskets is listed in Supplementary Table A2.\n\nBODY.RESEARCH DESIGN AND METHODS.DATA COLLECTION:\nSubjects provided blood samples at baseline and ∼36 weeks' gestation. Pregnancy outcomes, including birth weight, infant length, infant head circumference, and the need for emergency caesarean section, were obtained from the electronic medical records system. Gestational age was based on the last menstrual period and early pregnancy ultrasound. Birth weight centile was calculated using a macro program for Microsoft Excel (available from http://www.gestation.net) that adjusted for ethnic differences (16). The calculated birth weight centile was used to categorize the infant as small for gestational age (birth weight <10th centile), normal, or LGA (birth weight >90th centile). Ponderal index, an estimate of neonatal adiposity, was calculated as birth weight in kg × infant length (m)−3. Macrosomia was defined as birth weight >4 kg.\n\nBODY.RESEARCH DESIGN AND METHODS.NUTRITIONAL ANALYSIS AND ASSESSMENT OF COMPLIANCE:\nThe study dietitian entered the food records into Australian nutrition analysis software based on AUSNUT2001 (FoodWorks Professional 2009; Xyris Software, Brisbane, Australia). The GI of individual food items was assigned according to a published method (17). Dietary glycemic load (GL) was calculated as follows: ∑ GI × available carbohydrate of each food in a day/100. Dietary GI was calculated as follows: (dietary GL/total daily available carbohydrate) × 100. Subjects were deemed compliant if their final dietary GI was ≤50 in the LGI group and >50 in the HF group.\n\nBODY.RESEARCH DESIGN AND METHODS.POWER CALCULATION:\nBased on previous data, the study was designed to provide 80% statistical power to detect an ∼260 g difference in birth weight, with 60 subjects in each group. Recruitment was halted at 99 subjects because the SD in birth weight among the study population was smaller than expected. In the primary analysis, the observed SD of 416 g in birth weight provided 80% power to detect a group difference of 246 g in birth weight or an ∼17% point difference in birth weight centile.\n\nBODY.RESEARCH DESIGN AND METHODS.STATISTICAL ANALYSES:\nA biostatistician blinded to the diet allocation performed the statistical analyses. The primary analysis included all women randomized who attended at least one dietary education session but excluded those with preterm delivery (<37 weeks; n = 4; two from each group) regardless of compliance. All statistical analyses were performed with SPSS (version 19; IBM Australia, St. Leonards, Australia). Results for continuous data are reported as mean ± SD or mean ± SEM, and categorical data (e.g., need for insulin) are reported as percentage. Pearson χ2 test was used to test for differences between groups for categorical data, and continuous data were tested using one-way ANOVA. A paired t test was used to assess within-group changes from baseline to final outcomes. The study was conducted according to the guidelines laid down in the Declaration of Helsinki, and all procedures involving human subjects/patients were approved by the Human Research Ethics Committee of the Sydney South West Area Health Service (Royal Prince Alfred Hospital Zone). Informed consent was obtained from all subjects in this study.\n\nBODY.RESULTS:\nThe flow of subjects through the study is shown in Supplementary Fig. 1. Of the 99 subjects recruited, four delivered prematurely (<37 weeks) and three withdrew before the first dietary instruction session, leaving 92 subjects in the primary analysis. Subject characteristics are shown in Table 1. At baseline, subjects in the LGI group had significantly higher 2-h postload blood glucose levels (LGI 8.6 ± 1.2 mmol/L vs. HF 8.0 ± 1.3 mmol/L; P = 0.024) but were otherwise similar to those in the HF group. At baseline, both groups had a relatively LGI diet (LGI 49 ± 1 vs. HF 52 ± 2) (Table 2). At the end of the intervention (36–37 weeks' gestation), the diets were matched for macro- and micronutrients, but the LGI group had a significantly lower GI and GL than the HF group as per protocol (both P < 0.001). Compared with data at baseline, intake of fat, fiber, calcium, iron, zinc, and folate significantly increased in subjects in the LGI group. Subjects in the HF group had increased energy intake and GL but not GI. The results were similar in the secondary analysis of \"compliers\" only except that compliers in the LGI group (n = 30) had significantly decreased their GI, whereas those in the HF group (n = 34) remained unchanged from baseline (data not shown). Table 1 Subject characteristics LGI HF P * n 47 45 — Age (years) 34.0 ± 4.1 32.4 ± 4.5 0.062 Prepregnancy BMI (kg/m 2 ) 23.9 ± 4.4 24.1 ± 5.7 0.837 Ethnicity (%) Asian 59.6 55.6 0.697 Caucasian 31.9 40.0 0.419 Others 8.5 4.4 0.430 Week of gestation at diagnosis 26.1 ± 4.0 26.0 ± 4.3 0.951 Family history of type 2 diabetes (%) Maternal 23.4 20.0 0.692 Paternal 21.3 33.3 0.194 Week of gestation at start of intervention 29.0 ± 4.0 29.7 ± 3.5 0.410 75-g OGTT results (mmol/L) Fasting 4.6 ± 0.5 4.7 ± 0.7 0.279 1 h 9.4 ± 1.4 9.7 ± 1.6 0.501 2 h 8.6 ± 1.2 8.0 ± 1.3 0.024 Nulliparous (%) 61.7 64.4 0.785 Data are mean ± SD except for ethnicity, family history of type 2 diabetes, and nulliparous, which are expressed as percentages. OGTT, oral glucose tolerance test. * P values calculated by one-way ANOVA for continuous variables and Pearson χ 2 for categorical variables. P < 0.05 indicates statistical significance. Table 2 Baseline and end-of-intervention diet analysis Baseline P * End of intervention P * P † LGI HF LGI HF LGI HF n 44 40 42 42 Energy (kJ) 7,240 ± 240 6,630 ± 260 0.089 7,680 ± 260 8,090 ± 300 0.307 0.141 <0.001 Protein (g) 99.2 ± 4.4 93.1 ± 5.4 0.389 107.5 ± 4.2 107.2 ± 5.6 0.971 0.100 0.049 Total fat (g) 70.2 ± 3.7 61.4 ± 3.1 0.073 71.2 ± 3.5 75.3 ± 5.6 0.532 <0.001 0.029 Saturated fat (g) 23.5 ± 1.3 22.3 ± 1.4 0.553 24.2 ± 1.3 28.8 ± 3.1 0.181 0.515 0.090 Monounsaturated fat (g) 27.0 ± 1.7 22.4 ± 1.3 0.035 27.4 ± 1.6 26.8 ± 1.7 0.797 0.887 0.034 Polyunsaturated fat (g) 12.6 ± 0.9 10.1 ± 0.7 0.032 13.5 ± 0.8 12.5 ± 1.3 0.488 0.465 0.065 Total available carbohydrate (g) 165.1 ± 5.4 155.0 ± 7.9 0.289 177.8 ± 5.9 194.8 ± 6.2 0.051 0.066 <0.001 Sugars (g) 59.1 ± 3.3 56.0 ± 15.5 0.470 66.9 ± 4.1 70.5 ± 2.7 0.464 0.087 <0.001 Starch (g) 105.0 ± 3.5 99.6 ± 8.1 0.523 111.1 ± 4.1 124.6 ± 5.6 0.056 0.190 0.001 Dietary fiber (g) 23 ± 1 21 ± 1 0.245 27 ± 1 25 ± 1 0.222 0.001 0.012 Calcium (mg) 887 ± 54 915 ± 41 0.680 1,080 ± 62 1,030 ± 43 0.507 0.005 0.013 GI 49 ± 1 52 ± 2 0.171 47 ± 1 53 ± 1 <0.001 0.187 0.600 GL 81 ± 3 84 ± 6 0.598 84 ± 3 105 ± 4 <0.001 0.453 0.001 Data are mean ± SEM. * P values calculated by one-way ANOVA to test for difference between groups. † P values calculated by paired sample t test to test for difference compared with baseline. At the end of the intervention, biochemical parameters were similar between groups (Table 3). The results were similar in the compliers-only analysis (data not shown).In the primary analysis, there were no significant differences between groups in any of the pregnancy outcomes (Table 4). Fewer women in the LGI group gained an excessive amount of weight according to the American Institute of Medicine guidelines (LGI 25% vs. HF 42%; P = 0.095). Compliers in the LGI group appeared to gain less weight than those in the HF group (LGI 11.2 ± 0.9 kg vs. HF 13.7 ± 1.0 kg; P = 0.073). There was no significant difference in fetal abdominal circumference at 36–37 weeks' gestation (mean ± SEM LGI 327.6 ± 19.2 mm vs. HF 322.6 ± 14.6 mm; P = 0.186). Additional analyses with adjustments for ethnicity (Asian vs. Caucasian), BMI; oral glucose tolerance test results; baseline characteristics including daily intakes of energy, monounsaturated fatty acid, polyunsaturated fatty acid, and sodium; fasting BGL; fasting insulin; homeostasis model assessment of insulin resistance; and total cholesterol did not change the lack of significance of the between-group comparisons. Table 3 Biochemical parameters at baseline and end of intervention Baseline P * End of intervention P * LGI HF LGI HF n Mean ± SEM n Mean ± SEM n Mean ± SEM n Mean ± SEM BGL (mmol/L) 44 4.7 ± 0.1 42 4.6 ± 0.1 0.665 42 4.3 ± 0.1 32 4.4 ± 0.1 0.464 Insulin (pmol/L) 44 73.1 ± 9.4 42 70.5 ± 5.3 0.813 40 83.8 ± 16.1 30 73.0 ± 5.2 0.525 HOMA2-IR (%) 44 1.3 ± 0.2 42 1.3 ± 0.1 0.780 38 1.2 ± 0.1 39 1.3 ± 0.1 0.670 Fructosamine (μmol/L) 43 202.3 ± 2.5 41 199.9 ± 2.3 0.479 41 196.3 ± 2.3 40 193.7 ± 2.2 0.412 HbA 1c (%) 44 5.4 ± 0.1 42 5.4 ± 0.1 0.995 43 5.5 ± 0.1 41 5.5 ± 0.0 0.665 HOMA2-IR, homeostasis model assessment of insulin resistance. * P values calculated by one-way ANOVA to test for difference between groups. Table 4 Pregnancy outcomes by diet group LGI HF P * n Value n Value Gestational age (weeks) 47 39.1 ± 0.1 45 39.2 ± 0.1 0.552 Birth weight (kg) 47 3.3 ± 0.1 45 3.3 ± 0.1 0.619 Birth weight centile 47 52.5 ± 4.3 45 52.2 ± 4.0 0.969 LGA (%) 47 12.8 45 4.4 0.157 Small for gestational age (%) 47 10.6 45 8.9 0.778 Macrosomia (%) 47 2.1 45 6.7 0.286 Infant head circumference (cm) 43 34.4 ± 0.2 39 34.6 ± 0.3 0.478 Infant length (cm) 47 49.7 ± 0.3 45 49.7 ± 0.3 0.995 Ponderal index (kg/m 3 ) 47 27.2 ± 0.3 45 27.0 ± 0.4 0.614 Maternal weight gain (kg) 44 11.9 ± 0.7 43 13.1 ± 0.9 0.305 Below target (%) † 31.8 25.6 0.520 Within target (%) † 43.2 32.6 0.307 Above target (%) † 25.0 41.9 0.095 Insulin treatment (%) 47 53.2 45 65.1 0.251 Final daily insulin dose (units) 47 17.7 ± 4.1 43 20.0 ± 3.8 0.676 Emergency caesarean (%) 44 20.5 44 11.6 0.263 Data are mean ± SEM or percent. * P values calculated by one-way ANOVA for continuous variables and Pearson χ 2 for categorical variables. P < 0.05 indicates statistical significance. †Based on Institute of Medicine. Weight gain during pregnancy: reexamining the guidelines [article online], 2009. Available from http://www.iom.edu/~/media/files/report%20files/2009/weight-gain-during-pregnancy-reexamining-the-guidelines/report%20brief%20-%20weight%20gain%20during%20pregnancy.pdf . \n\nBODY.CONCLUSIONS:\nContrary to our hypothesis, this randomized controlled trial of an LGI diet versus a conventional high-fiber diet found no differences in key pregnancy outcomes in GDM. Average infant birth weight, birth weight centile, and ponderal index were within healthy norms in both groups. One explanation for the findings is that both groups of women achieved a relatively LGI diet, with only a modest 5-point difference between groups. Irrespective of dietary assignment, all had received early nutrition counseling in a group setting. Thus, on enrollment, both groups were found to be consuming a diet with a lower GI than population norms. Compared with routine care in another Australian study (18), both dietary interventions resulted in a lower prevalence of LGA (9 vs. 22%), macrosomia (4 vs. 21%), and emergency caesarean section (16 vs. 20%). Hence, in the setting of intensive medical management of GDM, our findings suggest that both an LGI and HF diet produce optimal pregnancy outcomes. Our findings increase the evidence supporting the safety and efficacy of an LGI diet in GDM. Moses et al. (12) also found no significant differences in key fetal and obstetric outcomes between subjects who followed an LGI diet (GI = 48) versus a higher-GI diet (GI = 56). However, unlike in the current study, they found that a significantly higher proportion of women in the higher-GI group met the criteria to commence insulin (59 vs. 29% in the LGI group). In addition, almost one-half of the women in the higher-GI group who met the criteria for insulin commencement avoided insulin by switching to an LGI diet. Their insulin treatment protocol, however, was different from that of the current study, in which more stringent criteria were used as the basis for insulin treatment. A recent Canadian study (19), in which women with GDM or impaired glucose tolerance monitored their own blood glucose levels, found that those who were randomized to an LGI diet versus those assigned to the conventional diet had a greater proportion of their 2-h postprandial levels on or below the treatment target. Although there was a tendency for higher birth weight in the control group, the study was a pilot and underpowered to detect a statistically significant difference. Another explanation for our findings is the relatively normal weight of most of our subjects (68% had a BMI <25 kg/m2). It is possible that an LGI diet may be more effective among overweight and obese gravidas with higher degrees of insulin resistance and β-cell deficiency (20). Rhodes et al. (21) reported higher head circumference and a lower proportion of early delivery (<38 weeks' gestation) in overweight and obese nondiabetic pregnant women assigned to a low GL diet. However, there was no significant difference in birth weight, ponderal index, or pregnancy weight gain, which are more sensitive to maternal glycemic control (22). The lack of difference in our study may also relate to the timing and duration of the intervention. Dietary instruction began at the start of the third trimester (29 weeks' gestation) and lasted, on average, 6–7 weeks. It is likely that maternal hyperglycemia during the first and second trimester will also drive excessive fetal growth. In a post hoc analysis of women who started dietary intervention before 25 weeks of gestation (10 from the LGI group and 5 from the HF group), those in the LGI group showed a tendency to lower birth weight (LGI 3.2 ± 0.2 kg vs. HF 3.5 ± 0.1 kg; P = 0.224) and lower birth centile (LGI 45.3 ± 11.0 vs. HF 57.5 ± 12.2; P = 0.476), suggesting that an earlier intervention may be beneficial. However, apart from a small number of high-risk women who are screened early, in most countries GDM screening occurs at 26–28 weeks' gestation (23,24), which means that any intervention in GDM will be necessarily short. A more viable test of our hypothesis would therefore be an appropriately powered study in women at high risk of developing GDM (e.g., women with a BMI >30 kg/m2 or previous GDM), starting on or before the start of the second trimester, to determine the effect of an LGI diet on both pregnancy outcome and risk of developing GDM. The failure to achieve the target GI of ∼60 in the HF group could reflect high recognition of the GI concept among Australians diagnosed with diabetes, particularly among those with higher education (in the current study, two of three subjects had a university degree). In the group education session conducted soon after diagnosis, all the women, irrespective of future dietary assignment, were encouraged to limit total carbohydrate to ∼180 g per day and to consume a greater proportion as fruit and dairy products—changes which are likely to lower the GI of the overall diet. Self-monitoring of blood glucose levels was also encouraged and may have provided feedback that discouraged consumption of high glycemic foods. Finally, the use of data collected from medical record may be subject to inaccuracy, e.g., birth weights were measured and entered by different staff, therefore biasing the result toward the null hypothesis. In conclusion, we found that both an LGI diet and a conventional high-fiber diet produced comparable pregnancy outcomes in women with GDM. Both groups achieved a relatively low GI diet and had mean birth weight, birth weight centile, and pregnancy weight gain within population norms. An LGI diet appears to be a safe alternative to the traditional pregnancy diet for women with GDM and expands the range of dietary strategies that can be offered. Further studies in overweight and obese individuals and earlier interventions in women with risk factors for GDM are warranted.\n\nBODY.SUPPLEMENTARY MATERIAL:\n\n \n Supplementary Data\n\n**Question:** Compared to high-fiber moderate-GI diet (HF) (target glycemic index GI ~60) what was the result of low–glycemic index diet (target glycemic index [GI] ~50) on birth weight, birth weight centile, prevalence of macrosomia, insulin treatment, adverse pregnancy outcomes?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
540
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Antibiotic Prophylaxis Using Third Generation Cephalosporins Can Reduce the Risk of Early Rebleeding in the First Acute Gastroesophageal Variceal Hemorrhage: A Prospective Randomized Study\n\n ABSTRACT:\nBacterial infection may be a critical trigger for variceal bleeding. Antibiotic prophylaxis can prevent rebleeding in patients with acute gastroesophageal variceal bleeding (GEVB). The aim of the study was to compare prophylactic third generation cephalosporins with on-demand antibiotics for the prevention of gastroesophageal variceal rebleeding. In a prospective trial, patients with the first acute GEVB were randomly assigned to receive prophylactic antibiotics (intravenous cefotaxime 2 g q 8 hr for 7 days, prophylactic antibiotics group) or to receive the same antibiotics only when infection became evident (on-demand group). Sixty-two patients in the prophylactic group and 58 patients in the on-demand group were included for analysis. Antibiotic prophylaxis decreased infection (3.2% vs. 15.5%, p=0.026). The actuarial rebleeding rate in the prophylactic group was significantly lower than that in the ondemand group (33.9% vs. 62.1%, p=0.004). The difference of rebleeding rate was mostly due to early rebleeding within 6 weeks (4.8% vs. 20.7%, p=0.012). On multivariate analysis, antibiotic prophylaxis (relative hazard: 0.248, 95% confidence interval (CI): 0.067-0.919, p=0.037) and bacterial infection (relative hazard: 3.901, 95% CI: 1.053-14.448, p=0.042) were two independent determinants of early rebleeding. In conclusion, antibiotic prophylaxis using third generation cephalosporins can prevent bacterial infection and early rebleeding in patients with the first acute GEVB.\n\nBODY.INTRODUCTION:\nGastroesophageal variceal bleeding (GEVB) is the most serious complication of portal hypertension and represents the leading cause of death in patients with liver cirrhosis. The patients who survive the initial episode of GEVB have a risk of recurrent bleeding approaching 80% at 2 yr (1). Failure to control bleeding and early rebleeding are the most important prognostic factors influencing the 6-week outcome of these patients (2). Rebleeding is associated with an increased risk of exsanguinations, development of liver failure, encephalopathy, and sepsis which contribute to mortality (3). Over the past two decades, many new treatment modalities have been introduced to improve the management of variceal bleeding, including endoscopic injection sclerotherapy (EIS) and variceal ligation (EVL), and new vasoactive agents such as terlipressin and somatostatin (4). Among them, EIS has been replaced almost universally by EVL, because EVL eradicates varices and provides a lower variceal rebleeding rate with fewer secondary effects than EIS does (5). However, the rebleeding rate following endoscopic treatment is still high; at around 25-50% (6). It is therefore important to define how to further reduce the rebleeding rate. Bacterial infections are frequently associated with upper gastrointestinal bleeding in cirrhotic patients (7). Bacterial infections are more common in cirrhotic patients with acute GEVB than those admitted to hospital with other forms of decompensation, such as encephalopathy (8). Infection may favour variceal bleeding by increasing sinusoidal pressure and altering hemostasis (9). In fact, endotoxemia secondary to bacterial infection may be the critical trigger for variceal bleeding as it produces a wide series of effects that may predispose the cirrhotic patient to bleeding (10). A recent randomized controlled clinical trial has documented the value of quinolone use in preventing rebleeding (6). Prophylactic quinolone can thus further reduce the rebleeding rate in cirrhotic patients with GEVB. However, the use of prophylactic antibiotics can lead to antibiotic resistance with potentially disastrous consequences. It is necessary to prove the benefit of other antibiotics including third generation cephalosporins in preventing rebleeding in cirrhotic patients with GEVB. Therefore, the aim of this study was to compare prophylactic third generation cephalosporins with on-demand antibiotics for the prevention of gastroesophageal variceal rebleeding.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nFrom June 2000 to December 2004, all patients with cirrhosis admitted with upper gastrointestinal bleeding via our hospital emergency room underwent endoscopy within 12 hr of admission. Male or female patients aged over 18 yr were eligible for inclusion in the study after fulfilling the following criteria: 1) diagnosis of cirrhosis on the basis of previous liver biopsy or clinical, biochemical, and radiologic findings of hepatic failure and portal hypertension; 2) bleeding from esophageal varices or gastric varices; and 3) no signs of infection at admission. The severity of cirrhosis was classified according to Child-Pugh's score (11). GEVB was diagnosed when the emergency endoscopy showed any of the following signs: 1) active bleeding from esophageal varices or gastric varices; 2) stigmata of recent hemorrhage over varices (adherent blood clots); or 3) when there was no other cause of upper gastrointestinal bleeding but fresh blood was found in the stomach. Possible complications of endoscopic treatment were discussed with the patients and their relatives, and written informed consent was obtained before entry into the trial. Patients were excluded from the study if they met the following criteria. First, the patient had a past history of GEVB, or surgical or endoscopic treatment of gastroesophageal varices. Second, the patient received antibiotics within the last 2 weeks. Third, the patient had a terminal illness of any major organ system, or non hepatic malignancy. Forth, the patient had any other causes of upper gastrointestinal bleeding. The diagnosis of hepatocellular carcinoma (HCC) was based on liver biopsy or two coincidental imaging studies as well as one imaging study associated with alpha fetoprotein (AFP) more than 400 ng/mL (12). The Ethics Committee of Chonnam National University Hospital approved the treatment protocol.\n\nBODY.MATERIALS AND METHODS.RANDOMIZATION:\nRandomization was performed at the time of the therapeutic endoscopy by an investigator after patients met clinical and laboratory entry criteria, lacked exclusions, and gave written informed consent for entry into this study. The allocation of patients to treatment was done by drawing sequentially numbered envelopes, each containing a previously determined, randomly selected assignment based on a table of random numbers. Patients in the prophylactic group received antibiotics treatment after randomization with intravenous cefotaxime 2 gram q 8 hr for 7 days. Patients in the on-demand group received antibiotics only when infection was suspected or established. Antibiotics were changed according to the antibiotic sensitivity profile of cultured microorganisms.\n\nBODY.MATERIALS AND METHODS.INFECTION ASSESSMENT:\nA physical examination, complete blood cell count, chest radiography, urine analysis and culture, blood culture, and ascitic fluid neutrophil count with culture (in patients with ascites) were routinely carried out before randomization. Patients were excluded when the initial bacteriologic examination turned out positive finding. If a new infection was suspected, the same procedures were carried out to assess infection. New infections were suspected when there was fever (>38°C), hypothermia (<36°C), unexplained hemodynamic instability, tachypnea, new onset of chest symptoms, dysuria, deterioration of renal function, bowel habit changes, abdominal pain, abdominal distention, as well as alteration of mental state (6). Respiratory infections were diagnosed by clinical symptoms and signs and positive chest radiography findings. Urinary tract infections were diagnosed by the positive urine culture of ≥105 colonies/mL and associated clinical pictures. The diagnosis of bacteremia was based on positive blood culture and clinical signs or symptoms of infection without other recognized causes. The diagnosis of spontaneous bacterial peritonitis was based on ≥250 neutrophils/μL in ascitic fluid (13). Patients without any identified infection source but with fever >38°C and leukocytosis >11,000/μL with neutrophilia were considered as having possible infections and received on demand antibiotics. In analyzing the incidence of infection and determining the effect of antibiotic prophylaxis, only infectious episodes occurring during the first hospitalization were considered. Therefore, the infection rate was compared by number of events in this period.\n\nBODY.MATERIALS AND METHODS.ENDOSCOPIC TREATMENT PROCEDURES:\nBefore endoscopic treatment, octreotide was used. If active bleeding was found during endoscopy, endoscopic treatment was performed immediately. EVL was performed for esophageal varices, and EIS was performed for gastric varices. Two experienced therapeutic endoscopists performed the diagnostic and therapeutic endoscopic procedures. They had 4 yr' experience of standard endoscopy. They did not participate in the postprocedure care of the patients, which was conducted by other physicians. Endoscopy was performed with a standard upper endoscope (Olympus GIF-XQ240, Olympus Optical Co., Ltd., Tokyo, Japan). After endoscopic treatment, octreotide was used for 5 days. EVL was performed by using a varioligator kit with a single-shot device (Top Corp., Tokyo, Japan) and a flexible overtube or multiband ligators (Wilson-Cook Medical, Winston-Salem, NC, U.S.A.). Size of esophageal varices was graded according to Conn's classification (14). Grade I-visible only during one phase of respiration/performance of Valsalva maneuver. Grade II-visible during both phases of respiration. Grade III-3-6 mm. Grade IV-varices of >6 mm. EVL was performed biweekly for the first 6 weeks until the varices were obliterated or reduced to Grade I size and could not be banded any further. Follow-up endoscopy was performed every 3 months and, if unremarkable, was moved to every 6 months. EIS was performed by using intravariceal injection with the 1:1 mixture of 0.5 mL N-butyl-2-cyanoacrylate (Histoacryl blue, Braun-Melsungen, Germany) and 0.5 mL Lipiodol (Guerbet Laboratory, Aulnay-Sous-Bris, France) in each shot. Rebleeding was defined as one or more of the ongoing bleeding signs including fresh hematemesis, hematochezia, fresh blood aspirated via a nasogastric tube, instability of vital signs, or a reduction of hemoglobin by more than 2 g/dL within 24 hr after initial hemostasis. When rebleeding was suspected, immediate endoscopy was performed. If active bleeding or a fresh blood clot was found at the varices, and if fresh blood was found in the stomach without any other causes of upper gastrointestinal bleeding, rebleeding was confirmed. Bleeding esophageal varices were ligated and bleeding gastric varices were injected with the previously mentioned tissue glue again. Rebleeding within 6 weeks of enrollment after initial control of active bleeding was defined as early rebleeding. Treatment failure was defined as a failure to control active bleeding after two attempts of endoscopic treatment, rebleeding more than twice, or bleeding-related death. Rebleeding index for each patient was calculated by dividing the months of follow-up by the number of rebleeding episodes plus one (6).\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nRebleeding rate as a primary outcome was compared between two groups, and secondary outcomes such as rebleeding index, treatment failure, bleeding related death, infection rate, transfusion requirements, and admission duration, were also compared between two groups. Quantitative data were summarized as mean±standard deviation. The Student t test was utilized to compare the mean values of continuous variables, and the chi-square test with Yate's correction or Fisher exact test was utilized for the comparison of discrete variables. Kaplan-Meier analysis with the log-rank test was used to compare differences of actuarial probability of rebleeding and survival between two groups. Univariate analysis and stepwise multivariate analysis were performed to assess the potential risk factors of early rebleeding using the Cox proportion hazards regression. A p value of less than 0.05 was accepted as statistically significant. The analysis was performed with statistical software package (SPSS 13.0 version for Windows, SPSS, Chicago, IL, U.S.A.). This study hypothesized a reduction of rebleeding rate from 45% to 20% by using prophylactic antibiotics (6). According to the sample size calculation, the study would require 54 patients in each group. The type I error and type II error were set to 0.05 and 0.2, respectively.\n\nBODY.RESULTS:\nDuring the study period, 152 patients with the first acute GEVB were recruited and randomized. Eight patients in the prophylactic group and 7 patients in the on-demand group were excluded from analysis due to occult infections. Six patients in the prophylactic group and 11 patients in the on-demand group were excluded due to their refusal to continue in the study. Therefore, 62 patients in the prophylactic group and 58 patients in the on-demand group were included for analysis. Data regarding the clinical characteristics of the patients at entry are outlined in Table 1. There were no significant differences between two groups with respect to age, gender, etiology, association of HCC, Child-Pugh's score, severity of bleeding, endoscopic characteristics, and period of follow-up (Table 1).\n\nBODY.RESULTS.INFECTION OUTCOMES AND BACTERIOLOGY:\nSummary of the infection sources and bacteriology is outlined in Table 2. The incidence of bacterial infection was significantly lower in patient receiving antibiotic prophylaxis (2/62, 3.2% vs. 9/58, 15.5%, p=0.026). Bacteremia and spontaneous bacterial peritonitis were the most common sources of infection. Enteric bacteria were more frequently identified in patients without antibiotic prophylaxis (0/62, 0% vs. 5/58, 8.6%, p=0.018). There were no significant side effects in antibiotic prophylactic group.\n\nBODY.RESULTS.HEMOSTATIC OUTCOMES:\nSummary of hemostatic outcome data is outlined in Table 3. The rebleeding rate in the prophylactic group was significantly lower than that in the on-demand group (21/62, 33.9% vs. 36/58, 62.1%, p=0.004). The difference of rebleeding was mostly due to early rebleeding within 6 weeks (3/62, 4.8% vs. 12/58, 20.7%, p=0.012). The cumulative total rebleeding rate and early rebleeding rate were also higher in the on-demand group (Fig. 1, 2). However, there was no significant difference in cumulative late rebleeding rate between the two groups (Fig. 3). The rebleeding sources were not different between the two groups (Table 2). The early rebleeding rate in the infected patients was significantly higher than that in the noninfected patients (4/11, 36.4% vs. 11/109, 10.1%, p=0.031). However, there was no difference in total rebleeding rate between the infected and the noninfected (6/11, 54.5% vs. 52/109, 47.7%, p=0.760). The transfusion requirement was significantly larger in on-demand group than that in prophylactic group (p=0.002). There were no differences in rebleeding index, treatment failure, and duration of hospital stay between the two groups. Univariate analysis showed the early rebleeding risk significantly linked to antibiotic prophylaxis and bacterial infection (Table 4). On multivariate analysis, antibiotic prophylaxis (relative hazard: 0.248, 95% confidence interval (CI): 0.067-0.919, p=0.037) and bacterial infection (relative hazard: 3.901, 95% CI: 1.053-14.448, p=0.042) were two independent determinants of early rebleeding (Table 5). Univariate analysis showed the late rebleeding risk significantly linked to alcoholics and presence of HCC (Table 6). On multivariate analysis, alcoholics (relative hazard: 1.968, 95% CI: 1.133-3.502, p=0.016) and association with hepatocellular carcinoma (relative hazard: 1.904, 95% CI: 1.035-3.502, p=0.039) were two independent factors predictive of late rebleeding.\n\nBODY.RESULTS.MORTALITY AND SURVIVAL:\nTwenty patients and 24 patients died in the prophylactic and on-demand group, respectively. Total mortality and 30-day mortality were not different between the two groups (Table 7). The overall rate of survival was similar between the two groups (Fig. 4). Univariate analysis showed that the survival was significantly related to the presence of HCC, Child-Pugh's score, and bacterial infection (Table 8). On multivariate analysis, presence of HCC (relative hazard: 4.134, 95% CI: 2.261-7.560, p<0.001) and Child-Pugh's score (relative hazard: 1.372, 95% CI: 1.173-1.603, p<0.001) were two independent risk factors determining survival.\n\nBODY.DISCUSSION:\nIn cirrhotic patients, there is a predisposition to intestinal bacterial overgrowth, intestinal dysmotility, and increased intestinal permeability, all leading to an increase in bacterial translocation. Bacterial translocation is the probable source of bacterial byproducts such as endotoxin which can cause an increase in portal pressure, impairment of liver function, and worsening of hemostasis (10). Endotoxemia secondary to bacterial infection may indeed be the critical trigger for variceal bleeding (15). Norfloxacin, ciprofloxacin, and ofloxacin have all been used with these indications (6, 16-21). According to our knowledge, previous studies have never used single third generation cephalosporin for antibiotic prophylaxis for gastrointestinal bleeding. For this reason, third generation cephalosporin can also be used to prevent bacterial infection and rebleeding in cirrhotic patients with an antibacterial resistance after a long term quinolone prophylaxis. In our study, third generation cephalosporin was used in order to prevent bacterial infection and rebleeding not only because it is safe and efficacious for enteric Gram-negative bacteria, which are the most common causative organisms in cirrhotic patients with acute gastrointestinal bleeding (16-20), but it also has a benefit of covering Gram positive bacteria. The benefit of third generation cephalosporins for preventing early rebleeding in cirrhotic patients with GEVB by decreasing bacterial infection is proved in our study. The prophylactic effect may not sustain over six weeks. However, the period of the greatest risk of early rebleeding is within the first 48 hr after admission (22). The use of early short term antibiotics is very effective in preventing early rebleeding in cirrhotic patients. In the present study, univariate analysis showed the early rebleeding risk significantly linked to antibiotic prophylaxis and bacterial infection. And, antibiotic prophylaxis (relative hazard: 0.248, 95% CI: 0.067-0.919, p=0.037) and bacterial infection (relative hazard: 3.901, 95% CI: 1.053-14.448, p=0.042) were two independent determinants of early rebleeding by the multivariate analysis. The results suggest that bacterial infection produces a wide series of effects that may predispose the cirrhotic patient to bleeding (10). Therefore, the effective antibiotic prophylaxis should be considered as an essential treatment to prevent early rebleeding. In our study, total rebleeding rates were higher than those of previous prospective randomized study (47% vs. 32%) (6). There are several possible explanations for these differences in the rebleeding rates. First, this may be because of a difference in the clinical characteristics of the study population, including habitual alcohol drinking. In our study, alcoholism was the most common etiology of liver cirrhosis compared with other study. Second, the difference in the rebleeding rates may stem from the type of antibiotics (quinolone vs. cephalosporin). In a recent survey, 26% of spontaneous bacterial peritonitis episodes were caused by quinolone resistant Gram negative bacilli over a two year period, related to long term treatment with quinolone (23). Fortunately, quinolone resistant E coli are still sensitive to third generation cephalosporins (9). In addition, there is a substantially increased likelihood of infections from Gram positive bacteria in patients who received quinolone prophylaxis (24). Finally, there was a difference in total follow-up periods between the studies. The total follow-up periods in our study (mean, 22 months) were longer than those in the other study (mean, 9 months) (6). Patients who survived after an initial episode have a risk of rebleeding rate approaching 80% in 2 yr (1). The risk of late rebleeding (more than 6 weeks after the initial episode) is related to such factors as continued alcohol consumption, variceal size, renal failure, degree of liver failure, and presence of HCC (2). Alcohol consumption continues to influence prognosis even after cirrhosis has developed. Patients with clinically compensated cirrhosis who become abstinent have a 90% chance of surviving for 5 yr. In contrast, if these patients continue to drink, their chance of survival falls to about 70% (25). In our study, continued alcohol drinking and the presence of HCC were the most important determinants of the late rebleeding. All alcoholic patients with variceal rebleeding continued their habitual alcohol consumption. Accordingly, there was a trend of more episodes of rebleeding in cirrhotic patients after longer follow-up period without correction of this risk factor. In order to lower the risk of late rebleeding, abstinence of alcohol and effective treatment of HCC should be encouraged. Although the effect of short-term prophylactic antibiotics in patients with GEVB is proved by the reduction of bacterial infection and early rebleeding rate, these beneficial effects are not reflected in terms of mortality and survival in this study. The lack of influence of antibiotic prophylaxis on mortality is likely because of infection is not an independent predictive factor for survival (6). The small impact of rebleeding on survival is possibly due to the fact that most rebleeding episodes can be further controlled by repeated endoscopic treatments (6). Furthermore, on multivariate analysis, presence of HCC (relative hazard: 4.134, 95% CI: 2.261-7.560, p<0.001) and Child-Pugh's score (relative hazard: 1.372, 95% CI: 1.173-1.603, p<0.001) were the only two independent risk factors determining survival in the present study. Actually, most patients died of hepatic failure or multiorgan failure associated with decreased residual liver function and HCC. However, a recent study reported that in-hospital mortality of patients with cirrhosis and acute variceal bleeding has greatly decreased over the past two decades, in concurrence with an early and combined use of pharmacological and endoscopic therapies and short-term antibiotic prophylaxis (26). The use of prophylactic antibiotics decreased the rate of bacterial infections in randomized controlled trials, and a meta-analysis showed that it was associated with improved survival (27). It warrants larger studies to confirm this benefit of antibiotic prophylaxis on mortality. In conclusion, antibiotic prophylaxis with third generation cephalosporins can prevent bacterial infection and early rebleeding in patients with the first acute GEVB. Although the results are hopeful, larger studies should be performed to confirm this benefit of antibiotics on mortality.\n\n**Question:** Compared to received antibiotics only when infection was suspected or established what was the result of received antibiotics treatment after randomization with intravenous cefotaxime 2 gram q 8 hr for 7 days on Total mortality and 30-day mortality?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
541
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Fibrin Glue Reduces the Duration of Lymphatic Drainage after Lumpectomy and Level II or III Axillary Lymph Node Dissection for Breast Cancer: A Prospective Randomized Trial\n\n ABSTRACT:\nThis randomized prospective study investigated the effect of fibrin glue use on drainage duration and overall drain output after lumpectomy and axillary dissection in breast cancer patients. A total of 100 patients undergoing breast lumpectomy and axillary dissection were randomized to a fibrin glue group (N=50; glue sprayed onto the axillary dissection site) or a control group (N=50). Outcome measures were drainage duration, overall drain output, and incidence of seroma. Overall, the fibrin glue and control groups were similar in terms of drainage duration, overall drain output, and incidence of seroma. However, subgroup analysis showed that fibrin glue use resulted in a shorter drainage duration (3.5 vs. 4.7 days; p=0.0006) and overall drain output (196 vs. 278 mL; p=0.0255) in patients undergoing level II or III axillary dissection. Fibrin glue use reduced drainage duration and overall drain output in breast cancer patients undergoing a lumpectomy and level II or III axillary dissection.\n\nBODY.INTRODUCTION:\nProlonged lymphatic drainage following axillary dissection in breast cancer remains a significant clinical problem Shortening the drainage duration is associated with shorter in-patient times and hence lower health care costs. Methods applied to reduce lymphatic drainage include compression dressings (1), closed suction drains (2), postoperative shoulder immobilization (3) and fibrin glue application to the axillary dissection site (4-6). The use of fibrin glue may reduce lymphatic drainage by reducing the number of transections of small vessels and lymphatics during axillary lymph node removal (7). However, conflicting clinical trial results exist regarding fibrin glue use in breast cancer surgery. Previous trials involved a wide variety of breast cancer surgery types or degrees of axillary dissection (8). The present randomized study investigated the effect of fibrin glue use on the duration of drainage and overall drain output after breast lumpectomy and axillary dissection for breast cancer.\n\nBODY.MATERIALS AND METHODS.PARTICIPANTS:\nA prospective, randomized study was performed between September 2006 and July 2007 at the Department of Surgery, Seoul National University Hospital. The inclusion criteria (9) were 1) newly diagnosed breast cancer, 2) female gender, 3) elective breast lumpectomy and axillary dissection, 4) informed consent, and 5) being outside of any exclusion criteria. The exclusion criteria (9) were: 1) male gender, 2) a body mass index (kg/m2) <18.5 or >30, 3) current steroid use, 4) systemic anticoagulation or significant coagulation disorder, 5) diabetes, 6) heart disease, 7) history of chest radiation, 8) receiving preoperative chemotherapy, 9) planned immediate breast reconstruction, 10) pregnant or lactating, 11) limited to sentinel node biopsy, or 12) no consent. The study was approved by the Institutional Review Board of the Seoul National University Hospital.\n\nBODY.MATERIALS AND METHODS.TREATMENT PROTOCOL:\nSurgery was performed by two surgeons using principally identical methods. All patients underwent a lumpectomy and level I or greater axillary lymph node dissection, and an effort was made to ligate major vessels. For the patients in the fibrin glue group, fibrin glue (Greenplast kit®, Green Cross, Seoul, Korea) was mixed intraoperatively and diluted twice according to standard instructions, and 2 mL was sprayed onto the axillary dissection site using an aerosol spray applicator (Green Jet V2®, Green Cross, Seoul, Korea), after which manual compression was applied for 2 min according to manufacturer's manual. A Jackson-Pratt closed suction 100 mL/3.2 mm drain was placed into the axillary dissection site for all patients. Compression dressings with surgical bras and pads were applied to all patients for the first 5 days after surgery. Arm movement was restricted to below 90 degrees for 5 days (3). Participants were discharged on postoperative day 5±1 regardless of drain removal, and were routinely followed-up on postoperative days 12±1 and 30±2.\n\nBODY.MATERIALS AND METHODS.OUTCOMES:\nThe primary outcome measure was the duration of drainage. Drainage was assessed daily from the day of surgery, and drains were removed when the drainage volume fell to <30 mL over a 24-hr period. Secondary outcome measures were overall drain output and the incidence of symptomatic seroma formation. A symptomatic seroma was defined as a palpable fluid collection under the wound with symptoms, and was treated using aspiration or open drain insertion. In addition, all wound-related complications were recorded. The wound was examined daily until discharge and during each clinic visit. Wound infections were defined as erythema and/or purulent discharge from the incision site, and were treated using an oral antibiotic for at least 3 days.\n\nBODY.MATERIALS AND METHODS.SAMPLE SIZE:\nThe primary endpoint was the duration of drainage. In a pilot study with 21 patients, the mean drainage duration was 3.0 days for the case group and 3.2 days for the control group, and the standard deviation of the mean difference between the case and control groups was 0.255. The current study had a power of 90 percent to show whether the drainage duration differed between the fibrin glue and non-fibrin glue groups. This approach assumed that the drainage duration for the two groups was equal, and that a difference of 10 percent or less was clinically irrelevant. This approach required each group to have a sample size of 49 considering a 30% dropout, and α (two-sided) was set at 0.05. The enrollment procedure engaged 50 patients per group.\n\nBODY.MATERIALS AND METHODS.RANDOMIZATION:\nPatients were randomized using a web-based program hosted at the Medical Research Collaborating Center at Seoul National University Hospital. Participant randomization was done after bleeding control and confirmation of a negative margin status, immediately before wound closure. Fig. 1 shows the Consolidated Standards of Reporting Trials (CONSORT) flow chart outlining the progress of participants through the study (10). One hundred participants were randomized, 50 to the fibrin glue group and 50 to the control group (non-fibrin glue). Three fibrin glue patients and two control patients were excluded after randomization due to postoperative bleeding.\n\nBODY.MATERIALS AND METHODS.BLINDING:\nThe surgical team was 'blinded' to treatment assignment until the completion of the surgical dissection and bleeding control just prior to randomization. The personnel involved in recording drainage volumes and complications were also blinded to the treatment assignment.\n\nBODY.MATERIALS AND METHODS.STATISTICAL METHODS:\nData were stored using the Excel (Microsoft Corporation, Redmond, WA, U.S.A.) spread sheet program, and statistical analyses were performed using SPSS software version 12.0 (SPSS, Chicago, IL, U.S.A.) and SAS (SAS Inc., Cray, NC, U.S.A.). Outcome criteria were analyzed on an intension-to-treat basis and all tests were two-tailed. Qualitative data were compared using the Pearson's chi-square-test for more than 30 samples and Fisher's exact test for less than 30 samples. Quantitative data were expressed as means (standard deviations), and were compared using Student t-tests for all group samples and using Mann-Whitney U tests for subgroup samples. Using the general linear model (GLM) procedure, two-way analysis of variance (ANOVA) was used to identify subgroups showing the greatest benefit from use of fibrin glue. A p value <0.05 was considered to indicate a significant difference.\n\nBODY.RESULTS:\nOf the 100 patients enrolled (50 fibrin glue, 50 control), 95 completed the study to the endpoint. All five of those that did not complete the study developed postoperative bleeding on the day of surgery, and four of them were conservatively treated (compression dressing with elastic bandage and open drain insertion) and the other underwent re-exploration for bleeding control and hematoma evacuation. It was not possible to measure the drainage duration or overall drain output in those five patients because the Jackson-Pratt closed suction drain was removed and an open drain inserted. There were no significant differences between the fibrin glue and control groups with respect to age, body mass index (BMI), tumor size, the number of lymph nodes removed, and the number of tumor-involved lymph nodes (Table 1). Level I axillary dissection and node-negative status were found to be associated with a shorter drainage duration (p=0.0001 and p=0.004, respectively) and lower overall drain output (p=0.0001 and p=0.003, respectively), while other factors such as age <60 yr and BMI <25 kg/m2 were not (Table 2).\n\nBODY.RESULTS.DURATION OF DRAINAGE, OVERALL DRAIN OUTPUT AND COMPLICATIONS:\nThe mean drainage duration was 3.3 days for the fibrin glue group and 3.8 days for the control group (p=0.067). The overall drain output was 174 mL for the fibrin glue group and 197 mL for the control group (p=0.309). The differences between groups for these two factors were not found to be statistically significant (Table 2). In addition, the fibrin glue and control groups were found to be similar in terms of the incidence of seroma, postoperative bleeding and wound infection (Table 4).\n\nBODY.RESULTS.SUBGROUP ANALYSIS:\nParticipants were classified according to two categorical factors and the data underwent an analysis of variance. One factor was the use of fibrin glue and the other factor was the axillary dissection level or node status. The variance between groups classified according to the use of fibrin glue and axillary dissection level was significant in terms of drainage duration (p=0.0005) and overall drain output (p=0.0098) (Table 3). The drainage duration was shorter (3.5 vs. 4.7 days; p=0.0006) and the overall drain output was lower (196 vs. 278 mL; p=0.0255) in the fibrin glue group compared with the control group among those undergoing level II or III axillary dissection. These differences were not apparent in those undergoing level I axillary dissection. While the data appeared to suggest there may have been a greater benefit from the use of fibrin glue in patients with a positive node status compared with a negative node status, the differences were not statistically significant (p=0.0818 for drainage duration and p=0.1123 for overall drain output).\n\nBODY.DISCUSSION:\nWhile prolonged axillary lymphatic drainage is not a serious complication after axillary dissection in breast cancer, it remains the main cause of prolonged hospital stays resulting in increased health care costs. Therefore, several approaches have been used to reduce axillary lymphatic drainage, such as the use of fibrin glue and immobilization of the affected arm (11). Although Lindsey et al. (12) reported that fibrin glue reduced lymphatic drainage in rats, conflicting results have been reported in clinical trials. Five studies (4-6, 9, 13) have examined the association between fibrin glue use and drainage duration or overall drain output. Three of those studies (4-6) showed that fibrin glue reduced both axillary lymphatic drainage and drainage duration, while two (9, 13) reported that fibrin glue had no effect on either axillary lymphatic drainage and drainage duration. Moreover, a meta-analysis of several published trials (8) reported that while the data appeared to suggest decreased overall drain output and a shorter drainage duration in patients receiving fibrin sealant, the findings were not statistically significant. Those studies enrolled almost exclusively mastectomy cases or various cases rarely involving lumpectomy, therefore making it difficult to accurately evaluate axillary lymphatic drainage due to the influence of fluid from the mastectomy site or the heterogeneity of surgery. The present study enrolled patients undergoing only breast lumpectomy and axillary dissection to minimize the influence of fluid from mastectomy or lumpectomy. The analysis of all patients showed that fibrin glue use did not reduce the drainage duration or the overall drain output. However, subgroup analysis showed that the use of fibrin glue reduced both drainage duration and overall drain output in patients undergoing level II or III axillary dissection. Fibrin glue had no such effect in patients undergoing level I axillary dissection. The current study found that in both fibrin glue and control groups, drainage duration and overall drain output increased as the level of axillary dissection or nodal stage increased, and that the benefit from the use of fibrin glue was greater in those undergoing higher level dissections. Moreover, the data suggest that a study using a larger population may find that there is greater benefit from fibrin glue use in node-positive patients compared to node-negative patients. The present results suggest that fibrin glue use will be beneficial under conditions of high drainage, such as axillary dissection extended to two or three levels, higher nodal stage (14), following preoperative chemotherapy, old age (2) and obesity (11). In contrast to previous studies (2, 11), the present study did not find an association between lymphatic drainage and age or obesity. This may have been because in this study the body mass index of participants was restricted ≤30 kg/m2 and the number of participants aged ≥60 yr was only 10. The current study found that the use of fibrin glue did not prevent seroma formation, which is consistent with other reports (4, 6, 8, 9, 13). One explanation is that perhaps fibrin glue had only a short and transient effect on drainage (4). Despite subgroup analysis showing a shorter drainage duration in the fibrin glue group compared to the control group, the groups did not differ in terms of seroma formation or the number of outpatient clinic visits due to wound issues. Thus, it appears that the use of fibrin glue can reduce the length of hospital stay and has no detrimental effect on the complication rate. In conclusion, the present results indicate that fibrin glue use can decrease the drainage duration and overall drain output after breast lumpectomy and axillary dissection in patients undergoing level II or III axillary dissection. Thus, fibrin glue use might be recommended in patients at a risk of high lymphatic drainage in order to reduce the length of hospital stays.\n\n**Question:** Compared to control group what was the result of fibrin glue group (glue sprayed onto the axillary dissection site) on drainage duration?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
422
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Six-week high-intensity exercise program for middle-aged patients with knee osteoarthritis: a randomized controlled trial [ISRCTN20244858]\n\n ABSTRACT.BACKGROUND:\nStudies on exercise in knee osteoarthritis (OA) have focused on elderly subjects. Subjects in this study were middle-aged with symptomatic and definite radiographic knee osteoarthritis. The aim was to test the effects of a short-term, high-intensity exercise program on self-reported pain, function and quality of life.\n\nABSTRACT.METHODS:\nPatients aged 36–65, with OA grade III (Kellgren & Lawrence) were recruited. They had been referred for radiographic examination due to knee pain and had no history of major knee injury. They were randomized to a twice weekly supervised one hour exercise intervention for six weeks, or to a non-intervention control group. Exercise was performed at ≥ 60% of maximum heart rate (HR max). The primary outcome measure was the Knee injury and Osteoarthritis Outcome Score (KOOS). Follow-up occurred at 6 weeks and 6 months.\n\nABSTRACT.RESULTS:\nSixty-one subjects (mean age 56 (SD 6), 51 % women, mean BMI 29.5 (SD 4.8)) were randomly assigned to intervention (n = 30) or control group (n = 31). No significant differences in the KOOS subscales assessing pain, other symptoms, or function in daily life or in sport and recreation were seen at any time point between exercisers and controls. In the exercise group, an improvement was seen at 6 weeks in the KOOS subscale quality of life compared to the control group (mean change 4.0 vs. -0.7, p = 0.05). The difference between groups was still persistent at 6 months (p = 0.02).\n\nABSTRACT.CONCLUSION:\nA six-week high-intensive exercise program had no effect on pain or function in middle-aged patients with moderate to severe radiographic knee OA. Some effect was seen on quality of life in the exercise group compared to the control group.\n\nBODY.BACKGROUND:\nExercise is considered to be one of the most important treatments for patients with mild to moderate knee osteoarthritis [1,2]. Positive effects on pain and function, as well as cost-effectiveness have been reported [3,4]. The effect size obtained on pain experience is similar to that of pharmacological treatment [3,5]. The side effects have also been reported to be favorable, including reduced risk of inactivity-related disorders, such as cardiovascular disease and diabetes [2,6,7]. Moderate levels of physical activity are not associated with radiographic progression, but activities involving a risk of severe knee injury are closely related to increased risk of developing radiographic knee osteoarthritis [8-12]. The dose-response relationship of exercise on symptoms and function is not clear and exercise recommendations in osteoarthritis guidelines are based mostly on studies on elderly people, i.e. mean age ≥ 65 [3,13-15]. It is not clear whether exercise has a similar effect on pain and function in middle-aged patients compared with elderly patients. The aim of this study was to examine the effects of a short-term, high-intensity exercise program in middle-aged subjects (age 36–65) with definite radiographic knee osteoarthritis on self-reported pain, function, and quality of life.\n\nBODY.METHODS.SUBJECTS:\nA flow chart of the recruitment process is given in Figure 1. Radiologists and orthopedic surgeons at the Halmstad County Hospital, in the south-west of Sweden, and general practitioners within the catchments area of this hospital, were informed about the study and asked to list patients with radiographic knee osteoarthritis on a \"patients eligible for research\" list. Between October 1998 and October 2001 121 patients, referred by their general practitioner for radiographic examination because of long standing knee pain, were listed. Ninety-seven fulfilled the inclusion criteria: age 35–65, living in the defined geographic area, and diagnosis of radiographic osteoarthritis of Kellgren and Lawrence grade III or more, i.e. definite osteophytes and joint space narrowing. All listed patients received written information about the study. One week after the information was sent, patients were contacted by telephone, and invited to participate in the study. Twenty-eight patients declined participation for various reasons, the most common reason being lack of time and interest. To ensure only patients with symptoms due to knee osteoarthritis and eligible for exercise intervention were included, the following exclusion criteria were used: inflammatory joint disease, anterior cruciate ligament injury, known symptomatic injury to the menisci, hip symptoms more aggravating than the knee symptoms, about to have knee replacement surgery within 6 months, and co-morbidities not allowing exercise (Figure 1). Figure 1Flowchart of recruitment process and included patients. When eight or more patients fulfilled the inclusion criteria they were invited to baseline interview and examination for determination of exclusion criteria. Randomization was performed after the baseline examination. All patients were informed that they could be randomly allocated to either the exercise or the control group. After written informed consent, sixty-five subjects were randomized. Randomization was performed by the patient drawing a sealed envelope containing a piece of folded paper with either the word \"exercise\" or \"control\" written on it. Four persons were falsely randomized (one was too old at inclusion, one had severe hip osteoarthritis, one had fibromyalgia, and one had only joint space narrowing and no significant osteophytes), and thus 61 subjects entered the study. Thirty persons were allocated to the exercise group and 31 to the control group. Patients in the control group were offered exercise classes after the six-month follow-up period.\n\nBODY.METHODS.SUBJECTS.EXERCISE GROUP:\nThe number of participants exercising together varied from two to nine. There were eight intervention groups in all. One-hour exercise sessions, twice a week for six weeks, were supervised by a physical therapist (CT). The program consisted of weight-bearing exercises aimed at increasing postural control and endurance and strength in the lower extremity (see additional file 1 for the complete exercise program). Exercises were performed at five stations at submaximal intensity (minimum 60% of maximum heart rate (HRmax)). Intensity was gradually and individually increased during the six weeks by increased lever arms or range of motion. Patients were encouraged to exercise at their most vigorous intensity possible, without losing quality in performance or severely exacerbating pain. Pain during exercise was not considered as an obstacle if the patient perceived it as \"acceptable\" and no increased symptoms were persistent after 24 hours [16]. If pain exceeded this level, exercise intensity was reduced occasionally, until the \"acceptable\" level was found. On every occasion, the heart rate of two random participants was estimated at each station using Polar pulsimeters (Polar® Accurex Plus, Polar, Sweden). The other patients had their heart rate measured by the physical therapist or themselves, palpating their carotid arteries. Notes were taken by the supervising physical therapist, on every occasion and on all patients, about exercise intensity, heart rate, and perceived exertion according to Borg's Rate of Perceived Exertion scale (RPE) at each station [17]. These data were used to give the physical therapist a view of exercise intensity and to assure the preservation or increase of intensity from time to time. Patients were encouraged to keep up and increase intensity whenever possible throughout the six weeks. Patients received a thera band to perform daily pulley exercises at home. In addition, three exercises, which were considered as the most challenging to the individual, were chosen as daily home exercises. Patients were recommended to perform some kind of weight bearing submaximal activity, such as walking or their home exercises, for at least 30 minutes or two times 15 minutes every day.\n\nBODY.METHODS.SUBJECTS.CONTROL GROUP:\nThe controls were told not to make any lifestyle changes. They met the physical therapist (CT) for one hour at three times; baseline, follow up at 6 weeks and 6 months. After six months they were offered exercise classes or instructions and a home-exercise program.\n\nBODY.METHODS.OUTCOME MEASURES.PRIMARY OUTCOME:\nThe primary outcome measure was the disease-specific Knee injury and Osteoarthritis Outcome Score (KOOS) [18,19]. The KOOS assesses the patients' self-report of pain, other symptoms, activities of daily living, sport and recreation function, and knee-related quality of life, in 42 questions which take about 10 minutes to complete. The KOOS is scored from 0 to 100, separately for each subscale, 0 indicating extreme problems and 100 indicating no problems. A change of 10 points or more is considered a clinically significant change [20]. The questionnaire and scoring manual can be found at . The Western Ontario and McMaster Osteoarthritis Index (WOMAC) [21] is included in the KOOS, and WOMAC scores can also be calculated.\n\nBODY.METHODS.OUTCOME MEASURES.SECONDARY OUTCOME:\nSecondary outcome measures were the Short Form-36 item (SF-36), ergometer test, and five tests of functional performance. The SF-36 is a generic, widely used measure of general health status, which comprises eight subscales: Physical Functioning (PF), Role-Physical (RP), Bodily Pain (BP), General Health (GH), Vitality (VT), Social Functioning (SF), Role-Emotional (RE) and Mental Health (MH) [22]. The SF-36 is self-explanatory and takes about 10 minutes to complete. The SF-36 is scored from 0 to 100, 0 indicating extreme problems and 100 indicating no problems. The subscales assessing mainly physical components (PF, RP, BP, GH) were summarized to a physical component summary score (PCS), and the mental subscales (VT, SF, RE, MH) to a mental component summary score (MCS) [23]. Values are norm-based scored, using the U.S. general population norms from 1998. Each scale has the mean of 50 and standard deviation of 10. Scale score below 50 indicates a health status below average, and a score above 50 indicates a health status above average. Questionnaires were distributed prior to randomization at baseline, after 6 weeks, and 6 months. A bicycle ergometer test and five tests of functional performance were assessed (Figure 2). Figure 2Tests of functional performance. A) Åstrand's cycle-ergometer test [24]. B) Rising on one leg from sitting on lowest possible height [25,26]. C) One-leg hop [25], [27]. D) Lateral step-up [28]. E) One-leg semi squatting; maximum number during 30 sec. [26]. F) Heel-rising on one leg; maximum number during 20 sec. [26], [29]. 1. Åstrand's bicycle-ergometer test [24] (Fig 2A). 2. Rising on one leg, from sitting on lowest possible height [25,26] (Fig 2B). 3. One-leg hop [25,27] (Fig 2C). 4. Lateral step-up [28] (Fig 2D). 5. One-leg semi squatting; maximum number during 30 seconds [26] (Fig 2E). 6. Heel-raising on one leg; maximum number during 20 seconds [26,29] (Fig 2F). Tests of functional performance were recorded on three occasions: prior to randomization at baseline, after 6 weeks, and at 6 months. To assess compliance the number of exercise occasions attended was noted.\n\nBODY.METHODS.STATISTICS:\nPost-hoc, a power analysis was performed to estimate the number of patients needed to show a clinically significant difference between groups. Estimating the least clinical significant difference to be 11 ± 15 KOOS points, a total of 30 subjects in each group were needed to detect a difference with 80% power, p = 0.05. Data were analyzed using nonparametric tests. P-values of less than or equal to 0.05 were considered to be significant, and all tests were two-tailed. To compare groups, Mann-Whitney U-test was used. Friedman's test was used for repeated measures analysis of variance. Six weeks was considered as the time-point of primary interest, and 6 months as follow-up. Wilcoxon signed rank test was performed to compare changes from baseline to six weeks and 6 months respectively. Analyses were performed using SPSS 12.0.1 for Windows [30]. The study was approved by the Research Ethics Committee at Lund University, Sweden (LU 99–98), and is in compliance with the Helsinki Declaration.\n\nBODY.RESULTS.SUBJECTS:\nThe mean age of the 61 included subjects was 56 ± 6 years, and the mean BMI was 29.5 ± 4.8 kg/m2. Patient characteristics are shown in table 1. Twenty-eight patients in each group were available for follow-up. The reasons for dropout were lack of time, reorganization at work, sudden illness, and increased knee symptoms (Figure 1). There were no clinically significant differences in baseline characteristics between the groups. Patient characteristics are shown in table 1. Table 1 Patient characteristics at baseline Exercise group n = 30 Control group n = 31 p-value Age (years) mean ± SD (range) 54.8 ± 7.1 (36–64) 57.3 ± 4.7 (46–65) 0.16 Gender number (%) women 15 (50%) 16 (52%) 0.90 BMI (kg/m) 2 mean ± SD 29.6 ± 4.5 29.5 ± 5.1 0.78 Aerobic capacity (ml O 2 /kg x min) mean ± SD 25.9 ± 6.4 25.2 ± 4.9 0.66 KOOS* pain 60 ± 18 64 ± 19 0.38 KOOS* symptoms 63 ± 20 66 ± 18 0.67 KOOS* ADL 69 ± 18 71 ± 21 0.76 KOOS* sport & recreation 34 ± 31 37 ± 29 0.54 KOOS* QOL 40 ± 15 46 ± 21 0.31 Knee Injury and Osteoarthritis Outcome Score [ 18 , 19 ] Score from 0–100, worst to best. \n\nBODY.RESULTS.COMPLIANCE:\nThe total number of performed supervised exercise sessions by the 28 patients available for follow-up in the intervention group was 302/336 (89.9%). Patients participated on average in 11 out of 12 possible exercise classes (12 classes (n = 11), 11 (n = 9), 10 (n = 6), 9 (n = 1), 2 (n = 1)). The most common reason for absence was illness not related to knee osteoarthritis, and work-related lack of time.\n\nBODY.RESULTS.BETWEEN-GROUP DIFFERENCES:\nThere was no difference between groups in pain or self-estimated function at either 6 week or 6 month follow-up. Quality of life improved significantly in the exercise group compared to the control group at 6 weeks (4.0 vs. -0.7, p = 0.05) and the results persisted at 6 months (5.1 vs. -2.3, p = 0.02, Table 2) Table 2 Comparisons of change in Knee injury and Osteoarthritis Outcome Score (KOOS) ‡ [ 18 , 19 ] subscales between exercise and control group KOOS Subscales Exercise group Control group Change in KOOS score* 95 % CI Change in KOOS score* 95 % CI p † Pain 6 w 1.8 -3.2 – 6.8 -0.3 -6.2 – 5.7 0.49 6 m 3.1 -1.9 – 8.2 -1.1 -6.6 – 4.4 0.32 Symptom 6 w 0.2 -5.1 – 5.6 -3.8 -7.7 – 0.0 0.07 6 m 1.0 -3.8 – 5.8 -3.4 -8.8 – 1.9 0.31 ADL 6 w 2.0 -2.3 – 6.3 -0.6 -7.0 – 5.8 0.96 6 m 0.9 -3.8 – 5.6 -1.9 -7.7 – 3.9 0.61 SportRec 6 w 1.2 -7.9 – 10.4 -4.4 -12.6 – 3.7 0.22 6 m 0.5 -10.1 – 11.2 -8.3 -19.5 – 2.8 0.32 QOL 6 w 4.0 -0.4 – 8.5 -0.7 -5.6 – 4.3 0.05 6 m 5.1 -0.7 – 11.0 -2.3 -9.5 – 4.9 0.02 * negative = worsening, positive = improvement † p-value for between group differences in change over time ‡ [ 18 , 19 ] The individual differences ranged from clinically significant improvement of at least 10 points to clinically significant deterioration in all KOOS subscales and in both the exercise and control group (Figure 3). Figure 3Change in KOOS pain score at six weeks. The individual change in KOOS pain at 6 weeks compared to baseline ranged from improvement to worsening, in both exercise and control group. A change of 10 points or more is considered clinically significant [20]. A similar pattern was seen for all KOOS and SF-36 subscales.\n\nBODY.RESULTS.BETWEEN-GROUP DIFFERENCES.SECONDARY OUTCOMES:\nA significant improvement was found in the exercise group compared to the control group at six weeks with regard to the SF-36 Mental Component Summary scale (MCS) (2.1 vs -1.6, p = 0.04). At six months follow-up this difference was no longer persistent (Table 3). Table 3 Comparisons of change in SF-36 Physical and Mental Components Summaries (PCS and MCS) [ 23 ] between exercise and control group. Short Form-36 item (SF-36) [22] Exercise group Control group mean 95%CI mean 95%CI p* Physical Component Summary (PCS) Baseline 42.5 24.4 – 57.5 43.8 24.2 – 57.3 0.49 Change at 6 weeks 3.0 -5.9 – 13.4 0.3 -15.2 – 12.6 0.13 Change at 6 months 3.0 -5.9 – 16.3 -0.7 -14.8 – 9.8 0.09 Mental Component Summary (MCS) Baseline 55.6 40.2 – 66.2 56.3 37.0 – 67.0 0.63 Change at 6 weeks 1.6 -10.6 – 15.0 -2.1 -16.9 – 11.5 0.04 Change at 6 months 0.7 -18.1 – 13.2 -0.7 -16.8 – 12.8 0.40 * Comparison between groups Improvements in functional performance of 0–20 % were seen in both groups at six weeks and six months. There was no difference in improvement between exercisers and controls (p = 0.08–0.9). See additional file 2 for the change in functional performance.\n\nBODY.DISCUSSION.MAIN MESSAGE:\nSix weeks of intensive exercise had no effect on self-reported pain or function in middle-aged patients with symptomatic and moderate-severe radiographic knee osteoarthritis.\n\nBODY.DISCUSSION.COMPARISONS WITH OTHER STUDIES:\nQuite opposite to previously published studies on exercise in knee osteoarthritis we found no improvement in pain or function. Possible reasons for this include our study group having moderate to severe osteoarthritis compared with mild to moderate in most previous studies, being younger than previously studied groups and the intervention being of comparably high intensity. It has been suggested that the responsiveness to exercise is modified by the loss of joint space width [31]. The homogeneity of this study population, with regard to radiographic changes, provided us the possibility to study the effects of exercise on patients with moderate to severe radiographic knee osteoarthritis. Can significant improvements of pain or self-reported function be expected in patients with radiographic knee osteoarthritis corresponding to Kellgren & Lawrence grade 3 or more? In this study, no improvements were seen on group level in pain or function. However, regular exercise in general is important to prevent diseases caused by inactivity [6], and thus patients with knee osteoarthritis should be encouraged to exercise. In clinical practice, patients with severe knee osteoarthritis should have treatments based on individual preferences and different stages of motivation [32]. It can be argued that the exercise intensity was too high for this group with moderate to severe knee osteoarthritis. Even though the intensity of each exercise was individually adapted, all individuals exercised at a minimum of 60% of HR max. It has been suggested that pain during exercise might be a protective mechanism in knee osteoarthritis, i.e. an increase in pain from too intensive exercises may restrain patients from further joint loading, which otherwise could cause further cartilage damage [33]. Patients in the current study were told to reduce the exercise intensity if pain during exercise was perceived as worse than 'acceptable', or persisted more than 24 hours. It is suggested that the different degrees of varus-valgus laxity should be taken into account in exercise interventions, to enhance the functional outcome [34,35]. Severe knee osteoarthritis is associated with a hip-knee-ankle malalignment and an increase in varus-valgus laxity compared to healthy knees [36]. It is possible that varus-valgus laxity mediated the effect of exercise on pain since all patients had radiographic changes corresponding to Kellgren and Lawrence grade III or more. Malalignment may cause increased joint loads, and greater quadriceps strength might further increase joint load by the muscles compressing the articular surfaces [37]. Younger patients are usually more physically active than elderly [38], and have higher demands on level of physical function and physical performance at work or leisure time. Thus, moderate to severe knee osteoarthritis might be perceived as more disabling by younger individuals compared to elderly. Our study population was younger (<65 years) and comprised more men (49%) than most other populations with knee osteoarthritis described in randomized controlled trials of exercise [13-15,39,40], which might have reduced the effect on self-reported function in the present study. This study showed no significant differences on self-reported pain and function either between or within groups. A post-hoc analysis was performed to study the possibility that the benefit from exercise was larger in subjects with worse pain at baseline. Fifteen patients in the exercise group were compared to 13 from the control group who had worse than total group median pain score (KOOS Pain 58 on a 0–100, worst to best scale) at baseline. The groups had comparable patient characteristics. The changes seen in these subgroups were however not different from the changes seen in the total groups. A possible limitation could be lack of power. A post-hoc analysis was performed to estimate the number of patients needed to show a clinically significant difference of 11 ± 15 KOOS-points [20]. The standard deviation of 15 is supported by results from randomized controlled trials of glucosamine supplementation [41] and a nutritional supplement [42] for knee osteoarthritis, where significant group differences were found in KOOS pain and ADL subscales. The number of subjects in each treatment arm in these RCT:s ranged from 15 to 27. The standard deviations in KOOS subscales have not previously been determined in exercise interventions. Only one of the five KOOS subscales showed a statistical significant improvement, and it can not be excluded that this result could be due to chance. The improvement of the KOOS subscale Quality Of Life in the exercise group was of doubtful clinical significance, however the improvement persisted over time, and is in accordance with previous findings of impact from exercise on mental health aspects in patients with knee osteoarthritis [31,43,44]. Group dynamics, support, or attention received may possibly have influenced the quality of life more than the exercise itself in the present study. Psychosocial factors are important determinants of physical function [45], and our results suggest that supervised exercises and follow-up are important, and that quality of life should be evaluated in osteoarthritis interventions.\n\nBODY.CONCLUSION:\nA six-week high-intensive exercise program had no effect on pain or function in middle-aged patients with moderate to severe radiographic knee OA. Some effect was seen on quality of life in the exercise group compared to the control group.\n\nBODY.COMPETING INTERESTS:\nThe author(s) declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nCT participated in design, exercise intervention, assessments and follow-ups, statistical analyses and writing. ER participated in design, analysis and interpretation of the data, and critically revised the article. IP participated in design and interpretation of the data and critically revised the article. CE initiated and obtained necessary permissions for the study, arranged the initial funding, and participated in the analyses, interpretation and revision of the manuscript. All authors read and approved the final manuscript.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: \n\nBODY.SUPPLEMENTARY MATERIAL:\nAdditional File 1Intensive exercise program CarinaClick here for file Additional File 2Tests of functional performance CarinaClick here for file\n\n**Question:** Compared to No exercise what was the result of Exercise on Knee injury and Osteoarthritis Outcome Score quality of life subscale at 6 weeks?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
557
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Lay support for pregnant women with social risk: a randomised controlled trial\n\n ABSTRACT.OBJECTIVES:\nWe sought evidence of effectiveness of lay support to improve maternal and child outcomes in disadvantaged families.\n\nABSTRACT.DESIGN:\nProspective, pragmatic, individually randomised controlled trial.\n\nABSTRACT.SETTING:\n3 Maternity Trusts in West Midlands, UK.\n\nABSTRACT.PARTICIPANTS:\nFollowing routine midwife systematic assessment of social risk factors, 1324 nulliparous women were assigned, using telephone randomisation, to standard maternity care, or addition of referral to a Pregnancy Outreach Worker (POW) service. Those under 16 years and teenagers recruited to the Family Nurse Partnership trial were excluded.\n\nABSTRACT.INTERVENTIONS:\nPOWs were trained to provide individual support and case management for the women including home visiting from randomisation to 6 weeks after birth. Standard maternity care (control) included provision for referring women with social risk factors to specialist midwifery services, available to both arms.\n\nABSTRACT.MAIN OUTCOME MEASURES:\nPrimary outcomes were antenatal visits attended and Edinburgh Postnatal Depression Scale (EPDS) 8–12 weeks postpartum. Prespecified, powered, subgroup comparison was among women with 2 or more social risks. Secondary outcomes included maternal and neonatal birth outcomes; maternal self-efficacy, and mother-to-infant bonding at 8–12 weeks; child development assessment at 6 weeks, breastfeeding at 6 weeks, and immunisation uptake at 4 months, all collected from routine child health systems.\n\nABSTRACT.RESULTS:\nAntenatal attendances were high in the standard care control and did not increase further with addition of the POW intervention (10.1 vs 10.1 (mean difference; MD) −0.00, 95% CI (95% CI −0.37 to 0.37)). In the powered subgroup of women with 2 or more social risk factors, mean EPDS (MD −0.79 (95% CI −1.56 to −0.02) was significantly better, although for all women recruited, no significant differences were seen (MD −0.59 (95% CI −1.24 to 0.06). Mother-to-infant bonding was significantly better in the intervention group for all women (MD −0.30 (95% CI −0.61 to −0.00) p=0.05), and there were no differences in other secondary outcomes.\n\nABSTRACT.CONCLUSIONS:\nThis trial demonstrates differences in depressive symptomatology with addition of the POW service in the powered subgroup of women with 2 or more social risk factors. Addition to existing evidence indicates benefit from lay interventions in preventing postnatal depression. This finding is important for women and their families given the known effect of maternal depression on longer term childhood outcomes.\n\nABSTRACT.TRIAL REGISTRATION NUMBER:\nISRCTN35027323; Results.\n\nBODY:\nStrengths and limitations of this studyLarge, robust, individual, randomised controlled trial to evaluate a real National Health Service service demonstrating differences in aspects of maternal psychological health from the addition of lay workers.Achieved excellent follow-up of both primary outcomes in intervention and control arms which is unusual in studies of women with social disadvantage.Baseline Edinburgh Postnatal Depression Scale scores not feasible in real service pragmatic trial, so change in score not obtained, but routine baseline data on current or previous mental health problem was the same across trial arms.Set within the UK maternity care system where standard care includes specialist midwife referral for women with some social risks, so effect of intervention may be greater in maternity systems without this.\n\nBODY.BACKGROUND:\nPostnatal depression is a major public health issue, with lasting effects on the child,1–3 and meta-analyses have reported prevalences of 13% and 19%.4–6 Women with antenatal depression, or with a previous history, are at higher risk,7 but most pregnant women who go on to have postnatal depression do not have these risk factors. It is known that postnatal depression is associated with social isolation and inadequate support.8 Many of the factors considered to be indicators of increased risk of adverse perinatal morbidity and mortality are also surrogates for social isolation, including teenage pregnancy,9 minority ethnic group,10\n11 experience of domestic violence,12 asylum seekers and refugees,13 and homelessness.14 A Cochrane review15 showed that taken as a group, psychosocial and psychological interventions were more effective in preventing postnatal depression than usual care, but there is little evidence regarding lay support except among women screened positive for possible depression. A recent synthesis of barriers to engagement with maternity services in women with social disadvantage16 suggested that lay workers providing non-judgemental support, working in conjunction with antenatal services, would be well received by women, however, evidence on effectiveness is lacking. The need to provide additional lay support (in this instance Pregnancy Outreach Workers, POWs) to women with identified social risk factors had been recognised in the West Midlands, and a service developed. The hypothesis was that this might improve engagement with maternity services (and thereby improve maternal and neonatal birth outcomes), and reduce postnatal depression, and we undertook a pragmatic randomised controlled trial to evaluate this.\n\nBODY.METHODS.DESIGN:\nThe study was a pragmatic, individually randomised, controlled trial across a UK geographical area containing three maternity units, where social risk factors are systematically identified at routine midwife antenatal booking. Nulliparous women under 28 weeks gestation, with social risk factors, were eligible. Exclusions were women under 16 years of age and teenagers already recruited to the Family Nurse Partnership Trial. Multiparous women were not included since some social support was already available for this group which could have masked a trial effect. Potentially eligible women (ie, nulliparous women with one or more social risk factor) were identified at midwife antenatal booking and given information about the trial. Following agreement, they were referred to specifically trained midwives who obtained informed consent, and randomised women. Randomisation to standard maternity care, or addition of the POW service was by telephone using a registered trials unit. Randomisation lists were computer generated (by trial statistician) using random block sizes (4–12) and stratified for Maternity Trust. POWs were trained to provide individual case management for the women including home visits, and were integrated into the community midwifery teams. Objectives were to encourage women to attend antenatal appointments, make healthy lifestyle choices, to provide social/emotional support, and help ensure benefits, housing difficulties and mental health problems were managed. In the postnatal period (to 6 weeks postpartum), POWs also provided breast feeding and advice about infant care. The POW service was developed before the trial began, but not available outside the trial, and was provided by an independent organisation, who had access to supervision from experts with specific skills and knowledge. Standard UK maternity care (control) included provision for referring women with social risk factors to specialist midwives or directing them to other agencies but did not include the offer of the POW service.\n\nBODY.METHODS.OUTCOME MEASURES, DATA COLLECTION AND FOLLOW-UP:\nThe two primary outcomes were engagement with antenatal care and maternal postnatal depression 8–12 weeks after birth. Antenatal attendance was assessed by number of antenatal visits attended, including all visits with a healthcare professional (midwife, obstetrician, mental health specialist) in hospital or community except for routine dating and abnormality scans. Maternal depression was assessed using the Edinburgh Postnatal Depression Scale17 (EPDS) at 8–12 weeks postpartum by postal/telephone questionnaire. We chose EPDS as it is the most commonly used validated instrument to assess postpartum symptoms. The original Cox publication17 quotes a cut-off score as ≥13, so we present data for that.\n\nBODY.METHODS.SECONDARY OUTCOMES:\nMaternal and neonatal birth outcomes included routinely collected birth outcome data detailed in online supplementary material. Data to evaluate other maternal psychological outcomes (self-efficacy and bonding) were collected using validated tools 8–12 weeks postpartum (Pearlin and Schooler Mastery Scale18 and Mother-to-infant Bonding Scale19). Longer term infant outcomes: attendance at child development assessments and breastfeeding at 6 weeks and immunisation uptake at 4 months were collected from routine child health systems (detailed in see online supplementary information). 10.1136/bmjopen-2015-009203.supp1Supplementary data\n\nBODY.METHODS.DATA COLLECTION:\nCollection of demographic data, gestation, ethnicity, medical history at booking and systematically assessed social risk factors (table 1) were part of midwife routine antenatal booking information and available for trial use. Blinding of women and caregivers was not possible, but those who collected/entered data remained blind to allocation. Table 1 Baseline characteristics and description of social risk factors identified at randomisation Baseline characteristics POW n=662 Standard care n=662 Maternal age (years) median, IQR 21.8 (19.0, 25.5) 21.5 (18.8, 24.6) Gestation at recruitment Median, IQR 12.9 (9.9, 17.3) 12.7 (9.9, 18.0) Under 12 weeks 288 (43) 283 (43) 12–19+6 weeks 266 (40) 252 (38) ≥20 weeks 108 (16) 127 (19) Ethnicity Africa (North Africa, sub-Sahara, other) 41 (6) 46 (8) Asia Pakistan 100 (15) 107 (16) India 26 (4) 27 (4) Bangladesh 24 (4) 19 (3) Other 22 (3) 16 (2) Caribbean 24 (4) 45 (7) European Britain 320 (48) 315 (48) Eastern Europe 23 (4) 20 (3) Other 6 (1) 6 (1) Middle East 23 (4) 19 (3) Other 53 (8) 42 (6) Index of multiple deprivation from postcode at recruitment Quintile 1 494 (75) 488 (74) Quintile 2 99 (15) 110 (17) Quintile 3 51 (8) 49 (7) Quintile 4 15 (2) 13 (2) Quintile 5 3 (<1) 2 (<1) Medical history noted at booking 320 (48) 301 (45) Social risk factor Housing problems such as rent arrears, temporary accommodation registered with National Asylum Support Service (NASS) or of No Fixed Abode (NFA) 282 (43) 262 (40) Teen parent (under 20 years old) 230 (35) 249 (38) Smoking 192 (29) 183 (28) Difficulty with the English language both spoken and written 176 (27) 169 (26) Identified benefit problem 154 (23) 160 (24) UK resident for under a year 116 (18) 93 (14) Clinical diagnosis of past or present mental illness 100 (15) 96 (15) No support from either partner or family or friend 63 (10) 80 (12) Body mass index ≥35 34 (5) 33 (5) Body mass index ≤18 32 (5) 26 (4) Late booking (defined as booking after 18 weeks gestation) 28 (4) 31 (5) Woman/household member in receipt of social services support, including child protection 24 (4) 34 (5) Drug misuse including other's in the household 19 (3) 17 (3) Domestic abuse 13 (2) 19 (3) Alcohol misuse 6 (1) 7 (1) DNA 2 or more antenatal appointments (under 28 weeks gestation) 5 (1) 8 (1) Number of social risk factors identified 1 social risk factor 174 (26) 194 (29) 2 social risk factors 269 (41) 247 (37) 3 social risk factors 141 (21) 145 (22) 4 or more social risk factors 78 (12) 76 (11) Values are numbers (percentages) unless otherwise stated. POW, Pregnancy Outreach Worker. Maternal and neonatal birth outcome data were obtained from hospital systems. Number of antenatal contacts was not recorded electronically, so was collected by hand-abstraction from notes. Maternal psychological outcomes were obtained from a postal questionnaire sent at 8–12 weeks postpartum using methods shown to maximise response rates.20 Women could opt to complete the questionnaire by phone, and interpreters were available. Details of these and the data quality checks are given in online supplementary material. Data on POW contacts, collected by the independent service and checked by the researchers, are shown in the online supplementary material.\n\nBODY.METHODS.STUDY OVERSIGHT:\nThe trial was not registered with the controlled trials register until after first patient recruitment. The trial was a pragmatic one to evaluate a real-time National Health Service implementation, so evaluation had to take place urgently, otherwise trial design would have been compromised. We were informed at that time that only CTIMP trials required trial registration prior to first patient enrolment. Our trial documentation is available for scrutiny, which provides evidence that this did not compromise our research probity.\n\nBODY.METHODS.SAMPLE SIZE JUSTIFICATION:\nThe sample size was 421 women per arm to provide 90% power (5% significance level) to detect 1.5 mean EPDS score reduction (SD 6), and provide greater than 90% power to detect 1.5–2 increased antenatal contacts (SD 6) allowing for 20% drop-out or loss to follow-up (detailed sample size rationale in published protocol).21 Prior to the trial, data was not available on numbers of social risk factors women had. Following a successful initial 6 months pilot where 475 women were recruited, it was observed that 64% had two or more social risk factors, and it was agreed to increase the sample size to allow power to detect differences in primary outcomes in the prespecified subgroup of women with two or more social risk factors, that is, so that the required sample size of 421 would be recruited within this subgroup. This powered subgroup gave a sample size of 658 women per arm.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nBaseline characteristics were summarised by control and intervention arms using means and SDs, medians and inter-quartile ranges, or numbers and percentages, as appropriate. For continuous outcomes, we reported mean (SE) in each arm, and mean difference. For continuous variables, statistical significance was assessed using two sample t tests assuming equal variances, or a Mann-Whitney U test, as appropriate. For binary outcomes, we reported the number (percentage) in each arm, along with relative risk (RR) and number needed to treat, calculated as 1 divided by risk difference; and also the risk difference (RD). For RRs, we calculated 95% CIs using standard normal approximation methods, and tested for statistical significance using χ2 test. Analyses were carried out in Stata V.12, according to intention to treat principles, and included women for whom outcomes could be collected. Analyses of primary outcomes were replicated independently. We undertook additional analysis of EPDS score ≥13 as a binary outcome17 to enable comparisons with other trials.\n\nBODY.RESULTS.WOMEN AND FOLLOW-UP:\nBetween July 2010 and October 2011, 1324 nulliparous women with identified social risk factors were randomised, 662 to standard maternity care and 662 to addition of the POW service. Follow-up data collection, which included both postal questionnaire and longer term infant outcomes data were completed by September 2013. Baseline characteristics were similar between groups including identified social risk factors (Table 1). Of women allocated standard care, 49 were not included in analyses (39 had subsequent miscarriage/termination, so no outcomes), and in those allocated POW service, 62 women were not included (30 had subsequent miscarriage/termination) (figure 1). Analyses, therefore, included 613 women allocated standard care, and 600 allocated the POW service. Primary outcome data regarding antenatal contacts were available for 99% of women in the standard care, and 100% in the POW service arms. Data from the questionnaire on EPDS 8–12 weeks postpartum was available for 85% and 82% of groups, respectively: 180 women completed the questionnaire via an interpreter, and 146 in English by phone as requested by the women. Figure 1Consort diagram. EPDS, Edinburgh Postnatal Depression Scale. Baseline characteristics of responders and non-responders to the postnatal questionnaire were broadly similar although marginally more non-responders were younger, recruited at earlier gestation, had housing problems, or were smokers (table 2). Table 2 Baseline characteristics for responders and non-responders to the questionnaire Responders n=1008 (83%) Non-responders n=205 (17%) Maternal age (years) median, IQR 21.0 (21.98, 22.58) 19.0 (20.48, 21.70) Gestation at recruitment Median, IQR 13.2 (14.05, 14.78) 12.6 (13.18, 14.59) Under 12 weeks 421 (41) 92 (45) 12–19+6 weeks 387 (38) 84 (41) ≥20 weeks 200 (20) 29 (14) Ethnicity Africa (North Africa, sub-Sahara, other) 68 (7) 12 (6) Asia Pakistan 163 (16) 26 (13) India 41 (4) 4 (2) Bangladesh 34 (3) 5 (2) Other 34 (3) 2 (1) Caribbean 53 (5) 12 (6) European Britain 475 (47) 110 (54) Eastern Europe 35 (3) 5 (2) Other 9 (0.9) 1 (1) Middle East 30 (3) 6 (3) Other 66 (7) 21 (10) Index of multiple deprivation from postcode at recruitment Quintile 1 750 (74) 143 (70) Quintile 2 151 (15) 40 (20) Quintile 3 81 (8) 17 (8) Quintile 4 22 (2) 5 (2) Quintile 5 4 (<0.5) NA Medical history noted at booking 687 (68) 140 (68) Social risk factors Housing problems such as rent arrears, temporary accommodation registered with National Asylum Support Service (NASS) or of No Fixed Abode (NFA) 392 (39) 107 (52) Teen parent (under 20 years old) 339 (34) 105 (51) Smoking 269 (27) 75 (37) Difficulty with the English language both spoken and written 277 (28) 40 (20) Identified benefit problem 244 (24) 51 (25) UK resident for under a year 166 (17) 24 (12) Clinical diagnosis of past or present mental illness 152 (15) 30 (15) No support from either partner or family or friend 99 (10) 28 (14) Body mass index ≥35 514 (5) 11 (5) Body mass index ≤18 46 (5) 10 (5) Late booking (defined as booking after 18 weeks gestation) 52 (5) 7 (3) Woman/household member in receipt of social services support, including child protection 37 (4) 16 (8) Drug misuse including other's in the household 23 (2) 9 (4) Domestic abuse 27 (3) 5 (2) Alcohol misuse 11 (1) 1 (0.5) DNA 2 or more antenatal appointments (under 28 weeks gestation) 7 (0.7) 5 (2) Social risk identified 0 social risk factor 1 (<0.5) NA 1 social risk factor 258 (26) 55 (27) 2 social risk factors 384 (38) 70 (34) 3 social risk factors 229 (23) 50 (24) 4 or more social risk factors 136 (14) 30 (15) Values are numbers (percentages) unless otherwise stated. NA, not applicable. \n\nBODY.RESULTS.PRIMARY OUTCOMES AND PRESPECIFIED SUBGROUP COMPARISONS:\nAntenatal attendance: No difference was seen between groups, either for all women or for women with two or more social risk factors (table 3). Table 3 Primary outcomes and prespecified subgroup analysis Antenatal attendance POW n=599 Standard care n=604 Mean difference (95% CI) p Value Number of contacts, mean (SE) 10.1 (0.14) 10.1 (0.13) −0.00 (−0.37 to 0.37) 0.99 Number with ≥10 contacts 322 (54.3) 320 (53.5) RR=1.01 (0.91 to 1.13) 0.78 Number of social risk factors 1 social risk factor 9.9 (0.27) n=152 10.0 (0.23) n=173 −0.19 (−0.89 to 0.51) 0.59 2 or more social risk factors 10.2 (0.16) n=440 10.1 (0.15) n=425 0.06 (−0.37 to 0.50) 0.82 EPDS POW n=489 (49) Standard Care n=519 (51) Mean Difference (95% CI) p Value NNT Mean, SE 6.76 (0.23) 7.35 (0.24) −0.59 (−1.24 to 0.06) 0.08 EPDS≥13 61 (12) 87 (17) RR=0.74 (0.55 to 1.01) 0.05 23 Number of social risk factors 1 social risk factor n=128 n=159 Mean, SE 6.8 (0.48) 6.9 (0.42) −0.14 (−1.38 to 1.10) 0.82 EPDS≥13 13 (10) 24 (15) RR=0.67 (0.36 to 1.27) 0.21 20 2 or more social risk factors n=361 n=360 Mean, SE 6.8 (0.27) 7.6 (0.29) −0.79 (−1.56 to −0.02) 0.05 EPDS≥13 48 (13) 63 (18) RR=0.76 (0.54, 1.07) 0.12 24 Values are numbers (%) unless otherwise stated. EPDS, Edinburgh Postnatal Depression Scale; NNT, number to treat; POW, pregnancy outreach worker. Postnatal depression: The prespecified comparison for women with two or more social risk factors showed a statistically significant reduction in mean EPDS (MD −0.79 (95% CI −1.56 to −0.02) p=0.05), although no significant differences were seen in the mean EPDS (mean difference (MD) −0.59 (95% CI −1.24 to 0.06)) for all the women recruited. The additional analysis of EPDS as a binary outcome showed a relative risk reduction of 26% for those with an EPDS ≥13 (RR 0.74 (95% CI 0.55 to 1.01) p=0.05), which equates to a reduction of five percentage points (17% vs 12%, RD 0.04 (95% CI −0.00 to 0.09)). In the group with two or more social risk factors, there was a reduction of five percentage points for EPDS ≥13 (18% vs 13%), giving an RD −0.04 (95% CI −0.09 to 0.01) and RR 0.76 (95% CI 0.54 to 1.07).\n\nBODY.RESULTS.SECONDARY OUTCOMES.MATERNAL AND INFANT OUTCOME DATA:\nNo differences were seen in any secondary maternal or neonatal birth outcomes, including the adverse perinatal composite outcome (see online supplementary tables S1 and S2). 10.1136/bmjopen-2015-009203.supp2Supplementary tables Mother-to-infant bonding was significantly better in the intervention group for all women (MD −0.30 (95% CI −0.61 to 0.00) p=0.05), but did not achieve statistical significance for those with two or more social risk factors (MD −0.35 (95% CI −0.72 to 0.01) p=0.06). Maternal self-efficacy was higher, but not significantly so, in both the intervention group overall (MD 0.43 (95% CI −0.06 to 0.91) p=0.08) and in the group with two or more social risks (MD 0.48 (95% CI −0.08 to 1.04) p=0.09) (see online supplementary table S3). Routine child assessment attendance, primary immunisation uptake, and breastfeeding at 6–8 weeks did not differ between groups (see online supplementary table S4).\n\nBODY.RESULTS.SECONDARY OUTCOMES.DESCRIPTION OF POW SERVICE:\nData on intensity of the POW service showed over 17 000 contacts between POWs and women, 27% of which were face to face, with half of them lasting 1–2 h (see online supplementary table S5). Most contacts took place antenatally (77%). The most common type of support recorded as given by the POWs (see online supplementary table S6) were finance/legal/benefits (19%), emotional and health matters (17%) and housing (15%). Additional social risk factors were disclosed to the POWs after recruitment by 83 women, most commonly; social service/child protection 35; domestic abuse 30; housing problems 21.\n\nBODY.DISCUSSION:\nDespite prior indication of local low engagement with maternity care services in disadvantaged women, no difference in antenatal contacts was identified between trial groups. This was at the UK recommended level of 1022 visits in both groups. Various other initiatives to encourage antenatal attendance and engagement had already occurred, thereby reducing potential for further improvement. Since antenatal attendance was unaffected, it is not surprising that maternal and neonatal birth outcomes were no different between trial groups. This trial, however, provides some evidence of a benefit of lay support to maternal depression in women with social risk factors relative to similar controls: while there was no significant difference in mean EPDS for the intervention group as a whole, there was a significant difference in the powered subgroup of women with two or more social risk factors, and mother-to-infant bonding scores were better than among controls overall. Systematic reviews show that children of depressed mothers are more likely to suffer insecure attachment, behavioural problems, cognitive developmental deficits and difficulties in emotional functioning, with impaired bonding between mother and child.23 The implications of a reduction in maternal depression are likely to be of lasting importance to the child, family and more generally to society. The strengths of this trial are that it was an evaluation of an existing service using highest quality methodology with excellent balance between groups, including social risks, and it achieved excellent retention and follow-up which is uncommon among disadvantaged women. A possible limitation is that EPDS was not administered at baseline, but this was not feasible as a pragmatic trial evaluating a real service with inclusion based on routine maternity booking information. The difference in maternal depression we have seen might have been influenced by baseline differences in previous or current mental health problems, but prevalence of this was the same at 15% in the trial groups. Our results could also have been influenced by the fact that 25 women recruited to the intervention group subsequently withdrew relative to only two in the control group, however, this was almost entirely a result of the women deciding that they did not want to continue with the POW service after meeting their POW, and not unsurprising within a real service situation. Improvements in aspects of maternal psychological health in women who received support from the POWs are plausible. For any service-level intervention to be effective it must be implemented and must show impact on the short-term factors that mediate improved long-term outcomes on the service user.24 In the case of the POW service, we have evidence that the service was implemented with commitment: there was an average of over six face-to-face contacts per woman, over half of which exceeded 1 h, and an overall average of more than 24 total contacts per woman. The ingredients shown in the literature to characterise an effective service, practical and emotional support,25 were also provided, and evidence that the POWs achieved positive relationships with women comes from the observation that many divulged sensitive information, for example, domestic abuse. The Cochrane review of 'Psychosocial and psychological interventions for preventing postpartum depression'15 identified 28 trials, involving almost 17 000 women with types of intervention divided into psychological (eg, debriefing, cognitive behavioural therapy) and psychosocial interventions (eg, antenatal/postnatal groups, professional/lay home visits). The review concluded that as a group these interventions significantly reduced the development of postpartum depression. However, only seven trials were of lay interventions, three of which recruited women screened positive for probable depression, and none of the remaining four trials were effective in preventing postnatal depression. No difference in mean depression scores at final study assessment overall was seen in the lay support trials (MD −10 (−0.20 to 0.01)), and the review recommended further trials of support by lay individuals. Addition of data from our trial to this meta-analysis indicates a significant reduction in mean depression scores MD −0.10 (−0.18 to −0.03) in lay support trials (figure 2). Before our trial, therefore, evidence was inconclusive on whether postnatal depression could be prevented through a lay-based intervention, except among women already exhibiting possible depression. Figure 2Forest plot of difference in mean depression scores at final study assessment in lay-based interventions. Two of the seven lay worker trials in the Cochrane review did not report mean depression score at final study assessment. One small trial (n=65) of women screened positive for probable depression reported depression diagnosis and showed a reduction with lay support, and the other in India (n=468) reported depressive symptomatology and showed no difference. Given that UK standard maternity care routinely provides some specialist services to support women with social risks, in international contexts where such standard services are lacking, benefit from a similar POW service might be greater than evidenced here. Moreover, this trial only included nulliparous women, and it is plausible that the effect of the service may be greater in multiparous women, likely to have more social risks. This trial provides evidence that a lay support service targeted to women with two or more social risk factors improves aspects of maternal psychological health relative to controls; such improvements are likely to be of lasting impact due to the known effect of maternal depression and poor attachment on longer term childhood outcomes. This, together with the relatively low costs of the service (approximately £500 000 for 1000 women annually), means that consideration should be given by policymakers to introduction of a lay support service.\n\n**Question:** Compared to standard maternity care what was the result of additional lay support (in this instance Pregnancy Outreach Workers, POWs) on Antenatal attendances?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
558
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Lay support for pregnant women with social risk: a randomised controlled trial\n\n ABSTRACT.OBJECTIVES:\nWe sought evidence of effectiveness of lay support to improve maternal and child outcomes in disadvantaged families.\n\nABSTRACT.DESIGN:\nProspective, pragmatic, individually randomised controlled trial.\n\nABSTRACT.SETTING:\n3 Maternity Trusts in West Midlands, UK.\n\nABSTRACT.PARTICIPANTS:\nFollowing routine midwife systematic assessment of social risk factors, 1324 nulliparous women were assigned, using telephone randomisation, to standard maternity care, or addition of referral to a Pregnancy Outreach Worker (POW) service. Those under 16 years and teenagers recruited to the Family Nurse Partnership trial were excluded.\n\nABSTRACT.INTERVENTIONS:\nPOWs were trained to provide individual support and case management for the women including home visiting from randomisation to 6 weeks after birth. Standard maternity care (control) included provision for referring women with social risk factors to specialist midwifery services, available to both arms.\n\nABSTRACT.MAIN OUTCOME MEASURES:\nPrimary outcomes were antenatal visits attended and Edinburgh Postnatal Depression Scale (EPDS) 8–12 weeks postpartum. Prespecified, powered, subgroup comparison was among women with 2 or more social risks. Secondary outcomes included maternal and neonatal birth outcomes; maternal self-efficacy, and mother-to-infant bonding at 8–12 weeks; child development assessment at 6 weeks, breastfeeding at 6 weeks, and immunisation uptake at 4 months, all collected from routine child health systems.\n\nABSTRACT.RESULTS:\nAntenatal attendances were high in the standard care control and did not increase further with addition of the POW intervention (10.1 vs 10.1 (mean difference; MD) −0.00, 95% CI (95% CI −0.37 to 0.37)). In the powered subgroup of women with 2 or more social risk factors, mean EPDS (MD −0.79 (95% CI −1.56 to −0.02) was significantly better, although for all women recruited, no significant differences were seen (MD −0.59 (95% CI −1.24 to 0.06). Mother-to-infant bonding was significantly better in the intervention group for all women (MD −0.30 (95% CI −0.61 to −0.00) p=0.05), and there were no differences in other secondary outcomes.\n\nABSTRACT.CONCLUSIONS:\nThis trial demonstrates differences in depressive symptomatology with addition of the POW service in the powered subgroup of women with 2 or more social risk factors. Addition to existing evidence indicates benefit from lay interventions in preventing postnatal depression. This finding is important for women and their families given the known effect of maternal depression on longer term childhood outcomes.\n\nABSTRACT.TRIAL REGISTRATION NUMBER:\nISRCTN35027323; Results.\n\nBODY:\nStrengths and limitations of this studyLarge, robust, individual, randomised controlled trial to evaluate a real National Health Service service demonstrating differences in aspects of maternal psychological health from the addition of lay workers.Achieved excellent follow-up of both primary outcomes in intervention and control arms which is unusual in studies of women with social disadvantage.Baseline Edinburgh Postnatal Depression Scale scores not feasible in real service pragmatic trial, so change in score not obtained, but routine baseline data on current or previous mental health problem was the same across trial arms.Set within the UK maternity care system where standard care includes specialist midwife referral for women with some social risks, so effect of intervention may be greater in maternity systems without this.\n\nBODY.BACKGROUND:\nPostnatal depression is a major public health issue, with lasting effects on the child,1–3 and meta-analyses have reported prevalences of 13% and 19%.4–6 Women with antenatal depression, or with a previous history, are at higher risk,7 but most pregnant women who go on to have postnatal depression do not have these risk factors. It is known that postnatal depression is associated with social isolation and inadequate support.8 Many of the factors considered to be indicators of increased risk of adverse perinatal morbidity and mortality are also surrogates for social isolation, including teenage pregnancy,9 minority ethnic group,10\n11 experience of domestic violence,12 asylum seekers and refugees,13 and homelessness.14 A Cochrane review15 showed that taken as a group, psychosocial and psychological interventions were more effective in preventing postnatal depression than usual care, but there is little evidence regarding lay support except among women screened positive for possible depression. A recent synthesis of barriers to engagement with maternity services in women with social disadvantage16 suggested that lay workers providing non-judgemental support, working in conjunction with antenatal services, would be well received by women, however, evidence on effectiveness is lacking. The need to provide additional lay support (in this instance Pregnancy Outreach Workers, POWs) to women with identified social risk factors had been recognised in the West Midlands, and a service developed. The hypothesis was that this might improve engagement with maternity services (and thereby improve maternal and neonatal birth outcomes), and reduce postnatal depression, and we undertook a pragmatic randomised controlled trial to evaluate this.\n\nBODY.METHODS.DESIGN:\nThe study was a pragmatic, individually randomised, controlled trial across a UK geographical area containing three maternity units, where social risk factors are systematically identified at routine midwife antenatal booking. Nulliparous women under 28 weeks gestation, with social risk factors, were eligible. Exclusions were women under 16 years of age and teenagers already recruited to the Family Nurse Partnership Trial. Multiparous women were not included since some social support was already available for this group which could have masked a trial effect. Potentially eligible women (ie, nulliparous women with one or more social risk factor) were identified at midwife antenatal booking and given information about the trial. Following agreement, they were referred to specifically trained midwives who obtained informed consent, and randomised women. Randomisation to standard maternity care, or addition of the POW service was by telephone using a registered trials unit. Randomisation lists were computer generated (by trial statistician) using random block sizes (4–12) and stratified for Maternity Trust. POWs were trained to provide individual case management for the women including home visits, and were integrated into the community midwifery teams. Objectives were to encourage women to attend antenatal appointments, make healthy lifestyle choices, to provide social/emotional support, and help ensure benefits, housing difficulties and mental health problems were managed. In the postnatal period (to 6 weeks postpartum), POWs also provided breast feeding and advice about infant care. The POW service was developed before the trial began, but not available outside the trial, and was provided by an independent organisation, who had access to supervision from experts with specific skills and knowledge. Standard UK maternity care (control) included provision for referring women with social risk factors to specialist midwives or directing them to other agencies but did not include the offer of the POW service.\n\nBODY.METHODS.OUTCOME MEASURES, DATA COLLECTION AND FOLLOW-UP:\nThe two primary outcomes were engagement with antenatal care and maternal postnatal depression 8–12 weeks after birth. Antenatal attendance was assessed by number of antenatal visits attended, including all visits with a healthcare professional (midwife, obstetrician, mental health specialist) in hospital or community except for routine dating and abnormality scans. Maternal depression was assessed using the Edinburgh Postnatal Depression Scale17 (EPDS) at 8–12 weeks postpartum by postal/telephone questionnaire. We chose EPDS as it is the most commonly used validated instrument to assess postpartum symptoms. The original Cox publication17 quotes a cut-off score as ≥13, so we present data for that.\n\nBODY.METHODS.SECONDARY OUTCOMES:\nMaternal and neonatal birth outcomes included routinely collected birth outcome data detailed in online supplementary material. Data to evaluate other maternal psychological outcomes (self-efficacy and bonding) were collected using validated tools 8–12 weeks postpartum (Pearlin and Schooler Mastery Scale18 and Mother-to-infant Bonding Scale19). Longer term infant outcomes: attendance at child development assessments and breastfeeding at 6 weeks and immunisation uptake at 4 months were collected from routine child health systems (detailed in see online supplementary information). 10.1136/bmjopen-2015-009203.supp1Supplementary data\n\nBODY.METHODS.DATA COLLECTION:\nCollection of demographic data, gestation, ethnicity, medical history at booking and systematically assessed social risk factors (table 1) were part of midwife routine antenatal booking information and available for trial use. Blinding of women and caregivers was not possible, but those who collected/entered data remained blind to allocation. Table 1 Baseline characteristics and description of social risk factors identified at randomisation Baseline characteristics POW n=662 Standard care n=662 Maternal age (years) median, IQR 21.8 (19.0, 25.5) 21.5 (18.8, 24.6) Gestation at recruitment Median, IQR 12.9 (9.9, 17.3) 12.7 (9.9, 18.0) Under 12 weeks 288 (43) 283 (43) 12–19+6 weeks 266 (40) 252 (38) ≥20 weeks 108 (16) 127 (19) Ethnicity Africa (North Africa, sub-Sahara, other) 41 (6) 46 (8) Asia Pakistan 100 (15) 107 (16) India 26 (4) 27 (4) Bangladesh 24 (4) 19 (3) Other 22 (3) 16 (2) Caribbean 24 (4) 45 (7) European Britain 320 (48) 315 (48) Eastern Europe 23 (4) 20 (3) Other 6 (1) 6 (1) Middle East 23 (4) 19 (3) Other 53 (8) 42 (6) Index of multiple deprivation from postcode at recruitment Quintile 1 494 (75) 488 (74) Quintile 2 99 (15) 110 (17) Quintile 3 51 (8) 49 (7) Quintile 4 15 (2) 13 (2) Quintile 5 3 (<1) 2 (<1) Medical history noted at booking 320 (48) 301 (45) Social risk factor Housing problems such as rent arrears, temporary accommodation registered with National Asylum Support Service (NASS) or of No Fixed Abode (NFA) 282 (43) 262 (40) Teen parent (under 20 years old) 230 (35) 249 (38) Smoking 192 (29) 183 (28) Difficulty with the English language both spoken and written 176 (27) 169 (26) Identified benefit problem 154 (23) 160 (24) UK resident for under a year 116 (18) 93 (14) Clinical diagnosis of past or present mental illness 100 (15) 96 (15) No support from either partner or family or friend 63 (10) 80 (12) Body mass index ≥35 34 (5) 33 (5) Body mass index ≤18 32 (5) 26 (4) Late booking (defined as booking after 18 weeks gestation) 28 (4) 31 (5) Woman/household member in receipt of social services support, including child protection 24 (4) 34 (5) Drug misuse including other's in the household 19 (3) 17 (3) Domestic abuse 13 (2) 19 (3) Alcohol misuse 6 (1) 7 (1) DNA 2 or more antenatal appointments (under 28 weeks gestation) 5 (1) 8 (1) Number of social risk factors identified 1 social risk factor 174 (26) 194 (29) 2 social risk factors 269 (41) 247 (37) 3 social risk factors 141 (21) 145 (22) 4 or more social risk factors 78 (12) 76 (11) Values are numbers (percentages) unless otherwise stated. POW, Pregnancy Outreach Worker. Maternal and neonatal birth outcome data were obtained from hospital systems. Number of antenatal contacts was not recorded electronically, so was collected by hand-abstraction from notes. Maternal psychological outcomes were obtained from a postal questionnaire sent at 8–12 weeks postpartum using methods shown to maximise response rates.20 Women could opt to complete the questionnaire by phone, and interpreters were available. Details of these and the data quality checks are given in online supplementary material. Data on POW contacts, collected by the independent service and checked by the researchers, are shown in the online supplementary material.\n\nBODY.METHODS.STUDY OVERSIGHT:\nThe trial was not registered with the controlled trials register until after first patient recruitment. The trial was a pragmatic one to evaluate a real-time National Health Service implementation, so evaluation had to take place urgently, otherwise trial design would have been compromised. We were informed at that time that only CTIMP trials required trial registration prior to first patient enrolment. Our trial documentation is available for scrutiny, which provides evidence that this did not compromise our research probity.\n\nBODY.METHODS.SAMPLE SIZE JUSTIFICATION:\nThe sample size was 421 women per arm to provide 90% power (5% significance level) to detect 1.5 mean EPDS score reduction (SD 6), and provide greater than 90% power to detect 1.5–2 increased antenatal contacts (SD 6) allowing for 20% drop-out or loss to follow-up (detailed sample size rationale in published protocol).21 Prior to the trial, data was not available on numbers of social risk factors women had. Following a successful initial 6 months pilot where 475 women were recruited, it was observed that 64% had two or more social risk factors, and it was agreed to increase the sample size to allow power to detect differences in primary outcomes in the prespecified subgroup of women with two or more social risk factors, that is, so that the required sample size of 421 would be recruited within this subgroup. This powered subgroup gave a sample size of 658 women per arm.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nBaseline characteristics were summarised by control and intervention arms using means and SDs, medians and inter-quartile ranges, or numbers and percentages, as appropriate. For continuous outcomes, we reported mean (SE) in each arm, and mean difference. For continuous variables, statistical significance was assessed using two sample t tests assuming equal variances, or a Mann-Whitney U test, as appropriate. For binary outcomes, we reported the number (percentage) in each arm, along with relative risk (RR) and number needed to treat, calculated as 1 divided by risk difference; and also the risk difference (RD). For RRs, we calculated 95% CIs using standard normal approximation methods, and tested for statistical significance using χ2 test. Analyses were carried out in Stata V.12, according to intention to treat principles, and included women for whom outcomes could be collected. Analyses of primary outcomes were replicated independently. We undertook additional analysis of EPDS score ≥13 as a binary outcome17 to enable comparisons with other trials.\n\nBODY.RESULTS.WOMEN AND FOLLOW-UP:\nBetween July 2010 and October 2011, 1324 nulliparous women with identified social risk factors were randomised, 662 to standard maternity care and 662 to addition of the POW service. Follow-up data collection, which included both postal questionnaire and longer term infant outcomes data were completed by September 2013. Baseline characteristics were similar between groups including identified social risk factors (Table 1). Of women allocated standard care, 49 were not included in analyses (39 had subsequent miscarriage/termination, so no outcomes), and in those allocated POW service, 62 women were not included (30 had subsequent miscarriage/termination) (figure 1). Analyses, therefore, included 613 women allocated standard care, and 600 allocated the POW service. Primary outcome data regarding antenatal contacts were available for 99% of women in the standard care, and 100% in the POW service arms. Data from the questionnaire on EPDS 8–12 weeks postpartum was available for 85% and 82% of groups, respectively: 180 women completed the questionnaire via an interpreter, and 146 in English by phone as requested by the women. Figure 1Consort diagram. EPDS, Edinburgh Postnatal Depression Scale. Baseline characteristics of responders and non-responders to the postnatal questionnaire were broadly similar although marginally more non-responders were younger, recruited at earlier gestation, had housing problems, or were smokers (table 2). Table 2 Baseline characteristics for responders and non-responders to the questionnaire Responders n=1008 (83%) Non-responders n=205 (17%) Maternal age (years) median, IQR 21.0 (21.98, 22.58) 19.0 (20.48, 21.70) Gestation at recruitment Median, IQR 13.2 (14.05, 14.78) 12.6 (13.18, 14.59) Under 12 weeks 421 (41) 92 (45) 12–19+6 weeks 387 (38) 84 (41) ≥20 weeks 200 (20) 29 (14) Ethnicity Africa (North Africa, sub-Sahara, other) 68 (7) 12 (6) Asia Pakistan 163 (16) 26 (13) India 41 (4) 4 (2) Bangladesh 34 (3) 5 (2) Other 34 (3) 2 (1) Caribbean 53 (5) 12 (6) European Britain 475 (47) 110 (54) Eastern Europe 35 (3) 5 (2) Other 9 (0.9) 1 (1) Middle East 30 (3) 6 (3) Other 66 (7) 21 (10) Index of multiple deprivation from postcode at recruitment Quintile 1 750 (74) 143 (70) Quintile 2 151 (15) 40 (20) Quintile 3 81 (8) 17 (8) Quintile 4 22 (2) 5 (2) Quintile 5 4 (<0.5) NA Medical history noted at booking 687 (68) 140 (68) Social risk factors Housing problems such as rent arrears, temporary accommodation registered with National Asylum Support Service (NASS) or of No Fixed Abode (NFA) 392 (39) 107 (52) Teen parent (under 20 years old) 339 (34) 105 (51) Smoking 269 (27) 75 (37) Difficulty with the English language both spoken and written 277 (28) 40 (20) Identified benefit problem 244 (24) 51 (25) UK resident for under a year 166 (17) 24 (12) Clinical diagnosis of past or present mental illness 152 (15) 30 (15) No support from either partner or family or friend 99 (10) 28 (14) Body mass index ≥35 514 (5) 11 (5) Body mass index ≤18 46 (5) 10 (5) Late booking (defined as booking after 18 weeks gestation) 52 (5) 7 (3) Woman/household member in receipt of social services support, including child protection 37 (4) 16 (8) Drug misuse including other's in the household 23 (2) 9 (4) Domestic abuse 27 (3) 5 (2) Alcohol misuse 11 (1) 1 (0.5) DNA 2 or more antenatal appointments (under 28 weeks gestation) 7 (0.7) 5 (2) Social risk identified 0 social risk factor 1 (<0.5) NA 1 social risk factor 258 (26) 55 (27) 2 social risk factors 384 (38) 70 (34) 3 social risk factors 229 (23) 50 (24) 4 or more social risk factors 136 (14) 30 (15) Values are numbers (percentages) unless otherwise stated. NA, not applicable. \n\nBODY.RESULTS.PRIMARY OUTCOMES AND PRESPECIFIED SUBGROUP COMPARISONS:\nAntenatal attendance: No difference was seen between groups, either for all women or for women with two or more social risk factors (table 3). Table 3 Primary outcomes and prespecified subgroup analysis Antenatal attendance POW n=599 Standard care n=604 Mean difference (95% CI) p Value Number of contacts, mean (SE) 10.1 (0.14) 10.1 (0.13) −0.00 (−0.37 to 0.37) 0.99 Number with ≥10 contacts 322 (54.3) 320 (53.5) RR=1.01 (0.91 to 1.13) 0.78 Number of social risk factors 1 social risk factor 9.9 (0.27) n=152 10.0 (0.23) n=173 −0.19 (−0.89 to 0.51) 0.59 2 or more social risk factors 10.2 (0.16) n=440 10.1 (0.15) n=425 0.06 (−0.37 to 0.50) 0.82 EPDS POW n=489 (49) Standard Care n=519 (51) Mean Difference (95% CI) p Value NNT Mean, SE 6.76 (0.23) 7.35 (0.24) −0.59 (−1.24 to 0.06) 0.08 EPDS≥13 61 (12) 87 (17) RR=0.74 (0.55 to 1.01) 0.05 23 Number of social risk factors 1 social risk factor n=128 n=159 Mean, SE 6.8 (0.48) 6.9 (0.42) −0.14 (−1.38 to 1.10) 0.82 EPDS≥13 13 (10) 24 (15) RR=0.67 (0.36 to 1.27) 0.21 20 2 or more social risk factors n=361 n=360 Mean, SE 6.8 (0.27) 7.6 (0.29) −0.79 (−1.56 to −0.02) 0.05 EPDS≥13 48 (13) 63 (18) RR=0.76 (0.54, 1.07) 0.12 24 Values are numbers (%) unless otherwise stated. EPDS, Edinburgh Postnatal Depression Scale; NNT, number to treat; POW, pregnancy outreach worker. Postnatal depression: The prespecified comparison for women with two or more social risk factors showed a statistically significant reduction in mean EPDS (MD −0.79 (95% CI −1.56 to −0.02) p=0.05), although no significant differences were seen in the mean EPDS (mean difference (MD) −0.59 (95% CI −1.24 to 0.06)) for all the women recruited. The additional analysis of EPDS as a binary outcome showed a relative risk reduction of 26% for those with an EPDS ≥13 (RR 0.74 (95% CI 0.55 to 1.01) p=0.05), which equates to a reduction of five percentage points (17% vs 12%, RD 0.04 (95% CI −0.00 to 0.09)). In the group with two or more social risk factors, there was a reduction of five percentage points for EPDS ≥13 (18% vs 13%), giving an RD −0.04 (95% CI −0.09 to 0.01) and RR 0.76 (95% CI 0.54 to 1.07).\n\nBODY.RESULTS.SECONDARY OUTCOMES.MATERNAL AND INFANT OUTCOME DATA:\nNo differences were seen in any secondary maternal or neonatal birth outcomes, including the adverse perinatal composite outcome (see online supplementary tables S1 and S2). 10.1136/bmjopen-2015-009203.supp2Supplementary tables Mother-to-infant bonding was significantly better in the intervention group for all women (MD −0.30 (95% CI −0.61 to 0.00) p=0.05), but did not achieve statistical significance for those with two or more social risk factors (MD −0.35 (95% CI −0.72 to 0.01) p=0.06). Maternal self-efficacy was higher, but not significantly so, in both the intervention group overall (MD 0.43 (95% CI −0.06 to 0.91) p=0.08) and in the group with two or more social risks (MD 0.48 (95% CI −0.08 to 1.04) p=0.09) (see online supplementary table S3). Routine child assessment attendance, primary immunisation uptake, and breastfeeding at 6–8 weeks did not differ between groups (see online supplementary table S4).\n\nBODY.RESULTS.SECONDARY OUTCOMES.DESCRIPTION OF POW SERVICE:\nData on intensity of the POW service showed over 17 000 contacts between POWs and women, 27% of which were face to face, with half of them lasting 1–2 h (see online supplementary table S5). Most contacts took place antenatally (77%). The most common type of support recorded as given by the POWs (see online supplementary table S6) were finance/legal/benefits (19%), emotional and health matters (17%) and housing (15%). Additional social risk factors were disclosed to the POWs after recruitment by 83 women, most commonly; social service/child protection 35; domestic abuse 30; housing problems 21.\n\nBODY.DISCUSSION:\nDespite prior indication of local low engagement with maternity care services in disadvantaged women, no difference in antenatal contacts was identified between trial groups. This was at the UK recommended level of 1022 visits in both groups. Various other initiatives to encourage antenatal attendance and engagement had already occurred, thereby reducing potential for further improvement. Since antenatal attendance was unaffected, it is not surprising that maternal and neonatal birth outcomes were no different between trial groups. This trial, however, provides some evidence of a benefit of lay support to maternal depression in women with social risk factors relative to similar controls: while there was no significant difference in mean EPDS for the intervention group as a whole, there was a significant difference in the powered subgroup of women with two or more social risk factors, and mother-to-infant bonding scores were better than among controls overall. Systematic reviews show that children of depressed mothers are more likely to suffer insecure attachment, behavioural problems, cognitive developmental deficits and difficulties in emotional functioning, with impaired bonding between mother and child.23 The implications of a reduction in maternal depression are likely to be of lasting importance to the child, family and more generally to society. The strengths of this trial are that it was an evaluation of an existing service using highest quality methodology with excellent balance between groups, including social risks, and it achieved excellent retention and follow-up which is uncommon among disadvantaged women. A possible limitation is that EPDS was not administered at baseline, but this was not feasible as a pragmatic trial evaluating a real service with inclusion based on routine maternity booking information. The difference in maternal depression we have seen might have been influenced by baseline differences in previous or current mental health problems, but prevalence of this was the same at 15% in the trial groups. Our results could also have been influenced by the fact that 25 women recruited to the intervention group subsequently withdrew relative to only two in the control group, however, this was almost entirely a result of the women deciding that they did not want to continue with the POW service after meeting their POW, and not unsurprising within a real service situation. Improvements in aspects of maternal psychological health in women who received support from the POWs are plausible. For any service-level intervention to be effective it must be implemented and must show impact on the short-term factors that mediate improved long-term outcomes on the service user.24 In the case of the POW service, we have evidence that the service was implemented with commitment: there was an average of over six face-to-face contacts per woman, over half of which exceeded 1 h, and an overall average of more than 24 total contacts per woman. The ingredients shown in the literature to characterise an effective service, practical and emotional support,25 were also provided, and evidence that the POWs achieved positive relationships with women comes from the observation that many divulged sensitive information, for example, domestic abuse. The Cochrane review of 'Psychosocial and psychological interventions for preventing postpartum depression'15 identified 28 trials, involving almost 17 000 women with types of intervention divided into psychological (eg, debriefing, cognitive behavioural therapy) and psychosocial interventions (eg, antenatal/postnatal groups, professional/lay home visits). The review concluded that as a group these interventions significantly reduced the development of postpartum depression. However, only seven trials were of lay interventions, three of which recruited women screened positive for probable depression, and none of the remaining four trials were effective in preventing postnatal depression. No difference in mean depression scores at final study assessment overall was seen in the lay support trials (MD −10 (−0.20 to 0.01)), and the review recommended further trials of support by lay individuals. Addition of data from our trial to this meta-analysis indicates a significant reduction in mean depression scores MD −0.10 (−0.18 to −0.03) in lay support trials (figure 2). Before our trial, therefore, evidence was inconclusive on whether postnatal depression could be prevented through a lay-based intervention, except among women already exhibiting possible depression. Figure 2Forest plot of difference in mean depression scores at final study assessment in lay-based interventions. Two of the seven lay worker trials in the Cochrane review did not report mean depression score at final study assessment. One small trial (n=65) of women screened positive for probable depression reported depression diagnosis and showed a reduction with lay support, and the other in India (n=468) reported depressive symptomatology and showed no difference. Given that UK standard maternity care routinely provides some specialist services to support women with social risks, in international contexts where such standard services are lacking, benefit from a similar POW service might be greater than evidenced here. Moreover, this trial only included nulliparous women, and it is plausible that the effect of the service may be greater in multiparous women, likely to have more social risks. This trial provides evidence that a lay support service targeted to women with two or more social risk factors improves aspects of maternal psychological health relative to controls; such improvements are likely to be of lasting impact due to the known effect of maternal depression and poor attachment on longer term childhood outcomes. This, together with the relatively low costs of the service (approximately £500 000 for 1000 women annually), means that consideration should be given by policymakers to introduction of a lay support service.\n\n**Question:** Compared to standard maternity care what was the result of additional lay support (in this instance Pregnancy Outreach Workers, POWs) on Mother-to-infant bonding?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
568
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Effects of 3-Dimensional Lumbar Stabilization Training for Balance in Chronic Hemiplegic Stroke Patients: A Randomized Controlled Trial\n\n ABSTRACT.OBJECTIVE:\nTo investigate the effects of the newly developed Spine Balance 3D system on the balance and gait abilities of hemiplegic stroke patients.\n\nABSTRACT.METHODS:\nTwenty-eight hemiplegic patients with chronic stroke were randomly assigned to an experimental (n=14) or control group (n=14). The experimental and control groups performed balance training by using the newly developed Spine Balance 3D system and the well-known Biodex Balance System 30 minutes per day, three times a week for 7 weeks. The Berg Balance Scale (BBS), 10-m walking test (10mWT), Timed Up and Go Test (TUG), Functional Reach Test (FRT), the Korean version of the Fall Efficacy Scale-International (KFES-I), trunk muscle strength and stability were evaluated before and after 7 weeks of intervention.\n\nABSTRACT.RESULTS:\nThe 10mWT improved significantly (p=0.001) in the experimental group (using the Spine Balance 3D system) but not in the control group, and core muscle strength, which we checked using Spine Balance 3D system evaluation program, improved more in the experimental group as well. The results of the BBS, FRT, TUG, KFES-I, and Biodex Balance System evaluation program improved in both groups after 7 weeks of balance training.\n\nABSTRACT.CONCLUSION:\nWe suggest that the newly-developed Spine Balance 3D system can be a more useful therapeutic tool for gait and dynamic balance rehabilitation in hemiplegic patients than a conventional 2D-based balance training system. A large-scale randomized controlled study is needed to prove the effect of this system.\n\nBODY.INTRODUCTION:\nA decrease in balance control can be caused by various factors, including central nervous system diseases (such as stroke and traumatic brain injury), musculoskeletal disorders (such as back pain or arthritis), and vestibular diseases. Loss of balance control decreases the ability and speed of patients' gait, especially in those with hemiplegia caused by brain damage. Fear of falling in these patients reduces their activity level and makes daily activities of living difficult for these patients. Therefore, improvements in balance control and mechanical movements are important treatment goals [1]. A combination of several factors, including vestibular, visual, somatosensory, and trunk strength, enables the maintenance of postural balance. Therefore, comprehensive, objective treatment methods are needed. Previous studies have reported on the relationship between gait ability, speed, and independence of performing daily activities from multiple angles. Physicians use various treatment methods and exercises, including trampoline training [2], visual feedback training [3], and sling exercise therapy for trunk muscles [456]. Along with the active development of rehabilitation equipment, physicians use many types of equipment that are already made in Korea in treatments to improve balance, including the iBalance (CyberMedic, Iksan, Korea) and Space Balance 3D (CyberMedic) systems. However, few studies exist on the actual effectiveness of this equipment, and established criteria to evaluate functional improvements are scarce. This study aimed to investigate whether the Spine Balance three-dimensional (3D) system, which was developed to strengthen the deep muscles of the vertebra via stabilization exercise of the lumbar spine, improves postural balance in patients with hemiplegia performing 3D rotational exercises. We expected that this exercise would increase trunk muscle strength and stabilize movement of the vertebra. In addition, this study aimed to study the improvement in gait and ability to carry out daily activities while proving the positive effects of using the Spine Balance 3D system's program and several balance control tests. The results were compared to those obtained with a Biodex Balance System [7], which is widely used for balance training, to prove its effectiveness.\n\nBODY.MATERIALS AND METHODS.SUBJECTS:\nThis study required patients to meet the following inclusion criteria: (1) patients at 6 months or more after stroke, (2) unilateral stroke (infarction, hemorrhage), (3) ability to understand and perform three-step verbal instructions, and (4) ability to stand independently. Patients with severe abnormalities in their biorhythms who require inpatient treatment and those who were deemed unqualified for the study were excluded. Thirty patients who met the requirements were chosen as subjects. The subjects were randomly divided into two groups of 15 to create experimental and control groups to be respectively treated using Spine Balance 3D (CyberMedic) and Biodex Balance System (Biodex Medical Systems, Shirley, NY, USA). The random distribution of the subjects into the experimental and control groups is based on a random allocation table in the order of registration of the subjects, and the process of patient recruitment took a total of 4 months. We conducted this prospective study at the Chonbuk National University Hospital, and we notified the subjects regarding the content of the study and obtained their written consent before the experiment was conducted. The hospital's board of audit and inspection approved our study.\n\nBODY.MATERIALS AND METHODS.METHOD:\nThe Berg Balance Scale (BBS), 10-m walking test (10mWT), Timed Up and Go (TUG) and Functional Reach Tests (FRT), and trunk strength evaluated using Spine Balance 3D system's evaluation program were used as clinical indicators to evaluate the level of function before the exercise. The Korean version of the Fall Efficacy Scale-International (KFES-I) was recorded using the information from the survey. The patients performed 30-minute exercises, three times a week for 7 weeks (Fig. 1). The Spine Balance 3D system allows balance training to be performed in 3D space detached from the ground surface by using a lift system that locks the hip and ankles to stabilize the body and prevent twisting. Exercises in eight directions (front, back, left, right, and diagonal) are possible in 3D space, and the system can be tilted up to 60° in each direction. The 3-axis sensor on the trunk accurately measures the movement of the patient's trunk and identifies and displays the center of gravity on the monitor (Fig. 2A). The experimental group underwent training in eight directions using the Spine Balance 3D system, starting from a 15° tilt and increasing up to 30° depending on the patient's condition. The control group underwent training by using the training mode in the Biodex Balance System. We configured the platform to the static state, and the patients underwent posture maintenance training and center of gravity transferring postural training in eight directions after initially aligning the center of gravity with the middle line of the monitor. We did not restrict any of the groups' activities to balance training, and we advised the subjects to perform their same daily activities as before (Fig. 2B).\n\nBODY.MATERIALS AND METHODS.METHOD.ASSESSMENT METHOD:\nBBS (range, 0–56 scores) and TUG indicated the dynamic balance, Biodex Balance System's evaluation program indicated stability, Spine Balance 3D system's evaluation program indicated trunk muscle strength, and 10mWT indicated gait ability. The FRT indicated static balance, and the KFES-I measured the risk of falling. The patients performed TUG, a test that measures the time it takes a patient to rise from a chair, walk 3 m, turn around, walk back to the chair and sit down, and a stopwatch was used to measure timing. We measured the time it takes a patient to walk a distance of 10 m marked by tapelines when performing the 10mWT, and sufficient space was provided before and after the 10 m region to allow acceleration and deceleration. The forward FRT was performed by measuring the difference between the locations of the 3rd metacarpophalangeal joint of the unaffected side from a normal standing position and from a maximally forward-leaning position, and a 100 cm-long ruler was set horizontally at the acromion level to measure the difference. The patients placed both clavicles perpendicular to the long ruler lines on the wall to avoid error caused by the decrease in ipsilateral muscle strength. We separately measured the values for the affected and unaffected side in the lateral FRT. The lateral FRT measures the differences in the location of the metacarpophalangeal joints after abduction of the arm on the desired side from a natural upright position and from a laterally tilted trunk position. If the strength of the affected arm was not sufficiently strong, we measured the acromion locations instead. The Biodex Balance System and Spine Balance 3D system objectively evaluated the balance control. We used Biodex Balance System's evaluation program to conduct postural stability test with eyes open and closed, along with the limits of the stability test. We conducted the postural stability test by having the subjects maintain a relaxed standing position with eyes open and closed for 10 seconds each. We obtained three measurements from each condition to calculate the overall stability index, which reflected the stability as it approximates 0. We conducted the limits of the stability test on an easy level. We obtained three measurements to calculate the overall direction control score, which reflected a higher ability to control direction as the score decreased. Spine Balance 3D system's blind and open modes were used to evaluate the balance control. The difference between the blind mode and the open mode is defined as the ability to display the actual balance status on the screen by using the sensors attached to the back of the patient. The monitor displayed the actual balance status in the open mode whereas the screen turned black in the blind mode to restrict compensation. We increased the tilt in each of the eight directions to 15° and 30° by 2°/s and stopped for 5 seconds at the maximum tilt (15° and 30°). The subjects maintained a certain trunk position, depending on the tilt, and the results were reported as the Balance Position Ratio (BRP), expressed as the percentage of deviation from reference for the direction and tilt measured using the trunk sensor system. A score close to 100% reflects a good trunk muscle strength.\n\nBODY.MATERIALS AND METHODS.METHOD.STATISTICAL ANALYSIS:\nWe performed the statistical analyses using SPSS ver. 18.0 (SPSS Inc., Chicago, IL, USA), and analyzed the demographics of the two groups and pre-treatment evaluations by using an independent t-test. We compared the pre-treatment evaluations with post-treatment evaluations in both groups to determine whether statistical changes were present. We analyzed the measured values before and after the treatment in each group by using Wilcoxon signed-rank tests, and considered only p-values less than 0.05 to be statistically significant.\n\nBODY.RESULTS.GENERAL CHARACTERISTICS OF SUBJECTS:\nThe experimental and control groups comprised 15 subjects each. However, one patient from the experimental group failed due to the aggravation of gout in the ankle joint, and a follow-up loss in the control group occurred due to a MERS coronavirus outbreak. Fourteen subjects in each group completed the clinical experiment. Table 1 shows the distribution of sex, age, average education, duration of stroke, and hemiplegic side in both groups. The demographics in the two groups did not show significant differences. The unaffected lateral FRT showed significantly higher results in the Biodex Balance System training group; whereas the rest of the tests showed no significant differences between the two groups (Table 2).\n\nBODY.RESULTS.TREATMENT EFFECTS:\nTable 3 shows that the experimental group showed significant improvements in all tests—BBS (p=0.001), TUG (p=0.001), forward FRT (p=0.001), affected lateral FRT (p=0.001), and unaffected lateral FRT (p=0.002)—when the values before and after training were compared in each group. The control group also showed significant improvements in the same tests. However, the results for the 10mWT showed only significant improvements in the experimental group (11.38±3.0 to 10.12±2.47 seconds; p=0.01); whereas the control group did not show significant improvements. The improvement levels of the trunk strength (BPR score) for the experimental group using Spine Balance 3D system's evaluation program showed significant improvements at the 15° open mode; whereas the control group did not show any significant improvement. However, both groups showed significant improvements during the experiment under the following three conditions: 15° blind, 30° open, and 30° blind (Table 3). In addition, among the three conditions used in Biodex Balance System's evaluation program, the experimental group showed significant improvements in a postural stability test with eyes open and closed under two conditions while the control group showed significant improvements in a postural stability test under a condition with closed eyes and a limit of stability test. As such, the two groups showed similar levels of improvement in terms of stability (Table 3).\n\nBODY.DISCUSSION:\nThe goal of this study was to investigate the effectiveness of the Spine Balance 3D system in improving gait and balance in patients with hemiplegia. This study confirms that balance training using the Spine Balance 3D system effectively improves dynamic balance, static balance, and gait by improving trunk muscle strength. Treatment using the Spine Balance 3D system showed significant improvements in gait, as measure in the 10mWT, compared to that achieved using the Biodex Balance System, and the Spine Balance 3D system's evaluation program showed that improvements in trunk control ability were relatively superior than those observed for the control group. The postural stability test, conducted using Biodex Balance System's evaluation program, revealed that the two groups showed similar levels of improvement in stability. The trunk stability maintains the overall balance and regulates the technical movement of the lower limbs. Hodges and Richardson [8] report that stabilization of the spine caused by the contraction of abdominal and multifidus muscles plays a role in inducing technical movement in the lower limbs. In addition, Kim et al. [9] report that trunk-activating exercises are important because weakening of the trunk is relevant to functional performance in patients with chronic stroke. Abdominal muscle strength exercises improve gait and balance in stroke patients [10], and improvements in trunk regulation increase dynamic balance, gait speed, and symmetrical movement of the trunk during gait in stroke patients [11]. Subsequently, various core stability exercises have been introduced to strengthen the trunk [12131415], and many types of modern equipment are currently in development, aiming to improve trunk strength through gait training. However, studies evaluating the effects of such equipment are rare. A study conducted 1-minute sit-up tests in a single-leg squat position on athletes after training with the Biodex Balance System and reported a relatively significant improvement in balance compared to the control group. This study proves that treatment using the Biodex Balance System improves stability by fortifying core strength [16]. Treatment using the Biodex Balance System significantly reduces the fear of falling (FES-I score >26) among the elderly, and their knee extensor and flexor isometric strength improves as a secondary gain [17]. Therefore, core muscle and lower extremity strength are expected to increase when training using the Biodex Balance System, and improvements in balance have been confirmed. Our study showed significant improvements not only in trunk muscle strength, but also in BBS, TUG, FRT, and KFES-I. This result coincides with the results from a study by Saeys et al. [18], which reports that trunk reposition error, trunk impairment scale, and TUG results improved in the weight-shifting training group compared to those in the control group. The only difference with the study by Saeys et al. [18] is that our weight-shifting training was conducted using the Biodex Balance System. We expect that the newly-developed Spine Balance 3D systems stabilize and fortify trunk muscles by inducing symmetrical contraction and relaxation of abdominal and multifidus muscles in 3D space when the body is tilted, and studies are currently in progress to determine its effectiveness. A recent study confirmed changes in the trunk muscle strength and body composition among elderly subjects after training using the Spine Balance 3D system. The experimental group showed a significant improvement in trunk muscle strength after analyzing the alignment of the system direction and tilt with the trunk sensors by using trunk maintenance ability as a reference for trunk muscle strength [19]. Our study showed a significant improvement in trunk muscle strength in both groups after the experiment when measured using the same method. However, the control group showed significant improvements in trunk muscle strength only under three conditions while the experimental group showed improvements in trunk muscle strength under all four tested conditions, and the experimental group showed a relatively higher improvement in the trunk muscle strength. The tests conducted using Biodex Balance System's evaluation program revealed that both the experimental and the control groups showed significant improvements in two of three conditions with similar magnitude. The experimental group showed significant improvements in a postural stability test with eyes open and closed under two conditions while the control group showed significant improvements in postural stability test under a condition with closed eyes condition and in the limit of stability test. Although each system's learning effect on outcomes cannot be neglected, the treatment effect of the experimental group who used the Spine Balance 3D system for training was confirmed to be superior to that of the control group through a comparative analysis. Compared to the Biodex Balance System, where balance training is conducted horizontally while standing perpendicular to the surface, the Spine Balance 3D system might be more effective because the trunk muscle is activated to maintain the body balance against increasing gravitational force caused by the increase in tilt angle in 3D space. We conclude that both the Biodex Balance System and the Spine Balance 3D system increase core muscle strength. However, the 3D stimulation in the Spine Balance 3D system is more effective to activate the trunk muscles. The dynamic balance improves as shown in the BBS, TUG, FRT, and KFES-I, and the 10mWT, which refers to gait ability, and shows a relatively higher improvement compared to the Biodex Balance System. We expect that the Spine Balance 3D system's superior treatment improves static balance, dynamic balance, and gait in stroke patients. This study has several limitations. First, both the experimental and control groups comprise a small number of subjects of only 14 each. Second, although there were no restrictions for registration, each subject was able to walk independently for 10 m or more, and their BBS scores were over 40, which means that the subjects had relatively mild conditions. Third the long-term effects of the treatment could not be confirmed. In addition, we could not exclude the learning effect for each evaluation system. Finally, the level of the trunk muscle activity could not be directly proven. Therefore, future studies need to include more subjects, and treatment methods should also be confirmed in subjects with more severe conditions. In addition, a method that can directly quantify trunk muscle strength, such as electromyography (EMG) activity, should also be attempted, and the studies should be designed to explore whether the treatment effects are still present months after the experiment. In conclusion, the Spine Balance 3D system, a newly-developed trunk-stabilizing exercise equipment, and the Biodex Balance system were applied to patients with hemiplegia. Although significant improvements in dynamic and static balance were confirmed in both the experimental and control groups, the 10mWT showed a significant improvement only in the experimental group treated with the Spine Balance 3D system, which means that the gait ability also showed a significant improvement and that the activation of the trunk muscles was more effective when using the program of the Spine Balance 3D system. The results indicate that the Spine Balance 3D System induces the activation of trunk muscles and comprises an effective treatment to improve the balance and gait in patients with hemiplegia.\n\n**Question:** Compared to Biodex Balance System (Biodex Medical Systems, Shirley, NY, USA) what was the result of Spine Balance 3D (CyberMedic) on The 10mWT (10-m walking test )?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
569
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Effects of 3-Dimensional Lumbar Stabilization Training for Balance in Chronic Hemiplegic Stroke Patients: A Randomized Controlled Trial\n\n ABSTRACT.OBJECTIVE:\nTo investigate the effects of the newly developed Spine Balance 3D system on the balance and gait abilities of hemiplegic stroke patients.\n\nABSTRACT.METHODS:\nTwenty-eight hemiplegic patients with chronic stroke were randomly assigned to an experimental (n=14) or control group (n=14). The experimental and control groups performed balance training by using the newly developed Spine Balance 3D system and the well-known Biodex Balance System 30 minutes per day, three times a week for 7 weeks. The Berg Balance Scale (BBS), 10-m walking test (10mWT), Timed Up and Go Test (TUG), Functional Reach Test (FRT), the Korean version of the Fall Efficacy Scale-International (KFES-I), trunk muscle strength and stability were evaluated before and after 7 weeks of intervention.\n\nABSTRACT.RESULTS:\nThe 10mWT improved significantly (p=0.001) in the experimental group (using the Spine Balance 3D system) but not in the control group, and core muscle strength, which we checked using Spine Balance 3D system evaluation program, improved more in the experimental group as well. The results of the BBS, FRT, TUG, KFES-I, and Biodex Balance System evaluation program improved in both groups after 7 weeks of balance training.\n\nABSTRACT.CONCLUSION:\nWe suggest that the newly-developed Spine Balance 3D system can be a more useful therapeutic tool for gait and dynamic balance rehabilitation in hemiplegic patients than a conventional 2D-based balance training system. A large-scale randomized controlled study is needed to prove the effect of this system.\n\nBODY.INTRODUCTION:\nA decrease in balance control can be caused by various factors, including central nervous system diseases (such as stroke and traumatic brain injury), musculoskeletal disorders (such as back pain or arthritis), and vestibular diseases. Loss of balance control decreases the ability and speed of patients' gait, especially in those with hemiplegia caused by brain damage. Fear of falling in these patients reduces their activity level and makes daily activities of living difficult for these patients. Therefore, improvements in balance control and mechanical movements are important treatment goals [1]. A combination of several factors, including vestibular, visual, somatosensory, and trunk strength, enables the maintenance of postural balance. Therefore, comprehensive, objective treatment methods are needed. Previous studies have reported on the relationship between gait ability, speed, and independence of performing daily activities from multiple angles. Physicians use various treatment methods and exercises, including trampoline training [2], visual feedback training [3], and sling exercise therapy for trunk muscles [456]. Along with the active development of rehabilitation equipment, physicians use many types of equipment that are already made in Korea in treatments to improve balance, including the iBalance (CyberMedic, Iksan, Korea) and Space Balance 3D (CyberMedic) systems. However, few studies exist on the actual effectiveness of this equipment, and established criteria to evaluate functional improvements are scarce. This study aimed to investigate whether the Spine Balance three-dimensional (3D) system, which was developed to strengthen the deep muscles of the vertebra via stabilization exercise of the lumbar spine, improves postural balance in patients with hemiplegia performing 3D rotational exercises. We expected that this exercise would increase trunk muscle strength and stabilize movement of the vertebra. In addition, this study aimed to study the improvement in gait and ability to carry out daily activities while proving the positive effects of using the Spine Balance 3D system's program and several balance control tests. The results were compared to those obtained with a Biodex Balance System [7], which is widely used for balance training, to prove its effectiveness.\n\nBODY.MATERIALS AND METHODS.SUBJECTS:\nThis study required patients to meet the following inclusion criteria: (1) patients at 6 months or more after stroke, (2) unilateral stroke (infarction, hemorrhage), (3) ability to understand and perform three-step verbal instructions, and (4) ability to stand independently. Patients with severe abnormalities in their biorhythms who require inpatient treatment and those who were deemed unqualified for the study were excluded. Thirty patients who met the requirements were chosen as subjects. The subjects were randomly divided into two groups of 15 to create experimental and control groups to be respectively treated using Spine Balance 3D (CyberMedic) and Biodex Balance System (Biodex Medical Systems, Shirley, NY, USA). The random distribution of the subjects into the experimental and control groups is based on a random allocation table in the order of registration of the subjects, and the process of patient recruitment took a total of 4 months. We conducted this prospective study at the Chonbuk National University Hospital, and we notified the subjects regarding the content of the study and obtained their written consent before the experiment was conducted. The hospital's board of audit and inspection approved our study.\n\nBODY.MATERIALS AND METHODS.METHOD:\nThe Berg Balance Scale (BBS), 10-m walking test (10mWT), Timed Up and Go (TUG) and Functional Reach Tests (FRT), and trunk strength evaluated using Spine Balance 3D system's evaluation program were used as clinical indicators to evaluate the level of function before the exercise. The Korean version of the Fall Efficacy Scale-International (KFES-I) was recorded using the information from the survey. The patients performed 30-minute exercises, three times a week for 7 weeks (Fig. 1). The Spine Balance 3D system allows balance training to be performed in 3D space detached from the ground surface by using a lift system that locks the hip and ankles to stabilize the body and prevent twisting. Exercises in eight directions (front, back, left, right, and diagonal) are possible in 3D space, and the system can be tilted up to 60° in each direction. The 3-axis sensor on the trunk accurately measures the movement of the patient's trunk and identifies and displays the center of gravity on the monitor (Fig. 2A). The experimental group underwent training in eight directions using the Spine Balance 3D system, starting from a 15° tilt and increasing up to 30° depending on the patient's condition. The control group underwent training by using the training mode in the Biodex Balance System. We configured the platform to the static state, and the patients underwent posture maintenance training and center of gravity transferring postural training in eight directions after initially aligning the center of gravity with the middle line of the monitor. We did not restrict any of the groups' activities to balance training, and we advised the subjects to perform their same daily activities as before (Fig. 2B).\n\nBODY.MATERIALS AND METHODS.METHOD.ASSESSMENT METHOD:\nBBS (range, 0–56 scores) and TUG indicated the dynamic balance, Biodex Balance System's evaluation program indicated stability, Spine Balance 3D system's evaluation program indicated trunk muscle strength, and 10mWT indicated gait ability. The FRT indicated static balance, and the KFES-I measured the risk of falling. The patients performed TUG, a test that measures the time it takes a patient to rise from a chair, walk 3 m, turn around, walk back to the chair and sit down, and a stopwatch was used to measure timing. We measured the time it takes a patient to walk a distance of 10 m marked by tapelines when performing the 10mWT, and sufficient space was provided before and after the 10 m region to allow acceleration and deceleration. The forward FRT was performed by measuring the difference between the locations of the 3rd metacarpophalangeal joint of the unaffected side from a normal standing position and from a maximally forward-leaning position, and a 100 cm-long ruler was set horizontally at the acromion level to measure the difference. The patients placed both clavicles perpendicular to the long ruler lines on the wall to avoid error caused by the decrease in ipsilateral muscle strength. We separately measured the values for the affected and unaffected side in the lateral FRT. The lateral FRT measures the differences in the location of the metacarpophalangeal joints after abduction of the arm on the desired side from a natural upright position and from a laterally tilted trunk position. If the strength of the affected arm was not sufficiently strong, we measured the acromion locations instead. The Biodex Balance System and Spine Balance 3D system objectively evaluated the balance control. We used Biodex Balance System's evaluation program to conduct postural stability test with eyes open and closed, along with the limits of the stability test. We conducted the postural stability test by having the subjects maintain a relaxed standing position with eyes open and closed for 10 seconds each. We obtained three measurements from each condition to calculate the overall stability index, which reflected the stability as it approximates 0. We conducted the limits of the stability test on an easy level. We obtained three measurements to calculate the overall direction control score, which reflected a higher ability to control direction as the score decreased. Spine Balance 3D system's blind and open modes were used to evaluate the balance control. The difference between the blind mode and the open mode is defined as the ability to display the actual balance status on the screen by using the sensors attached to the back of the patient. The monitor displayed the actual balance status in the open mode whereas the screen turned black in the blind mode to restrict compensation. We increased the tilt in each of the eight directions to 15° and 30° by 2°/s and stopped for 5 seconds at the maximum tilt (15° and 30°). The subjects maintained a certain trunk position, depending on the tilt, and the results were reported as the Balance Position Ratio (BRP), expressed as the percentage of deviation from reference for the direction and tilt measured using the trunk sensor system. A score close to 100% reflects a good trunk muscle strength.\n\nBODY.MATERIALS AND METHODS.METHOD.STATISTICAL ANALYSIS:\nWe performed the statistical analyses using SPSS ver. 18.0 (SPSS Inc., Chicago, IL, USA), and analyzed the demographics of the two groups and pre-treatment evaluations by using an independent t-test. We compared the pre-treatment evaluations with post-treatment evaluations in both groups to determine whether statistical changes were present. We analyzed the measured values before and after the treatment in each group by using Wilcoxon signed-rank tests, and considered only p-values less than 0.05 to be statistically significant.\n\nBODY.RESULTS.GENERAL CHARACTERISTICS OF SUBJECTS:\nThe experimental and control groups comprised 15 subjects each. However, one patient from the experimental group failed due to the aggravation of gout in the ankle joint, and a follow-up loss in the control group occurred due to a MERS coronavirus outbreak. Fourteen subjects in each group completed the clinical experiment. Table 1 shows the distribution of sex, age, average education, duration of stroke, and hemiplegic side in both groups. The demographics in the two groups did not show significant differences. The unaffected lateral FRT showed significantly higher results in the Biodex Balance System training group; whereas the rest of the tests showed no significant differences between the two groups (Table 2).\n\nBODY.RESULTS.TREATMENT EFFECTS:\nTable 3 shows that the experimental group showed significant improvements in all tests—BBS (p=0.001), TUG (p=0.001), forward FRT (p=0.001), affected lateral FRT (p=0.001), and unaffected lateral FRT (p=0.002)—when the values before and after training were compared in each group. The control group also showed significant improvements in the same tests. However, the results for the 10mWT showed only significant improvements in the experimental group (11.38±3.0 to 10.12±2.47 seconds; p=0.01); whereas the control group did not show significant improvements. The improvement levels of the trunk strength (BPR score) for the experimental group using Spine Balance 3D system's evaluation program showed significant improvements at the 15° open mode; whereas the control group did not show any significant improvement. However, both groups showed significant improvements during the experiment under the following three conditions: 15° blind, 30° open, and 30° blind (Table 3). In addition, among the three conditions used in Biodex Balance System's evaluation program, the experimental group showed significant improvements in a postural stability test with eyes open and closed under two conditions while the control group showed significant improvements in a postural stability test under a condition with closed eyes and a limit of stability test. As such, the two groups showed similar levels of improvement in terms of stability (Table 3).\n\nBODY.DISCUSSION:\nThe goal of this study was to investigate the effectiveness of the Spine Balance 3D system in improving gait and balance in patients with hemiplegia. This study confirms that balance training using the Spine Balance 3D system effectively improves dynamic balance, static balance, and gait by improving trunk muscle strength. Treatment using the Spine Balance 3D system showed significant improvements in gait, as measure in the 10mWT, compared to that achieved using the Biodex Balance System, and the Spine Balance 3D system's evaluation program showed that improvements in trunk control ability were relatively superior than those observed for the control group. The postural stability test, conducted using Biodex Balance System's evaluation program, revealed that the two groups showed similar levels of improvement in stability. The trunk stability maintains the overall balance and regulates the technical movement of the lower limbs. Hodges and Richardson [8] report that stabilization of the spine caused by the contraction of abdominal and multifidus muscles plays a role in inducing technical movement in the lower limbs. In addition, Kim et al. [9] report that trunk-activating exercises are important because weakening of the trunk is relevant to functional performance in patients with chronic stroke. Abdominal muscle strength exercises improve gait and balance in stroke patients [10], and improvements in trunk regulation increase dynamic balance, gait speed, and symmetrical movement of the trunk during gait in stroke patients [11]. Subsequently, various core stability exercises have been introduced to strengthen the trunk [12131415], and many types of modern equipment are currently in development, aiming to improve trunk strength through gait training. However, studies evaluating the effects of such equipment are rare. A study conducted 1-minute sit-up tests in a single-leg squat position on athletes after training with the Biodex Balance System and reported a relatively significant improvement in balance compared to the control group. This study proves that treatment using the Biodex Balance System improves stability by fortifying core strength [16]. Treatment using the Biodex Balance System significantly reduces the fear of falling (FES-I score >26) among the elderly, and their knee extensor and flexor isometric strength improves as a secondary gain [17]. Therefore, core muscle and lower extremity strength are expected to increase when training using the Biodex Balance System, and improvements in balance have been confirmed. Our study showed significant improvements not only in trunk muscle strength, but also in BBS, TUG, FRT, and KFES-I. This result coincides with the results from a study by Saeys et al. [18], which reports that trunk reposition error, trunk impairment scale, and TUG results improved in the weight-shifting training group compared to those in the control group. The only difference with the study by Saeys et al. [18] is that our weight-shifting training was conducted using the Biodex Balance System. We expect that the newly-developed Spine Balance 3D systems stabilize and fortify trunk muscles by inducing symmetrical contraction and relaxation of abdominal and multifidus muscles in 3D space when the body is tilted, and studies are currently in progress to determine its effectiveness. A recent study confirmed changes in the trunk muscle strength and body composition among elderly subjects after training using the Spine Balance 3D system. The experimental group showed a significant improvement in trunk muscle strength after analyzing the alignment of the system direction and tilt with the trunk sensors by using trunk maintenance ability as a reference for trunk muscle strength [19]. Our study showed a significant improvement in trunk muscle strength in both groups after the experiment when measured using the same method. However, the control group showed significant improvements in trunk muscle strength only under three conditions while the experimental group showed improvements in trunk muscle strength under all four tested conditions, and the experimental group showed a relatively higher improvement in the trunk muscle strength. The tests conducted using Biodex Balance System's evaluation program revealed that both the experimental and the control groups showed significant improvements in two of three conditions with similar magnitude. The experimental group showed significant improvements in a postural stability test with eyes open and closed under two conditions while the control group showed significant improvements in postural stability test under a condition with closed eyes condition and in the limit of stability test. Although each system's learning effect on outcomes cannot be neglected, the treatment effect of the experimental group who used the Spine Balance 3D system for training was confirmed to be superior to that of the control group through a comparative analysis. Compared to the Biodex Balance System, where balance training is conducted horizontally while standing perpendicular to the surface, the Spine Balance 3D system might be more effective because the trunk muscle is activated to maintain the body balance against increasing gravitational force caused by the increase in tilt angle in 3D space. We conclude that both the Biodex Balance System and the Spine Balance 3D system increase core muscle strength. However, the 3D stimulation in the Spine Balance 3D system is more effective to activate the trunk muscles. The dynamic balance improves as shown in the BBS, TUG, FRT, and KFES-I, and the 10mWT, which refers to gait ability, and shows a relatively higher improvement compared to the Biodex Balance System. We expect that the Spine Balance 3D system's superior treatment improves static balance, dynamic balance, and gait in stroke patients. This study has several limitations. First, both the experimental and control groups comprise a small number of subjects of only 14 each. Second, although there were no restrictions for registration, each subject was able to walk independently for 10 m or more, and their BBS scores were over 40, which means that the subjects had relatively mild conditions. Third the long-term effects of the treatment could not be confirmed. In addition, we could not exclude the learning effect for each evaluation system. Finally, the level of the trunk muscle activity could not be directly proven. Therefore, future studies need to include more subjects, and treatment methods should also be confirmed in subjects with more severe conditions. In addition, a method that can directly quantify trunk muscle strength, such as electromyography (EMG) activity, should also be attempted, and the studies should be designed to explore whether the treatment effects are still present months after the experiment. In conclusion, the Spine Balance 3D system, a newly-developed trunk-stabilizing exercise equipment, and the Biodex Balance system were applied to patients with hemiplegia. Although significant improvements in dynamic and static balance were confirmed in both the experimental and control groups, the 10mWT showed a significant improvement only in the experimental group treated with the Spine Balance 3D system, which means that the gait ability also showed a significant improvement and that the activation of the trunk muscles was more effective when using the program of the Spine Balance 3D system. The results indicate that the Spine Balance 3D System induces the activation of trunk muscles and comprises an effective treatment to improve the balance and gait in patients with hemiplegia.\n\n**Question:** Compared to Biodex Balance System (Biodex Medical Systems, Shirley, NY, USA) what was the result of Spine Balance 3D (CyberMedic) on trunk strength (BPR score)?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
574
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Implementing a structured education program for children with diabetes: lessons learnt from an integrated process evaluation\n\n ABSTRACT.BACKGROUND:\nThere is recognition of an urgent need for clinic-based interventions for young people with type 1 diabetes mellitus that improve glycemic control and quality of life. The Child and Adolescent Structured Competencies Approach to Diabetes Education (CASCADE) is a structured educational group program, using psychological techniques, delivered primarily by diabetes nurses. Composed of four modules, it is designed for children with poor diabetic control and their parents. A mixed methods process evaluation, embedded within a cluster randomized control trial, aimed to assess the feasibility, acceptability, fidelity, and perceived impact of CASCADE.\n\nABSTRACT.METHODS:\n28 pediatric diabetes clinics across England participated and 362 children aged 8–16 years, with type 1 diabetes and a mean glycosylated hemoglobin (HbA1c) of 8.5 or above, took part. The process evaluation used a wide range of research methods.\n\nABSTRACT.RESULTS:\nOf the 180 families in the intervention group, only 55 (30%) received the full program with 53% attending at least one module. Only 68% of possible groups were run. Staff found organizing the groups burdensome in terms of arranging suitable dates/times and satisfactory group composition. Some staff also reported difficulties in mastering the psychological techniques. Uptake, by families, was influenced by the number of groups run and by school, work and other commitments. Attendees described improved: family relationships; knowledge and understanding; confidence; motivation to manage the disease. The results of the trial showed that the intervention did not significantly improve HbA1c at 12 or 24 months.\n\nABSTRACT.CONCLUSIONS:\nClinic-based structured group education delivered by staff using psychological techniques had perceived benefits for parents and young people. Staff and families considered it a valuable intervention, yet uptake was poor and the burden on staff was high. Recommendations are made to inform issues related to organization, design, and delivery in order to potentially enhance the impact of CASCADE and future programs.\n\nABSTRACT.CURRENT CONTROLLED TRIALS:\nISRCTN52537669.\n\nBODY:\nKey messagesThe Child and Adolescent Structured Competencies Approach to Diabetes Education (CASCADE) structured education program is perceived by young people and parents who attend as having benefits but practical challenges associated with attendance result in low uptake.Staff are positive about the potential of the program but organizational aspects are unacceptably burdensome.CASCADE is potentially deliverable to families as part of routine care and could be a useful intervention. However, improvements in clinical and administrative support, staff training, program content, and service structures are required to ensure fidelity to the program and feasibility and acceptability to key stakeholders.\n\nBODY.INTRODUCTION:\nType 1 diabetes mellitus (T1DM) in children and young people is increasing worldwide. Fewer than one in six children and young people achieve glycosylated fraction of hemoglobin (HbA1c) values in the range identified as providing best future outcomes.1 It has been recognized that there is an urgent need for clinic-based pragmatic, feasible, and effective interventions that improve both glycemic control and quality of life, with a particular emphasis on structured education programs.2 In recent years, a number of large multicenter studies have trialed a standard education intervention.3–5 Findings published, to date, report no significant positive impact on glycemic control as measured by HbA1c and only limited impact on a wide range of secondary measures.4\n5 Nevertheless, the recent Best Practice Tariff for Paediatric Diabetes for diabetes services in the UK6 requires the provision of structured educational programs for young people and their families and, as a consequence, there is an urgent need for high-quality evidence to inform the implementation of this recommendation. The CASCADE (Child and Adolescent Structured Competencies Approach to Diabetes Education) pragmatic cluster randomized controlled trial (RCT) with integral process and economic evaluation is the most recent study. It was undertaken by a team that included clinicians from a London-based pediatric diabetes clinic, a representative from a diabetes patient organization and researcher teams from three universities in London. The CASCADE intervention is a structured education program designed for children and young people with T1DM aged between 8 and 16 years and their parents or carers.7 The intervention underwent phase 1 pilot work and a non-randomized trial, in which the delivery was carried out by a psychologist.8 The CASCADE intervention was then modified to be delivered by two members of a diabetes multidisciplinary team (MDT) who receive 2 days of training to enable them to become 'site educators'. CASCADE is a manual-based program. It is delivered in four modules over 4 months, each lasting approximately 2 hours, to groups of three to four families with children and young people grouped according to age (8–11 or 12–16 years). Two psychological approaches, motivational interviewing and solution-focused brief therapy, shown to have potential with children with diabetes are central to the CASCADE intervention.9\n10 These aim to engage participants to identify and develop their own positive approaches and consequent behavior change relevant to the management of their condition. The intervention thus offers both structured education, to ensure young people (and their parents) know what they need to know, and a delivery model designed to motivate self-management through empowerment techniques (see table 1). Table 1 Outline of the CASCADE program (as set out in the manual) The teaching plan Session activities, objectives, time guides, and resources including key information essential for the educator, learning objective for the family, and brief descriptions of each activity Each module starts with a review of, and since, the previous session, creating an opportunity for families to highlight any changes that have taken place and to congratulate young people on successes Module 1 Focuses on the relationship between food, insulin, and BG ( eg, considering the pros and cons of matching insulin to food to attain better glycemic control ) Module 2 Reviews BG testing and factors influencing BG fluctuation ( eg, identifying factors that cause BG to rise and fall and explore hypoglycemia definitions, reviewing symptoms according to severity) Module 3 Looks at the pros and cons of adjusting insulin (eg, a brainstorming session considers when, how, and who to contact for help managing hyperglycemia) Module 4 Addresses aspects of living with diabetes, including managing BG levels and exercise ( eg, young people and families complete a ‘blueprint for success’. This marks the end of the sessions and acknowledges the steps into the future the young person has already made) Homework tasks are given to families to consolidate learning after each module BG, blood glucose; CASCADE, Child and Adolescent Structured Competencies Approach to Diabetes Education. The intention is that delivering CASCADE to groups will provide staff with an alternative mode of working with young people in the clinic setting to improve outcomes, rather than requiring additional work.\n\nBODY.CASCADE TRIAL SUMMARY:\nThe trial involved young people with T1DM and family members in 28 English pediatric diabetes clinics (randomly assigned at clinic level to intervention or control) in London, South East England, and the Midlands. Clinics eligible to participate were staffed by at least one pediatrician and pediatric nurse with an interest in diabetes. Other inclusion criteria included not running a group education program at time of recruitment and not participating in a similar pediatric diabetes trial within the past 12 months. It was approved by the University College London (UCL)/UCLH Research Ethics Committee (REC) reference number 07/HO714/112. Site-specific approval was granted at each site. Three hundred and sixty-two young people were recruited to the study. Inclusion criteria included: diagnosis with a duration ≥12 months; mean 12-month HbA1c of 8.5 or above; aged 8–16 years. Clinical staff identified eligible young people from their patient list. Researchers sent letters and information sheets to these young people and their parents or carers inviting them to participate in the research and to speak to a researcher at their next clinical appointment. Recruitment was primarily carried out by members of the process evaluation team who attended clinics at which eligible young people had an appointment. Signed consent forms were collected from parents and children wishing to participate. The primary outcome measure was venous HbA1c at 12 and 24 months. Secondary outcomes included: knowledge, skills and responsibilities associated with diabetes management; emotional and behavioral adjustment; quality of life. Two staff members from each intervention site clinical team participated in the 2 days CASCADE training program. These site educators then took responsibility for organizing the modules at their clinics and delivering the intervention. The extensive and integral process evaluation was designed to enable an understanding of the implementation of CASCADE and examination of the interaction of causal mechanisms and contextual factors that may be determinants of the intervention's success or failure, as assessed by the trial.11 Given that the trial found no evidence of benefits on venous HbA1c at 12 and 24 months and little evidence of benefits on secondary outcomes, the focus of this paper is to use the findings of the process evaluation to suggest how future structured education may be more effectively implemented.12\n\nBODY.PROCESS EVALUATION METHODS:\nThe process evaluation aimed to assess the feasibility, acceptability, fidelity and perceived impact of the CASCADE intervention. It ran for the 4-year life of the trial and included the multiple methods shown in table 2. Researchers from the process evaluation teams at the Institute of Education (IOE) and the School of Pharmacy (SOP) conducted the fieldwork. Table 2 Process evaluation methods and response rates Phase of the study Methods Purpose of methods Response rates Two-day training of site educators Unstructured observation of training of site educators by a member of the research team Fidelity of training 6 training days observed Participant questionnaires (completed 2 weeks after training) Description of participants Participant experience/acceptability of training 27 participant questionnaires from 18 nurses, 8 dietitians, and 1 doctor (63% of participants) Semistructured interviews with the two trainers Background to intervention development; views on training days Both trainers Delivery of CASCADE modules with patients/carers Observation of modules carried out by a member of research team including rating of fidelity to psychological techniques and content of manual Fidelity of delivery Experience/acceptability of delivery of program to site educators Experience/acceptability of participation in the program by young people/parents 47 CASCADE modules observed across 13 intervention sites (12 each of modules 1, 2, and 4; 11 of module 3) Self-complete feedback proformas for site educators Who delivered each module; who attended each module Self-assessment of delivery fidelity and general feedback on each module Site educators returned 125 feedback proformas (94% of 131 completed modules) Following delivery of all CASCADE groups Young person and parent 12 and 24 month questionnaires in intervention arm Perceptions of impact Acceptability of the intervention Process questions were completed on questionnaires by 135 young people (82%) and 121 parents (66%) at 12 months; 121 young people (66%) and 114 (63%) parents at 24 months Semistructured interviews (audio-recorded) with site staff (nurses and dietitians), young people, and parents/carers in both trial arms Description of standard care—including any structured education currently delivered Intervention arm only—experiences of the intervention (training and delivery) 30 site staff (16 intervention sites; 14 control) 53 young people (32 intervention/21 control) and 52 parents were interviewed. Of the young people, 31 were female; 17 were 10–11 years old; and 36 were 12–18 years old CASCADE, Child and Adolescent Structured Competencies Approach to Diabetes Education. \n\nBODY.PROCESS EVALUATION DATA ANALYSIS:\nQualitative data analysis was carried out by the process evaluation teams at IOE and SOP (all the authors except LB, RT, and DC). Qualitative analysis of the interview data, supported by the use of NVivo software, identified key topics and issues that emerged through familiarization with transcripts.13 Pertinent excerpts were coded and memos written to summarize and synthesize emerging themes. Researchers refined their analysis ensuring that themes were crosschecked with other data, first within and then between transcripts. Analysis of each training workshop observation was carried out by a researcher, who was not the observer, reading through the notes made by the observer and identifying key themes and fidelity issues emerging from the data. Quantitative data were analyzed by MW using Excel and the SPSS V.19 software for statistical tests. In terms of the CASCADE modules delivered in the sites, composite fidelity delivery scores were created for content and for technique from individual researcher observer and site educator self-rated scores. A further composite variable was then calculated which summed the content and technique scores for each site across all four modules, allowing comparison across sites and modules.\n\nBODY.PROCESS EVALUATION RESULTS:\nThe results are structured under the following themes: recruitment and training of site educators; organizing the groups; delivery of the modules; uptake and acceptability of the modules; and perceptions of impact. Response rates are reported in table 2.\n\nBODY.PROCESS EVALUATION RESULTS.RECRUITMENT AND TRAINING OF SITE EDUCATORS:\nThe National Institute for Health and Care Excellence (NICE) requirement,2 that structured education programs are delivered as part of routine care was widely recognized by clinic staff and, as a consequence, it proved relatively straightforward to recruit two members of the MDT from each of the 14 intervention sites to become site educators. The majority of site educators were experienced pediatric diabetes specialist nurses (PDSNs); in approximately half of the sites one of the educators was a dietitian. The diabetes specialist nurse and psychologist who developed the intervention delivered the 2 day CASCADE training for site educators in four workshop sessions. In general, it was feasible for sites to send the required minimum of two staff to the core workshops. A few sites sent additional interested members of the MDT though only four consultants attended some or all of the training. The training was delivered in a central London location, except for one site where following a request, training was delivered locally. Site staff reported this change in location to be helpful. The majority of staff who completed the questionnaire following the workshops indicated they had been 'extremely' or 'very' keen to participate. Most staff thought the training was very good, motivating, and comprehensive. The most common concern raised in staff interviews about becoming site educators and running the CASCADE program, both before and after the training, was additional workload. Other concerns included practical constraints such as finding available rooms in which to run the groups and ability to rapidly change their practice to employ the psychological approaches underpinning CASCADE. One site educator commented.It [the training] was a lot in the few days. Teaching people theories and expecting them to suddenly change their behaviour I think is very difficult. The two trainers, and some attendees, expressed concern about levels of diabetes knowledge among the site educators.Some of it [the training] was ending up teaching them the content as opposed to teaching them the style of delivery. (UCLH trainer)At the time [of the training] I'd got very little diabetes knowledge so, for me, I was actually learning from it and I know that's not really what it was about but a lot of it was that...I found it quite intimidating because of my lack of knowledge. (Site educator)\n\nBODY.PROCESS EVALUATION RESULTS.ORGANIZING THE GROUPS:\nA total of 30 complete CASCADE groups, comprising all four modules, were run across 12 of the 14 intervention sites. A post hoc calculation, based on the number of study recruits in a site and the optimum group size of 3–4 young people, suggested 44 groups should have been run across the 14 intervention sites. Thus, 68% of possible groups ran, with only three clinics completing the maximum number of groups possible for their site. A key reason for this limited delivery was difficulties with organizing the groups. The organization was undertaken by the site educators in all the sites. This involved: deciding which participants should be grouped together using similar ages as a key criterion; setting dates and times; inviting families to attend; and booking a room. Interviews revealed that site educators found these processes frustrating and very time-consuming. One site educator commented:I didn't notice that it saved me any time because I was constantly chasing them [families] up to be there. One site delivered no modules because the lead site educator left her PDSN post soon after the training. Another site delivered only the first module because of a number of challenges which included: the small number of potential eligible patients on the clinic list; poor uptake of the first module by young people/parents; practical organizational constraints. All the sites ran the groups in addition to routine clinics where standard care continued to be received by patients on an individual basis. Staff interview data revealed that the pressure on hospital clinic facilities was too great to make running the groups feasible during clinics. Establishing a date and time for the group sessions that was acceptable to the families was extremely challenging. To maximize attendance, some site educators tried a range of timings including during school hours, after school, weekends, and school holidays. Communication with families, about groups, was via a combination of letter, telephone, and (occasionally) text messages. No sites used email or online meeting booking sites. Despite all the negotiation and careful planning by site educators, late cancellation or non-attendance by participants was reported as common.Some didn't even bother to get back to us and some did and said they were still gonna come but still didn't come. It is frustrating and I think that's what was time consuming, which I hadn't really accounted for...(Site educator) As a result of these difficulties, compromises were made to the intended group size and composition. Groups often had small numbers (sometimes one family only) and/or a wide age range among the young people attending. Although the intention was to run four modules with the same participants, the composition of many groups changed.\n\nBODY.PROCESS EVALUATION RESULTS.DELIVERY OF THE MODULES:\nThe site educators believed they were appropriate individuals to deliver the intervention because they knew patients well, although familiarity with patients was not a requirement. Participating families appeared to support this view. All sites had continuity of at least one trained site educator, but complications in sustaining the availability of a second educator in a few sites resulted in some lack of continuity of trainer pairs. Site educators reported that the time required to organize sessions meant that they often had little or no time for planning and practising delivery of the modules. Observation data and some staff interviews suggested that this lack of practice time was particularly challenging when staff had limited experience in group work. Researcher observation of the modules and site educator feedback forms indicated that site educators generally delivered activities as described in the manual. However, less time than was recommended was spent on some of the key exercises due to staff finding them difficult to deliver and/or not well received by groups. One such example was the 'review since the previous session' exercise at the beginning of each module. Also, while researcher observation and staff feedback showed fidelity of CASCADE psychological techniques was good across sessions in half the sites, it was not optimal in the remainder. Difficulties in delivering the intervention particularly occurred when sessions had groups of participants with a wide age range or group numbers were very small.The first group that we ran had two girls and a boy and the boy was at the younger end of the teenage years and the girls were at the older, it was unfortunate because we didn't have that many patients as part of the study so it was very difficult then to get the groups sorted out so we kind of had to put them together. [...] He was just a bit of a silly boy in that...I don't mean horribly, he was lovely, but just kind of played the fool a little bit whereas the girls were older and a similar age and a lot more grown up about it all. (Site educator) Staff reported that the organization and delivery of the intervention was affected by the research context in a number of ways. First, having to restrict the education groups to a subset of recruited patients, instead of offering them to the entire clinic list, was perceived as making the organization of the groups more challenging. This meant that natural groupings of patients (by age or geographical area) often proved too difficult to achieve. Second, delays encountered in the recruitment of families to the trial in many sites (see12 for detail on this), meant site educators often had to wait several months after their training before they could start to organize groups and deliver the intervention. Third, some site educators reported that additional trial-related tasks, such as organizing research blood samples added to their workload and took time away from organization of, and preparation for, groups.\n\nBODY.PROCESS EVALUATION RESULTS.UPTAKE AND ACCEPTABILITY OF THE MODULES:\nOf the 180 young people recruited to the intervention arm, only 55 (30%) received the full education program of four modules with just over half of the original recruits (53%) attending at least one module. Eighty-four young people (47%) failed to attend any modules. Those who attended had significantly lower mean baseline HbA1c scores than those who were offered the sessions but did not attend (9.52 vs 10.33, p<0.01). Significantly more children (8–12 years) attended at least one module compared with teenagers (13–16 years; 64% vs 44%, p<0.01). Clinics were permitted to offer sessions at a time of their choice. If out of school hours sessions were not offered, the main reason given for young people not attending modules was that they did not want to miss school. For parents, taking time off work during the day was a barrier to attendance. Other reasons for non-attendance cited by children and parents included holidays and other extracurricular activities. On most occasions a parent/carer attended with the young person. Parents and young people reported that joint attendance was a very positive aspect of the experience (see table 3). Staff also, in most instances, found it helpful to include parents. Table 3 Acceptability of CASCADE to parents and young people attending at least one CASCADE module (12-month questionnaire) Themes Young people Parents/carers ‘Quite a lot’ or ‘A great deal’ n/N (%) ‘Quite a lot’ or ‘A great deal’ n/N (%) Group dynamic Liked parents/young people being together in modules 81/90 (90) 81/84 (96) Felt learnt something from other people in the group 64/93 (69) 60/85 (71) Teaching style and length Liked the way the trainers taught 74/93 (81) 81/86 (94) Felt the sessions were too long 22/94 (23) 7/85 (8) Content Felt that some of the things covered were too complicated 7/92 (8) 8/85 (9) Felt that some of the things covered they knew before 48/91 (53) 42/86 (49) \n\nBODY.PROCESS EVALUATION RESULTS.PERCEPTIONS OF IMPACT:\nThe majority of parents and young people who attended CASCADE groups described some positive impacts, including improved family relationships, wider knowledge and understanding of diabetes, greater confidence, and increased motivation to manage the disease (see table 4 and young person's comment below).\nI've been more happier...yeah, like around the house I've been more happier. Not so many strops...'cause my readings are better and we've been given a lot more information about the ketones and how to treat it....I found it really good. [Young person] Table 4 Parents’ and young people's perceptions of influence of CASCADE (12-month questionnaire) Questionnaire items Answered ‘Quite a lot’/‘A great deal’ Question: After attending some or all of the CASCADE diabetes education sessions, how much did your child/you…? Parent N=90 Young person N=97 Knowledge Understand better how insulin works 66 (74%) 70 (73%) Understand better which foods contain CHO 73 (81%) 68 (70%) See why counting the CHO in the food your child/you eat(s) can be helpful 80 (90%) 73 (75%) Intention to change Want to stop your child's/your glucose levels from going too low or high 85 (94%) 85 (87.5%) Want to test your child's/your BG levels more often 56 (43%) 40 (42%) Control Feel more in charge of your child's/your diabetes 61 (69%) 65 (68%) Feel able to change your child's/your insulin dose when they are exercising 68 (77%) 66 (69%) Feel you are able to control your child's/your BG levels better 70 (78%) 64 (67%) Access to care Feel more able to ring/contact your diabetes nurse/GP/hospital if your child/ you need(s) help 72 (82%) 52 (54%) Family dynamic Feel you had a better understanding of how diabetes affects your family 67 (75%) 69 (72%) BG, blood glucose; CASCADE, Child and Adolescent Structured Competencies Approach to Diabetes Education; CHO, carbohydrate; GP, general practitioner. A number of young people and parents mentioned that timing of the CASCADE sessions would be more appropriate and useful sooner after diagnosis; site educators also commented that this may lead to better uptake of the sessions and have greater impact.I felt they were of little use to me as I already knew everything however this kind of session would be useful to someone who had just been diagnosed. (Young person)They're a bit sort of more 'do as they're told' for the first 12 months, they're more likely to attend and perhaps take it on board, it gets them in the right frame of mind early. (Site educator) Twenty-four months after the intervention, when asked in the questionnaire what effect the program had had, nearly half of the young people selected the response \"The sessions made me want to try harder and I have carried on trying\". However, these impacts were not reflected in the primary or secondary outcome measures, even for the subgroup of those who attended.\n\nBODY.DISCUSSION:\nThe CASCADE intervention aimed to train PDSNs and other members of diabetes teams to deliver a manualised, structured education program, based on behavior change methods, to groups of families. Training of these site educators took place over 2 days. Few members of the MDT, other than PDSNs, attended the training. Trainee educators expressed enthusiasm for the program but highlighted concerns including that: CASCADE would increase their workload; there would be practical constraints to setting up and running groups; and that incorporating the CASCADE psychological model into their practice would be challenging. Following delivery of CASCADE in the sites, PDSNs and other clinical staff were positive about the program. Having PDSNs and dietitians, who knew the patients, as site educators worked well for both the educators and families. There were, however, feasibility issues with regard to running the program in its current form in the 'real world' of the National Health Service. These were evidenced by low uptake by families and staff feeling unacceptably burdened by organizational aspects of the intervention. Organizing groups was, as anticipated by staff, challenging and time-consuming and many groups did not comprise the recommended number or age range of young people. This affected group dynamics and made it difficult to run the sessions as set out in the manual. It was also difficult to keep a group together for the planned four modules. Delivery of the modules was further compromised by: the gap in time between training and delivering sessions; time spent on organizing group sessions at the expense of practising delivery of the modules; and finding some exercises consistently hard to deliver. Despite the fact that families and staff reported that they liked the program and felt that it offered benefits, the trial found no evidence of impact on venous HbA1c at 12 and 24 months and little evidence of benefits on secondary outcomes, even with the subgroup who attended the training. We think the reasons behind this are twofold. First the organizational difficulties that made the intended group composition problematic and second the difficulties with delivery, especially the lack of fidelity to the psychological techniques. To address these issues, and to support the development of other structured education programs, we make a range of recommendations.\n\nBODY.DISCUSSION.RECOMMENDATIONS:\nTo reduce the burden on the site educators more members of the MDT, including consultants, could attend the program training to foster greater buy-in and a team approach to facilitate sharing of the workload. To make this feasible, including containing cost, training of teams could be conducted at local sites rather than centrally in London. Furthermore, dedicated administrative support to organize venues, appointments, groups, and effective reminder systems would increase the likelihood of improved overall uptake, and would help with grouping the young people by age, as intended. Additional support for site educators in practising and sustaining quality of delivery would have been beneficial. Possible approaches could include: those associated with the successful DAFNE program,14 such as longer training, a greater focus in the training on improving group work skills, and an observation of CASCADE experts delivering the program; site level mentoring from CASCADE experts including feedback on site educators delivering trial runs; face-to-face mentoring from local colleagues, such as psychologists. In addition, before undertaking structured education programs, there may be a need to improve the knowledge base of some of the current pediatric diabetes service workforce, as levels of knowledge were very variable. Raising knowledge levels may be addressed by the development of a curriculum for professionals specifically in diabetes, ranging from a core curriculum (basic knowledge that all team members would be expected to know) to an extended curriculum (covering high level application of knowledge specific to individual team members). This finding may have relevance to other medical specialisms where structured education programs are being considered. The uptake of the education sessions was low. For families the key issue was the challenge of fitting attendance into busy day-to-day routines. The education modules were offered in sessions independent of routine clinic appointments. Our data suggest that to improve accessibility it could have been advantageous to make the modules an integral part of routine clinic appointments, thereby overcoming the need for families to make additional hospital visits, with the implications this has for time away from school and work. This would require those in organizational administrative roles to assist with sustainable organizational adjustments required for extending clinic services. This finding and the suggestion that there should be greater 'buy-in' from the wider clinic team echo those in the broader literature on group-based programs.15 Furthermore in the study, participants had to have been diagnosed with diabetes for more than a year to meet the inclusion criteria for participation. Our data suggest that if the program was offered to families sooner after the initial diabetes diagnosis, this might lead to improved motivation to attend the groups. Additionally offering this structured group education more universally might be more successful, including making the organization of groups by age more feasible, than targeting those with the poorest control of their blood glucose levels. It may be more realistic to assume that those with the very poorest control might also require the greater flexibility and intensity that individualized interventions with a psychologist would offer. A summary of the key recommendations is presented in box 1.\nBox 1Summary of key recommendations to improve training in, and delivery of, structured education sessionsMore involvement of the wider clinical team facilitated by local training;Greater mentoring of site educators by trainers;Practice sessions with feedback from trainers for site educators before going 'live' and time between training and delivery of first session kept to a minimum;More diabetes-specific training for the pediatric diabetes service workforce to guarantee a basic level of diabetes knowledge prior to training in the program;Dedicated administrative support to assist with organizing the sessions;Education sessions to be held within clinic time;Offer the sessions to all young people on clinic lists and soon after diagnosis.\n\nBODY.DISCUSSION.STRENGTHS AND LIMITATIONS OF THE STUDY:\nIt is a strength of the study that the process evaluation was unusually extensive and fully integrated into the main trial. Data were collected from all key stakeholders through a range of different methods throughout the different phases of the implementation of the intervention. Triangulation of findings enabled an evaluation of the implementation, barriers, and facilitators in relation to all aspects of implementation, operation, and perceived impact to be examined. It was also a strength that as a pragmatic RCT this intervention was evaluated in 'real-life' and representative settings. One limitation of the study was the impact of the research context on implementation, but steps were taken in the information and reassurance provided, methods, and timing of data collection to minimize effects as much as possible. Additionally, a major hindrance to the intervention was the lower than expected number of CASCADE groups run and the poor uptake of these groups by families. This might suggest a weakness in the intervention's pilot, which was not carried out within the same clinical contexts as the main trial. As such, opportunities to address challenges in organization and delivery were missed prior to, or through carefully managed processes within, the full trial.16 Experience from pragmatic studies of complex interventions such as CASCADE has yielded valuable new learning on the importance of particular investment in the developmental and piloting stages of complex interventions.17\n\nBODY.CONCLUSION:\nThe extensive multimethod process evaluation showed that the CASCADE structured education program was deliverable; however, improvements in clinical and administrative support, staff training, program content, and service structures to improve accessibility for families were required. The suggested improvements identified in this study all have resource implications, and thus any future research requires cost-benefit considerations. These findings give valuable information on what is required not only in CASCADE but also other similar programs to achieve their aims.\n\n**Question:** Compared to control what was the result of The Child and Adolescent Structured Competencies Approach to Diabetes Education (CASCADE) is a structured educational group program, using psychological techniques, delivered primarily by diabetes nurses. on HbA1c at 12 or 24 months.?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
576
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: The effect of uphill stride manipulation on race walking gait\n\n ABSTRACT:\nStride length analysis represents an easy method for assessing race walking kinematics. However, the stride parameters emerging from such an analysis have never been used to design a training protocol aimed at increasing stride length. With this aim, we investigated the effects of stride frequency manipulation during three weeks of uphill (2%) training on stride length at iso-efficiency speed. Twelve male race walkers were randomly allocated to one of two training groups: stride frequency manipulation (RWM, n=6) and free stride frequency (RWF, n=6). Results. Kinematic parameters measured before and after the 3-week training in RWM showed increased stride length (4.54%; p<0.0001) and contact time (4.58%; p<0.001); inversely, a decreased stride frequency (4.44%; p<0.0001) and internal work (7.09%; p<0.05) were found. In RWF the effect of the training showed a decrease in stride length (1.18%; p<0.0001) and contact time (<1%; p<0.0001) with respect to baseline conditions and an increased stride frequency and internal work of 1.19% (p<0.0001). These results suggest that using slopes (2%) as RWM could help coaches to provide some training methods that would improve an athlete's performance, through increasing stride length without altering his or her race walking technique or metabolic demands.\n\nBODY.INTRODUCTION:\nOlympic race walking (RW) is an historical competition, even though only a small number of athletes participate; indeed, race walking has been investigated more often in the laboratory than during competition [1]. An increasing interest in race walking competitions can be seen in the research [2–5]. Moreover, numerous factors have been shown to influence RW performance, including metabolic demand [4, 5], stride technique [2, 3, 6] and nutritional factors [7]. Indeed, race walkers require considerable training and preparation [8]. The importance of investigating various critical aspects involved in RW competitions [2, 3], such as energy cost [9], has become evident in recent years. In particular, researchers have taken a strong interest in training studies in order to understand how energetic cost in high level race walkers can be optimized [10, 11]. Within RW races there are variations in the track terrain, in which small differences in the slope that can influence the mechanics of RW are often present [12]. During a longer competition, such as the 50 km race, top level race walkers usually take approximately 52,600 strides [6], and stride length can decrease by 4% between the start and the end of the race [3]. Therefore, increases in stride length could be advantageous, because this would allow for the same speed to have a lower stride frequency and a better mechanical efficiency [13]. According to this hypothesis, focusing on stride parameters which change the individual stride frequency [6] is desirable in training for improving the stride length, as demonstrated in marathon runners [14]. Usually, uphill RW is used to improve race walking gait [6, 13], but its chronic effects are unknown. Furthermore, it can be stated that uphill RW alone does not help to improve stride length [6]. Indeed, a recent study has shown that even at low speeds on small slopes (2%), RW energy cost increased by 0.30 J/(kg · m) [15] over the energy cost at 0%, while the stride length decreased by ∼4% at both constant and low speed with respect to the level gradient [6]. Therefore, it may be useful to perform race walking on a slope at iso-efficiency speed (decreasing the velocity) [13], without increasing the metabolic demand, as well as on the level, as demonstrated in running [16], but manipulating stride frequency. In addition, considering that during uphill RW stride length decreases [6], it is important to decrease the speed to allow race walkers to adequately modify stride parameters during uphill RW training. In the current study, we hypothesize that manipulating the stride frequency in uphill training will prove advantageous to stride length during level RW. Therefore, the aim of this study was to investigate the effects of the stride frequency manipulation (same stride length on level gradient) vs. free stride frequency during training on a slope (2%) at iso-efficiency speed [13] in national race walkers.\n\nBODY.MATERIALS AND METHODS.PARTICIPANTS:\nTwelve male race walkers (Senior's category) were selected for this study following the approval of the University Ethical Committee. All the subjects were randomly assigned to one [17] of the two groups: stride frequency manipulation (RWM= 6, age 24.8±7.4 years, height 1.77±0.08 m, weight 60±6.32 kg, body mass index (BMI) 19.14±0.72 kg · m−2) and free stride frequency (RWF= 6, age 24.2±5.7 years, height 1.78±0.05 m, weight 61.85±4.74 kg, BMI 19.44±1.16 kg · m−2). The inclusion criterion was: high skill with more than six years of training (all were ranked at the national level in their category). None of the athletes suffered from nutritional disturbances, none had any musculoskeletal injuries, and no medications or drugs expected to affect their physical performance were taken during the course of this investigation. In order to make the group homogeneous with regard to the training conditions, none of the subjects performed any strenuous endurance activity and/or resistance training outside of their normal endurance training protocol. The diet control was designed to eliminate the risk of any differences in the total consumption of proteins, carbohydrates and of saturated and unsaturated fats; all the athletes lived together and followed the recommendations of the same sports nutritionist. The TCU Institutional Review Board for the use of Human Subjects approved the details of this study, as well as all related informational and consent documentation, before any data collection was performed. After being informed of the procedures, methods, benefits and possible risks involved in the study, each subject reviewed and signed an informed consent form prior to participation in the study, in accordance with the ethical standards.\n\nBODY.MATERIALS AND METHODS.PROCEDURES:\nAll subjects were tested before (double check for the reliability of the measures) and after the training intervention in the Human Performance Laboratory. All the tests were carried out in a climate-controlled laboratory: average temperature 23.5°C (min 23°C, max 24°C), between 4:00 p.m. and 7:00 p.m. to control for circadian variation [18]. Riley et al. (2008) reported a high correlation (r=0.93) between over-ground and treadmill walking [19]. All the subjects wore RW shoes (Category A2, 135 g) and performed a standardized 15-min warm-up, consisting of RW at 9 km · h−1, in order to familiarize themselves with the treadmill [20] (Run Race Technogym Run 500, Gambettola Italy [21]). The subjects performed 5 min of dynamic muscular stretching [22] prior to performing the treadmill test for kinematic analysis. The treadmill was calibrated and checked before and after each test, according to the instructions of the manufacturer [20]. Percent grade (%) was expressed as being equal to the tangent [theta] × 100 [20]. The speed at \"0\" level (mean ± SD) for the 5-min duration was set at 1 km · h−1 less than the best mean speed performed by each participant for 10,000 m (IES0) corresponding to 12.83±0.60 km · h−1 [13]. Previous studies have found that this corresponds to ∼50% (estimate) maximal oxygen consumption (VO2max) [23] and requires an energy cost (Cw) of 5.0 J · (kg · m) −1 [9, 23]. Furthermore, according to the previous data [15] the increase in Cw as a result of a level gradient is:Cwi=0.15×slopei(%)+Cw0, where Cw0 is the Cw at a level gradient (0%). As mentioned above, oxygen consumption (VO2) is proportional to the energetic cost and velocity, so for each gradient the velocity (IESi) at which the VO2 was equal to level RW was calculated by taking VO2= [(Cw0 / (21 (J · min−1)) × ((IES0 / 0.06 (m · min−1)))], where 21 (J · min−1) and 0.06 (m · min−1) are constant values. This leads to the equation:IESi(km·h−1)=[(VO2(kJ/min/kg)×21(J/l)×0.06(m/min))/(0.15×slopei(%)+Cw0)].\n\nBODY.MATERIALS AND METHODS.KINEMATIC ANALYSES:\nPre- and post-training two-dimensional (2D) video data of the subjects' RW on the treadmill were collected using a high-speed (210 Hz) camera (Casio Exilim FH20, Japan). In accordance with previous studies [13, 14, 24], considering that the treadmill device was 50 cm high, the camera was positioned on a 1.5 m high tripod standing 6 m from the participant, and was located perpendicular to the plane of motion and the participant's sagittal plane [25] as standard calibration. The film sequences were analyzed off-line using Dartfish 5.5-Pro motion analysis software (Dartfish, Fribourg, CH). The following kinematic variables were studied: (i) contact time (ms), (ii) stride length (m), and (iii) stride frequency (Hz); 100 strides were sampled [26] within the 5-min duration of the test. Stride frequency was freely chosen within the pre and post-test training. Since the velocity of the treadmill was known, both stride length (left/right, SL) and stride frequency (SF) could be calculated. The contact time (CT) was calculated for both the left and the right foot [27]. The CT was defined and calculated as the time between initial contact (rear foot) with the ground and the last frame of contact before toe-off (forefoot). Initial contact and toe-off were visually detected. According to previous studies [6, 13, 16, 28], SF was calculated as SF= [1000/CT)]; alternatively, SL was calculated with the following equation: SL= [(speed/3.6)/SF].\n\nBODY.MATERIALS AND METHODS.INTERNAL WORK:\nWe calculated the internal work (WINT) with the Nardello equation [29]WINT=SF·v·(1+(DF·(1-DF)-1)2)·q, where SF is the stride frequency (Hz), v is the speed (m · s−1), DF is the duty factor – i.e. deflection of the duration of stride period when each foot is on the ground (%) and q the value of 0.1 referring to the inertial properties of the oscillating limbs.\n\nBODY.MATERIALS AND METHODS.TRAINING ON A SLOPE:\nSlope training was carried out on the treadmill (Run Race Technogym Run 500, Gambettola Italy) over three weeks, with two training sessions per week (Monday and Friday), in accordance with a previous study [14]. All the participants wore RW shoes (Category A2) and performed a standardized 15-min warm-up, consisting of RW at 9 km · h−1 on a treadmill at a level gradient and following 3 min of RW on a 2% slope before each set. The RWM group performed the following training procedure on the treadmill: 5 sets of 5-min RW at a 2% gradient at IES (IES2) with a manipulated individualized stride frequency. Between each set 5 min of active recovery was performed, which consisted of RW at 0% gradient and speed corresponding to IES2 minus 1.5 km · h−1. IES2 and stride frequency were 12.08±0.59 km · h−1 and 3.07±0.25 Hz, respectively. Manipulated stride frequency on a slope was predetermined. SF was calculated in order to replicate the same stride length elicited during level RW at IES, in accordance with the training equation [6]. The athletes were requested to count their strides and to replicate the number each minute (visual counter each 30 s with treadmill display, with an error of one stride). Training equation for slope= [(speed (km · h−1) / 3.6 (m · s−1)) during slope / SL (m) during level × 60 (min)] [6]. The RWF group performed the following training procedure on the treadmill: 5 sets of 5-min RW at 2% gradient at IES2 with a freely chosen stride frequency. IES2 and stride frequency were 12.13±0.58 km · h−1 and 2.92±0.15 Hz, respectively. Between each set, 5 min of active recovery was performed, which consisted of RW at 0% gradient and speed corresponding to IES2 minus 1.5 km · h−1. To balance the training load, both groups (RWM-RWF) during the training weeks (4 days per week) performed the same normal training programme on a level gradient (based on ∼14.5 km per day).\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nData are reported as mean ± SD. The kinematic variables (i) contact time, (ii) stride length, (iii) stride frequency and (iv) internal work were analysed using a separated two-way ANOVA with repeated measures and Bonferroni post-hoc tests. The effect size (η2) was calculated for all variables between pre- and post-testing. For testing the repeatability of the measure [30], we first calculated the intra-class correlation coefficient (ICC) for each variable measured. Assumption of normality was verified using the Shapiro-Wilk W. Test. The within factor was time with two levels (pre- and post-training) and the between factor was the training with at two levels (RWM and RWF). Furthermore, a t-test was used to compare pre- and post-training in different groups for: (i) contact time, (ii) stride length, and (iii) stride frequency. Then, a pair-wise comparison was performed when the main effect was significant, and the significance level was set at p<0.05. Statistical analysis was performed using SigmaPlot software 11.0 (Systat Software, Tulsa, OK).\n\nBODY.RESULTS:\nThere were no differences between the two groups at baseline conditions for age, height, weight, training experience or RW velocity on both the level and a slope (2%). The test-retest reliability of this testing procedure was demonstrated through an ICC and standard error of measurements (SEM) for the following variables: stride length (ICC: 0.97–0.98, SEM: 0.03–0.07 m), contact time (ICC: 0.96–0.98, SEM: 9–11 ms) and stride frequency (ICC: 0.95–0.98, SEM: 0.8–0.11 Hz). Repeated measures ANOVA showed significant differences between the two training groups in CT: F(1,10)= 32.856, p<0.0001 (η2= 0.767) and the interaction training type × time F(1,10)= 94.776, p<0.0001 (η2= 0.905). Significant differences were also found for SF: F(1,10)= 24.038, p<0.001 (η2= 0.706) and the interaction training type × time F(1,10)= 71.022, p<0.0001 (η2= 0.877). Similarly, significant differences were found for the SL: F(1,10)= 40.941, p<0.0001 (η2= 0.804) and the interaction training type × time F(1,10)= 120.115, p<0.0001 (η2= 0.923). WINT showed significant differences: F(1,10)= 5.784, p=0.037 (η2= 0.584) and the interaction training type × time F(1,10)= 11.372, p=0.007 (η2= 0.859). With regard to the two training strategies, within the RWM group the CT significantly increased by 4.58% (p<0.001), as did SL (4.54% with p<0.0001) between pre- and post-training (Table 1). SF and WINT (Figure 1) also significantly decreased by 4.44% and 7.09% (p<0.0001 with p=0.03), respectively, within the RWM. Conversely, in RWF the SL and CT decreased by 1.18% with p<0.0001 and <1% with p<0.0001, respectively, between pre- and post-training, while the SF and WINT increased (1.19% with p<0.0001) respectively. FIG. 1Changes in the WINT variable (means and SE) for the stride frequency manipulation (RWM) and free stride frequency groups (RWF) depending on the time (pre- and post-training). \"†\" represents significant (p<0.0001) training × time interaction; \"*\" p<0.05 and \"**\" p<0.01 represent significant differences between pre- and post-training. TABLE 1 Effects of uphill race walking training on step analysis. BASELINE RWM RWF Contact time (ms) 311 ± 16.89 324 ± 22.96* 308 ± 7.56† Step frequency (Hz) 3.23 ± 0.18 3.10 ± 0.23† 3.25 ± 0.08† Stride length (m) 1.11 ± 0.09 1.15 ± 0.12† 1.10 ± 0.07† Note: Kinematic variables in the step frequency manipulation group (RWM) and the free step frequency group (RWF) between post-training and the baseline conditions with “*” p<0.001, or “†” p<0.0001. \n\nBODY.DISCUSSION:\nThe current study shows for the first time the effect of stride frequency manipulation on kinematic parameters during uphill training in national race walkers. The study investigated the effects of two types of uphill RW training – RWM and RWF. The uphill training aimed to reproduce the same stride length that was elicited during RW on a level gradient. Uphill RW speed was therefore slower compared to level RW, 12.11±0.56 km · h−1 and 12.83±0.59 km · h−1, respectively. The previous research that carried out RW training programmes used greater slopes, which produced higher speeds [6]. Such conditions would produce unnatural conditions for race walkers [31, 32]. This would presumably increase the energy cost of RW [15, 33] and lead to improvements in the cardiovascular system. Within the current study, the aim was to look at kinematic parameters and maintain a similar metabolic cost; due to this, IES was used [13]. In the present study the reduction in speed [13] allowed for effective stride frequency manipulation. Research suggests that race walkers often unconsciously select a stride frequency which minimizes injury and energy expenditure [8, 23] and is modulated by the central pattern generators [34], as in running [24]. Due to this notion, race walkers within the RWM group found it problematic during the first training session to alter their stride pattern. The RWF group, however, did not have such issues, as stride frequency was freely chosen. The results following six uphill training sessions (over 3 weeks) suggest that the RWM group elicited kinematic improvements. Conversely, the RWF group did not show any significant kinematic improvements. Some researchers suggest that successful running race performances are characterized by increased stride length, increased cadence becomes more important at greater speeds [35, 36] and contact times are shorter. Our results support this approach, and following training the RWM group increased SL by 4.54% with p<0.0001 related to decreased WINT (7.05% p<0.05; Figure 1). During training the RWM group subjects were required to reduce their mechanical pattern in order to reduce their stride frequency (∼5%). Changes in CT were also evident: RWM increased by 4.58% (p<0.001), but only a <1% decrease was found for the RWF group. The decreases in CT may have produced greater peak vertical force [37], thus providing longer stride lengths. This was supported within the RWM group in the current study. The kinematic adaptations elicited by the RWM group were characteristic of better race walkers, as energy efficient performances are. Longer contact times and smaller stride frequencies are associated with energy efficiency [13, 38]. A particular limitation of this study, concerning the low sample size, can be explained considering the kind of discipline involved: in the last 30 years the mean number of subjects studied in the laboratory was very low (male, n=7±4.5; female n=4±2.7 [1]), due to the specificity of the RW technique.\n\nBODY.CONCLUSIONS:\nIn conclusion, this study showed how the stride frequency manipulation during uphill RW training alters subsequent level RW kinematics, and presumably aids efficient RW performance. The increase in SL could provide an advantageous alteration to kinematics. Because of the direct positive relationship between SL and speed, increasing SL could significantly increase the speed (which is the race walker's aim), assuming that the foot does not advance too far ahead of the centre of mass, providing a braking effect [39]. Considering that the RW race (50 km) record is 3 h 32 min 33 s [40], and the stride length decrease is 4% [3], this study could be useful in closing this gap with the training method of increasing athletes' stride length, leading to the first time an athlete could complete a race under 3 h 30 min The same training protocol could also be applied for a middle distance race (20 km), where a decrease of stride length by 2.4 and 2.7% was observed in males and females respectively between the last and first kilometres [12]. An uphill race walking protocol (changing stride frequency) could be useful to diversify athletes' common training protocol without stressing their current metabolic demand. In addition, given that several physiological systems are involved during RW, the possible effect of combining different training strategies, shown to be effective in isolation, warrants future studies.\n\n**Question:** Compared to free stride frequency what was the result of stride frequency manipulation on contact time?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
577
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: The effect of uphill stride manipulation on race walking gait\n\n ABSTRACT:\nStride length analysis represents an easy method for assessing race walking kinematics. However, the stride parameters emerging from such an analysis have never been used to design a training protocol aimed at increasing stride length. With this aim, we investigated the effects of stride frequency manipulation during three weeks of uphill (2%) training on stride length at iso-efficiency speed. Twelve male race walkers were randomly allocated to one of two training groups: stride frequency manipulation (RWM, n=6) and free stride frequency (RWF, n=6). Results. Kinematic parameters measured before and after the 3-week training in RWM showed increased stride length (4.54%; p<0.0001) and contact time (4.58%; p<0.001); inversely, a decreased stride frequency (4.44%; p<0.0001) and internal work (7.09%; p<0.05) were found. In RWF the effect of the training showed a decrease in stride length (1.18%; p<0.0001) and contact time (<1%; p<0.0001) with respect to baseline conditions and an increased stride frequency and internal work of 1.19% (p<0.0001). These results suggest that using slopes (2%) as RWM could help coaches to provide some training methods that would improve an athlete's performance, through increasing stride length without altering his or her race walking technique or metabolic demands.\n\nBODY.INTRODUCTION:\nOlympic race walking (RW) is an historical competition, even though only a small number of athletes participate; indeed, race walking has been investigated more often in the laboratory than during competition [1]. An increasing interest in race walking competitions can be seen in the research [2–5]. Moreover, numerous factors have been shown to influence RW performance, including metabolic demand [4, 5], stride technique [2, 3, 6] and nutritional factors [7]. Indeed, race walkers require considerable training and preparation [8]. The importance of investigating various critical aspects involved in RW competitions [2, 3], such as energy cost [9], has become evident in recent years. In particular, researchers have taken a strong interest in training studies in order to understand how energetic cost in high level race walkers can be optimized [10, 11]. Within RW races there are variations in the track terrain, in which small differences in the slope that can influence the mechanics of RW are often present [12]. During a longer competition, such as the 50 km race, top level race walkers usually take approximately 52,600 strides [6], and stride length can decrease by 4% between the start and the end of the race [3]. Therefore, increases in stride length could be advantageous, because this would allow for the same speed to have a lower stride frequency and a better mechanical efficiency [13]. According to this hypothesis, focusing on stride parameters which change the individual stride frequency [6] is desirable in training for improving the stride length, as demonstrated in marathon runners [14]. Usually, uphill RW is used to improve race walking gait [6, 13], but its chronic effects are unknown. Furthermore, it can be stated that uphill RW alone does not help to improve stride length [6]. Indeed, a recent study has shown that even at low speeds on small slopes (2%), RW energy cost increased by 0.30 J/(kg · m) [15] over the energy cost at 0%, while the stride length decreased by ∼4% at both constant and low speed with respect to the level gradient [6]. Therefore, it may be useful to perform race walking on a slope at iso-efficiency speed (decreasing the velocity) [13], without increasing the metabolic demand, as well as on the level, as demonstrated in running [16], but manipulating stride frequency. In addition, considering that during uphill RW stride length decreases [6], it is important to decrease the speed to allow race walkers to adequately modify stride parameters during uphill RW training. In the current study, we hypothesize that manipulating the stride frequency in uphill training will prove advantageous to stride length during level RW. Therefore, the aim of this study was to investigate the effects of the stride frequency manipulation (same stride length on level gradient) vs. free stride frequency during training on a slope (2%) at iso-efficiency speed [13] in national race walkers.\n\nBODY.MATERIALS AND METHODS.PARTICIPANTS:\nTwelve male race walkers (Senior's category) were selected for this study following the approval of the University Ethical Committee. All the subjects were randomly assigned to one [17] of the two groups: stride frequency manipulation (RWM= 6, age 24.8±7.4 years, height 1.77±0.08 m, weight 60±6.32 kg, body mass index (BMI) 19.14±0.72 kg · m−2) and free stride frequency (RWF= 6, age 24.2±5.7 years, height 1.78±0.05 m, weight 61.85±4.74 kg, BMI 19.44±1.16 kg · m−2). The inclusion criterion was: high skill with more than six years of training (all were ranked at the national level in their category). None of the athletes suffered from nutritional disturbances, none had any musculoskeletal injuries, and no medications or drugs expected to affect their physical performance were taken during the course of this investigation. In order to make the group homogeneous with regard to the training conditions, none of the subjects performed any strenuous endurance activity and/or resistance training outside of their normal endurance training protocol. The diet control was designed to eliminate the risk of any differences in the total consumption of proteins, carbohydrates and of saturated and unsaturated fats; all the athletes lived together and followed the recommendations of the same sports nutritionist. The TCU Institutional Review Board for the use of Human Subjects approved the details of this study, as well as all related informational and consent documentation, before any data collection was performed. After being informed of the procedures, methods, benefits and possible risks involved in the study, each subject reviewed and signed an informed consent form prior to participation in the study, in accordance with the ethical standards.\n\nBODY.MATERIALS AND METHODS.PROCEDURES:\nAll subjects were tested before (double check for the reliability of the measures) and after the training intervention in the Human Performance Laboratory. All the tests were carried out in a climate-controlled laboratory: average temperature 23.5°C (min 23°C, max 24°C), between 4:00 p.m. and 7:00 p.m. to control for circadian variation [18]. Riley et al. (2008) reported a high correlation (r=0.93) between over-ground and treadmill walking [19]. All the subjects wore RW shoes (Category A2, 135 g) and performed a standardized 15-min warm-up, consisting of RW at 9 km · h−1, in order to familiarize themselves with the treadmill [20] (Run Race Technogym Run 500, Gambettola Italy [21]). The subjects performed 5 min of dynamic muscular stretching [22] prior to performing the treadmill test for kinematic analysis. The treadmill was calibrated and checked before and after each test, according to the instructions of the manufacturer [20]. Percent grade (%) was expressed as being equal to the tangent [theta] × 100 [20]. The speed at \"0\" level (mean ± SD) for the 5-min duration was set at 1 km · h−1 less than the best mean speed performed by each participant for 10,000 m (IES0) corresponding to 12.83±0.60 km · h−1 [13]. Previous studies have found that this corresponds to ∼50% (estimate) maximal oxygen consumption (VO2max) [23] and requires an energy cost (Cw) of 5.0 J · (kg · m) −1 [9, 23]. Furthermore, according to the previous data [15] the increase in Cw as a result of a level gradient is:Cwi=0.15×slopei(%)+Cw0, where Cw0 is the Cw at a level gradient (0%). As mentioned above, oxygen consumption (VO2) is proportional to the energetic cost and velocity, so for each gradient the velocity (IESi) at which the VO2 was equal to level RW was calculated by taking VO2= [(Cw0 / (21 (J · min−1)) × ((IES0 / 0.06 (m · min−1)))], where 21 (J · min−1) and 0.06 (m · min−1) are constant values. This leads to the equation:IESi(km·h−1)=[(VO2(kJ/min/kg)×21(J/l)×0.06(m/min))/(0.15×slopei(%)+Cw0)].\n\nBODY.MATERIALS AND METHODS.KINEMATIC ANALYSES:\nPre- and post-training two-dimensional (2D) video data of the subjects' RW on the treadmill were collected using a high-speed (210 Hz) camera (Casio Exilim FH20, Japan). In accordance with previous studies [13, 14, 24], considering that the treadmill device was 50 cm high, the camera was positioned on a 1.5 m high tripod standing 6 m from the participant, and was located perpendicular to the plane of motion and the participant's sagittal plane [25] as standard calibration. The film sequences were analyzed off-line using Dartfish 5.5-Pro motion analysis software (Dartfish, Fribourg, CH). The following kinematic variables were studied: (i) contact time (ms), (ii) stride length (m), and (iii) stride frequency (Hz); 100 strides were sampled [26] within the 5-min duration of the test. Stride frequency was freely chosen within the pre and post-test training. Since the velocity of the treadmill was known, both stride length (left/right, SL) and stride frequency (SF) could be calculated. The contact time (CT) was calculated for both the left and the right foot [27]. The CT was defined and calculated as the time between initial contact (rear foot) with the ground and the last frame of contact before toe-off (forefoot). Initial contact and toe-off were visually detected. According to previous studies [6, 13, 16, 28], SF was calculated as SF= [1000/CT)]; alternatively, SL was calculated with the following equation: SL= [(speed/3.6)/SF].\n\nBODY.MATERIALS AND METHODS.INTERNAL WORK:\nWe calculated the internal work (WINT) with the Nardello equation [29]WINT=SF·v·(1+(DF·(1-DF)-1)2)·q, where SF is the stride frequency (Hz), v is the speed (m · s−1), DF is the duty factor – i.e. deflection of the duration of stride period when each foot is on the ground (%) and q the value of 0.1 referring to the inertial properties of the oscillating limbs.\n\nBODY.MATERIALS AND METHODS.TRAINING ON A SLOPE:\nSlope training was carried out on the treadmill (Run Race Technogym Run 500, Gambettola Italy) over three weeks, with two training sessions per week (Monday and Friday), in accordance with a previous study [14]. All the participants wore RW shoes (Category A2) and performed a standardized 15-min warm-up, consisting of RW at 9 km · h−1 on a treadmill at a level gradient and following 3 min of RW on a 2% slope before each set. The RWM group performed the following training procedure on the treadmill: 5 sets of 5-min RW at a 2% gradient at IES (IES2) with a manipulated individualized stride frequency. Between each set 5 min of active recovery was performed, which consisted of RW at 0% gradient and speed corresponding to IES2 minus 1.5 km · h−1. IES2 and stride frequency were 12.08±0.59 km · h−1 and 3.07±0.25 Hz, respectively. Manipulated stride frequency on a slope was predetermined. SF was calculated in order to replicate the same stride length elicited during level RW at IES, in accordance with the training equation [6]. The athletes were requested to count their strides and to replicate the number each minute (visual counter each 30 s with treadmill display, with an error of one stride). Training equation for slope= [(speed (km · h−1) / 3.6 (m · s−1)) during slope / SL (m) during level × 60 (min)] [6]. The RWF group performed the following training procedure on the treadmill: 5 sets of 5-min RW at 2% gradient at IES2 with a freely chosen stride frequency. IES2 and stride frequency were 12.13±0.58 km · h−1 and 2.92±0.15 Hz, respectively. Between each set, 5 min of active recovery was performed, which consisted of RW at 0% gradient and speed corresponding to IES2 minus 1.5 km · h−1. To balance the training load, both groups (RWM-RWF) during the training weeks (4 days per week) performed the same normal training programme on a level gradient (based on ∼14.5 km per day).\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSIS:\nData are reported as mean ± SD. The kinematic variables (i) contact time, (ii) stride length, (iii) stride frequency and (iv) internal work were analysed using a separated two-way ANOVA with repeated measures and Bonferroni post-hoc tests. The effect size (η2) was calculated for all variables between pre- and post-testing. For testing the repeatability of the measure [30], we first calculated the intra-class correlation coefficient (ICC) for each variable measured. Assumption of normality was verified using the Shapiro-Wilk W. Test. The within factor was time with two levels (pre- and post-training) and the between factor was the training with at two levels (RWM and RWF). Furthermore, a t-test was used to compare pre- and post-training in different groups for: (i) contact time, (ii) stride length, and (iii) stride frequency. Then, a pair-wise comparison was performed when the main effect was significant, and the significance level was set at p<0.05. Statistical analysis was performed using SigmaPlot software 11.0 (Systat Software, Tulsa, OK).\n\nBODY.RESULTS:\nThere were no differences between the two groups at baseline conditions for age, height, weight, training experience or RW velocity on both the level and a slope (2%). The test-retest reliability of this testing procedure was demonstrated through an ICC and standard error of measurements (SEM) for the following variables: stride length (ICC: 0.97–0.98, SEM: 0.03–0.07 m), contact time (ICC: 0.96–0.98, SEM: 9–11 ms) and stride frequency (ICC: 0.95–0.98, SEM: 0.8–0.11 Hz). Repeated measures ANOVA showed significant differences between the two training groups in CT: F(1,10)= 32.856, p<0.0001 (η2= 0.767) and the interaction training type × time F(1,10)= 94.776, p<0.0001 (η2= 0.905). Significant differences were also found for SF: F(1,10)= 24.038, p<0.001 (η2= 0.706) and the interaction training type × time F(1,10)= 71.022, p<0.0001 (η2= 0.877). Similarly, significant differences were found for the SL: F(1,10)= 40.941, p<0.0001 (η2= 0.804) and the interaction training type × time F(1,10)= 120.115, p<0.0001 (η2= 0.923). WINT showed significant differences: F(1,10)= 5.784, p=0.037 (η2= 0.584) and the interaction training type × time F(1,10)= 11.372, p=0.007 (η2= 0.859). With regard to the two training strategies, within the RWM group the CT significantly increased by 4.58% (p<0.001), as did SL (4.54% with p<0.0001) between pre- and post-training (Table 1). SF and WINT (Figure 1) also significantly decreased by 4.44% and 7.09% (p<0.0001 with p=0.03), respectively, within the RWM. Conversely, in RWF the SL and CT decreased by 1.18% with p<0.0001 and <1% with p<0.0001, respectively, between pre- and post-training, while the SF and WINT increased (1.19% with p<0.0001) respectively. FIG. 1Changes in the WINT variable (means and SE) for the stride frequency manipulation (RWM) and free stride frequency groups (RWF) depending on the time (pre- and post-training). \"†\" represents significant (p<0.0001) training × time interaction; \"*\" p<0.05 and \"**\" p<0.01 represent significant differences between pre- and post-training. TABLE 1 Effects of uphill race walking training on step analysis. BASELINE RWM RWF Contact time (ms) 311 ± 16.89 324 ± 22.96* 308 ± 7.56† Step frequency (Hz) 3.23 ± 0.18 3.10 ± 0.23† 3.25 ± 0.08† Stride length (m) 1.11 ± 0.09 1.15 ± 0.12† 1.10 ± 0.07† Note: Kinematic variables in the step frequency manipulation group (RWM) and the free step frequency group (RWF) between post-training and the baseline conditions with “*” p<0.001, or “†” p<0.0001. \n\nBODY.DISCUSSION:\nThe current study shows for the first time the effect of stride frequency manipulation on kinematic parameters during uphill training in national race walkers. The study investigated the effects of two types of uphill RW training – RWM and RWF. The uphill training aimed to reproduce the same stride length that was elicited during RW on a level gradient. Uphill RW speed was therefore slower compared to level RW, 12.11±0.56 km · h−1 and 12.83±0.59 km · h−1, respectively. The previous research that carried out RW training programmes used greater slopes, which produced higher speeds [6]. Such conditions would produce unnatural conditions for race walkers [31, 32]. This would presumably increase the energy cost of RW [15, 33] and lead to improvements in the cardiovascular system. Within the current study, the aim was to look at kinematic parameters and maintain a similar metabolic cost; due to this, IES was used [13]. In the present study the reduction in speed [13] allowed for effective stride frequency manipulation. Research suggests that race walkers often unconsciously select a stride frequency which minimizes injury and energy expenditure [8, 23] and is modulated by the central pattern generators [34], as in running [24]. Due to this notion, race walkers within the RWM group found it problematic during the first training session to alter their stride pattern. The RWF group, however, did not have such issues, as stride frequency was freely chosen. The results following six uphill training sessions (over 3 weeks) suggest that the RWM group elicited kinematic improvements. Conversely, the RWF group did not show any significant kinematic improvements. Some researchers suggest that successful running race performances are characterized by increased stride length, increased cadence becomes more important at greater speeds [35, 36] and contact times are shorter. Our results support this approach, and following training the RWM group increased SL by 4.54% with p<0.0001 related to decreased WINT (7.05% p<0.05; Figure 1). During training the RWM group subjects were required to reduce their mechanical pattern in order to reduce their stride frequency (∼5%). Changes in CT were also evident: RWM increased by 4.58% (p<0.001), but only a <1% decrease was found for the RWF group. The decreases in CT may have produced greater peak vertical force [37], thus providing longer stride lengths. This was supported within the RWM group in the current study. The kinematic adaptations elicited by the RWM group were characteristic of better race walkers, as energy efficient performances are. Longer contact times and smaller stride frequencies are associated with energy efficiency [13, 38]. A particular limitation of this study, concerning the low sample size, can be explained considering the kind of discipline involved: in the last 30 years the mean number of subjects studied in the laboratory was very low (male, n=7±4.5; female n=4±2.7 [1]), due to the specificity of the RW technique.\n\nBODY.CONCLUSIONS:\nIn conclusion, this study showed how the stride frequency manipulation during uphill RW training alters subsequent level RW kinematics, and presumably aids efficient RW performance. The increase in SL could provide an advantageous alteration to kinematics. Because of the direct positive relationship between SL and speed, increasing SL could significantly increase the speed (which is the race walker's aim), assuming that the foot does not advance too far ahead of the centre of mass, providing a braking effect [39]. Considering that the RW race (50 km) record is 3 h 32 min 33 s [40], and the stride length decrease is 4% [3], this study could be useful in closing this gap with the training method of increasing athletes' stride length, leading to the first time an athlete could complete a race under 3 h 30 min The same training protocol could also be applied for a middle distance race (20 km), where a decrease of stride length by 2.4 and 2.7% was observed in males and females respectively between the last and first kilometres [12]. An uphill race walking protocol (changing stride frequency) could be useful to diversify athletes' common training protocol without stressing their current metabolic demand. In addition, given that several physiological systems are involved during RW, the possible effect of combining different training strategies, shown to be effective in isolation, warrants future studies.\n\n**Question:** Compared to free stride frequency what was the result of stride frequency manipulation on stride frequency?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
584
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Behavioural recovery after treatment for varicose veins\n\n ABSTRACT.BACKGROUND:\nThe aim of this study was to assess behavioural recovery from the patient's perspective as a prespecified secondary outcome in a multicentre parallel‐group randomized clinical trial comparing ultrasound‐guided foam sclerotherapy (UGFS), endovenous laser ablation (EVLA) and surgery for the treatment of primary varicose veins.\n\nABSTRACT.METHODS:\nParticipants were recruited from 11 UK sites as part of the CLASS trial, a randomized trial of UGFS, EVLA or surgery for varicose veins. Patients were followed up 6 weeks after treatment and asked to complete the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This is a 15‐item instrument that covers eight activity behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven participation behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective.\n\nABSTRACT.RESULTS:\nA total of 798 participants were recruited. Both UGFS and EVLA resulted in a significantly quicker recovery compared with surgery for 13 of the 15 behaviours assessed. UGFS was superior to EVLA in terms of return to full‐time work (hazard ratio 1·43, 95 per cent c.i. 1·11 to 1·85), looking after children (1·45, 1·04 to 2·02) and walks of short (1·48, 1·19 to 1·84) and longer (1·32, 1·05 to 1·66) duration.\n\nABSTRACT.CONCLUSION:\nBoth UGFS and EVLA resulted in more rapid recovery than surgery, and UGFS was superior to EVLA for one‐quarter of the behaviours assessed. The BRAVVO questionnaire has the potential to provide important meaningful information to patients about their early recovery and what they may expect to be able to achieve after treatment.\n\nBODY.INTRODUCTION:\nMinimally invasive treatments for varicose veins such as ultrasound‐guided foam sclerotherapy (UGFS) and thermal ablation techniques have become widely used alternatives to surgery for the treatment of varicose veins. One of the advantages of these techniques is the reported quicker return to normal activities, particularly following UGFS1, 2, 3. However, it is unclear whether thermal ablation, in particular endovenous laser ablation (EVLA), is also associated with a clinically significant quicker return to normal activities compared with surgery; some studies4, 5 have shown an earlier return and others2, 6, 7, 8 no difference. Until recently, there was no standard means of assessing recovery from the patient's perspective. This led to the use of varying definitions such as return to 'normal activities', 'full activity', 'daily activity' or 'basic physical activities' and/or 'return to work' in previous studies. This lack of standardization led the authors to develop a 15‐item questionnaire to assess distinct aspects of normal activities that were identified as important by patients9 – the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This paper reports behavioural recovery results from a multicentre parallel‐group randomized clinical trial (CLASS, Comparison of LAser, Surgery and foam Sclerotherapy) that compared the clinical efficacy and cost‐effectiveness of three treatment modalities: UGFS, EVLA with delayed foam sclerotherapy to residual varicosities if required, and surgery. Behavioural recovery was one of the prespecified secondary outcomes of the CLASS trial. The clinical and cost‐effectiveness results have been reported elsewhere10, 11.\n\nBODY.METHODS:\nPatients were recruited from 11 centres in the UK between November 2008 and October 2012. This study (ISRCTN51995477) had research ethics committee and Medicines and Healthcare products Regulatory Authority approval. Eight centres randomized participants to one of three treatment options, and three centres offered only UGFS and surgery. Participants were randomized between the treatments with even allocation, using a minimization algorithm that included centre, age (less than 50 years, 50 years or more), sex, great saphenous vein (GSV) or small saphenous vein (SSV) reflux, and unilateral or bilateral disease. Inclusion criteria were: age over 18 years; primary unilateral or bilateral symptomatic varicose veins (Clinical Etiologic Anatomic Pathophysiological (CEAP) grade C2 or above); GSV and/or SSV involvement; and reflux exceeding 1 s on duplex ultrasonography. Exclusion criteria were: current deep vein thrombosis; acute superficial vein thrombosis; a GSV or SSV diameter smaller than 3 mm or larger than 15 mm; tortuous veins considered unsuitable for EVLA or stripping; and contraindications to UGFS or to general/regional anaesthesia that would be required for surgery.\n\nBODY.METHODS.TREATMENTS:\nThe treatments have been described in detail elsewhere9, 10. For UGFS, foam was produced using the Tessari technique12 using a ratio of 0·5 ml sodium tetradecyl sulphate to 1·5 ml air (3 per cent for GSV/SSV truncal veins, 1 per cent for varicosities; maximum 12 ml foam per session). EVLA of GSVs/SSVs was performed under local anaesthetic, and patients were offered UGFS to any residual varicosities at 6‐week follow‐up if required, with the exception of one centre that performed concurrent phlebectomies. Surgery in the form of proximal GSV/SSV ligation and stripping (all GSV) and concurrent phlebectomies was performed under general or regional anaesthetic as a day‐case procedure. Compression stockings were applied after all three treatments.\n\nBODY.METHODS.POST‐TREATMENT ACTIVITY:\nAll participants were given a study patient information leaflet (PIL), which recommended a return to all normal activities as soon as they were able, but that strenuous activity/contact sport should be avoided for 1–2 weeks. The PIL specifically stated that following EVLA or UGFS 'most people are able to return to work within 2–3 days of treatment, but some people go back the following day or even the same day', and that following surgery 'people can return to office or sedentary work after 2–3 days; and that most people will be back at work within a week after surgery to one leg and 2 weeks after surgery to both legs; but there is no reason to remain off work as long if it can be managed with reasonable comfort'. Participants undergoing UGFS or EVLA were advised to wear compression stocking for 10 days constantly (day and night). Those in the surgery group were advised that bandages would be removed the day after operation, following which they should wear a stocking for 10 days, but that it was reasonable to remove the stocking after 4 or 5 days, providing that they were active.\n\nBODY.METHODS.DATA COLLECTION:\nThe participants were asked to complete the BRAVVO questionnaire along with other study questionnaires (Aberdeen Varicose Vein Questionnaire, EQ‐5DTM (EuroQoL, Rotterdam, The Netherlands) and Short Form 36 (QualityMetric, Lincoln, Rhode Island, USA)) at the 6‐week follow‐up appointment. Participants who failed to attend the 6‐week appointment were sent the questionnaire to complete at home. The BRAVVO questionnaire was developed as an instrument to assess the activity and participation components of the World Health Organization International Classification of Disability and Function model13. Variation in activity and participation is not fully explained by impairment and so these constructs are important additional indicators of health outcome. An interview study involving 17 patients who had recently undergone varicose vein treatment was carried out to identify normal activities and 'milestone' behaviours to incorporate into the questionnaire. In addition to sampling from the three treatment options, diversity sampling was used in an attempt to gain a mix of sex, age and rural–urban location. Seventeen interview transcripts were content‐analysed in four stages to identify appropriate items to include in a questionnaire. Full details of this process have been published previously9. The BRAVVO questionnaire assesses the time taken for patients to return to performing 15 behaviours: eight 'activity' behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven 'participation' behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective9. Fig. 1 shows the question layout. Figure 1Question layoutBJS-10081-FIG-0001-c\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData from the BRAVVO questionnaire were analysed within an interval‐censored time‐to‐event framework using flexible parametric survival models14. For each behaviour item, each participant's response was converted into the number of days to return to that behaviour. If a participant indicated that return to the behaviour was on the day of the procedure, this was assumed to be interval‐censored between day 0 and day 1. If a participant indicated return to the behaviour was after a number of weeks, not days, this was assumed to be interval‐censored between the previous week and the week indicated. For example, if a participant reported 5 weeks, it was assumed that the return to the behaviour took place between 28 and 35 days. A participant who indicated that they had not returned to a behaviour that they usually performed was right‐censored at 42 days. Participants who indicated that they did not normally perform a specific behaviour were not included in analysis of that behaviour. No missing data were imputed. Data are reported as the number of days for 50 and 90 per cent of participants to return to each behaviour, estimated from the parametric survival models (the 50 per cent value represents the median time to return to this behaviour). Extrapolation beyond the 42‐day cut‐off was performed for behaviours where 90 per cent of participants had not returned to the behaviour by 42 days. Treatment effects are presented as hazard ratios with associated 95 per cent c.i. All analyses were carried out in Stata® 1215. Flexible parametric survival models were fitted using the stpm package16.\n\nBODY.RESULTS:\nSeven hundred and ninety‐eight participants were recruited, of whom 13 were ineligible (for example because they had recurrent veins or veins larger than 15 mm in diameter) after randomization and were considered postrandomization exclusions (Fig. \n2). The groups were well balanced in terms of demographic characteristics at baseline, but there was an increased incidence of deep venous reflux in the foam group compared with the surgery group (P = 0·005) (Table \n1). Of the 670 participants who completed the 6‐week questionnaire, 655 completed at least one of the BRAVVO questions. Completion rates were slightly lower for the questions about going out socially (74·8 per cent) and sporting activity (66·0 per cent), which may not have been relevant to all participants. For all behaviours, except wearing clothes that show the leg, going out socially and sporting activities, over 95 per cent of participants had returned to normal behaviour within 6 weeks of intervention. Figure 2CONSORT diagram for the trial. Reasons for postrandomization exclusion included: recurrent varicose veins and veins larger than 15 mm. Reasons for withdrawal from follow‐up included: patient decided not to proceed with treatment (and also declined follow‐up), declined follow‐up after treatment or did not wish to complete questionnaires. UGFS, ultrasound‐guided foam sclerotherapy; EVLA, endovenous laser ablationBJS-10081-FIG-0002-c Table 1 Demographic details at recruitment EVLA UGFS Surgery ( n = 210) ( n = 286) ( n = 289) Age (years) * \n 49·7 (18–80) 49·0 (19–78) 49·2 (22–85) Sex ratio (F : M) 120 : 90 162 : 124 163 : 126 Body mass index (kg/m 2 ) * \n 27·0 (17–42) 27·1 (17–44) 27·7 (17–44) Unilateral disease 153 (72·9) 215 (75·2) 196 (67·8) Employment status Self‐employed 21 (10·2) 37 (13·0) 29 (10·3) Employed 120 (58·3) 169 (59·3) 179 (63·5) Other 65 (31·6) 79 (27·7) 74 (26·2) Unknown 4 1 7 Saphenous vein involvement Great saphenous 182 (86·7) 232 (81·1) 239 (82·7) Small saphenous 14 (6·7) 21 (7·3) 21 (7·3) Great and small saphenous 14 (6·7) 33 (11·5) 29 (10·0) Deep vein reflux 28 of 205 (13·7) 47 of 280 (16·8) 25 of 282 (8·9) CEAP classification C2, varicose veins over 3 mm 113 (54·1) 169 (59·1) 147 (51·2) C3, oedema 28 (13·4) 35 (12·2) 39 (13·6) C4, skin/subcutaneous changes 56 (26·8) 74 (25·9) 90 (31·4) C5/C6, healed/active venous ulcer 12 (5·7) 8 (2·8) 11 (3·8) Unknown 1 0 2 Values in parentheses are percentages unless indicated otherwise; * values are mean (range). EVLA, endovenous laser ablation; UGFS, ultrasound‐guided foam sclerotherapy; CEAP, Clinical Etiologic Anatomic Pathophysiologic. \n\nBODY.RESULTS.ULTRASOUND‐GUIDED FOAM SCLEROTHERAPY :\nParticipants randomized to UGFS recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n2\n). The two behaviours for which there was no evidence of a difference in the time to recover between the trial arms were 'having a bath or shower' and 'wearing clothes that show the legs'. In general, the median time to return to the activity behaviours was 5 days or less for those randomized to UGFS and up to 9 days for those randomized to surgery. In both groups, there was greater variation in the median time to return to the participation behaviours than the activity behaviours. Table 2 Behavioural recovery: ultrasound‐guided foam sclerotherapy versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n UGFS Surgery Activity items Bending the legs without discomfort 50 3·0 4·6 1·38 (1·14, 1·67) 90 14·1 21·3 Lifting heavy objects without discomfort 50 4·8 9·8 1·97 (1·59, 2·44) 90 16·9 34·5 Moving from standing to sitting without discomfort 50 1·9 3·7 1·63 (1·35, 1·97) 90 9·3 17·5 Standing still for a long time (> 15 min ) without discomfort 50 3·9 7·1 1·67 (1·36, 2·05) 90 15·8 28·7 Walking short distances (< 20 min ) without discomfort 50 1·9 4·4 2·00 (1·65, 2·42) 90 8·2 19·1 Walking long distances (> 20 min) 50 4·5 8·0 1·76 (1·45, 2·14) 90 15·2 27·1 Having a bath or shower 50 5·4 4·9 0·85 (0·70, 1·03) 90 11·4 10·3 Driving a car 50 4·1 7·0 1·78 (1·45, 2·19) 90 12·4 21·1 Participation items Doing housework 50 2·1 4·5 2·10 (1·72, 2·56) 90 7·3 15·7 Looking after children 50 1·2 3·5 2·20 (1·61, 3·00) 90 6·2 17·9 Wearing clothes that show the legs 50 12·4 12·8 1·03 (0·78, 1·35) 90 56·6 58·7 Partial return to normal work/employment 50 4·4 9·9 2·16 (1·72, 2·72) 90 15·4 34·2 Full return to normal work/employment 50 4·8 11·7 2·56 (2·05, 3·21) 90 14·9 36·2 Going out socially 50 7·1 9·3 1·29 (1·06, 1·57) 90 25·8 34·0 Sporting activity or exercise 50 15·7 21·8 1·33 (1·05, 1·68) 90 62·6 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.RESULTS.ENDOVENOUS LASER ABLATION :\nParticipants randomized to EVLA recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n3). Return to 'having a bath or shower' was quicker after surgery than after EVLA. There was no difference in time to return to the participation behaviour of 'wearing clothes that show the legs'. Table 3 Behavioural recovery: endovenous laser ablation versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n EVLA Surgery Activity items Bending the legs without discomfort 50 2·7 4·6 1·49 (1·19, 1·75) 90 12·6 21·3 Lifting heavy objects without discomfort 50 5·9 9·8 1·79 (1·39, 2·27) 90 20·5 34·5 Moving from standing to sitting without discomfort 50 2·2 3·7 1·56 (1·27, 1·96) 90 10·4 17·5 Standing still for a long time (> 15 min) without discomfort 50 4·8 7·1 1·41 (1·11, 1·79) 90 20·0 28·7 Walking short distances (< 20 min) without discomfort 50 3·0 4·4 1·30 (1·04, 1·61) 90 13·2 19·1 Walking long distances (> 20 min) 50 5·6 8·0 1·53 (1·06, 1·67) 90 19·8 27·1 Having a bath or shower 50 5·5 4·9 0·74 (0·59, 0·93) 90 12·8 10·3 Driving a car 50 4·4 7·0 1·82 (1·43, 2·33) 90 12·7 21·1 Participation items Doing housework 50 2·5 4·5 1·89 (1·49, 2·38) 90 8·4 15·7 Looking after children 50 1·9 3·5 1·61 (1·15, 2·27) 90 8·8 17·9 Wearing clothes that show the legs 50 14·6 12·8 0·97 (0·69, 1·35) 90 75·1 58·7 Partial return to normal work/employment 50 6·3 9·9 1·75 (1·33, 2·27) 90 21·1 34·2 Full return to normal work/employment 50 7·7 11·7 1·79 (1·37, 2·27) 90 23·5 36·2 Going out socially 50 6·9 9·3 1·41 (1·12, 1·75) 90 23·9 34·0 Sporting activity or exercise 50 14·2 21·8 1·47 (1·12, 1·92) 90 55·5 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. EVLA, endovenous laser ablation. There were no differences in the time taken to return to 11 of the 15 behaviours between participants randomized to EVLA and those randomized to UGFS (Table \n4). Return to 'walking short distances without discomfort', 'walking long distances', 'looking after children' and 'full return to normal work/employment' took longer for the EVLA group than the UGFS group. Following UGFS or EVLA only one‐third of the specific behaviours could be carried out by 50 per cent of participants by 3 days after treatment. Table 4 Behavioural recovery: endovenous laser ablation versus ultrasound‐guided foam sclerotherapy Proportion carrying out behaviour (%) Time until specified proportion of participants can carry out behaviour (days) * \n Hazard ratio † \n EVLA UGFS Activity items Bending the legs without discomfort 50 2·7 3·0 0·94 (0·75, 1·17) 90 12·6 14·1 Lifting heavy objects without discomfort 50 5·9 4·8 1·11 (0·87, 1·42) 90 20·5 16·9 Moving from standing to sitting without discomfort 50 2·2 1·9 1·12 (0·90, 1·40) 90 10·4 9·3 Standing still for a long time (> 15 min) without discomfort 50 4·8 3·9 1·14 (0·90, 1·44) 90 20·0 15·8 Walking short distances (< 20 min) without discomfort 50 3·0 1·9 1·48 (1·19, 1·84) 90 13·2 8·2 Walking long distances (> 20 min) 50 5·6 4·5 1·32 (1·05, 1·66) 90 19·8 15·2 Having a bath or shower 50 5·5 5·4 1·19 (0·96, 1·48) 90 12·8 11·4 Driving a car 50 4·4 4·1 0·95 (0·74, 1·21) 90 12·7 12·4 Participation items Doing housework 50 2·5 2·1 1·03 (0·82, 1·29) 90 8·4 7·3 Looking after children 50 1·9 1·2 1·45 (1·04, 2·02) 90 8·8 6·2 Wearing clothes that show the legs 50 14·6 12·4 1·17 (0·83, 1·64) 90 75·1 56·6 Partial return to normal work/employment 50 6·3 4·4 1·17 (0·89, 1·52) 90 21·1 15·4 Full return to normal work/employment 50 7·7 4·8 1·43 (1·11, 1·85) 90 23·5 14·9 Going out socially 50 6·9 7·1 0·88 (0·70, 1·10) 90 23·9 25·8 Sporting activity or exercise 50 14·2 15·7 0·80 (0·61, 1·04) 90 55·5 62·6 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the endovenous laser ablation (EVLA) arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.DISCUSSION:\nThis study showed that both UGFS and EVLA resulted in a more rapid recovery compared with surgery for 13 of the 15 behaviours. UGFS was superior to EVLA in terms of return to full time work, looking after children and walking (both short and long distances). Importantly, the specific behaviours assessed were shown to have a range of different recovery trajectories. Previous randomized clinical trials showed behavioural recovery to be more rapid following UGFS compared with surgery1, 2, but the benefit of EVLA over surgery was less clear2, 4, 8 . In this study, for all but two behaviours (wearing clothes that showed the legs and showering/bathing) the recovery was quicker following UGFS or EVLA compared with surgery. These findings may have arisen as a result of information contained in the study PIL, which recommended that compression hosiery was worn continuously for 10 days following UGFS or EVLA but for 4–5 days routinely after surgery. In the comparison between UGFS and EVLA, behavioural recovery was faster following UGFS for four of the 15 behaviours; there was no difference between the groups for the other behaviours. Two previous randomized trials2, 3 showed earlier return to 'normal activities' in patients undergoing UGFS compared with EVLA. Specifically, the present study showed a quicker return to full‐time work following UGFS, similar to the findings of Rasmussen and colleagues2. The median time taken to return to work following EVLA (7·7 days) was within the ranges reported2, 4, 5, 6, 7, 8. However, Rasmussen and colleagues2 reported earlier return to work after UGFS compared with the present study (median 2·9 versus 4·8 days respectively). A partial explanation of the difference between the two studies may be that, unlike the previous study, the present analysis did not correct for weekends. For other behaviours, the recalled recovery times following both UGFS and EVLA were longer than might be expected from the literature2, 3, 4, 5, 8. This may be explained by the timing of the questionnaire at 6 weeks, and thus it is the nature of the differences between treatment groups rather than the absolute timings taken to return to these activities that the authors wish to highlight in this paper. The extent of this overall delay in recovery is hard to justify, particularly in light of the standard information and advice given in the study PIL. There may have been a number of external influences affecting participants' recollection of their recovery, including misinformation and fear. Although attitudes to recovery and return to normal behaviours have changed in secondary care, this may not have filtered into primary care or 'public knowledge'. Fear of activity or fear of pain caused by activity has been documented following surgery for other conditions17, 18. It is possible that some people undergoing treatment for varicose veins experience similar fears, and this may limit or restrict their activity following treatment. With regard to return to work, there are clearly a number of additional factors that might play a role, such as a person's employment status (employed or self‐employed), the sickness benefits they are entitled to, the type of work they are employed to do, how long they are 'signed off' by the doctor, and the views of their employer on return to work after an operation. It should be noted that this study distinguished between partial and full return to work, and that no difference was noted in partial return to work following UGFS and EVLA. This finding may be of substantial importance to patients, their employers and the economy as a whole. The main strength of this study is that the behaviours investigated were based on systematic investigation of the recovery milestones that are important to patients following treatment for varicose veins. Hence, the findings are of personal importance from a patient perspective. Distinguishing between the behaviours that contribute to 'normal activity' helps build a profile of recovery that may be particularly useful for patients preparing for, or recovering from, treatment. Furthermore, the methodology used to develop the BRAVVO questionnaire could be used in other conditions to provide normative information about behavioural recovery that is relevant to patients. The BRAVVO questionnaire was pilot tested and found to be acceptable to patients, comprehensible and appropriate for self‐completion. Despite this, a potential weakness of the study is that the level of missing data in the BRAVVO questionnaire was higher for two of the questions. Further work to reformat or rephrase the questions or response options may help minimize levels of missing data. A further potential weakness is the choice of assessment time point (6 weeks after treatment). This may have compromised recall, particularly for behaviours that participants were able to return to a short time after treatment; however, any compromise in recall is likely to have affected the three treatment groups equally. Other study outcomes were assessed at 6 weeks, and behavioural recovery was assessed at the same time point to minimize participant burden. Further work is required to determine the optimal timing(s) of this questionnaire. Given that the median time to return to the behaviour was less than 14 days for 13 of the behaviours, and up to 22 days for the other two (wearing clothes that show the legs, sporting activity or exercise), the use of the questionnaire at approximately 2–3 weeks would seem appropriate.\n\n**Question:** Compared to surgery what was the result of Ultrasound‐guided foam sclerotherapy on Lifting heavy objects without discomfort?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
588
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Behavioural recovery after treatment for varicose veins\n\n ABSTRACT.BACKGROUND:\nThe aim of this study was to assess behavioural recovery from the patient's perspective as a prespecified secondary outcome in a multicentre parallel‐group randomized clinical trial comparing ultrasound‐guided foam sclerotherapy (UGFS), endovenous laser ablation (EVLA) and surgery for the treatment of primary varicose veins.\n\nABSTRACT.METHODS:\nParticipants were recruited from 11 UK sites as part of the CLASS trial, a randomized trial of UGFS, EVLA or surgery for varicose veins. Patients were followed up 6 weeks after treatment and asked to complete the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This is a 15‐item instrument that covers eight activity behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven participation behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective.\n\nABSTRACT.RESULTS:\nA total of 798 participants were recruited. Both UGFS and EVLA resulted in a significantly quicker recovery compared with surgery for 13 of the 15 behaviours assessed. UGFS was superior to EVLA in terms of return to full‐time work (hazard ratio 1·43, 95 per cent c.i. 1·11 to 1·85), looking after children (1·45, 1·04 to 2·02) and walks of short (1·48, 1·19 to 1·84) and longer (1·32, 1·05 to 1·66) duration.\n\nABSTRACT.CONCLUSION:\nBoth UGFS and EVLA resulted in more rapid recovery than surgery, and UGFS was superior to EVLA for one‐quarter of the behaviours assessed. The BRAVVO questionnaire has the potential to provide important meaningful information to patients about their early recovery and what they may expect to be able to achieve after treatment.\n\nBODY.INTRODUCTION:\nMinimally invasive treatments for varicose veins such as ultrasound‐guided foam sclerotherapy (UGFS) and thermal ablation techniques have become widely used alternatives to surgery for the treatment of varicose veins. One of the advantages of these techniques is the reported quicker return to normal activities, particularly following UGFS1, 2, 3. However, it is unclear whether thermal ablation, in particular endovenous laser ablation (EVLA), is also associated with a clinically significant quicker return to normal activities compared with surgery; some studies4, 5 have shown an earlier return and others2, 6, 7, 8 no difference. Until recently, there was no standard means of assessing recovery from the patient's perspective. This led to the use of varying definitions such as return to 'normal activities', 'full activity', 'daily activity' or 'basic physical activities' and/or 'return to work' in previous studies. This lack of standardization led the authors to develop a 15‐item questionnaire to assess distinct aspects of normal activities that were identified as important by patients9 – the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This paper reports behavioural recovery results from a multicentre parallel‐group randomized clinical trial (CLASS, Comparison of LAser, Surgery and foam Sclerotherapy) that compared the clinical efficacy and cost‐effectiveness of three treatment modalities: UGFS, EVLA with delayed foam sclerotherapy to residual varicosities if required, and surgery. Behavioural recovery was one of the prespecified secondary outcomes of the CLASS trial. The clinical and cost‐effectiveness results have been reported elsewhere10, 11.\n\nBODY.METHODS:\nPatients were recruited from 11 centres in the UK between November 2008 and October 2012. This study (ISRCTN51995477) had research ethics committee and Medicines and Healthcare products Regulatory Authority approval. Eight centres randomized participants to one of three treatment options, and three centres offered only UGFS and surgery. Participants were randomized between the treatments with even allocation, using a minimization algorithm that included centre, age (less than 50 years, 50 years or more), sex, great saphenous vein (GSV) or small saphenous vein (SSV) reflux, and unilateral or bilateral disease. Inclusion criteria were: age over 18 years; primary unilateral or bilateral symptomatic varicose veins (Clinical Etiologic Anatomic Pathophysiological (CEAP) grade C2 or above); GSV and/or SSV involvement; and reflux exceeding 1 s on duplex ultrasonography. Exclusion criteria were: current deep vein thrombosis; acute superficial vein thrombosis; a GSV or SSV diameter smaller than 3 mm or larger than 15 mm; tortuous veins considered unsuitable for EVLA or stripping; and contraindications to UGFS or to general/regional anaesthesia that would be required for surgery.\n\nBODY.METHODS.TREATMENTS:\nThe treatments have been described in detail elsewhere9, 10. For UGFS, foam was produced using the Tessari technique12 using a ratio of 0·5 ml sodium tetradecyl sulphate to 1·5 ml air (3 per cent for GSV/SSV truncal veins, 1 per cent for varicosities; maximum 12 ml foam per session). EVLA of GSVs/SSVs was performed under local anaesthetic, and patients were offered UGFS to any residual varicosities at 6‐week follow‐up if required, with the exception of one centre that performed concurrent phlebectomies. Surgery in the form of proximal GSV/SSV ligation and stripping (all GSV) and concurrent phlebectomies was performed under general or regional anaesthetic as a day‐case procedure. Compression stockings were applied after all three treatments.\n\nBODY.METHODS.POST‐TREATMENT ACTIVITY:\nAll participants were given a study patient information leaflet (PIL), which recommended a return to all normal activities as soon as they were able, but that strenuous activity/contact sport should be avoided for 1–2 weeks. The PIL specifically stated that following EVLA or UGFS 'most people are able to return to work within 2–3 days of treatment, but some people go back the following day or even the same day', and that following surgery 'people can return to office or sedentary work after 2–3 days; and that most people will be back at work within a week after surgery to one leg and 2 weeks after surgery to both legs; but there is no reason to remain off work as long if it can be managed with reasonable comfort'. Participants undergoing UGFS or EVLA were advised to wear compression stocking for 10 days constantly (day and night). Those in the surgery group were advised that bandages would be removed the day after operation, following which they should wear a stocking for 10 days, but that it was reasonable to remove the stocking after 4 or 5 days, providing that they were active.\n\nBODY.METHODS.DATA COLLECTION:\nThe participants were asked to complete the BRAVVO questionnaire along with other study questionnaires (Aberdeen Varicose Vein Questionnaire, EQ‐5DTM (EuroQoL, Rotterdam, The Netherlands) and Short Form 36 (QualityMetric, Lincoln, Rhode Island, USA)) at the 6‐week follow‐up appointment. Participants who failed to attend the 6‐week appointment were sent the questionnaire to complete at home. The BRAVVO questionnaire was developed as an instrument to assess the activity and participation components of the World Health Organization International Classification of Disability and Function model13. Variation in activity and participation is not fully explained by impairment and so these constructs are important additional indicators of health outcome. An interview study involving 17 patients who had recently undergone varicose vein treatment was carried out to identify normal activities and 'milestone' behaviours to incorporate into the questionnaire. In addition to sampling from the three treatment options, diversity sampling was used in an attempt to gain a mix of sex, age and rural–urban location. Seventeen interview transcripts were content‐analysed in four stages to identify appropriate items to include in a questionnaire. Full details of this process have been published previously9. The BRAVVO questionnaire assesses the time taken for patients to return to performing 15 behaviours: eight 'activity' behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven 'participation' behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective9. Fig. 1 shows the question layout. Figure 1Question layoutBJS-10081-FIG-0001-c\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData from the BRAVVO questionnaire were analysed within an interval‐censored time‐to‐event framework using flexible parametric survival models14. For each behaviour item, each participant's response was converted into the number of days to return to that behaviour. If a participant indicated that return to the behaviour was on the day of the procedure, this was assumed to be interval‐censored between day 0 and day 1. If a participant indicated return to the behaviour was after a number of weeks, not days, this was assumed to be interval‐censored between the previous week and the week indicated. For example, if a participant reported 5 weeks, it was assumed that the return to the behaviour took place between 28 and 35 days. A participant who indicated that they had not returned to a behaviour that they usually performed was right‐censored at 42 days. Participants who indicated that they did not normally perform a specific behaviour were not included in analysis of that behaviour. No missing data were imputed. Data are reported as the number of days for 50 and 90 per cent of participants to return to each behaviour, estimated from the parametric survival models (the 50 per cent value represents the median time to return to this behaviour). Extrapolation beyond the 42‐day cut‐off was performed for behaviours where 90 per cent of participants had not returned to the behaviour by 42 days. Treatment effects are presented as hazard ratios with associated 95 per cent c.i. All analyses were carried out in Stata® 1215. Flexible parametric survival models were fitted using the stpm package16.\n\nBODY.RESULTS:\nSeven hundred and ninety‐eight participants were recruited, of whom 13 were ineligible (for example because they had recurrent veins or veins larger than 15 mm in diameter) after randomization and were considered postrandomization exclusions (Fig. \n2). The groups were well balanced in terms of demographic characteristics at baseline, but there was an increased incidence of deep venous reflux in the foam group compared with the surgery group (P = 0·005) (Table \n1). Of the 670 participants who completed the 6‐week questionnaire, 655 completed at least one of the BRAVVO questions. Completion rates were slightly lower for the questions about going out socially (74·8 per cent) and sporting activity (66·0 per cent), which may not have been relevant to all participants. For all behaviours, except wearing clothes that show the leg, going out socially and sporting activities, over 95 per cent of participants had returned to normal behaviour within 6 weeks of intervention. Figure 2CONSORT diagram for the trial. Reasons for postrandomization exclusion included: recurrent varicose veins and veins larger than 15 mm. Reasons for withdrawal from follow‐up included: patient decided not to proceed with treatment (and also declined follow‐up), declined follow‐up after treatment or did not wish to complete questionnaires. UGFS, ultrasound‐guided foam sclerotherapy; EVLA, endovenous laser ablationBJS-10081-FIG-0002-c Table 1 Demographic details at recruitment EVLA UGFS Surgery ( n = 210) ( n = 286) ( n = 289) Age (years) * \n 49·7 (18–80) 49·0 (19–78) 49·2 (22–85) Sex ratio (F : M) 120 : 90 162 : 124 163 : 126 Body mass index (kg/m 2 ) * \n 27·0 (17–42) 27·1 (17–44) 27·7 (17–44) Unilateral disease 153 (72·9) 215 (75·2) 196 (67·8) Employment status Self‐employed 21 (10·2) 37 (13·0) 29 (10·3) Employed 120 (58·3) 169 (59·3) 179 (63·5) Other 65 (31·6) 79 (27·7) 74 (26·2) Unknown 4 1 7 Saphenous vein involvement Great saphenous 182 (86·7) 232 (81·1) 239 (82·7) Small saphenous 14 (6·7) 21 (7·3) 21 (7·3) Great and small saphenous 14 (6·7) 33 (11·5) 29 (10·0) Deep vein reflux 28 of 205 (13·7) 47 of 280 (16·8) 25 of 282 (8·9) CEAP classification C2, varicose veins over 3 mm 113 (54·1) 169 (59·1) 147 (51·2) C3, oedema 28 (13·4) 35 (12·2) 39 (13·6) C4, skin/subcutaneous changes 56 (26·8) 74 (25·9) 90 (31·4) C5/C6, healed/active venous ulcer 12 (5·7) 8 (2·8) 11 (3·8) Unknown 1 0 2 Values in parentheses are percentages unless indicated otherwise; * values are mean (range). EVLA, endovenous laser ablation; UGFS, ultrasound‐guided foam sclerotherapy; CEAP, Clinical Etiologic Anatomic Pathophysiologic. \n\nBODY.RESULTS.ULTRASOUND‐GUIDED FOAM SCLEROTHERAPY :\nParticipants randomized to UGFS recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n2\n). The two behaviours for which there was no evidence of a difference in the time to recover between the trial arms were 'having a bath or shower' and 'wearing clothes that show the legs'. In general, the median time to return to the activity behaviours was 5 days or less for those randomized to UGFS and up to 9 days for those randomized to surgery. In both groups, there was greater variation in the median time to return to the participation behaviours than the activity behaviours. Table 2 Behavioural recovery: ultrasound‐guided foam sclerotherapy versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n UGFS Surgery Activity items Bending the legs without discomfort 50 3·0 4·6 1·38 (1·14, 1·67) 90 14·1 21·3 Lifting heavy objects without discomfort 50 4·8 9·8 1·97 (1·59, 2·44) 90 16·9 34·5 Moving from standing to sitting without discomfort 50 1·9 3·7 1·63 (1·35, 1·97) 90 9·3 17·5 Standing still for a long time (> 15 min ) without discomfort 50 3·9 7·1 1·67 (1·36, 2·05) 90 15·8 28·7 Walking short distances (< 20 min ) without discomfort 50 1·9 4·4 2·00 (1·65, 2·42) 90 8·2 19·1 Walking long distances (> 20 min) 50 4·5 8·0 1·76 (1·45, 2·14) 90 15·2 27·1 Having a bath or shower 50 5·4 4·9 0·85 (0·70, 1·03) 90 11·4 10·3 Driving a car 50 4·1 7·0 1·78 (1·45, 2·19) 90 12·4 21·1 Participation items Doing housework 50 2·1 4·5 2·10 (1·72, 2·56) 90 7·3 15·7 Looking after children 50 1·2 3·5 2·20 (1·61, 3·00) 90 6·2 17·9 Wearing clothes that show the legs 50 12·4 12·8 1·03 (0·78, 1·35) 90 56·6 58·7 Partial return to normal work/employment 50 4·4 9·9 2·16 (1·72, 2·72) 90 15·4 34·2 Full return to normal work/employment 50 4·8 11·7 2·56 (2·05, 3·21) 90 14·9 36·2 Going out socially 50 7·1 9·3 1·29 (1·06, 1·57) 90 25·8 34·0 Sporting activity or exercise 50 15·7 21·8 1·33 (1·05, 1·68) 90 62·6 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.RESULTS.ENDOVENOUS LASER ABLATION :\nParticipants randomized to EVLA recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n3). Return to 'having a bath or shower' was quicker after surgery than after EVLA. There was no difference in time to return to the participation behaviour of 'wearing clothes that show the legs'. Table 3 Behavioural recovery: endovenous laser ablation versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n EVLA Surgery Activity items Bending the legs without discomfort 50 2·7 4·6 1·49 (1·19, 1·75) 90 12·6 21·3 Lifting heavy objects without discomfort 50 5·9 9·8 1·79 (1·39, 2·27) 90 20·5 34·5 Moving from standing to sitting without discomfort 50 2·2 3·7 1·56 (1·27, 1·96) 90 10·4 17·5 Standing still for a long time (> 15 min) without discomfort 50 4·8 7·1 1·41 (1·11, 1·79) 90 20·0 28·7 Walking short distances (< 20 min) without discomfort 50 3·0 4·4 1·30 (1·04, 1·61) 90 13·2 19·1 Walking long distances (> 20 min) 50 5·6 8·0 1·53 (1·06, 1·67) 90 19·8 27·1 Having a bath or shower 50 5·5 4·9 0·74 (0·59, 0·93) 90 12·8 10·3 Driving a car 50 4·4 7·0 1·82 (1·43, 2·33) 90 12·7 21·1 Participation items Doing housework 50 2·5 4·5 1·89 (1·49, 2·38) 90 8·4 15·7 Looking after children 50 1·9 3·5 1·61 (1·15, 2·27) 90 8·8 17·9 Wearing clothes that show the legs 50 14·6 12·8 0·97 (0·69, 1·35) 90 75·1 58·7 Partial return to normal work/employment 50 6·3 9·9 1·75 (1·33, 2·27) 90 21·1 34·2 Full return to normal work/employment 50 7·7 11·7 1·79 (1·37, 2·27) 90 23·5 36·2 Going out socially 50 6·9 9·3 1·41 (1·12, 1·75) 90 23·9 34·0 Sporting activity or exercise 50 14·2 21·8 1·47 (1·12, 1·92) 90 55·5 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. EVLA, endovenous laser ablation. There were no differences in the time taken to return to 11 of the 15 behaviours between participants randomized to EVLA and those randomized to UGFS (Table \n4). Return to 'walking short distances without discomfort', 'walking long distances', 'looking after children' and 'full return to normal work/employment' took longer for the EVLA group than the UGFS group. Following UGFS or EVLA only one‐third of the specific behaviours could be carried out by 50 per cent of participants by 3 days after treatment. Table 4 Behavioural recovery: endovenous laser ablation versus ultrasound‐guided foam sclerotherapy Proportion carrying out behaviour (%) Time until specified proportion of participants can carry out behaviour (days) * \n Hazard ratio † \n EVLA UGFS Activity items Bending the legs without discomfort 50 2·7 3·0 0·94 (0·75, 1·17) 90 12·6 14·1 Lifting heavy objects without discomfort 50 5·9 4·8 1·11 (0·87, 1·42) 90 20·5 16·9 Moving from standing to sitting without discomfort 50 2·2 1·9 1·12 (0·90, 1·40) 90 10·4 9·3 Standing still for a long time (> 15 min) without discomfort 50 4·8 3·9 1·14 (0·90, 1·44) 90 20·0 15·8 Walking short distances (< 20 min) without discomfort 50 3·0 1·9 1·48 (1·19, 1·84) 90 13·2 8·2 Walking long distances (> 20 min) 50 5·6 4·5 1·32 (1·05, 1·66) 90 19·8 15·2 Having a bath or shower 50 5·5 5·4 1·19 (0·96, 1·48) 90 12·8 11·4 Driving a car 50 4·4 4·1 0·95 (0·74, 1·21) 90 12·7 12·4 Participation items Doing housework 50 2·5 2·1 1·03 (0·82, 1·29) 90 8·4 7·3 Looking after children 50 1·9 1·2 1·45 (1·04, 2·02) 90 8·8 6·2 Wearing clothes that show the legs 50 14·6 12·4 1·17 (0·83, 1·64) 90 75·1 56·6 Partial return to normal work/employment 50 6·3 4·4 1·17 (0·89, 1·52) 90 21·1 15·4 Full return to normal work/employment 50 7·7 4·8 1·43 (1·11, 1·85) 90 23·5 14·9 Going out socially 50 6·9 7·1 0·88 (0·70, 1·10) 90 23·9 25·8 Sporting activity or exercise 50 14·2 15·7 0·80 (0·61, 1·04) 90 55·5 62·6 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the endovenous laser ablation (EVLA) arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.DISCUSSION:\nThis study showed that both UGFS and EVLA resulted in a more rapid recovery compared with surgery for 13 of the 15 behaviours. UGFS was superior to EVLA in terms of return to full time work, looking after children and walking (both short and long distances). Importantly, the specific behaviours assessed were shown to have a range of different recovery trajectories. Previous randomized clinical trials showed behavioural recovery to be more rapid following UGFS compared with surgery1, 2, but the benefit of EVLA over surgery was less clear2, 4, 8 . In this study, for all but two behaviours (wearing clothes that showed the legs and showering/bathing) the recovery was quicker following UGFS or EVLA compared with surgery. These findings may have arisen as a result of information contained in the study PIL, which recommended that compression hosiery was worn continuously for 10 days following UGFS or EVLA but for 4–5 days routinely after surgery. In the comparison between UGFS and EVLA, behavioural recovery was faster following UGFS for four of the 15 behaviours; there was no difference between the groups for the other behaviours. Two previous randomized trials2, 3 showed earlier return to 'normal activities' in patients undergoing UGFS compared with EVLA. Specifically, the present study showed a quicker return to full‐time work following UGFS, similar to the findings of Rasmussen and colleagues2. The median time taken to return to work following EVLA (7·7 days) was within the ranges reported2, 4, 5, 6, 7, 8. However, Rasmussen and colleagues2 reported earlier return to work after UGFS compared with the present study (median 2·9 versus 4·8 days respectively). A partial explanation of the difference between the two studies may be that, unlike the previous study, the present analysis did not correct for weekends. For other behaviours, the recalled recovery times following both UGFS and EVLA were longer than might be expected from the literature2, 3, 4, 5, 8. This may be explained by the timing of the questionnaire at 6 weeks, and thus it is the nature of the differences between treatment groups rather than the absolute timings taken to return to these activities that the authors wish to highlight in this paper. The extent of this overall delay in recovery is hard to justify, particularly in light of the standard information and advice given in the study PIL. There may have been a number of external influences affecting participants' recollection of their recovery, including misinformation and fear. Although attitudes to recovery and return to normal behaviours have changed in secondary care, this may not have filtered into primary care or 'public knowledge'. Fear of activity or fear of pain caused by activity has been documented following surgery for other conditions17, 18. It is possible that some people undergoing treatment for varicose veins experience similar fears, and this may limit or restrict their activity following treatment. With regard to return to work, there are clearly a number of additional factors that might play a role, such as a person's employment status (employed or self‐employed), the sickness benefits they are entitled to, the type of work they are employed to do, how long they are 'signed off' by the doctor, and the views of their employer on return to work after an operation. It should be noted that this study distinguished between partial and full return to work, and that no difference was noted in partial return to work following UGFS and EVLA. This finding may be of substantial importance to patients, their employers and the economy as a whole. The main strength of this study is that the behaviours investigated were based on systematic investigation of the recovery milestones that are important to patients following treatment for varicose veins. Hence, the findings are of personal importance from a patient perspective. Distinguishing between the behaviours that contribute to 'normal activity' helps build a profile of recovery that may be particularly useful for patients preparing for, or recovering from, treatment. Furthermore, the methodology used to develop the BRAVVO questionnaire could be used in other conditions to provide normative information about behavioural recovery that is relevant to patients. The BRAVVO questionnaire was pilot tested and found to be acceptable to patients, comprehensible and appropriate for self‐completion. Despite this, a potential weakness of the study is that the level of missing data in the BRAVVO questionnaire was higher for two of the questions. Further work to reformat or rephrase the questions or response options may help minimize levels of missing data. A further potential weakness is the choice of assessment time point (6 weeks after treatment). This may have compromised recall, particularly for behaviours that participants were able to return to a short time after treatment; however, any compromise in recall is likely to have affected the three treatment groups equally. Other study outcomes were assessed at 6 weeks, and behavioural recovery was assessed at the same time point to minimize participant burden. Further work is required to determine the optimal timing(s) of this questionnaire. Given that the median time to return to the behaviour was less than 14 days for 13 of the behaviours, and up to 22 days for the other two (wearing clothes that show the legs, sporting activity or exercise), the use of the questionnaire at approximately 2–3 weeks would seem appropriate.\n\n**Question:** Compared to surgery what was the result of Ultrasound‐guided foam sclerotherapy on Walking long distances (> 20 min)?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
594
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Behavioural recovery after treatment for varicose veins\n\n ABSTRACT.BACKGROUND:\nThe aim of this study was to assess behavioural recovery from the patient's perspective as a prespecified secondary outcome in a multicentre parallel‐group randomized clinical trial comparing ultrasound‐guided foam sclerotherapy (UGFS), endovenous laser ablation (EVLA) and surgery for the treatment of primary varicose veins.\n\nABSTRACT.METHODS:\nParticipants were recruited from 11 UK sites as part of the CLASS trial, a randomized trial of UGFS, EVLA or surgery for varicose veins. Patients were followed up 6 weeks after treatment and asked to complete the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This is a 15‐item instrument that covers eight activity behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven participation behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective.\n\nABSTRACT.RESULTS:\nA total of 798 participants were recruited. Both UGFS and EVLA resulted in a significantly quicker recovery compared with surgery for 13 of the 15 behaviours assessed. UGFS was superior to EVLA in terms of return to full‐time work (hazard ratio 1·43, 95 per cent c.i. 1·11 to 1·85), looking after children (1·45, 1·04 to 2·02) and walks of short (1·48, 1·19 to 1·84) and longer (1·32, 1·05 to 1·66) duration.\n\nABSTRACT.CONCLUSION:\nBoth UGFS and EVLA resulted in more rapid recovery than surgery, and UGFS was superior to EVLA for one‐quarter of the behaviours assessed. The BRAVVO questionnaire has the potential to provide important meaningful information to patients about their early recovery and what they may expect to be able to achieve after treatment.\n\nBODY.INTRODUCTION:\nMinimally invasive treatments for varicose veins such as ultrasound‐guided foam sclerotherapy (UGFS) and thermal ablation techniques have become widely used alternatives to surgery for the treatment of varicose veins. One of the advantages of these techniques is the reported quicker return to normal activities, particularly following UGFS1, 2, 3. However, it is unclear whether thermal ablation, in particular endovenous laser ablation (EVLA), is also associated with a clinically significant quicker return to normal activities compared with surgery; some studies4, 5 have shown an earlier return and others2, 6, 7, 8 no difference. Until recently, there was no standard means of assessing recovery from the patient's perspective. This led to the use of varying definitions such as return to 'normal activities', 'full activity', 'daily activity' or 'basic physical activities' and/or 'return to work' in previous studies. This lack of standardization led the authors to develop a 15‐item questionnaire to assess distinct aspects of normal activities that were identified as important by patients9 – the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This paper reports behavioural recovery results from a multicentre parallel‐group randomized clinical trial (CLASS, Comparison of LAser, Surgery and foam Sclerotherapy) that compared the clinical efficacy and cost‐effectiveness of three treatment modalities: UGFS, EVLA with delayed foam sclerotherapy to residual varicosities if required, and surgery. Behavioural recovery was one of the prespecified secondary outcomes of the CLASS trial. The clinical and cost‐effectiveness results have been reported elsewhere10, 11.\n\nBODY.METHODS:\nPatients were recruited from 11 centres in the UK between November 2008 and October 2012. This study (ISRCTN51995477) had research ethics committee and Medicines and Healthcare products Regulatory Authority approval. Eight centres randomized participants to one of three treatment options, and three centres offered only UGFS and surgery. Participants were randomized between the treatments with even allocation, using a minimization algorithm that included centre, age (less than 50 years, 50 years or more), sex, great saphenous vein (GSV) or small saphenous vein (SSV) reflux, and unilateral or bilateral disease. Inclusion criteria were: age over 18 years; primary unilateral or bilateral symptomatic varicose veins (Clinical Etiologic Anatomic Pathophysiological (CEAP) grade C2 or above); GSV and/or SSV involvement; and reflux exceeding 1 s on duplex ultrasonography. Exclusion criteria were: current deep vein thrombosis; acute superficial vein thrombosis; a GSV or SSV diameter smaller than 3 mm or larger than 15 mm; tortuous veins considered unsuitable for EVLA or stripping; and contraindications to UGFS or to general/regional anaesthesia that would be required for surgery.\n\nBODY.METHODS.TREATMENTS:\nThe treatments have been described in detail elsewhere9, 10. For UGFS, foam was produced using the Tessari technique12 using a ratio of 0·5 ml sodium tetradecyl sulphate to 1·5 ml air (3 per cent for GSV/SSV truncal veins, 1 per cent for varicosities; maximum 12 ml foam per session). EVLA of GSVs/SSVs was performed under local anaesthetic, and patients were offered UGFS to any residual varicosities at 6‐week follow‐up if required, with the exception of one centre that performed concurrent phlebectomies. Surgery in the form of proximal GSV/SSV ligation and stripping (all GSV) and concurrent phlebectomies was performed under general or regional anaesthetic as a day‐case procedure. Compression stockings were applied after all three treatments.\n\nBODY.METHODS.POST‐TREATMENT ACTIVITY:\nAll participants were given a study patient information leaflet (PIL), which recommended a return to all normal activities as soon as they were able, but that strenuous activity/contact sport should be avoided for 1–2 weeks. The PIL specifically stated that following EVLA or UGFS 'most people are able to return to work within 2–3 days of treatment, but some people go back the following day or even the same day', and that following surgery 'people can return to office or sedentary work after 2–3 days; and that most people will be back at work within a week after surgery to one leg and 2 weeks after surgery to both legs; but there is no reason to remain off work as long if it can be managed with reasonable comfort'. Participants undergoing UGFS or EVLA were advised to wear compression stocking for 10 days constantly (day and night). Those in the surgery group were advised that bandages would be removed the day after operation, following which they should wear a stocking for 10 days, but that it was reasonable to remove the stocking after 4 or 5 days, providing that they were active.\n\nBODY.METHODS.DATA COLLECTION:\nThe participants were asked to complete the BRAVVO questionnaire along with other study questionnaires (Aberdeen Varicose Vein Questionnaire, EQ‐5DTM (EuroQoL, Rotterdam, The Netherlands) and Short Form 36 (QualityMetric, Lincoln, Rhode Island, USA)) at the 6‐week follow‐up appointment. Participants who failed to attend the 6‐week appointment were sent the questionnaire to complete at home. The BRAVVO questionnaire was developed as an instrument to assess the activity and participation components of the World Health Organization International Classification of Disability and Function model13. Variation in activity and participation is not fully explained by impairment and so these constructs are important additional indicators of health outcome. An interview study involving 17 patients who had recently undergone varicose vein treatment was carried out to identify normal activities and 'milestone' behaviours to incorporate into the questionnaire. In addition to sampling from the three treatment options, diversity sampling was used in an attempt to gain a mix of sex, age and rural–urban location. Seventeen interview transcripts were content‐analysed in four stages to identify appropriate items to include in a questionnaire. Full details of this process have been published previously9. The BRAVVO questionnaire assesses the time taken for patients to return to performing 15 behaviours: eight 'activity' behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven 'participation' behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective9. Fig. 1 shows the question layout. Figure 1Question layoutBJS-10081-FIG-0001-c\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData from the BRAVVO questionnaire were analysed within an interval‐censored time‐to‐event framework using flexible parametric survival models14. For each behaviour item, each participant's response was converted into the number of days to return to that behaviour. If a participant indicated that return to the behaviour was on the day of the procedure, this was assumed to be interval‐censored between day 0 and day 1. If a participant indicated return to the behaviour was after a number of weeks, not days, this was assumed to be interval‐censored between the previous week and the week indicated. For example, if a participant reported 5 weeks, it was assumed that the return to the behaviour took place between 28 and 35 days. A participant who indicated that they had not returned to a behaviour that they usually performed was right‐censored at 42 days. Participants who indicated that they did not normally perform a specific behaviour were not included in analysis of that behaviour. No missing data were imputed. Data are reported as the number of days for 50 and 90 per cent of participants to return to each behaviour, estimated from the parametric survival models (the 50 per cent value represents the median time to return to this behaviour). Extrapolation beyond the 42‐day cut‐off was performed for behaviours where 90 per cent of participants had not returned to the behaviour by 42 days. Treatment effects are presented as hazard ratios with associated 95 per cent c.i. All analyses were carried out in Stata® 1215. Flexible parametric survival models were fitted using the stpm package16.\n\nBODY.RESULTS:\nSeven hundred and ninety‐eight participants were recruited, of whom 13 were ineligible (for example because they had recurrent veins or veins larger than 15 mm in diameter) after randomization and were considered postrandomization exclusions (Fig. \n2). The groups were well balanced in terms of demographic characteristics at baseline, but there was an increased incidence of deep venous reflux in the foam group compared with the surgery group (P = 0·005) (Table \n1). Of the 670 participants who completed the 6‐week questionnaire, 655 completed at least one of the BRAVVO questions. Completion rates were slightly lower for the questions about going out socially (74·8 per cent) and sporting activity (66·0 per cent), which may not have been relevant to all participants. For all behaviours, except wearing clothes that show the leg, going out socially and sporting activities, over 95 per cent of participants had returned to normal behaviour within 6 weeks of intervention. Figure 2CONSORT diagram for the trial. Reasons for postrandomization exclusion included: recurrent varicose veins and veins larger than 15 mm. Reasons for withdrawal from follow‐up included: patient decided not to proceed with treatment (and also declined follow‐up), declined follow‐up after treatment or did not wish to complete questionnaires. UGFS, ultrasound‐guided foam sclerotherapy; EVLA, endovenous laser ablationBJS-10081-FIG-0002-c Table 1 Demographic details at recruitment EVLA UGFS Surgery ( n = 210) ( n = 286) ( n = 289) Age (years) * \n 49·7 (18–80) 49·0 (19–78) 49·2 (22–85) Sex ratio (F : M) 120 : 90 162 : 124 163 : 126 Body mass index (kg/m 2 ) * \n 27·0 (17–42) 27·1 (17–44) 27·7 (17–44) Unilateral disease 153 (72·9) 215 (75·2) 196 (67·8) Employment status Self‐employed 21 (10·2) 37 (13·0) 29 (10·3) Employed 120 (58·3) 169 (59·3) 179 (63·5) Other 65 (31·6) 79 (27·7) 74 (26·2) Unknown 4 1 7 Saphenous vein involvement Great saphenous 182 (86·7) 232 (81·1) 239 (82·7) Small saphenous 14 (6·7) 21 (7·3) 21 (7·3) Great and small saphenous 14 (6·7) 33 (11·5) 29 (10·0) Deep vein reflux 28 of 205 (13·7) 47 of 280 (16·8) 25 of 282 (8·9) CEAP classification C2, varicose veins over 3 mm 113 (54·1) 169 (59·1) 147 (51·2) C3, oedema 28 (13·4) 35 (12·2) 39 (13·6) C4, skin/subcutaneous changes 56 (26·8) 74 (25·9) 90 (31·4) C5/C6, healed/active venous ulcer 12 (5·7) 8 (2·8) 11 (3·8) Unknown 1 0 2 Values in parentheses are percentages unless indicated otherwise; * values are mean (range). EVLA, endovenous laser ablation; UGFS, ultrasound‐guided foam sclerotherapy; CEAP, Clinical Etiologic Anatomic Pathophysiologic. \n\nBODY.RESULTS.ULTRASOUND‐GUIDED FOAM SCLEROTHERAPY :\nParticipants randomized to UGFS recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n2\n). The two behaviours for which there was no evidence of a difference in the time to recover between the trial arms were 'having a bath or shower' and 'wearing clothes that show the legs'. In general, the median time to return to the activity behaviours was 5 days or less for those randomized to UGFS and up to 9 days for those randomized to surgery. In both groups, there was greater variation in the median time to return to the participation behaviours than the activity behaviours. Table 2 Behavioural recovery: ultrasound‐guided foam sclerotherapy versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n UGFS Surgery Activity items Bending the legs without discomfort 50 3·0 4·6 1·38 (1·14, 1·67) 90 14·1 21·3 Lifting heavy objects without discomfort 50 4·8 9·8 1·97 (1·59, 2·44) 90 16·9 34·5 Moving from standing to sitting without discomfort 50 1·9 3·7 1·63 (1·35, 1·97) 90 9·3 17·5 Standing still for a long time (> 15 min ) without discomfort 50 3·9 7·1 1·67 (1·36, 2·05) 90 15·8 28·7 Walking short distances (< 20 min ) without discomfort 50 1·9 4·4 2·00 (1·65, 2·42) 90 8·2 19·1 Walking long distances (> 20 min) 50 4·5 8·0 1·76 (1·45, 2·14) 90 15·2 27·1 Having a bath or shower 50 5·4 4·9 0·85 (0·70, 1·03) 90 11·4 10·3 Driving a car 50 4·1 7·0 1·78 (1·45, 2·19) 90 12·4 21·1 Participation items Doing housework 50 2·1 4·5 2·10 (1·72, 2·56) 90 7·3 15·7 Looking after children 50 1·2 3·5 2·20 (1·61, 3·00) 90 6·2 17·9 Wearing clothes that show the legs 50 12·4 12·8 1·03 (0·78, 1·35) 90 56·6 58·7 Partial return to normal work/employment 50 4·4 9·9 2·16 (1·72, 2·72) 90 15·4 34·2 Full return to normal work/employment 50 4·8 11·7 2·56 (2·05, 3·21) 90 14·9 36·2 Going out socially 50 7·1 9·3 1·29 (1·06, 1·57) 90 25·8 34·0 Sporting activity or exercise 50 15·7 21·8 1·33 (1·05, 1·68) 90 62·6 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.RESULTS.ENDOVENOUS LASER ABLATION :\nParticipants randomized to EVLA recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n3). Return to 'having a bath or shower' was quicker after surgery than after EVLA. There was no difference in time to return to the participation behaviour of 'wearing clothes that show the legs'. Table 3 Behavioural recovery: endovenous laser ablation versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n EVLA Surgery Activity items Bending the legs without discomfort 50 2·7 4·6 1·49 (1·19, 1·75) 90 12·6 21·3 Lifting heavy objects without discomfort 50 5·9 9·8 1·79 (1·39, 2·27) 90 20·5 34·5 Moving from standing to sitting without discomfort 50 2·2 3·7 1·56 (1·27, 1·96) 90 10·4 17·5 Standing still for a long time (> 15 min) without discomfort 50 4·8 7·1 1·41 (1·11, 1·79) 90 20·0 28·7 Walking short distances (< 20 min) without discomfort 50 3·0 4·4 1·30 (1·04, 1·61) 90 13·2 19·1 Walking long distances (> 20 min) 50 5·6 8·0 1·53 (1·06, 1·67) 90 19·8 27·1 Having a bath or shower 50 5·5 4·9 0·74 (0·59, 0·93) 90 12·8 10·3 Driving a car 50 4·4 7·0 1·82 (1·43, 2·33) 90 12·7 21·1 Participation items Doing housework 50 2·5 4·5 1·89 (1·49, 2·38) 90 8·4 15·7 Looking after children 50 1·9 3·5 1·61 (1·15, 2·27) 90 8·8 17·9 Wearing clothes that show the legs 50 14·6 12·8 0·97 (0·69, 1·35) 90 75·1 58·7 Partial return to normal work/employment 50 6·3 9·9 1·75 (1·33, 2·27) 90 21·1 34·2 Full return to normal work/employment 50 7·7 11·7 1·79 (1·37, 2·27) 90 23·5 36·2 Going out socially 50 6·9 9·3 1·41 (1·12, 1·75) 90 23·9 34·0 Sporting activity or exercise 50 14·2 21·8 1·47 (1·12, 1·92) 90 55·5 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. EVLA, endovenous laser ablation. There were no differences in the time taken to return to 11 of the 15 behaviours between participants randomized to EVLA and those randomized to UGFS (Table \n4). Return to 'walking short distances without discomfort', 'walking long distances', 'looking after children' and 'full return to normal work/employment' took longer for the EVLA group than the UGFS group. Following UGFS or EVLA only one‐third of the specific behaviours could be carried out by 50 per cent of participants by 3 days after treatment. Table 4 Behavioural recovery: endovenous laser ablation versus ultrasound‐guided foam sclerotherapy Proportion carrying out behaviour (%) Time until specified proportion of participants can carry out behaviour (days) * \n Hazard ratio † \n EVLA UGFS Activity items Bending the legs without discomfort 50 2·7 3·0 0·94 (0·75, 1·17) 90 12·6 14·1 Lifting heavy objects without discomfort 50 5·9 4·8 1·11 (0·87, 1·42) 90 20·5 16·9 Moving from standing to sitting without discomfort 50 2·2 1·9 1·12 (0·90, 1·40) 90 10·4 9·3 Standing still for a long time (> 15 min) without discomfort 50 4·8 3·9 1·14 (0·90, 1·44) 90 20·0 15·8 Walking short distances (< 20 min) without discomfort 50 3·0 1·9 1·48 (1·19, 1·84) 90 13·2 8·2 Walking long distances (> 20 min) 50 5·6 4·5 1·32 (1·05, 1·66) 90 19·8 15·2 Having a bath or shower 50 5·5 5·4 1·19 (0·96, 1·48) 90 12·8 11·4 Driving a car 50 4·4 4·1 0·95 (0·74, 1·21) 90 12·7 12·4 Participation items Doing housework 50 2·5 2·1 1·03 (0·82, 1·29) 90 8·4 7·3 Looking after children 50 1·9 1·2 1·45 (1·04, 2·02) 90 8·8 6·2 Wearing clothes that show the legs 50 14·6 12·4 1·17 (0·83, 1·64) 90 75·1 56·6 Partial return to normal work/employment 50 6·3 4·4 1·17 (0·89, 1·52) 90 21·1 15·4 Full return to normal work/employment 50 7·7 4·8 1·43 (1·11, 1·85) 90 23·5 14·9 Going out socially 50 6·9 7·1 0·88 (0·70, 1·10) 90 23·9 25·8 Sporting activity or exercise 50 14·2 15·7 0·80 (0·61, 1·04) 90 55·5 62·6 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the endovenous laser ablation (EVLA) arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.DISCUSSION:\nThis study showed that both UGFS and EVLA resulted in a more rapid recovery compared with surgery for 13 of the 15 behaviours. UGFS was superior to EVLA in terms of return to full time work, looking after children and walking (both short and long distances). Importantly, the specific behaviours assessed were shown to have a range of different recovery trajectories. Previous randomized clinical trials showed behavioural recovery to be more rapid following UGFS compared with surgery1, 2, but the benefit of EVLA over surgery was less clear2, 4, 8 . In this study, for all but two behaviours (wearing clothes that showed the legs and showering/bathing) the recovery was quicker following UGFS or EVLA compared with surgery. These findings may have arisen as a result of information contained in the study PIL, which recommended that compression hosiery was worn continuously for 10 days following UGFS or EVLA but for 4–5 days routinely after surgery. In the comparison between UGFS and EVLA, behavioural recovery was faster following UGFS for four of the 15 behaviours; there was no difference between the groups for the other behaviours. Two previous randomized trials2, 3 showed earlier return to 'normal activities' in patients undergoing UGFS compared with EVLA. Specifically, the present study showed a quicker return to full‐time work following UGFS, similar to the findings of Rasmussen and colleagues2. The median time taken to return to work following EVLA (7·7 days) was within the ranges reported2, 4, 5, 6, 7, 8. However, Rasmussen and colleagues2 reported earlier return to work after UGFS compared with the present study (median 2·9 versus 4·8 days respectively). A partial explanation of the difference between the two studies may be that, unlike the previous study, the present analysis did not correct for weekends. For other behaviours, the recalled recovery times following both UGFS and EVLA were longer than might be expected from the literature2, 3, 4, 5, 8. This may be explained by the timing of the questionnaire at 6 weeks, and thus it is the nature of the differences between treatment groups rather than the absolute timings taken to return to these activities that the authors wish to highlight in this paper. The extent of this overall delay in recovery is hard to justify, particularly in light of the standard information and advice given in the study PIL. There may have been a number of external influences affecting participants' recollection of their recovery, including misinformation and fear. Although attitudes to recovery and return to normal behaviours have changed in secondary care, this may not have filtered into primary care or 'public knowledge'. Fear of activity or fear of pain caused by activity has been documented following surgery for other conditions17, 18. It is possible that some people undergoing treatment for varicose veins experience similar fears, and this may limit or restrict their activity following treatment. With regard to return to work, there are clearly a number of additional factors that might play a role, such as a person's employment status (employed or self‐employed), the sickness benefits they are entitled to, the type of work they are employed to do, how long they are 'signed off' by the doctor, and the views of their employer on return to work after an operation. It should be noted that this study distinguished between partial and full return to work, and that no difference was noted in partial return to work following UGFS and EVLA. This finding may be of substantial importance to patients, their employers and the economy as a whole. The main strength of this study is that the behaviours investigated were based on systematic investigation of the recovery milestones that are important to patients following treatment for varicose veins. Hence, the findings are of personal importance from a patient perspective. Distinguishing between the behaviours that contribute to 'normal activity' helps build a profile of recovery that may be particularly useful for patients preparing for, or recovering from, treatment. Furthermore, the methodology used to develop the BRAVVO questionnaire could be used in other conditions to provide normative information about behavioural recovery that is relevant to patients. The BRAVVO questionnaire was pilot tested and found to be acceptable to patients, comprehensible and appropriate for self‐completion. Despite this, a potential weakness of the study is that the level of missing data in the BRAVVO questionnaire was higher for two of the questions. Further work to reformat or rephrase the questions or response options may help minimize levels of missing data. A further potential weakness is the choice of assessment time point (6 weeks after treatment). This may have compromised recall, particularly for behaviours that participants were able to return to a short time after treatment; however, any compromise in recall is likely to have affected the three treatment groups equally. Other study outcomes were assessed at 6 weeks, and behavioural recovery was assessed at the same time point to minimize participant burden. Further work is required to determine the optimal timing(s) of this questionnaire. Given that the median time to return to the behaviour was less than 14 days for 13 of the behaviours, and up to 22 days for the other two (wearing clothes that show the legs, sporting activity or exercise), the use of the questionnaire at approximately 2–3 weeks would seem appropriate.\n\n**Question:** Compared to surgery what was the result of Ultrasound‐guided foam sclerotherapy on Partial return to normal work/employment?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
596
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Behavioural recovery after treatment for varicose veins\n\n ABSTRACT.BACKGROUND:\nThe aim of this study was to assess behavioural recovery from the patient's perspective as a prespecified secondary outcome in a multicentre parallel‐group randomized clinical trial comparing ultrasound‐guided foam sclerotherapy (UGFS), endovenous laser ablation (EVLA) and surgery for the treatment of primary varicose veins.\n\nABSTRACT.METHODS:\nParticipants were recruited from 11 UK sites as part of the CLASS trial, a randomized trial of UGFS, EVLA or surgery for varicose veins. Patients were followed up 6 weeks after treatment and asked to complete the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This is a 15‐item instrument that covers eight activity behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven participation behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective.\n\nABSTRACT.RESULTS:\nA total of 798 participants were recruited. Both UGFS and EVLA resulted in a significantly quicker recovery compared with surgery for 13 of the 15 behaviours assessed. UGFS was superior to EVLA in terms of return to full‐time work (hazard ratio 1·43, 95 per cent c.i. 1·11 to 1·85), looking after children (1·45, 1·04 to 2·02) and walks of short (1·48, 1·19 to 1·84) and longer (1·32, 1·05 to 1·66) duration.\n\nABSTRACT.CONCLUSION:\nBoth UGFS and EVLA resulted in more rapid recovery than surgery, and UGFS was superior to EVLA for one‐quarter of the behaviours assessed. The BRAVVO questionnaire has the potential to provide important meaningful information to patients about their early recovery and what they may expect to be able to achieve after treatment.\n\nBODY.INTRODUCTION:\nMinimally invasive treatments for varicose veins such as ultrasound‐guided foam sclerotherapy (UGFS) and thermal ablation techniques have become widely used alternatives to surgery for the treatment of varicose veins. One of the advantages of these techniques is the reported quicker return to normal activities, particularly following UGFS1, 2, 3. However, it is unclear whether thermal ablation, in particular endovenous laser ablation (EVLA), is also associated with a clinically significant quicker return to normal activities compared with surgery; some studies4, 5 have shown an earlier return and others2, 6, 7, 8 no difference. Until recently, there was no standard means of assessing recovery from the patient's perspective. This led to the use of varying definitions such as return to 'normal activities', 'full activity', 'daily activity' or 'basic physical activities' and/or 'return to work' in previous studies. This lack of standardization led the authors to develop a 15‐item questionnaire to assess distinct aspects of normal activities that were identified as important by patients9 – the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This paper reports behavioural recovery results from a multicentre parallel‐group randomized clinical trial (CLASS, Comparison of LAser, Surgery and foam Sclerotherapy) that compared the clinical efficacy and cost‐effectiveness of three treatment modalities: UGFS, EVLA with delayed foam sclerotherapy to residual varicosities if required, and surgery. Behavioural recovery was one of the prespecified secondary outcomes of the CLASS trial. The clinical and cost‐effectiveness results have been reported elsewhere10, 11.\n\nBODY.METHODS:\nPatients were recruited from 11 centres in the UK between November 2008 and October 2012. This study (ISRCTN51995477) had research ethics committee and Medicines and Healthcare products Regulatory Authority approval. Eight centres randomized participants to one of three treatment options, and three centres offered only UGFS and surgery. Participants were randomized between the treatments with even allocation, using a minimization algorithm that included centre, age (less than 50 years, 50 years or more), sex, great saphenous vein (GSV) or small saphenous vein (SSV) reflux, and unilateral or bilateral disease. Inclusion criteria were: age over 18 years; primary unilateral or bilateral symptomatic varicose veins (Clinical Etiologic Anatomic Pathophysiological (CEAP) grade C2 or above); GSV and/or SSV involvement; and reflux exceeding 1 s on duplex ultrasonography. Exclusion criteria were: current deep vein thrombosis; acute superficial vein thrombosis; a GSV or SSV diameter smaller than 3 mm or larger than 15 mm; tortuous veins considered unsuitable for EVLA or stripping; and contraindications to UGFS or to general/regional anaesthesia that would be required for surgery.\n\nBODY.METHODS.TREATMENTS:\nThe treatments have been described in detail elsewhere9, 10. For UGFS, foam was produced using the Tessari technique12 using a ratio of 0·5 ml sodium tetradecyl sulphate to 1·5 ml air (3 per cent for GSV/SSV truncal veins, 1 per cent for varicosities; maximum 12 ml foam per session). EVLA of GSVs/SSVs was performed under local anaesthetic, and patients were offered UGFS to any residual varicosities at 6‐week follow‐up if required, with the exception of one centre that performed concurrent phlebectomies. Surgery in the form of proximal GSV/SSV ligation and stripping (all GSV) and concurrent phlebectomies was performed under general or regional anaesthetic as a day‐case procedure. Compression stockings were applied after all three treatments.\n\nBODY.METHODS.POST‐TREATMENT ACTIVITY:\nAll participants were given a study patient information leaflet (PIL), which recommended a return to all normal activities as soon as they were able, but that strenuous activity/contact sport should be avoided for 1–2 weeks. The PIL specifically stated that following EVLA or UGFS 'most people are able to return to work within 2–3 days of treatment, but some people go back the following day or even the same day', and that following surgery 'people can return to office or sedentary work after 2–3 days; and that most people will be back at work within a week after surgery to one leg and 2 weeks after surgery to both legs; but there is no reason to remain off work as long if it can be managed with reasonable comfort'. Participants undergoing UGFS or EVLA were advised to wear compression stocking for 10 days constantly (day and night). Those in the surgery group were advised that bandages would be removed the day after operation, following which they should wear a stocking for 10 days, but that it was reasonable to remove the stocking after 4 or 5 days, providing that they were active.\n\nBODY.METHODS.DATA COLLECTION:\nThe participants were asked to complete the BRAVVO questionnaire along with other study questionnaires (Aberdeen Varicose Vein Questionnaire, EQ‐5DTM (EuroQoL, Rotterdam, The Netherlands) and Short Form 36 (QualityMetric, Lincoln, Rhode Island, USA)) at the 6‐week follow‐up appointment. Participants who failed to attend the 6‐week appointment were sent the questionnaire to complete at home. The BRAVVO questionnaire was developed as an instrument to assess the activity and participation components of the World Health Organization International Classification of Disability and Function model13. Variation in activity and participation is not fully explained by impairment and so these constructs are important additional indicators of health outcome. An interview study involving 17 patients who had recently undergone varicose vein treatment was carried out to identify normal activities and 'milestone' behaviours to incorporate into the questionnaire. In addition to sampling from the three treatment options, diversity sampling was used in an attempt to gain a mix of sex, age and rural–urban location. Seventeen interview transcripts were content‐analysed in four stages to identify appropriate items to include in a questionnaire. Full details of this process have been published previously9. The BRAVVO questionnaire assesses the time taken for patients to return to performing 15 behaviours: eight 'activity' behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven 'participation' behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective9. Fig. 1 shows the question layout. Figure 1Question layoutBJS-10081-FIG-0001-c\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData from the BRAVVO questionnaire were analysed within an interval‐censored time‐to‐event framework using flexible parametric survival models14. For each behaviour item, each participant's response was converted into the number of days to return to that behaviour. If a participant indicated that return to the behaviour was on the day of the procedure, this was assumed to be interval‐censored between day 0 and day 1. If a participant indicated return to the behaviour was after a number of weeks, not days, this was assumed to be interval‐censored between the previous week and the week indicated. For example, if a participant reported 5 weeks, it was assumed that the return to the behaviour took place between 28 and 35 days. A participant who indicated that they had not returned to a behaviour that they usually performed was right‐censored at 42 days. Participants who indicated that they did not normally perform a specific behaviour were not included in analysis of that behaviour. No missing data were imputed. Data are reported as the number of days for 50 and 90 per cent of participants to return to each behaviour, estimated from the parametric survival models (the 50 per cent value represents the median time to return to this behaviour). Extrapolation beyond the 42‐day cut‐off was performed for behaviours where 90 per cent of participants had not returned to the behaviour by 42 days. Treatment effects are presented as hazard ratios with associated 95 per cent c.i. All analyses were carried out in Stata® 1215. Flexible parametric survival models were fitted using the stpm package16.\n\nBODY.RESULTS:\nSeven hundred and ninety‐eight participants were recruited, of whom 13 were ineligible (for example because they had recurrent veins or veins larger than 15 mm in diameter) after randomization and were considered postrandomization exclusions (Fig. \n2). The groups were well balanced in terms of demographic characteristics at baseline, but there was an increased incidence of deep venous reflux in the foam group compared with the surgery group (P = 0·005) (Table \n1). Of the 670 participants who completed the 6‐week questionnaire, 655 completed at least one of the BRAVVO questions. Completion rates were slightly lower for the questions about going out socially (74·8 per cent) and sporting activity (66·0 per cent), which may not have been relevant to all participants. For all behaviours, except wearing clothes that show the leg, going out socially and sporting activities, over 95 per cent of participants had returned to normal behaviour within 6 weeks of intervention. Figure 2CONSORT diagram for the trial. Reasons for postrandomization exclusion included: recurrent varicose veins and veins larger than 15 mm. Reasons for withdrawal from follow‐up included: patient decided not to proceed with treatment (and also declined follow‐up), declined follow‐up after treatment or did not wish to complete questionnaires. UGFS, ultrasound‐guided foam sclerotherapy; EVLA, endovenous laser ablationBJS-10081-FIG-0002-c Table 1 Demographic details at recruitment EVLA UGFS Surgery ( n = 210) ( n = 286) ( n = 289) Age (years) * \n 49·7 (18–80) 49·0 (19–78) 49·2 (22–85) Sex ratio (F : M) 120 : 90 162 : 124 163 : 126 Body mass index (kg/m 2 ) * \n 27·0 (17–42) 27·1 (17–44) 27·7 (17–44) Unilateral disease 153 (72·9) 215 (75·2) 196 (67·8) Employment status Self‐employed 21 (10·2) 37 (13·0) 29 (10·3) Employed 120 (58·3) 169 (59·3) 179 (63·5) Other 65 (31·6) 79 (27·7) 74 (26·2) Unknown 4 1 7 Saphenous vein involvement Great saphenous 182 (86·7) 232 (81·1) 239 (82·7) Small saphenous 14 (6·7) 21 (7·3) 21 (7·3) Great and small saphenous 14 (6·7) 33 (11·5) 29 (10·0) Deep vein reflux 28 of 205 (13·7) 47 of 280 (16·8) 25 of 282 (8·9) CEAP classification C2, varicose veins over 3 mm 113 (54·1) 169 (59·1) 147 (51·2) C3, oedema 28 (13·4) 35 (12·2) 39 (13·6) C4, skin/subcutaneous changes 56 (26·8) 74 (25·9) 90 (31·4) C5/C6, healed/active venous ulcer 12 (5·7) 8 (2·8) 11 (3·8) Unknown 1 0 2 Values in parentheses are percentages unless indicated otherwise; * values are mean (range). EVLA, endovenous laser ablation; UGFS, ultrasound‐guided foam sclerotherapy; CEAP, Clinical Etiologic Anatomic Pathophysiologic. \n\nBODY.RESULTS.ULTRASOUND‐GUIDED FOAM SCLEROTHERAPY :\nParticipants randomized to UGFS recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n2\n). The two behaviours for which there was no evidence of a difference in the time to recover between the trial arms were 'having a bath or shower' and 'wearing clothes that show the legs'. In general, the median time to return to the activity behaviours was 5 days or less for those randomized to UGFS and up to 9 days for those randomized to surgery. In both groups, there was greater variation in the median time to return to the participation behaviours than the activity behaviours. Table 2 Behavioural recovery: ultrasound‐guided foam sclerotherapy versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n UGFS Surgery Activity items Bending the legs without discomfort 50 3·0 4·6 1·38 (1·14, 1·67) 90 14·1 21·3 Lifting heavy objects without discomfort 50 4·8 9·8 1·97 (1·59, 2·44) 90 16·9 34·5 Moving from standing to sitting without discomfort 50 1·9 3·7 1·63 (1·35, 1·97) 90 9·3 17·5 Standing still for a long time (> 15 min ) without discomfort 50 3·9 7·1 1·67 (1·36, 2·05) 90 15·8 28·7 Walking short distances (< 20 min ) without discomfort 50 1·9 4·4 2·00 (1·65, 2·42) 90 8·2 19·1 Walking long distances (> 20 min) 50 4·5 8·0 1·76 (1·45, 2·14) 90 15·2 27·1 Having a bath or shower 50 5·4 4·9 0·85 (0·70, 1·03) 90 11·4 10·3 Driving a car 50 4·1 7·0 1·78 (1·45, 2·19) 90 12·4 21·1 Participation items Doing housework 50 2·1 4·5 2·10 (1·72, 2·56) 90 7·3 15·7 Looking after children 50 1·2 3·5 2·20 (1·61, 3·00) 90 6·2 17·9 Wearing clothes that show the legs 50 12·4 12·8 1·03 (0·78, 1·35) 90 56·6 58·7 Partial return to normal work/employment 50 4·4 9·9 2·16 (1·72, 2·72) 90 15·4 34·2 Full return to normal work/employment 50 4·8 11·7 2·56 (2·05, 3·21) 90 14·9 36·2 Going out socially 50 7·1 9·3 1·29 (1·06, 1·57) 90 25·8 34·0 Sporting activity or exercise 50 15·7 21·8 1·33 (1·05, 1·68) 90 62·6 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.RESULTS.ENDOVENOUS LASER ABLATION :\nParticipants randomized to EVLA recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n3). Return to 'having a bath or shower' was quicker after surgery than after EVLA. There was no difference in time to return to the participation behaviour of 'wearing clothes that show the legs'. Table 3 Behavioural recovery: endovenous laser ablation versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n EVLA Surgery Activity items Bending the legs without discomfort 50 2·7 4·6 1·49 (1·19, 1·75) 90 12·6 21·3 Lifting heavy objects without discomfort 50 5·9 9·8 1·79 (1·39, 2·27) 90 20·5 34·5 Moving from standing to sitting without discomfort 50 2·2 3·7 1·56 (1·27, 1·96) 90 10·4 17·5 Standing still for a long time (> 15 min) without discomfort 50 4·8 7·1 1·41 (1·11, 1·79) 90 20·0 28·7 Walking short distances (< 20 min) without discomfort 50 3·0 4·4 1·30 (1·04, 1·61) 90 13·2 19·1 Walking long distances (> 20 min) 50 5·6 8·0 1·53 (1·06, 1·67) 90 19·8 27·1 Having a bath or shower 50 5·5 4·9 0·74 (0·59, 0·93) 90 12·8 10·3 Driving a car 50 4·4 7·0 1·82 (1·43, 2·33) 90 12·7 21·1 Participation items Doing housework 50 2·5 4·5 1·89 (1·49, 2·38) 90 8·4 15·7 Looking after children 50 1·9 3·5 1·61 (1·15, 2·27) 90 8·8 17·9 Wearing clothes that show the legs 50 14·6 12·8 0·97 (0·69, 1·35) 90 75·1 58·7 Partial return to normal work/employment 50 6·3 9·9 1·75 (1·33, 2·27) 90 21·1 34·2 Full return to normal work/employment 50 7·7 11·7 1·79 (1·37, 2·27) 90 23·5 36·2 Going out socially 50 6·9 9·3 1·41 (1·12, 1·75) 90 23·9 34·0 Sporting activity or exercise 50 14·2 21·8 1·47 (1·12, 1·92) 90 55·5 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. EVLA, endovenous laser ablation. There were no differences in the time taken to return to 11 of the 15 behaviours between participants randomized to EVLA and those randomized to UGFS (Table \n4). Return to 'walking short distances without discomfort', 'walking long distances', 'looking after children' and 'full return to normal work/employment' took longer for the EVLA group than the UGFS group. Following UGFS or EVLA only one‐third of the specific behaviours could be carried out by 50 per cent of participants by 3 days after treatment. Table 4 Behavioural recovery: endovenous laser ablation versus ultrasound‐guided foam sclerotherapy Proportion carrying out behaviour (%) Time until specified proportion of participants can carry out behaviour (days) * \n Hazard ratio † \n EVLA UGFS Activity items Bending the legs without discomfort 50 2·7 3·0 0·94 (0·75, 1·17) 90 12·6 14·1 Lifting heavy objects without discomfort 50 5·9 4·8 1·11 (0·87, 1·42) 90 20·5 16·9 Moving from standing to sitting without discomfort 50 2·2 1·9 1·12 (0·90, 1·40) 90 10·4 9·3 Standing still for a long time (> 15 min) without discomfort 50 4·8 3·9 1·14 (0·90, 1·44) 90 20·0 15·8 Walking short distances (< 20 min) without discomfort 50 3·0 1·9 1·48 (1·19, 1·84) 90 13·2 8·2 Walking long distances (> 20 min) 50 5·6 4·5 1·32 (1·05, 1·66) 90 19·8 15·2 Having a bath or shower 50 5·5 5·4 1·19 (0·96, 1·48) 90 12·8 11·4 Driving a car 50 4·4 4·1 0·95 (0·74, 1·21) 90 12·7 12·4 Participation items Doing housework 50 2·5 2·1 1·03 (0·82, 1·29) 90 8·4 7·3 Looking after children 50 1·9 1·2 1·45 (1·04, 2·02) 90 8·8 6·2 Wearing clothes that show the legs 50 14·6 12·4 1·17 (0·83, 1·64) 90 75·1 56·6 Partial return to normal work/employment 50 6·3 4·4 1·17 (0·89, 1·52) 90 21·1 15·4 Full return to normal work/employment 50 7·7 4·8 1·43 (1·11, 1·85) 90 23·5 14·9 Going out socially 50 6·9 7·1 0·88 (0·70, 1·10) 90 23·9 25·8 Sporting activity or exercise 50 14·2 15·7 0·80 (0·61, 1·04) 90 55·5 62·6 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the endovenous laser ablation (EVLA) arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.DISCUSSION:\nThis study showed that both UGFS and EVLA resulted in a more rapid recovery compared with surgery for 13 of the 15 behaviours. UGFS was superior to EVLA in terms of return to full time work, looking after children and walking (both short and long distances). Importantly, the specific behaviours assessed were shown to have a range of different recovery trajectories. Previous randomized clinical trials showed behavioural recovery to be more rapid following UGFS compared with surgery1, 2, but the benefit of EVLA over surgery was less clear2, 4, 8 . In this study, for all but two behaviours (wearing clothes that showed the legs and showering/bathing) the recovery was quicker following UGFS or EVLA compared with surgery. These findings may have arisen as a result of information contained in the study PIL, which recommended that compression hosiery was worn continuously for 10 days following UGFS or EVLA but for 4–5 days routinely after surgery. In the comparison between UGFS and EVLA, behavioural recovery was faster following UGFS for four of the 15 behaviours; there was no difference between the groups for the other behaviours. Two previous randomized trials2, 3 showed earlier return to 'normal activities' in patients undergoing UGFS compared with EVLA. Specifically, the present study showed a quicker return to full‐time work following UGFS, similar to the findings of Rasmussen and colleagues2. The median time taken to return to work following EVLA (7·7 days) was within the ranges reported2, 4, 5, 6, 7, 8. However, Rasmussen and colleagues2 reported earlier return to work after UGFS compared with the present study (median 2·9 versus 4·8 days respectively). A partial explanation of the difference between the two studies may be that, unlike the previous study, the present analysis did not correct for weekends. For other behaviours, the recalled recovery times following both UGFS and EVLA were longer than might be expected from the literature2, 3, 4, 5, 8. This may be explained by the timing of the questionnaire at 6 weeks, and thus it is the nature of the differences between treatment groups rather than the absolute timings taken to return to these activities that the authors wish to highlight in this paper. The extent of this overall delay in recovery is hard to justify, particularly in light of the standard information and advice given in the study PIL. There may have been a number of external influences affecting participants' recollection of their recovery, including misinformation and fear. Although attitudes to recovery and return to normal behaviours have changed in secondary care, this may not have filtered into primary care or 'public knowledge'. Fear of activity or fear of pain caused by activity has been documented following surgery for other conditions17, 18. It is possible that some people undergoing treatment for varicose veins experience similar fears, and this may limit or restrict their activity following treatment. With regard to return to work, there are clearly a number of additional factors that might play a role, such as a person's employment status (employed or self‐employed), the sickness benefits they are entitled to, the type of work they are employed to do, how long they are 'signed off' by the doctor, and the views of their employer on return to work after an operation. It should be noted that this study distinguished between partial and full return to work, and that no difference was noted in partial return to work following UGFS and EVLA. This finding may be of substantial importance to patients, their employers and the economy as a whole. The main strength of this study is that the behaviours investigated were based on systematic investigation of the recovery milestones that are important to patients following treatment for varicose veins. Hence, the findings are of personal importance from a patient perspective. Distinguishing between the behaviours that contribute to 'normal activity' helps build a profile of recovery that may be particularly useful for patients preparing for, or recovering from, treatment. Furthermore, the methodology used to develop the BRAVVO questionnaire could be used in other conditions to provide normative information about behavioural recovery that is relevant to patients. The BRAVVO questionnaire was pilot tested and found to be acceptable to patients, comprehensible and appropriate for self‐completion. Despite this, a potential weakness of the study is that the level of missing data in the BRAVVO questionnaire was higher for two of the questions. Further work to reformat or rephrase the questions or response options may help minimize levels of missing data. A further potential weakness is the choice of assessment time point (6 weeks after treatment). This may have compromised recall, particularly for behaviours that participants were able to return to a short time after treatment; however, any compromise in recall is likely to have affected the three treatment groups equally. Other study outcomes were assessed at 6 weeks, and behavioural recovery was assessed at the same time point to minimize participant burden. Further work is required to determine the optimal timing(s) of this questionnaire. Given that the median time to return to the behaviour was less than 14 days for 13 of the behaviours, and up to 22 days for the other two (wearing clothes that show the legs, sporting activity or exercise), the use of the questionnaire at approximately 2–3 weeks would seem appropriate.\n\n**Question:** Compared to surgery what was the result of Ultrasound‐guided foam sclerotherapy on Going out socially?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
597
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Behavioural recovery after treatment for varicose veins\n\n ABSTRACT.BACKGROUND:\nThe aim of this study was to assess behavioural recovery from the patient's perspective as a prespecified secondary outcome in a multicentre parallel‐group randomized clinical trial comparing ultrasound‐guided foam sclerotherapy (UGFS), endovenous laser ablation (EVLA) and surgery for the treatment of primary varicose veins.\n\nABSTRACT.METHODS:\nParticipants were recruited from 11 UK sites as part of the CLASS trial, a randomized trial of UGFS, EVLA or surgery for varicose veins. Patients were followed up 6 weeks after treatment and asked to complete the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This is a 15‐item instrument that covers eight activity behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven participation behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective.\n\nABSTRACT.RESULTS:\nA total of 798 participants were recruited. Both UGFS and EVLA resulted in a significantly quicker recovery compared with surgery for 13 of the 15 behaviours assessed. UGFS was superior to EVLA in terms of return to full‐time work (hazard ratio 1·43, 95 per cent c.i. 1·11 to 1·85), looking after children (1·45, 1·04 to 2·02) and walks of short (1·48, 1·19 to 1·84) and longer (1·32, 1·05 to 1·66) duration.\n\nABSTRACT.CONCLUSION:\nBoth UGFS and EVLA resulted in more rapid recovery than surgery, and UGFS was superior to EVLA for one‐quarter of the behaviours assessed. The BRAVVO questionnaire has the potential to provide important meaningful information to patients about their early recovery and what they may expect to be able to achieve after treatment.\n\nBODY.INTRODUCTION:\nMinimally invasive treatments for varicose veins such as ultrasound‐guided foam sclerotherapy (UGFS) and thermal ablation techniques have become widely used alternatives to surgery for the treatment of varicose veins. One of the advantages of these techniques is the reported quicker return to normal activities, particularly following UGFS1, 2, 3. However, it is unclear whether thermal ablation, in particular endovenous laser ablation (EVLA), is also associated with a clinically significant quicker return to normal activities compared with surgery; some studies4, 5 have shown an earlier return and others2, 6, 7, 8 no difference. Until recently, there was no standard means of assessing recovery from the patient's perspective. This led to the use of varying definitions such as return to 'normal activities', 'full activity', 'daily activity' or 'basic physical activities' and/or 'return to work' in previous studies. This lack of standardization led the authors to develop a 15‐item questionnaire to assess distinct aspects of normal activities that were identified as important by patients9 – the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This paper reports behavioural recovery results from a multicentre parallel‐group randomized clinical trial (CLASS, Comparison of LAser, Surgery and foam Sclerotherapy) that compared the clinical efficacy and cost‐effectiveness of three treatment modalities: UGFS, EVLA with delayed foam sclerotherapy to residual varicosities if required, and surgery. Behavioural recovery was one of the prespecified secondary outcomes of the CLASS trial. The clinical and cost‐effectiveness results have been reported elsewhere10, 11.\n\nBODY.METHODS:\nPatients were recruited from 11 centres in the UK between November 2008 and October 2012. This study (ISRCTN51995477) had research ethics committee and Medicines and Healthcare products Regulatory Authority approval. Eight centres randomized participants to one of three treatment options, and three centres offered only UGFS and surgery. Participants were randomized between the treatments with even allocation, using a minimization algorithm that included centre, age (less than 50 years, 50 years or more), sex, great saphenous vein (GSV) or small saphenous vein (SSV) reflux, and unilateral or bilateral disease. Inclusion criteria were: age over 18 years; primary unilateral or bilateral symptomatic varicose veins (Clinical Etiologic Anatomic Pathophysiological (CEAP) grade C2 or above); GSV and/or SSV involvement; and reflux exceeding 1 s on duplex ultrasonography. Exclusion criteria were: current deep vein thrombosis; acute superficial vein thrombosis; a GSV or SSV diameter smaller than 3 mm or larger than 15 mm; tortuous veins considered unsuitable for EVLA or stripping; and contraindications to UGFS or to general/regional anaesthesia that would be required for surgery.\n\nBODY.METHODS.TREATMENTS:\nThe treatments have been described in detail elsewhere9, 10. For UGFS, foam was produced using the Tessari technique12 using a ratio of 0·5 ml sodium tetradecyl sulphate to 1·5 ml air (3 per cent for GSV/SSV truncal veins, 1 per cent for varicosities; maximum 12 ml foam per session). EVLA of GSVs/SSVs was performed under local anaesthetic, and patients were offered UGFS to any residual varicosities at 6‐week follow‐up if required, with the exception of one centre that performed concurrent phlebectomies. Surgery in the form of proximal GSV/SSV ligation and stripping (all GSV) and concurrent phlebectomies was performed under general or regional anaesthetic as a day‐case procedure. Compression stockings were applied after all three treatments.\n\nBODY.METHODS.POST‐TREATMENT ACTIVITY:\nAll participants were given a study patient information leaflet (PIL), which recommended a return to all normal activities as soon as they were able, but that strenuous activity/contact sport should be avoided for 1–2 weeks. The PIL specifically stated that following EVLA or UGFS 'most people are able to return to work within 2–3 days of treatment, but some people go back the following day or even the same day', and that following surgery 'people can return to office or sedentary work after 2–3 days; and that most people will be back at work within a week after surgery to one leg and 2 weeks after surgery to both legs; but there is no reason to remain off work as long if it can be managed with reasonable comfort'. Participants undergoing UGFS or EVLA were advised to wear compression stocking for 10 days constantly (day and night). Those in the surgery group were advised that bandages would be removed the day after operation, following which they should wear a stocking for 10 days, but that it was reasonable to remove the stocking after 4 or 5 days, providing that they were active.\n\nBODY.METHODS.DATA COLLECTION:\nThe participants were asked to complete the BRAVVO questionnaire along with other study questionnaires (Aberdeen Varicose Vein Questionnaire, EQ‐5DTM (EuroQoL, Rotterdam, The Netherlands) and Short Form 36 (QualityMetric, Lincoln, Rhode Island, USA)) at the 6‐week follow‐up appointment. Participants who failed to attend the 6‐week appointment were sent the questionnaire to complete at home. The BRAVVO questionnaire was developed as an instrument to assess the activity and participation components of the World Health Organization International Classification of Disability and Function model13. Variation in activity and participation is not fully explained by impairment and so these constructs are important additional indicators of health outcome. An interview study involving 17 patients who had recently undergone varicose vein treatment was carried out to identify normal activities and 'milestone' behaviours to incorporate into the questionnaire. In addition to sampling from the three treatment options, diversity sampling was used in an attempt to gain a mix of sex, age and rural–urban location. Seventeen interview transcripts were content‐analysed in four stages to identify appropriate items to include in a questionnaire. Full details of this process have been published previously9. The BRAVVO questionnaire assesses the time taken for patients to return to performing 15 behaviours: eight 'activity' behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven 'participation' behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective9. Fig. 1 shows the question layout. Figure 1Question layoutBJS-10081-FIG-0001-c\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData from the BRAVVO questionnaire were analysed within an interval‐censored time‐to‐event framework using flexible parametric survival models14. For each behaviour item, each participant's response was converted into the number of days to return to that behaviour. If a participant indicated that return to the behaviour was on the day of the procedure, this was assumed to be interval‐censored between day 0 and day 1. If a participant indicated return to the behaviour was after a number of weeks, not days, this was assumed to be interval‐censored between the previous week and the week indicated. For example, if a participant reported 5 weeks, it was assumed that the return to the behaviour took place between 28 and 35 days. A participant who indicated that they had not returned to a behaviour that they usually performed was right‐censored at 42 days. Participants who indicated that they did not normally perform a specific behaviour were not included in analysis of that behaviour. No missing data were imputed. Data are reported as the number of days for 50 and 90 per cent of participants to return to each behaviour, estimated from the parametric survival models (the 50 per cent value represents the median time to return to this behaviour). Extrapolation beyond the 42‐day cut‐off was performed for behaviours where 90 per cent of participants had not returned to the behaviour by 42 days. Treatment effects are presented as hazard ratios with associated 95 per cent c.i. All analyses were carried out in Stata® 1215. Flexible parametric survival models were fitted using the stpm package16.\n\nBODY.RESULTS:\nSeven hundred and ninety‐eight participants were recruited, of whom 13 were ineligible (for example because they had recurrent veins or veins larger than 15 mm in diameter) after randomization and were considered postrandomization exclusions (Fig. \n2). The groups were well balanced in terms of demographic characteristics at baseline, but there was an increased incidence of deep venous reflux in the foam group compared with the surgery group (P = 0·005) (Table \n1). Of the 670 participants who completed the 6‐week questionnaire, 655 completed at least one of the BRAVVO questions. Completion rates were slightly lower for the questions about going out socially (74·8 per cent) and sporting activity (66·0 per cent), which may not have been relevant to all participants. For all behaviours, except wearing clothes that show the leg, going out socially and sporting activities, over 95 per cent of participants had returned to normal behaviour within 6 weeks of intervention. Figure 2CONSORT diagram for the trial. Reasons for postrandomization exclusion included: recurrent varicose veins and veins larger than 15 mm. Reasons for withdrawal from follow‐up included: patient decided not to proceed with treatment (and also declined follow‐up), declined follow‐up after treatment or did not wish to complete questionnaires. UGFS, ultrasound‐guided foam sclerotherapy; EVLA, endovenous laser ablationBJS-10081-FIG-0002-c Table 1 Demographic details at recruitment EVLA UGFS Surgery ( n = 210) ( n = 286) ( n = 289) Age (years) * \n 49·7 (18–80) 49·0 (19–78) 49·2 (22–85) Sex ratio (F : M) 120 : 90 162 : 124 163 : 126 Body mass index (kg/m 2 ) * \n 27·0 (17–42) 27·1 (17–44) 27·7 (17–44) Unilateral disease 153 (72·9) 215 (75·2) 196 (67·8) Employment status Self‐employed 21 (10·2) 37 (13·0) 29 (10·3) Employed 120 (58·3) 169 (59·3) 179 (63·5) Other 65 (31·6) 79 (27·7) 74 (26·2) Unknown 4 1 7 Saphenous vein involvement Great saphenous 182 (86·7) 232 (81·1) 239 (82·7) Small saphenous 14 (6·7) 21 (7·3) 21 (7·3) Great and small saphenous 14 (6·7) 33 (11·5) 29 (10·0) Deep vein reflux 28 of 205 (13·7) 47 of 280 (16·8) 25 of 282 (8·9) CEAP classification C2, varicose veins over 3 mm 113 (54·1) 169 (59·1) 147 (51·2) C3, oedema 28 (13·4) 35 (12·2) 39 (13·6) C4, skin/subcutaneous changes 56 (26·8) 74 (25·9) 90 (31·4) C5/C6, healed/active venous ulcer 12 (5·7) 8 (2·8) 11 (3·8) Unknown 1 0 2 Values in parentheses are percentages unless indicated otherwise; * values are mean (range). EVLA, endovenous laser ablation; UGFS, ultrasound‐guided foam sclerotherapy; CEAP, Clinical Etiologic Anatomic Pathophysiologic. \n\nBODY.RESULTS.ULTRASOUND‐GUIDED FOAM SCLEROTHERAPY :\nParticipants randomized to UGFS recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n2\n). The two behaviours for which there was no evidence of a difference in the time to recover between the trial arms were 'having a bath or shower' and 'wearing clothes that show the legs'. In general, the median time to return to the activity behaviours was 5 days or less for those randomized to UGFS and up to 9 days for those randomized to surgery. In both groups, there was greater variation in the median time to return to the participation behaviours than the activity behaviours. Table 2 Behavioural recovery: ultrasound‐guided foam sclerotherapy versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n UGFS Surgery Activity items Bending the legs without discomfort 50 3·0 4·6 1·38 (1·14, 1·67) 90 14·1 21·3 Lifting heavy objects without discomfort 50 4·8 9·8 1·97 (1·59, 2·44) 90 16·9 34·5 Moving from standing to sitting without discomfort 50 1·9 3·7 1·63 (1·35, 1·97) 90 9·3 17·5 Standing still for a long time (> 15 min ) without discomfort 50 3·9 7·1 1·67 (1·36, 2·05) 90 15·8 28·7 Walking short distances (< 20 min ) without discomfort 50 1·9 4·4 2·00 (1·65, 2·42) 90 8·2 19·1 Walking long distances (> 20 min) 50 4·5 8·0 1·76 (1·45, 2·14) 90 15·2 27·1 Having a bath or shower 50 5·4 4·9 0·85 (0·70, 1·03) 90 11·4 10·3 Driving a car 50 4·1 7·0 1·78 (1·45, 2·19) 90 12·4 21·1 Participation items Doing housework 50 2·1 4·5 2·10 (1·72, 2·56) 90 7·3 15·7 Looking after children 50 1·2 3·5 2·20 (1·61, 3·00) 90 6·2 17·9 Wearing clothes that show the legs 50 12·4 12·8 1·03 (0·78, 1·35) 90 56·6 58·7 Partial return to normal work/employment 50 4·4 9·9 2·16 (1·72, 2·72) 90 15·4 34·2 Full return to normal work/employment 50 4·8 11·7 2·56 (2·05, 3·21) 90 14·9 36·2 Going out socially 50 7·1 9·3 1·29 (1·06, 1·57) 90 25·8 34·0 Sporting activity or exercise 50 15·7 21·8 1·33 (1·05, 1·68) 90 62·6 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.RESULTS.ENDOVENOUS LASER ABLATION :\nParticipants randomized to EVLA recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n3). Return to 'having a bath or shower' was quicker after surgery than after EVLA. There was no difference in time to return to the participation behaviour of 'wearing clothes that show the legs'. Table 3 Behavioural recovery: endovenous laser ablation versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n EVLA Surgery Activity items Bending the legs without discomfort 50 2·7 4·6 1·49 (1·19, 1·75) 90 12·6 21·3 Lifting heavy objects without discomfort 50 5·9 9·8 1·79 (1·39, 2·27) 90 20·5 34·5 Moving from standing to sitting without discomfort 50 2·2 3·7 1·56 (1·27, 1·96) 90 10·4 17·5 Standing still for a long time (> 15 min) without discomfort 50 4·8 7·1 1·41 (1·11, 1·79) 90 20·0 28·7 Walking short distances (< 20 min) without discomfort 50 3·0 4·4 1·30 (1·04, 1·61) 90 13·2 19·1 Walking long distances (> 20 min) 50 5·6 8·0 1·53 (1·06, 1·67) 90 19·8 27·1 Having a bath or shower 50 5·5 4·9 0·74 (0·59, 0·93) 90 12·8 10·3 Driving a car 50 4·4 7·0 1·82 (1·43, 2·33) 90 12·7 21·1 Participation items Doing housework 50 2·5 4·5 1·89 (1·49, 2·38) 90 8·4 15·7 Looking after children 50 1·9 3·5 1·61 (1·15, 2·27) 90 8·8 17·9 Wearing clothes that show the legs 50 14·6 12·8 0·97 (0·69, 1·35) 90 75·1 58·7 Partial return to normal work/employment 50 6·3 9·9 1·75 (1·33, 2·27) 90 21·1 34·2 Full return to normal work/employment 50 7·7 11·7 1·79 (1·37, 2·27) 90 23·5 36·2 Going out socially 50 6·9 9·3 1·41 (1·12, 1·75) 90 23·9 34·0 Sporting activity or exercise 50 14·2 21·8 1·47 (1·12, 1·92) 90 55·5 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. EVLA, endovenous laser ablation. There were no differences in the time taken to return to 11 of the 15 behaviours between participants randomized to EVLA and those randomized to UGFS (Table \n4). Return to 'walking short distances without discomfort', 'walking long distances', 'looking after children' and 'full return to normal work/employment' took longer for the EVLA group than the UGFS group. Following UGFS or EVLA only one‐third of the specific behaviours could be carried out by 50 per cent of participants by 3 days after treatment. Table 4 Behavioural recovery: endovenous laser ablation versus ultrasound‐guided foam sclerotherapy Proportion carrying out behaviour (%) Time until specified proportion of participants can carry out behaviour (days) * \n Hazard ratio † \n EVLA UGFS Activity items Bending the legs without discomfort 50 2·7 3·0 0·94 (0·75, 1·17) 90 12·6 14·1 Lifting heavy objects without discomfort 50 5·9 4·8 1·11 (0·87, 1·42) 90 20·5 16·9 Moving from standing to sitting without discomfort 50 2·2 1·9 1·12 (0·90, 1·40) 90 10·4 9·3 Standing still for a long time (> 15 min) without discomfort 50 4·8 3·9 1·14 (0·90, 1·44) 90 20·0 15·8 Walking short distances (< 20 min) without discomfort 50 3·0 1·9 1·48 (1·19, 1·84) 90 13·2 8·2 Walking long distances (> 20 min) 50 5·6 4·5 1·32 (1·05, 1·66) 90 19·8 15·2 Having a bath or shower 50 5·5 5·4 1·19 (0·96, 1·48) 90 12·8 11·4 Driving a car 50 4·4 4·1 0·95 (0·74, 1·21) 90 12·7 12·4 Participation items Doing housework 50 2·5 2·1 1·03 (0·82, 1·29) 90 8·4 7·3 Looking after children 50 1·9 1·2 1·45 (1·04, 2·02) 90 8·8 6·2 Wearing clothes that show the legs 50 14·6 12·4 1·17 (0·83, 1·64) 90 75·1 56·6 Partial return to normal work/employment 50 6·3 4·4 1·17 (0·89, 1·52) 90 21·1 15·4 Full return to normal work/employment 50 7·7 4·8 1·43 (1·11, 1·85) 90 23·5 14·9 Going out socially 50 6·9 7·1 0·88 (0·70, 1·10) 90 23·9 25·8 Sporting activity or exercise 50 14·2 15·7 0·80 (0·61, 1·04) 90 55·5 62·6 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the endovenous laser ablation (EVLA) arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.DISCUSSION:\nThis study showed that both UGFS and EVLA resulted in a more rapid recovery compared with surgery for 13 of the 15 behaviours. UGFS was superior to EVLA in terms of return to full time work, looking after children and walking (both short and long distances). Importantly, the specific behaviours assessed were shown to have a range of different recovery trajectories. Previous randomized clinical trials showed behavioural recovery to be more rapid following UGFS compared with surgery1, 2, but the benefit of EVLA over surgery was less clear2, 4, 8 . In this study, for all but two behaviours (wearing clothes that showed the legs and showering/bathing) the recovery was quicker following UGFS or EVLA compared with surgery. These findings may have arisen as a result of information contained in the study PIL, which recommended that compression hosiery was worn continuously for 10 days following UGFS or EVLA but for 4–5 days routinely after surgery. In the comparison between UGFS and EVLA, behavioural recovery was faster following UGFS for four of the 15 behaviours; there was no difference between the groups for the other behaviours. Two previous randomized trials2, 3 showed earlier return to 'normal activities' in patients undergoing UGFS compared with EVLA. Specifically, the present study showed a quicker return to full‐time work following UGFS, similar to the findings of Rasmussen and colleagues2. The median time taken to return to work following EVLA (7·7 days) was within the ranges reported2, 4, 5, 6, 7, 8. However, Rasmussen and colleagues2 reported earlier return to work after UGFS compared with the present study (median 2·9 versus 4·8 days respectively). A partial explanation of the difference between the two studies may be that, unlike the previous study, the present analysis did not correct for weekends. For other behaviours, the recalled recovery times following both UGFS and EVLA were longer than might be expected from the literature2, 3, 4, 5, 8. This may be explained by the timing of the questionnaire at 6 weeks, and thus it is the nature of the differences between treatment groups rather than the absolute timings taken to return to these activities that the authors wish to highlight in this paper. The extent of this overall delay in recovery is hard to justify, particularly in light of the standard information and advice given in the study PIL. There may have been a number of external influences affecting participants' recollection of their recovery, including misinformation and fear. Although attitudes to recovery and return to normal behaviours have changed in secondary care, this may not have filtered into primary care or 'public knowledge'. Fear of activity or fear of pain caused by activity has been documented following surgery for other conditions17, 18. It is possible that some people undergoing treatment for varicose veins experience similar fears, and this may limit or restrict their activity following treatment. With regard to return to work, there are clearly a number of additional factors that might play a role, such as a person's employment status (employed or self‐employed), the sickness benefits they are entitled to, the type of work they are employed to do, how long they are 'signed off' by the doctor, and the views of their employer on return to work after an operation. It should be noted that this study distinguished between partial and full return to work, and that no difference was noted in partial return to work following UGFS and EVLA. This finding may be of substantial importance to patients, their employers and the economy as a whole. The main strength of this study is that the behaviours investigated were based on systematic investigation of the recovery milestones that are important to patients following treatment for varicose veins. Hence, the findings are of personal importance from a patient perspective. Distinguishing between the behaviours that contribute to 'normal activity' helps build a profile of recovery that may be particularly useful for patients preparing for, or recovering from, treatment. Furthermore, the methodology used to develop the BRAVVO questionnaire could be used in other conditions to provide normative information about behavioural recovery that is relevant to patients. The BRAVVO questionnaire was pilot tested and found to be acceptable to patients, comprehensible and appropriate for self‐completion. Despite this, a potential weakness of the study is that the level of missing data in the BRAVVO questionnaire was higher for two of the questions. Further work to reformat or rephrase the questions or response options may help minimize levels of missing data. A further potential weakness is the choice of assessment time point (6 weeks after treatment). This may have compromised recall, particularly for behaviours that participants were able to return to a short time after treatment; however, any compromise in recall is likely to have affected the three treatment groups equally. Other study outcomes were assessed at 6 weeks, and behavioural recovery was assessed at the same time point to minimize participant burden. Further work is required to determine the optimal timing(s) of this questionnaire. Given that the median time to return to the behaviour was less than 14 days for 13 of the behaviours, and up to 22 days for the other two (wearing clothes that show the legs, sporting activity or exercise), the use of the questionnaire at approximately 2–3 weeks would seem appropriate.\n\n**Question:** Compared to surgery what was the result of Ultrasound‐guided foam sclerotherapy on Sporting activity or exercise?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
600
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Behavioural recovery after treatment for varicose veins\n\n ABSTRACT.BACKGROUND:\nThe aim of this study was to assess behavioural recovery from the patient's perspective as a prespecified secondary outcome in a multicentre parallel‐group randomized clinical trial comparing ultrasound‐guided foam sclerotherapy (UGFS), endovenous laser ablation (EVLA) and surgery for the treatment of primary varicose veins.\n\nABSTRACT.METHODS:\nParticipants were recruited from 11 UK sites as part of the CLASS trial, a randomized trial of UGFS, EVLA or surgery for varicose veins. Patients were followed up 6 weeks after treatment and asked to complete the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This is a 15‐item instrument that covers eight activity behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven participation behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective.\n\nABSTRACT.RESULTS:\nA total of 798 participants were recruited. Both UGFS and EVLA resulted in a significantly quicker recovery compared with surgery for 13 of the 15 behaviours assessed. UGFS was superior to EVLA in terms of return to full‐time work (hazard ratio 1·43, 95 per cent c.i. 1·11 to 1·85), looking after children (1·45, 1·04 to 2·02) and walks of short (1·48, 1·19 to 1·84) and longer (1·32, 1·05 to 1·66) duration.\n\nABSTRACT.CONCLUSION:\nBoth UGFS and EVLA resulted in more rapid recovery than surgery, and UGFS was superior to EVLA for one‐quarter of the behaviours assessed. The BRAVVO questionnaire has the potential to provide important meaningful information to patients about their early recovery and what they may expect to be able to achieve after treatment.\n\nBODY.INTRODUCTION:\nMinimally invasive treatments for varicose veins such as ultrasound‐guided foam sclerotherapy (UGFS) and thermal ablation techniques have become widely used alternatives to surgery for the treatment of varicose veins. One of the advantages of these techniques is the reported quicker return to normal activities, particularly following UGFS1, 2, 3. However, it is unclear whether thermal ablation, in particular endovenous laser ablation (EVLA), is also associated with a clinically significant quicker return to normal activities compared with surgery; some studies4, 5 have shown an earlier return and others2, 6, 7, 8 no difference. Until recently, there was no standard means of assessing recovery from the patient's perspective. This led to the use of varying definitions such as return to 'normal activities', 'full activity', 'daily activity' or 'basic physical activities' and/or 'return to work' in previous studies. This lack of standardization led the authors to develop a 15‐item questionnaire to assess distinct aspects of normal activities that were identified as important by patients9 – the Behavioural Recovery After treatment for Varicose Veins (BRAVVO) questionnaire. This paper reports behavioural recovery results from a multicentre parallel‐group randomized clinical trial (CLASS, Comparison of LAser, Surgery and foam Sclerotherapy) that compared the clinical efficacy and cost‐effectiveness of three treatment modalities: UGFS, EVLA with delayed foam sclerotherapy to residual varicosities if required, and surgery. Behavioural recovery was one of the prespecified secondary outcomes of the CLASS trial. The clinical and cost‐effectiveness results have been reported elsewhere10, 11.\n\nBODY.METHODS:\nPatients were recruited from 11 centres in the UK between November 2008 and October 2012. This study (ISRCTN51995477) had research ethics committee and Medicines and Healthcare products Regulatory Authority approval. Eight centres randomized participants to one of three treatment options, and three centres offered only UGFS and surgery. Participants were randomized between the treatments with even allocation, using a minimization algorithm that included centre, age (less than 50 years, 50 years or more), sex, great saphenous vein (GSV) or small saphenous vein (SSV) reflux, and unilateral or bilateral disease. Inclusion criteria were: age over 18 years; primary unilateral or bilateral symptomatic varicose veins (Clinical Etiologic Anatomic Pathophysiological (CEAP) grade C2 or above); GSV and/or SSV involvement; and reflux exceeding 1 s on duplex ultrasonography. Exclusion criteria were: current deep vein thrombosis; acute superficial vein thrombosis; a GSV or SSV diameter smaller than 3 mm or larger than 15 mm; tortuous veins considered unsuitable for EVLA or stripping; and contraindications to UGFS or to general/regional anaesthesia that would be required for surgery.\n\nBODY.METHODS.TREATMENTS:\nThe treatments have been described in detail elsewhere9, 10. For UGFS, foam was produced using the Tessari technique12 using a ratio of 0·5 ml sodium tetradecyl sulphate to 1·5 ml air (3 per cent for GSV/SSV truncal veins, 1 per cent for varicosities; maximum 12 ml foam per session). EVLA of GSVs/SSVs was performed under local anaesthetic, and patients were offered UGFS to any residual varicosities at 6‐week follow‐up if required, with the exception of one centre that performed concurrent phlebectomies. Surgery in the form of proximal GSV/SSV ligation and stripping (all GSV) and concurrent phlebectomies was performed under general or regional anaesthetic as a day‐case procedure. Compression stockings were applied after all three treatments.\n\nBODY.METHODS.POST‐TREATMENT ACTIVITY:\nAll participants were given a study patient information leaflet (PIL), which recommended a return to all normal activities as soon as they were able, but that strenuous activity/contact sport should be avoided for 1–2 weeks. The PIL specifically stated that following EVLA or UGFS 'most people are able to return to work within 2–3 days of treatment, but some people go back the following day or even the same day', and that following surgery 'people can return to office or sedentary work after 2–3 days; and that most people will be back at work within a week after surgery to one leg and 2 weeks after surgery to both legs; but there is no reason to remain off work as long if it can be managed with reasonable comfort'. Participants undergoing UGFS or EVLA were advised to wear compression stocking for 10 days constantly (day and night). Those in the surgery group were advised that bandages would be removed the day after operation, following which they should wear a stocking for 10 days, but that it was reasonable to remove the stocking after 4 or 5 days, providing that they were active.\n\nBODY.METHODS.DATA COLLECTION:\nThe participants were asked to complete the BRAVVO questionnaire along with other study questionnaires (Aberdeen Varicose Vein Questionnaire, EQ‐5DTM (EuroQoL, Rotterdam, The Netherlands) and Short Form 36 (QualityMetric, Lincoln, Rhode Island, USA)) at the 6‐week follow‐up appointment. Participants who failed to attend the 6‐week appointment were sent the questionnaire to complete at home. The BRAVVO questionnaire was developed as an instrument to assess the activity and participation components of the World Health Organization International Classification of Disability and Function model13. Variation in activity and participation is not fully explained by impairment and so these constructs are important additional indicators of health outcome. An interview study involving 17 patients who had recently undergone varicose vein treatment was carried out to identify normal activities and 'milestone' behaviours to incorporate into the questionnaire. In addition to sampling from the three treatment options, diversity sampling was used in an attempt to gain a mix of sex, age and rural–urban location. Seventeen interview transcripts were content‐analysed in four stages to identify appropriate items to include in a questionnaire. Full details of this process have been published previously9. The BRAVVO questionnaire assesses the time taken for patients to return to performing 15 behaviours: eight 'activity' behaviours (tasks or actions an individual is capable of doing in an idealized situation) and seven 'participation' behaviours (what the individual does in an everyday, real‐world situation) that were identified to be important from the patient's perspective9. Fig. 1 shows the question layout. Figure 1Question layoutBJS-10081-FIG-0001-c\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData from the BRAVVO questionnaire were analysed within an interval‐censored time‐to‐event framework using flexible parametric survival models14. For each behaviour item, each participant's response was converted into the number of days to return to that behaviour. If a participant indicated that return to the behaviour was on the day of the procedure, this was assumed to be interval‐censored between day 0 and day 1. If a participant indicated return to the behaviour was after a number of weeks, not days, this was assumed to be interval‐censored between the previous week and the week indicated. For example, if a participant reported 5 weeks, it was assumed that the return to the behaviour took place between 28 and 35 days. A participant who indicated that they had not returned to a behaviour that they usually performed was right‐censored at 42 days. Participants who indicated that they did not normally perform a specific behaviour were not included in analysis of that behaviour. No missing data were imputed. Data are reported as the number of days for 50 and 90 per cent of participants to return to each behaviour, estimated from the parametric survival models (the 50 per cent value represents the median time to return to this behaviour). Extrapolation beyond the 42‐day cut‐off was performed for behaviours where 90 per cent of participants had not returned to the behaviour by 42 days. Treatment effects are presented as hazard ratios with associated 95 per cent c.i. All analyses were carried out in Stata® 1215. Flexible parametric survival models were fitted using the stpm package16.\n\nBODY.RESULTS:\nSeven hundred and ninety‐eight participants were recruited, of whom 13 were ineligible (for example because they had recurrent veins or veins larger than 15 mm in diameter) after randomization and were considered postrandomization exclusions (Fig. \n2). The groups were well balanced in terms of demographic characteristics at baseline, but there was an increased incidence of deep venous reflux in the foam group compared with the surgery group (P = 0·005) (Table \n1). Of the 670 participants who completed the 6‐week questionnaire, 655 completed at least one of the BRAVVO questions. Completion rates were slightly lower for the questions about going out socially (74·8 per cent) and sporting activity (66·0 per cent), which may not have been relevant to all participants. For all behaviours, except wearing clothes that show the leg, going out socially and sporting activities, over 95 per cent of participants had returned to normal behaviour within 6 weeks of intervention. Figure 2CONSORT diagram for the trial. Reasons for postrandomization exclusion included: recurrent varicose veins and veins larger than 15 mm. Reasons for withdrawal from follow‐up included: patient decided not to proceed with treatment (and also declined follow‐up), declined follow‐up after treatment or did not wish to complete questionnaires. UGFS, ultrasound‐guided foam sclerotherapy; EVLA, endovenous laser ablationBJS-10081-FIG-0002-c Table 1 Demographic details at recruitment EVLA UGFS Surgery ( n = 210) ( n = 286) ( n = 289) Age (years) * \n 49·7 (18–80) 49·0 (19–78) 49·2 (22–85) Sex ratio (F : M) 120 : 90 162 : 124 163 : 126 Body mass index (kg/m 2 ) * \n 27·0 (17–42) 27·1 (17–44) 27·7 (17–44) Unilateral disease 153 (72·9) 215 (75·2) 196 (67·8) Employment status Self‐employed 21 (10·2) 37 (13·0) 29 (10·3) Employed 120 (58·3) 169 (59·3) 179 (63·5) Other 65 (31·6) 79 (27·7) 74 (26·2) Unknown 4 1 7 Saphenous vein involvement Great saphenous 182 (86·7) 232 (81·1) 239 (82·7) Small saphenous 14 (6·7) 21 (7·3) 21 (7·3) Great and small saphenous 14 (6·7) 33 (11·5) 29 (10·0) Deep vein reflux 28 of 205 (13·7) 47 of 280 (16·8) 25 of 282 (8·9) CEAP classification C2, varicose veins over 3 mm 113 (54·1) 169 (59·1) 147 (51·2) C3, oedema 28 (13·4) 35 (12·2) 39 (13·6) C4, skin/subcutaneous changes 56 (26·8) 74 (25·9) 90 (31·4) C5/C6, healed/active venous ulcer 12 (5·7) 8 (2·8) 11 (3·8) Unknown 1 0 2 Values in parentheses are percentages unless indicated otherwise; * values are mean (range). EVLA, endovenous laser ablation; UGFS, ultrasound‐guided foam sclerotherapy; CEAP, Clinical Etiologic Anatomic Pathophysiologic. \n\nBODY.RESULTS.ULTRASOUND‐GUIDED FOAM SCLEROTHERAPY :\nParticipants randomized to UGFS recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n2\n). The two behaviours for which there was no evidence of a difference in the time to recover between the trial arms were 'having a bath or shower' and 'wearing clothes that show the legs'. In general, the median time to return to the activity behaviours was 5 days or less for those randomized to UGFS and up to 9 days for those randomized to surgery. In both groups, there was greater variation in the median time to return to the participation behaviours than the activity behaviours. Table 2 Behavioural recovery: ultrasound‐guided foam sclerotherapy versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n UGFS Surgery Activity items Bending the legs without discomfort 50 3·0 4·6 1·38 (1·14, 1·67) 90 14·1 21·3 Lifting heavy objects without discomfort 50 4·8 9·8 1·97 (1·59, 2·44) 90 16·9 34·5 Moving from standing to sitting without discomfort 50 1·9 3·7 1·63 (1·35, 1·97) 90 9·3 17·5 Standing still for a long time (> 15 min ) without discomfort 50 3·9 7·1 1·67 (1·36, 2·05) 90 15·8 28·7 Walking short distances (< 20 min ) without discomfort 50 1·9 4·4 2·00 (1·65, 2·42) 90 8·2 19·1 Walking long distances (> 20 min) 50 4·5 8·0 1·76 (1·45, 2·14) 90 15·2 27·1 Having a bath or shower 50 5·4 4·9 0·85 (0·70, 1·03) 90 11·4 10·3 Driving a car 50 4·1 7·0 1·78 (1·45, 2·19) 90 12·4 21·1 Participation items Doing housework 50 2·1 4·5 2·10 (1·72, 2·56) 90 7·3 15·7 Looking after children 50 1·2 3·5 2·20 (1·61, 3·00) 90 6·2 17·9 Wearing clothes that show the legs 50 12·4 12·8 1·03 (0·78, 1·35) 90 56·6 58·7 Partial return to normal work/employment 50 4·4 9·9 2·16 (1·72, 2·72) 90 15·4 34·2 Full return to normal work/employment 50 4·8 11·7 2·56 (2·05, 3·21) 90 14·9 36·2 Going out socially 50 7·1 9·3 1·29 (1·06, 1·57) 90 25·8 34·0 Sporting activity or exercise 50 15·7 21·8 1·33 (1·05, 1·68) 90 62·6 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.RESULTS.ENDOVENOUS LASER ABLATION :\nParticipants randomized to EVLA recalled being able to carry out 13 of the 15 behaviours significantly more quickly than those randomized to surgery (Table \n3). Return to 'having a bath or shower' was quicker after surgery than after EVLA. There was no difference in time to return to the participation behaviour of 'wearing clothes that show the legs'. Table 3 Behavioural recovery: endovenous laser ablation versus surgery Proportion carrying out behaviour (%) Time until specified proportion of participants could carry out behaviour (days) * \n Hazard ratio † \n EVLA Surgery Activity items Bending the legs without discomfort 50 2·7 4·6 1·49 (1·19, 1·75) 90 12·6 21·3 Lifting heavy objects without discomfort 50 5·9 9·8 1·79 (1·39, 2·27) 90 20·5 34·5 Moving from standing to sitting without discomfort 50 2·2 3·7 1·56 (1·27, 1·96) 90 10·4 17·5 Standing still for a long time (> 15 min) without discomfort 50 4·8 7·1 1·41 (1·11, 1·79) 90 20·0 28·7 Walking short distances (< 20 min) without discomfort 50 3·0 4·4 1·30 (1·04, 1·61) 90 13·2 19·1 Walking long distances (> 20 min) 50 5·6 8·0 1·53 (1·06, 1·67) 90 19·8 27·1 Having a bath or shower 50 5·5 4·9 0·74 (0·59, 0·93) 90 12·8 10·3 Driving a car 50 4·4 7·0 1·82 (1·43, 2·33) 90 12·7 21·1 Participation items Doing housework 50 2·5 4·5 1·89 (1·49, 2·38) 90 8·4 15·7 Looking after children 50 1·9 3·5 1·61 (1·15, 2·27) 90 8·8 17·9 Wearing clothes that show the legs 50 14·6 12·8 0·97 (0·69, 1·35) 90 75·1 58·7 Partial return to normal work/employment 50 6·3 9·9 1·75 (1·33, 2·27) 90 21·1 34·2 Full return to normal work/employment 50 7·7 11·7 1·79 (1·37, 2·27) 90 23·5 36·2 Going out socially 50 6·9 9·3 1·41 (1·12, 1·75) 90 23·9 34·0 Sporting activity or exercise 50 14·2 21·8 1·47 (1·12, 1·92) 90 55·5 86·7 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the surgery arm. EVLA, endovenous laser ablation. There were no differences in the time taken to return to 11 of the 15 behaviours between participants randomized to EVLA and those randomized to UGFS (Table \n4). Return to 'walking short distances without discomfort', 'walking long distances', 'looking after children' and 'full return to normal work/employment' took longer for the EVLA group than the UGFS group. Following UGFS or EVLA only one‐third of the specific behaviours could be carried out by 50 per cent of participants by 3 days after treatment. Table 4 Behavioural recovery: endovenous laser ablation versus ultrasound‐guided foam sclerotherapy Proportion carrying out behaviour (%) Time until specified proportion of participants can carry out behaviour (days) * \n Hazard ratio † \n EVLA UGFS Activity items Bending the legs without discomfort 50 2·7 3·0 0·94 (0·75, 1·17) 90 12·6 14·1 Lifting heavy objects without discomfort 50 5·9 4·8 1·11 (0·87, 1·42) 90 20·5 16·9 Moving from standing to sitting without discomfort 50 2·2 1·9 1·12 (0·90, 1·40) 90 10·4 9·3 Standing still for a long time (> 15 min) without discomfort 50 4·8 3·9 1·14 (0·90, 1·44) 90 20·0 15·8 Walking short distances (< 20 min) without discomfort 50 3·0 1·9 1·48 (1·19, 1·84) 90 13·2 8·2 Walking long distances (> 20 min) 50 5·6 4·5 1·32 (1·05, 1·66) 90 19·8 15·2 Having a bath or shower 50 5·5 5·4 1·19 (0·96, 1·48) 90 12·8 11·4 Driving a car 50 4·4 4·1 0·95 (0·74, 1·21) 90 12·7 12·4 Participation items Doing housework 50 2·5 2·1 1·03 (0·82, 1·29) 90 8·4 7·3 Looking after children 50 1·9 1·2 1·45 (1·04, 2·02) 90 8·8 6·2 Wearing clothes that show the legs 50 14·6 12·4 1·17 (0·83, 1·64) 90 75·1 56·6 Partial return to normal work/employment 50 6·3 4·4 1·17 (0·89, 1·52) 90 21·1 15·4 Full return to normal work/employment 50 7·7 4·8 1·43 (1·11, 1·85) 90 23·5 14·9 Going out socially 50 6·9 7·1 0·88 (0·70, 1·10) 90 23·9 25·8 Sporting activity or exercise 50 14·2 15·7 0·80 (0·61, 1·04) 90 55·5 62·6 Values in parentheses are 95 per cent c.i. * The 50 per cent value is equivalent to the median time to return to the behaviour. † A hazard ratio greater than 1·00 shows that return to the behaviour took longer in the endovenous laser ablation (EVLA) arm. UGFS, ultrasound‐guided foam sclerotherapy. \n\nBODY.DISCUSSION:\nThis study showed that both UGFS and EVLA resulted in a more rapid recovery compared with surgery for 13 of the 15 behaviours. UGFS was superior to EVLA in terms of return to full time work, looking after children and walking (both short and long distances). Importantly, the specific behaviours assessed were shown to have a range of different recovery trajectories. Previous randomized clinical trials showed behavioural recovery to be more rapid following UGFS compared with surgery1, 2, but the benefit of EVLA over surgery was less clear2, 4, 8 . In this study, for all but two behaviours (wearing clothes that showed the legs and showering/bathing) the recovery was quicker following UGFS or EVLA compared with surgery. These findings may have arisen as a result of information contained in the study PIL, which recommended that compression hosiery was worn continuously for 10 days following UGFS or EVLA but for 4–5 days routinely after surgery. In the comparison between UGFS and EVLA, behavioural recovery was faster following UGFS for four of the 15 behaviours; there was no difference between the groups for the other behaviours. Two previous randomized trials2, 3 showed earlier return to 'normal activities' in patients undergoing UGFS compared with EVLA. Specifically, the present study showed a quicker return to full‐time work following UGFS, similar to the findings of Rasmussen and colleagues2. The median time taken to return to work following EVLA (7·7 days) was within the ranges reported2, 4, 5, 6, 7, 8. However, Rasmussen and colleagues2 reported earlier return to work after UGFS compared with the present study (median 2·9 versus 4·8 days respectively). A partial explanation of the difference between the two studies may be that, unlike the previous study, the present analysis did not correct for weekends. For other behaviours, the recalled recovery times following both UGFS and EVLA were longer than might be expected from the literature2, 3, 4, 5, 8. This may be explained by the timing of the questionnaire at 6 weeks, and thus it is the nature of the differences between treatment groups rather than the absolute timings taken to return to these activities that the authors wish to highlight in this paper. The extent of this overall delay in recovery is hard to justify, particularly in light of the standard information and advice given in the study PIL. There may have been a number of external influences affecting participants' recollection of their recovery, including misinformation and fear. Although attitudes to recovery and return to normal behaviours have changed in secondary care, this may not have filtered into primary care or 'public knowledge'. Fear of activity or fear of pain caused by activity has been documented following surgery for other conditions17, 18. It is possible that some people undergoing treatment for varicose veins experience similar fears, and this may limit or restrict their activity following treatment. With regard to return to work, there are clearly a number of additional factors that might play a role, such as a person's employment status (employed or self‐employed), the sickness benefits they are entitled to, the type of work they are employed to do, how long they are 'signed off' by the doctor, and the views of their employer on return to work after an operation. It should be noted that this study distinguished between partial and full return to work, and that no difference was noted in partial return to work following UGFS and EVLA. This finding may be of substantial importance to patients, their employers and the economy as a whole. The main strength of this study is that the behaviours investigated were based on systematic investigation of the recovery milestones that are important to patients following treatment for varicose veins. Hence, the findings are of personal importance from a patient perspective. Distinguishing between the behaviours that contribute to 'normal activity' helps build a profile of recovery that may be particularly useful for patients preparing for, or recovering from, treatment. Furthermore, the methodology used to develop the BRAVVO questionnaire could be used in other conditions to provide normative information about behavioural recovery that is relevant to patients. The BRAVVO questionnaire was pilot tested and found to be acceptable to patients, comprehensible and appropriate for self‐completion. Despite this, a potential weakness of the study is that the level of missing data in the BRAVVO questionnaire was higher for two of the questions. Further work to reformat or rephrase the questions or response options may help minimize levels of missing data. A further potential weakness is the choice of assessment time point (6 weeks after treatment). This may have compromised recall, particularly for behaviours that participants were able to return to a short time after treatment; however, any compromise in recall is likely to have affected the three treatment groups equally. Other study outcomes were assessed at 6 weeks, and behavioural recovery was assessed at the same time point to minimize participant burden. Further work is required to determine the optimal timing(s) of this questionnaire. Given that the median time to return to the behaviour was less than 14 days for 13 of the behaviours, and up to 22 days for the other two (wearing clothes that show the legs, sporting activity or exercise), the use of the questionnaire at approximately 2–3 weeks would seem appropriate.\n\n**Question:** Compared to surgery what was the result of Endovenous laser ablation on Bending the legs without discomfort, Lifting heavy objects without discomfort, Moving from standing to sitting without discomfort, Standing still for a long time (> 15 min) without discomfort, Walking short distances (< 20 min) without discomfort, Walking long distances (> 20 min), Driving a car, Doing housework, Looking after children, Partial return to normal work/employment, Full return to normal work/employment, Going out socially, Sporting activity or exercise, ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
606
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Premedication with midazolam prior to cesarean delivery in preeclamptic parturients: A randomized controlled trial\n\n ABSTRACT.BACKGROUND:\nAnxiety is a concern in obstetrics, especially in preeclamptic mothers. Sedation is not commonly used in parturients for fear of adverse neonatal effect. We investigated maternal and neonatal outcome of midazolam as an adjuvant to spinal anesthesia for elective cesarean delivery.\n\nABSTRACT.METHODS:\nA prospective randomized controlled trial, in which eighty preeclamptic parturients received either an intravenous dose of 0.035 mg/kg of midazolam or an equal volume of normal saline, 30 min before spinal anesthesia. Maternal anxiety was assessed using Amsterdam Preoperative Anxiety and Information Scale (APAIS); postoperative maternal satisfaction was assessed using Maternal Satisfaction Scale for Cesarean Section (MSSCS). Newborns were assessed using Apgar score, Neonatal Neurologic and Adaptive Capacity Score (NACS), and umbilical artery blood gases.\n\nABSTRACT.RESULTS:\nMothers premedicated with midazolam showed a lower level of preoperative anxiety and a higher degree of postoperative satisfaction than the control group. There were no between-group differences regarding the neonatal outcome.\n\nABSTRACT.CONCLUSION:\nPreeclamptic parturients premedicated with midazolam (0.035 mg/kg) before spinal anesthesia have lower anxiety and higher postoperative satisfaction levels, with no adverse effects on the newborns.\n\nBODY.INTRODUCTION:\nNeuraxial anesthesia is progressively used for elective cesarean delivery as it is associated with the best maternal and neonatal outcomes. In preeclampsia, spinal anesthesia provides hemodynamic stability and best risk-benefit outcome; it avoids the detrimental effects of general anesthesia on maternal blood pressure and the risk of difficult intubation.[1] By the mid-1990s, clinical trials demonstrated the safety of neuraxial anesthesia as an accepted alternative to general anesthesia for preeclamptic patients.[234] Recently, a focused review confirmed this fact.[5] One study has reported that 60–80% of patients suffers from preoperative anxiety.[6] Some studies showed a clear correlation between anxiety and preeclampsia.[78] Anxiety is a particular concern in obstetrics, as it may lead to autonomic vasoconstriction in the uterine arteries, which may induce fetal distress.[910] Parturients may endure a great level of anxiety and discomfort during the placement of the spinal needle; a condition could be worsened by preeclampsia. Sedation for neuraxial blockade in pregnant patients remained controversial, based on its potential adverse effects on the fetus, such as decreased motor tone and respiratory compromise. In the 1960s, several case reports showed decreased motor tone in newborns related to maternal diazepam.[1112] In contrast, midazolam is three to four times more potent than diazepam and is used mainly for maternal sedation. Although it crosses the placental barrier, in small doses, it does not cause any adverse effects in the neonate.[13] However, when used in high doses of 0.3 mg/kg for the induction of general anesthesia, the umbilical vein to maternal vein ratio was high (0.96), and the elimination half-life in the neonate was 6.3 h.[14] In the 1980s, a few reports discussed the intravenous (iv) administration of midazolam during pregnancy without providing much information about its use close to delivery.[1516] More recent studies investigated the sedative effect of midazolam with or without narcotics on normal parturients.[171819] However, the impact of midazolam as a sedative on preeclamptics has not been sufficiently studied prospectively. In this concern, we decided to study the maternal and neonatal outcomes of a sedative dose of midazolam in these cases.\n\nBODY.INTRODUCTION.AIMS:\nThis work aimed to determine the effect of premedication with midazolam on preoperative anxiety, perioperative hemodynamics, and postoperative satisfaction of preeclamptic parturients scheduled for elective cesarean delivery under spinal anesthesia. It was also designed to observe the adverse effects of midazolam on the neonatal outcome.\n\nBODY.METHODS:\nAfter approval of our Institutional Ethical Committee and obtaining informed written consents from all parturients included in this study, this prospective randomized controlled study was conducted on eighty full-term, of American Society of Anesthesiologists (ASA) Class I or II, 18–40-year-old parturients presenting with mild preeclampsia as defined by the American College of Obstetricians and Gynecologists.[20] They were scheduled for elective cesarean delivery under spinal anesthesia after excluding the contraindications of technique. This study was performed in our university hospital from October 1, 2014, to September 30, 2015. Emergency cases, patients with evidence of intrauterine growth restriction or fetal compromise, patients with severe preeclampsia, thrombocytopenia, HELLP syndrome (hemolysis, elevated liver enzymes, and low platelet levels), parturients receiving magnesium therapy, or with a body mass index >30 were excluded from the study. History of cardiac, pulmonary, hepatic, renal, neuropsychiatric or other diseases or substance abuse also were excluded from the study. All patients had fetal heart monitoring preoperatively to exclude fetal heart rate (HR) abnormalities. Preoperatively, a complete blood count, prothrombin time, liver and kidney function tests were done and recorded for each participant. All patients were assessed clinically and investigated for the exclusion of any of the above-mentioned contraindications. All patients were randomly allocated into two groups, midazolam group (Group M) and normal saline control group (Group S), using a computer-generated randomization list and a sealed envelope technique (n = 40/group). The study solution (midazolam or normal saline) was prepared in a 2 mL volume, by an anesthesiologist not involved in the care of the woman or collecting the data for the study. Another anesthesiologist who was blinded to the study provided perioperative care and collected perioperative data. All patients were booked on a morning list, instructed for the same preoperative fasting protocol and were educated as to how to complete the questionnaires required for the study. On arrival of the patients to the preoperative waiting room, routine monitoring (Electrocardiography, pulse oximeter probe, and a noninvasive blood pressure cuff) were applied, and wide-bore venous access was established for the infusion of lactated Ringer's solution. Thirty minutes before the induction of spinal anesthesia, group (M) was given iv premedication with midazolam (0.035 mg/kg) in 2 mL solution, whereas group (S) was given an equal quantity of normal saline. The Amsterdam Preoperative Anxiety and Information Scale (APAIS) was used in this study for the objective analysis of anxiety in all patients [Figure 1]. It consists of six questions receiving a score between one (none) and five (most), with a total score of 30, investigating patients' concerns and anxieties. It is short, reliable, and easy to administer. Figure 1Amsterdam Preoperative Anxiety and Information Scale APAIS was applied twice by the same anesthesia assistant in a preoperative visit to all patients in their rooms 1⁄2 h before their transfer to the operating theater (A1), and 5 min after the administration of the study drug (A2). Twenty minutes before the induction of spinal anesthesia, all patients received a rapid iv infusion of 500 mL of lactated Ringer's solution as a preload, followed by a replacement rate of 15 mL/kg/h. For spinal anesthesia, 2.5 mL of intrathecal hyperbaric bupivacaine (0.5%) was injected using a 25-gauge spinal needle with patients in the lateral decubitus position at the L 3/4 interspace, under strict aseptic precautions. Parturients were then immediately placed in the tilted supine position. The level of sensory block was determined with cold and pinprick tests. Oxygen by nasal cannula (2 L/min) was applied to all patients. Urinary catheterization was performed, and surgery started when a sufficient level of sensory block (T4) was achieved. The maternal HR, systolic blood pressure (SBP), and diastolic blood pressure (DBP) noninvasive arterial pressure were recorded on arrival to the preoperative waiting room (T0), 5 min after injecting the tested drug (T1), during the insertion of spinal needle (TS), 2 min (T2), and 5 min (T5) after the induction of spinal anesthesia. Hypotension was defined as a drop of SBP <100 mmHg or a drop >20% from (T1), which was considered as the baseline value. SBP <90 mmHg was treated with ivboluses of ephedrine in increments of 10 mg. Tachycardia was defined as HR >100 and bradycardia when HR <60. When HR was lower than 50 beats/min, atropine 0.5 mg ivwas administered. Once the baby was delivered, the umbilical cord was double-clamped, and a blood sample from an umbilical artery (UA) was collected for blood gas analysis. Basic neonatal examination was performed, and Apgar scores were recorded at min 1 and 5, and the Neonatal Neurological and Adaptive Capacity Scoring (NACS) was measured and recorded at 15 min.[21] Postoperatively, patients were kept in the recovery room for 1 h and then sent to the ward. The Maternal Satisfaction Scale for cesarean section (MSSCS)[22] is a 22-item questionnaire specifically designed to evaluate maternal satisfaction with neuraxial anesthesia for elective cesarean delivery. Each item has a 7-point scale with minimum total score of 22 and maximum of 154, a higher score representing higher satisfaction. It was applied to all patients on the 1st postoperative day between 8:00 am and 1:00 pm. The development of seizures in cases of mild preeclampsia is extremely rare; however, if it took place, our protocol was to treat it with magnesium sulfate (loading dose of 4–6 g followed by continuous infusion of 1-2 g/h),[120] and the case was dropped out from the study. For sample size calculation, preoperative anxiety was taken as a primary parameter of interest. The power analysis is based on independent sample t-test and a 25% decrease of the APAIS score; the α value was 0.05 and the power (1-β) of the study was 0.80. Depending on the previous studies,[1823] it was calculated that a minimum of 36 patients would be required per group. However, we enrolled eighty patients (40/group) to allow for drop-outs. Data were analyzed using the SPSS statistics program (Version 16, SPSS Inc., Chicago, IL, USA). According to the type of data, they were represented as mean and standard deviation or frequencies and percentages. Comparisons of the two studied groups were performed using independent sample t-test or Mann–Whitney U-test as appropriate while repeated measures within the same group were compared using paired t-test. In all tests, results were considered statistically significant if P < 0.05.\n\nBODY.RESULTS:\nEighty cases were initially investigated, but five cases were excluded during the study; two cases in group (M) and one case in group (S) due to an inadequate spinal block, and one case in each group because of failure to collect umbilical arterial blood. In both groups, there were no significant differences regarding age, body weight, height, and spinal injection to delivery time as shown in Table 1. Table 1 Patients characteristics in both groups After administration of the tested drug (midazolam or normal saline), there was a significant reduction in APAIS readings (A2) in group (M); with a significant difference in (A2) between the two groups while there was no between-group difference before administration (A1) as shown in Table 2. Maternal Satisfaction Scale for cesarean section showed a significant level of maternal satisfaction in group (M) compared to group (S). There was no difference between the groups regarding the newborn Apgar or NACS scores as shown in Table 2. No significant differences were found between the two groups regarding the pH, PaCO2, PaO2, and base deficit in the umbilical arterial samples as listed in Table 3. Table 2 Amsterdam Preoperative Anxiety and Information Scale, Maternal Satisfaction Scale for cesarean section, Apgar score and neonatal neurologic and adaptive capacity score in both groups Table 3 Blood gas analysis of umbilical artery blood samples in both groups Regarding maternal hemodynamics, baseline HR, SBP, and DBP were comparable between the two groups before the administration of the tested drug. However, 5 min after injecting the tested drug, there was a significant decrease in all parameters in group (M) compared to group (S). During insertion of the spinal needle, there was a rise in HR and SBP in group (S) compared to group (M) while DBP was at a lower level in group (M). After the induction of spinal anesthesia and placing the patient into the tilted supine position, there was an increase in HR with some decrease in blood pressure parameters in both groups as shown in Tables 4–6. Table 4 Maternal heart rate in both groups Table 5 Systolic blood pressure in both groups Table 6 Diastolic blood pressure in both groups Hypotension occurred in three patients in the group (M) and one patient in the group (S), requiring a single bolus of ephedrine for each. No bradycardia was observed in any patient. Hemodynamic parameters then remained stable and comparable in both groups.\n\nBODY.DISCUSSION:\nThis study has shown a significant improvement of preoperative anxiety and postoperative satisfaction in parturients premedicated with midazolam compared to those in the control group, with no significant neonatal adverse effects. The study also documented improved maternal hemodynamics in the treated group before the administration of spinal anesthesia. However, there was no significant difference between groups regarding maternal hemodynamics throughout the rest of the procedure. The progressive increase in the number of cesarean sections[24] draws the attention to the psychological aspects of parturients, including their level of anxiety and perception of obstetric care they received.[25] Some studies tried to solve the problem of preoperative anxiety via nonpharmacological measures, such as the use of a preoperative information video in obstetric[26] and nonobstetric[27] patients, but their results were disappointing. However, other studies applied a preoperative information system and proved its effectiveness on the level of anxiety and postoperative satisfaction in nonobstetric patients.[282930] Midazolam is a commonly used sedative as it is fast-acting and of short duration, making it superior to other benzodiazepines. It is a lipophilic drug that can cross the placenta by passive diffusion. In large induction doses, midazolam and its metabolites cross the placenta in both animal[31] and human[14] studies. However, early in 1984, Kanto et al.[32] proved its excellent sedative effect following cesarean delivery performed under epidural anesthesia. They gave a relatively large iv dose (0.075 mg/kg) following baby removal, resulted in a rapid and marked sedative effect lasted for 2–3 h while patients were completely cooperative in the recovery room. Frölich et al.[19] gave a single iv dose of 0.02 mg/kg midazolam plus 1 μg/kg fentanyl to parturients undergoing cesarean delivery shortly before spinal needle insertion. Similar to our study, Apgar scores showed no difference between the treated group and the control group. They evaluated maternal anxiety with two methods; maternal plasma catecholamine levels at the time of delivery and three postoperative questions. They found a higher level of patient satisfaction in the treated group; otherwise, there were no between-group differences. In contrast, Senel and Mergan[18] gave a single iv dose of 0.025 mg/kg midazolam to parturients 30 min before cesarean delivery. They evaluated maternal anxiety using APAIS score and newborns with Apgar and NACS scores. They reported significantly lower anxiety scores in the treated groups, without any adverse neonatal outcome. However, they recommended further clinical trials with higher sample size to assess the larger doses of midazolam. Similar findings were found by Fung et al. in 1992, where 90% of mothers fell asleep with midazolam premedication before the start of surgery, with no adverse neonatal outcome; comparing the Apgar scores and umbilical venous pH values to the control group.[17] We chose the midazolam dose (0.035 mg/kg) based on these previous studies,[1819] and according to our own experience with Egyptian parturients, aiming for the best degree of maternal satisfaction without causing maternal hypoventilation or neonatal depression. We chose a single bolus based on body weight; however, in clinical practice, some may prefer to titrate iv drugs to effect. Thus, our results cannot be compared to other studies with repeated doses or iv infusion. The timing of premedication is also crucial. We chose it 30 min before the induction of spinal anesthesia, to allow enough time for suppression of anxiety; an important consideration in preeclampsia, whose cardiovascular responses are exaggerated. This is in contrast to Frölich et al., who gave their premedication immediately before the spinal anesthesia procedure. We employed several parameters of neonatal outcome. The Apgar scoring system is routinely used, due to its clear physiological correlation with neonatal well-being.[33] It is easily applied and gives a quick idea about newborn's clinical condition and efficiency of resuscitation efforts. We also used the NACS scoring system, a neurobehavioral scale that allows for the evaluation of potential effects of neonatal drug exposure. It is designed to distinguish drug-induced neonatal depression from that secondary to asphyxia. It stresses on motor tone as a main indicator of drug-induced depression.[21] However, Brockhurst et al. indicate its poor reliability regarding obstetric anesthesia research.[21] We also recorded UA blood gas values and noted no significant difference between groups. Again, the reliability of this test to detect neonatal depression has been questioned.[3435] That is why we employed a combination of several parameters to assess neonatal outcome. As part of this study, we evaluated the postoperative maternal satisfaction of anesthesia and birth. It is an important outcome that is commonly reported;[253637] since in healthy parturients, a pleasant experience is expected. Furthermore, anxiety may decrease the level of overall satisfaction with perioperative care.[38] In 1998, Robinson et al. highlighted some important factors that may affect satisfaction in the obstetric patient.[36] The development of a reliable and valid satisfaction scale for cesarean delivery has allowed to assess the effectiveness of sedatives on maternal satisfaction.[22] MSCCS has proven more sensitive than the standard VAS as it samples from the various physiological and psychological factors that make up satisfaction.[39] The reliability of a scale is directly related to the number of its items so that VAS would be expected to be of low reliability.[22] Our data revealed a remarkable level of maternal satisfaction in the group premedicated with midazolam compared to the control group. To the best of our knowledge, none of the studies concerned with sedatives during cesarean delivery under spinal anesthesia focused on this scale. Instead, Frölich et al. applied a simple questionnaire of three questions while Senel and Mergan and Fung et al. did not focus on this important outcome. The main limitation of this study was the inability to measure the placental transfer of midazolam and its plasma level in the fetal circulation, due to financial difficulties. However, this had been widely investigated by several authors.[143140] Another limitation is this study only enrolled mild preeclamptic patients. Thus, the extension of these findings to those with more severe features of preeclampsia (and potentially more adverse uteroplacental blood flow) remains to be investigated.\n\nBODY.CONCLUSION:\nA dose of 0.035 mg/kg of iv midazolam, administered 30 min before spinal anesthesia, is associated with improved preoperative anxiety, postoperative satisfaction, and maternal hemodynamics in preeclamptic parturients scheduled for elective cesarean delivery, with no adverse effects on the newborn.\n\nBODY.CONCLUSION.FINANCIAL SUPPORT AND SPONSORSHIP:\nNil.\n\nBODY.CONCLUSION.CONFLICTS OF INTEREST:\nThere are no conflicts of interest.\n\n**Question:** Compared to equal volume of normal saline, 30 min before spinal anesthesia what was the result of intravenous dose of 0.035 mg/kg of midazolam on preoperative anxiety?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
612
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy and safety of collagenase clostridium histolyticum for Dupuytren disease nodules: a randomized controlled trial\n\n ABSTRACT.BACKGROUND:\nTo determine the safety and efficacy of collagenase clostridium histolyticum (CCH) injection for the treatment of palmar Dupuytren disease nodules.\n\nABSTRACT.METHODS:\nIn this 8-week, double-blind trial, palpable palmar nodules on one hand of adults with Dupuytren disease were selected for treatment. Patients were randomly assigned using an interactive web response system to receive a dose of 0.25 mg, 0.40 mg, or 0.60 mg (1:1:1 ratio) and then allocated to active treatment (CCH) or placebo (4:1 ratio). All patients and investigators were blinded to treatment. One injection was made in the selected nodule on Day 1. Caliper measurements of nodule length and width were performed at screening and at Weeks 4 and 8. Investigator-reported nodular consistency and hardness were evaluated at baseline and Weeks 1, 4, and 8. Investigator-rated patient improvement (1 [very much improved] to 7 [very much worse]) and patient satisfaction were assessed at study end.\n\nABSTRACT.RESULTS:\nIn the efficacy population (n = 74), percentage changes in area were significantly greater with CCH 0.40 mg (−80.1%, P = 0.0002) and CCH 0.60 mg (−78.2%, P = 0.0003), but not CCH 0.25 mg (−58.3%, P = 0.079), versus placebo (−42.2%) at post-treatment Week 8. Mean change in nodular consistency and hardness were significantly improved with CCH versus placebo at Weeks 4 and 8 (P ≤ 0.0139 for all). At Week 8, investigator global assessment of improvement was significantly greater with CCH 0.40 mg and 0.60 mg (P ≤ 0.0014) but not statistically significant with CCH 0.25 mg versus placebo (P = 0.13). Most patients were \"very satisfied\" or \"quite satisfied\" with CCH 0.40 mg and 0.60 mg. Contusion/bruising (50.0% to 59.1%) was the most common adverse event with CCH treatment.\n\nABSTRACT.CONCLUSION:\nIn patients with Dupuytren disease, a single CCH injection significantly improved palmar nodule size and hardness. The safety of CCH was similar to that observed previously in patients with Dupuytren contracture.\n\nABSTRACT.TRIAL REGISTRATION:\n\nClinicalTrials.gov identifier: NCT02193828. Date of trial registration: July 2, 2014 to December 5, 2014\n\nBODY.BACKGROUND:\nDupuytren disease is a common fibroproliferative disease of the palmar fascia [1] that is reported to affect between 1% and 32% of individuals in Western countries [2, 3]. It is characterized by the formation of thick collagen nodules that can progress to fibrous cords capable of producing digital flexion contractures and reducing hand function [4]. Dupuytren disease exhibits three clinical phases known as the proliferative, contractile, and residual phases [5]. In the early proliferative phase, nodules form as myofibroblasts and proliferate around microvessels [5]. This myofibroblast proliferation may lead to vessel occlusion and hypoxia, and signal infiltration of immune cells [5]. Expression of inflammatory signals and growth factors (eg, transforming growth factor-β) by immune cells may stimulate myofibroblast differentiation [6] and contraction [7] and augment the production of extracellular matrix proteins, such as fibronectin and collagen within nodules [8, 9]. In the contractile phase, nodules are reduced in size and myofibroblasts become arranged around the major areas of stress within the nodule, forming a cord [4]. Myofibroblasts also continue to produce collagen, particularly Type III, as well as fibronectin [4]. In the residual phase, nodules have been replaced by fibrous cords, which can shorten and cause further contracture [4]. Currently, no treatment has been approved for nodules associated with Dupuytren disease, although many nodules are symptomatic when pressure is applied to the palm and many will progress to cords with resultant contracture [10]. When treatment (eg, the injection of collagenase clostridium histolyticum [CCH] or surgery) is considered appropriate, it is generally applied during the contractile and residual phases once cords have developed. However, given that collagen augments the disease process and decreases with disease progression [4, 11, 12], earlier treatment with agents that disrupt collagen formation (eg, CCH) is thought to potentially alter disease progression and reduce nodule size, symptoms, and clinical impact [13, 14]. The CCH formulation Xiaflex® (Endo Pharmaceuticals Inc., Malvern, PA, USA) is a combination of two Clostridium histolyticum collagenases (AUX-I and AUX-II) that is currently approved in the United States, Europe, and Australia for the treatment of adult patients with Dupuytren contracture with a palpable cord [1]. These enzymes hydrolyze type I and type III collagen into smaller peptides, which may then be degraded by endogenous human collagenases [1]. In two phase 3 trials (Collagenase Option for the Reduction of Dupuytren [CORD I and CORD II]), injection of CCH into the cords of patients with Dupuytren contracture reduced joint contraction to 0–5° of full extension within 30 days of the last injection in a significantly greater percentage of joints versus placebo injection (CORD I: 64.0% with CCH vs 6.8% with placebo; CORD II: 44.4% vs 4.8%; P < 0.001 for both) [13, 14]. This phase 2a study evaluated the safety and efficacy of multiple doses of CCH injections for the treatment of palmar Dupuytren disease nodules.\n\nBODY.METHODS.PATIENT POPULATION:\nPatients ≥18 years of age with Dupuytren disease who had ≥1 palpable palmar nodule that was not associated with a cord and measured between 0.5 cm and 2.0 cm in length and between 0.5 cm and 2.0 cm in width were eligible for inclusion in the study. Patients who had received steroid injections or collagenase treatment (including Santyl® ointment, Smith & Nephew, Inc., Fort Worth, TX, USA) for the treatment of the selected nodule within the past 30 days or surgery on the selected hand within 3 months were excluded. Patients were also ineligible if they had a chronic hand-related muscular, neurologic, or neuromuscular condition, had received or were planning to receive anticoagulant medication within 7 days of study initiation, or had a recent history of stroke or bleeding. All patients included in the study received injection of either CCH or placebo.\n\nBODY.METHODS.CLINICAL STUDY DESIGN:\nThis 8-week, double-blind, placebo-controlled, exploratory phase 2a study (ClinicalTrials.gov identifier: NCT02193828) was conducted between July 2, 2014, and December 5, 2014 at 11 centers in the United States and Australia. During the screening visit, a palpable palmar nodule on one hand was selected to receive treatment for each eligible patient. On Day 1, patients were randomly assigned to a dose group (based on doses of CCH evaluated in the study) in a 1:1:1 ratio and then further randomly assigned to active treatment [CCH] or placebo in a 4:1 ratio using an interactive web response system. All patients and study site personnel involved in patient evaluation, including the investigators, were blinded to treatment throughout the study. Both CCH and placebo were reconstituted in a solution containing 0.9% NaCl and 0.03% CaCl. Patients received CCH 0.25 mg, 0.40 mg, or 0.60 mg (plus Tris-HCl and sucrose) in a 0.11-, 0.17-, or 0.21-mL total injection volume, respectively, or volume-matched placebo (Tris-HCl and sucrose). Different injection volumes for each treatment group were necessary to ensure delivery of the appropriate concentration of CCH. Patients received a single injection directly into the selected hand nodule using a 26- or 27-gauge, 13-mm needle. The needle was inserted horizontally along the length of the nodule but did not penetrate the opposite side of the nodule. Treatment volume was dispensed as the needle was withdrawn to ensure complete deposition within the nodule. Patients were monitored for immediate immunologic adverse events (AEs) for 20 min post-injection. Follow-up visits occurred at post-injection Week 1, Week 4, and Week 8. Starting at Week 1, all patients were instructed to massage the nodule (massage for 30 s, rest for 30 s, and repeat) twice daily until Week 4. The study was approved by central or local institutional review boards at each participating center within Australia and the United States and followed Good Clinical Practice and principles expressed in the Declaration of Helsinki. All patients provided written informed consent.\n\nBODY.METHODS.STUDY ASSESSMENTS:\nThe size of the selected nodule was measured at screening, Week 4, and Week 8 using hand-held calipers (for length and width), and at screening and Week 8 using ultrasonography (for length, width, and depth). Nodular consistency was rated by the investigator on a 5-point scale (5 [hard/solid], 4 [firm throughout], 3 [moderate firmness], 2 [soft], or 1 [non-palpable]) after palpation of the selected nodule on Day 1 (the day of injection) and at Weeks 1, 4 and 8. Nodule hardness and pain were assessed on Day 1 and at Weeks 1, 4 and 8. A durometer was used to assess the hardness of the selected nodule with a range of 0–100. Nodular pain was induced using a dynamometer (by applying direct pressure to the nodule) and was then measured on a visual analog scale from 0 (no pain or discomfort) to 10 (extreme pain or discomfort). Investigators rated patient improvement from screening to Week 8 on a scale from 1 (very much improved) to 7 (very much worse). Patient satisfaction with treatment was assessed at Week 8 using a 5-point scale: 1 (very satisfied), 2 (quite satisfied), 3 (neither satisfied nor dissatisfied), 4 (quite dissatisfied), and 5 (very dissatisfied). Treatment-emergent AEs were monitored and vital signs were collected throughout the study. Serum samples for the determination of AUX-I and AUX-II antibodies were collected at screening and the final visit (Week 8).\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nSample size was estimated assuming response rates of 15% for all placebo groups, 50% for CCH 0.60-mg, 40% for CCH 0.40-mg, and 35% for CCH 0.25-mg groups. Thus, a sample size of 80 patients would be required to achieve ≥85% power to detect differences between placebo and CCH 0.60 mg or CCH 0.40 mg. Assuming a common dropout rate (10%), 90 patients were determined to be sufficient for enrollment. The safety population included any patients who received an injection of the study drug. All patients in the safety population who also had pre- and post-injection nodule measurements were included in the efficacy population. The primary end point was the percentage change from baseline in surface area, as measured by calipers, of the treated nodule at Week 8. Secondary end points included percent change from baseline in surface area (as measured by ultrasound) of the treated nodule at Week 8, change from baseline in consistency and hardness of the treated nodule at Week 8, change in nodule pain from baseline to Week 8, investigator global assessment of improvement and patient satisfaction at Week 8, and composite responder analysis at Week 8. Patients who reported being satisfied with treatment (ie, responded very satisfied [1] or quite satisfied [2]) and reported improvement according to investigator assessment (ie, very much improved [1], much improved [2], or minimally improved [3]) were considered composite responders. Between-group differences in categorical variables other than the composite responder end point (ie, investigator global assessment of improvement, patient satisfaction, nodular consistency, change from baseline in nodular consistency) were analyzed using a Kruskal-Wallis test. Differences between each CCH-dose group and placebo were compared using a Mann-Whitney test. For the composite responder end point, the Fisher's exact test was used to analyze between-group comparisons. One-way analysis of variance was used to assess between-group differences in continuous variables (percent change in area [using caliper or ultrasound measurement], nodular hardness, and change in nodular pain). Pairwise comparisons were performed to compare each CCH dose and placebo. Occurrences of AEs were reported using descriptive statistics. The overall count and percentage of patients with AUX-I and AUX-II antibodies were summarized as categorical variables. Log-transformed AUX-I and AUX-II titer values and vital sign measurements were summarized as continuous variables.\n\nBODY.RESULTS.STUDY POPULATION:\nOf 84 patients screened, 76 patients met eligibility criteria and were randomly assigned to treatment. Of those, 75 patients were included in the safety population (1 patient withdrew consent before treatment administration; Fig. 1). Demographics and baseline characteristics for the safety population (n = 75) were similar among groups (Table 1). Seventy patients overall (86.4% to 100.0% of patients in each treatment group) had not received previous treatment for Dupuytren disease. One patient in the safety population received study medication but did not complete any post-treatment efficacy evaluations; therefore, only 74 patients were included in the efficacy analyses (Fig. 1).Fig. 1Patient disposition. One patient withdrew consent before receiving study drug on Day 1 and was excluded from all analyses (safety and efficacy). CCH, collagenase clostridium histolyticum\nTable 1Demographic and Baseline Characteristicsa\nParameterCCH 0.25 mg(n = 22)CCH 0.40 mg(n = 18)CCH 0.60 mg(n = 18)Placebo(n = 17)Mean age, y (SD)57.9 (10.0)58.1 (12.4)60.0 (10.2)59.9 (8.8)Sex, n (%) Female11 (50.0)10 (55.6)6 (33.3)7 (41.2) Male11 (50.0)8 (44.4)12 (66.7)10 (58.8)Race, n (%) White22 (100.0)17 (94.4)18 (100.0)17 (100.0) Other01 (5.6)00Mean age at Dupuytren disease onset, y (SD)51.6 (13.5)50.4 (13.8)55.8 (8.3)54.7 (11.2)Nodules on selected hand, n (%) 19 (40.9)9 (50.0)10 (55.6)6 (35.3) 26 (27.3)3 (16.7)4 (22.2)5 (29.4) ≥ 37 (31.8)6 (33.3)4 (22.2)6 (35.3)Mean nodule areab, cm2 (SD)0.7 (0.3)0.7 (0.4)0.7 (0.3)0.8 (0.4)Prior Dupuytren disease treatments None19 (86.4)18 (100.0)16 (88.9)17 (100.0) Fasciectomy2 (9.1)000 Needle aponeurotomy001 (5.6)0 CCH1 (4.5)02 (11.1)0\naSafety population (n = 75)\nbMeasured using calipers. Calculated as 0.79 × length × width\nCCH collagenase clostridium histolyticum, SD standard deviation\n\n\nBODY.RESULTS.EFFICACY:\nIn the efficacy population at Week 4, improvements in caliper-measured nodular surface area (change from baseline: CCH 0.25 mg, −0.30 cm2; CCH 0.40 mg, −0.49 cm2; CCH 0.60 mg, −0.50 cm2) were numerically greater in all CCH groups versus placebo (−0.21 cm2). Percentage reductions in area at Week 4 were significantly greater with CCH 0.40 mg (−58.8%, P = 0.0109) and CCH 0.60 mg (−72.4%, P = 0.0003) versus placebo (−27.9%), but not with CCH 0.25 mg (−41.4%; P = 0.24). At Week 8, significant differences versus placebo were observed in caliper-measured nodular surface area for CCH 0.60 mg (P = 0.0003) and CCH 0.40 mg (P = 0.0002), but not with CCH 0.25 mg (P = 0.08; Fig. 2) Ultrasound measurements of nodule size did not correlate with direct caliper measurements and were, therefore, considered an unreliable assessment of treatment efficacy and not reported for this study. Nodular consistency and hardness improved from baseline to Week 1, with significant improvements in all CCH groups versus placebo at Weeks 4 and 8 (Table 2). At Week 8, soft or non-palpable nodules were observed in 8 (36.4%) of 22 nodules in the 0.25-mg group, 12 (70.6%) of 17 nodules in the CCH 0.40-mg group, and 12 (75.0%) of 16 nodules in the CCH 0.60-mg group. Baseline median pain scores were low for all treatment groups (placebo and CCH 0.25 mg [2.0], CCH 0.40 mg [0.5], CCH 0.60 mg [0.0]), illustrating that most patients had little to no nodular pain at study initiation. Significant improvement in nodular pain from baseline was not observed between any CCH group and placebo at any time point. Investigator global assessment of improvement and patient satisfaction at Week 8 were significantly greater in the 0.60-mg and 0.40-mg CCH groups versus placebo (Fig. 3a). A significantly greater percentage of patients in the higher CCH-dose groups were composite responders (CCH 0.40 mg, 88.9%, P = 0.003; CCH 0.60 mg, 77.8%, P = 0.03) compared with those in the placebo group (37.5%; Fig. 3b). Although the percentage of responders in the 0.25-mg group (54.5%) was numerically greater than that reported for placebo responders (37.5%), this difference was not statistically significant (P = 0.34).Fig. 2Nodular area at baseline and Week 8. Error bars represent standard deviations. *\nP ≤ 0.0003 vs placebo. CCH, collagenase clostridium histolyticum\nTable 2Nodule Consistency and HardnessParameterCCH 0.25 mg(n = 22)CCH 0.40 mg(n = 18)CCH 0.60 mg(n = 18)Placebo(n = 16)Nodule Consistency Scorea\nBaseline, mean (SD)4.2 (0.7)4.1 (0.7)4.1 (0.5)3.7 (0.6)Week 1b\n Mean (SD)3.1 (0.8)2.7 (0.8)2.6 (0.8)3.6 (0.7) Mean change from baseline (SD)−1.0 (0.8)−1.4 (0.6)−1.4 (0.9)−0.1 (0.7)Week 4 Mean (SD)3.1 (0.8)2.4 (1.0)c\n2.0 (0.8)d\n3.5 (0.8) Mean change from baseline (SD)−1.1 (0.9)c\n−1.7 (0.8)d\n−2.1 (0.9)d\n−0.2 (0.8)Week 8 Mean (SD)3.0 (1.1)2.2 (1.0)c\n2.1 (0.8)d\n3.4 (1.0) Mean change from baseline (SD)−1.2 (1.1)c\n−1.9 (1.1)d\n−1.9 (0.9)d\n−0.3 (1.0)Nodule Hardness Scoree\nBaseline, mean (SD)68.7 (12.5)67.0 (8.8)68.2 (8.0)63.0 (10.0)Week 1b,f\n Mean (SD)58.3 (12.8)52.8 (8.6)55.0 (10.4)65.3 (10.6) Mean change from baseline (SD)−10.4 (13.3)−14.2 (12.5)−13.2 (11.8)2.3 (12.6)Week 4g\n Mean (SD)56.4 (10.9)54.7 (9.3)55.6 (12.6)63.1 (11.6) Mean change from baseline (SD)−12.0c (11.3)−12.3 (10.6)c\n−13.1 (14.3)c\n0.3 (12.6)Week 8h\n Mean (SD)55.9 (15.2)46.9 (17.8)56.4 (10.9)64.3 (10.4) Mean change from baseline (SD)−12.8 (14.9)c\n−19.6 (14.4)d\n−12.1 (11.8)c\n1.5 (12.5)\naNodular consistency was rated as 5 (hard/solid), 4 (firm throughout), 3 (moderate firmness), 2 (soft), or 1 (non-palpable). Negative percentage change indicates improvement\nbStatistical analyses were not performed on Week 1 data\nc\nP < 0.02 vs placebo\nd\nP < 0.001 vs placebo\neHardness of the nodule was assessed using a durometer on a scale of 0–100\nfPlacebo, n = 16; CCH 0.25 mg, n = 22; CCH 0.40 mg, n = 18; CCH 0.60 mg, n = 18\ngPlacebo, n = 15; CCH 0.25 mg, n = 21; CCH 0.40 mg, n = 18; CCH 0.60 mg, n = 17\nhPlacebo, n = 15; CCH 0.25 mg, n = 22; CCH 0.40 mg, n = 17; CCH 0.60 mg, n = 16\nCCH collagenase clostridium histolyticum, SD standard deviation\nFig. 3Investigator- and patient-reported assessments at Week 8. Investigator-reported improvement (rating: 1 [very much improved] to 7 [very much worse]) and patient-reported satisfaction (rating: 1 [very satisfied] to 5 [very dissatisfied]) (a) and percentage of composite responders (b). Error bars represent standard deviations. *\nP ≤ 0.03 vs placebo. CCH, collagenase clostridium histolyticum\n\n\nBODY.RESULTS.SAFETY:\nThe most common AEs in the CCH groups were contusion/bruising, extremity pain, and localized swelling (Table 3). There were no trends for increased AE occurrence with increasing CCH dose, except for injection-site bruising and localized swelling. Most AEs in all CCH groups were mild (84.5% with 0.25 mg, 69.1% with 0.40 mg, and 84.2% with 0.60 mg) or moderate (15.5%, 30.9%, 14.0%, with CCH 0.25 mg, 0.40 mg, and 0.60 mg, respectively). Severe treatment-related injection-site pain was reported in one patient receiving CCH 0.60 mg. No clinically meaningful changes in vital signs were observed. No deaths or patient discontinuations because of a treatment-emergent AE were reported. At Week 8, most patients in all CCH groups (86.4–100.0%) tested positive for antibodies against AUX-I and AUX-II; however, mean log antibody titers were low (ie, <3.2).Table 3Adverse Events Reported by ≥2 Patients in Any Treatment Group (Safety Population)a\nAE, n (%)CCH 0.25 mg(n = 22)CCH 0.40 mg(n = 18)CCH 0.60 mg(n = 18)Placebo(n = 17)Any AE21 (95.5)18 (100.0)17 (94.4)7 (41.2) Discontinuations due to AEs0000 Any serious AE0000 Contusion/bruising13 (59.1)9 (50.0)9 (50.0)1 (5.9) Extremity pain10 (45.5)10 (55.6)7 (38.9)1 (5.9) Local swelling8 (36.4)7 (38.9)10 (55.6)3 (17.6) Injection-site bruising5 (22.7)4 (22.2)6 (33.3)0 Axillary pain6 (27.3)1 (5.6)4 (22.2)0 Injection-site pain4 (18.2)4 (22.2)2 (11.1)0 Injection-site swelling5 (22.7)4 (22.2)00 Injection-site pruritus2 (9.1)3 (16.7)2 (11.1)1 (5.9) Injection-site edema2 (9.1)02 (11.1)0 Pruritus2 (9.1)2 (11.1)1 (5.6)0 Injection-site hemorrhage2 (9.1)01 (5.6)0\naPresented in order of occurrence in the active treatment groups\nAE adverse event, CCH collagenase clostridium histolyticum\n\n\nBODY.DISCUSSION:\nCurrently, no treatments have been approved for Dupuytren nodules, although a retrospective chart review by Reilly et al. showed that 51% of patients with nodules who returned for follow-up (mean time between diagnosis and follow-up: 8.7 years, range, 6–15 years) had developed a cord and 8% had progressed to full contracture [10]. In addition, nodules may be painful in some patients and impair their ability to grip objects or use their hands successfully. Although the pathophysiology underlying Dupuytren disease remains a controversial topic, inflammatory and growth factor signals likely play a role through the augmentation of specific aspects of the disease (eg, myoblast proliferation and collagen production) [5, 6, 8, 9]. Dupuytren nodules are rich in collagen type I and III (ie, the substrates for CCH) [15] and in vitro, CCH has been shown to reduce the expression of extracellular matrix components, cytokines, and growth factors that may contribute to nodule formation and progression [15]. Thus, the properties of CCH at the site of local injection suggest CCH as a possible treatment option for nodules. The results of the current phase 2a, dose-ranging study support continued investigation into the efficacy and safety of CCH for the treatment of Dupuytren nodules. Despite a greater than expected improvement in caliper-measured nodular surface area from baseline to Week 8 in the placebo group (42.2%), improvement was only significantly greater with CCH 0.40 mg (80.1%, P = 0.0002) and 0.60 mg (78.2%, P = 0.0003). Improvement in the lowest CCH-dose group (0.25 mg: 58.3%) was numerically greater than that observed with placebo (42.2%); however, the difference did not reach statistical significance (ie, P > 0.05). Significant improvements from baseline versus placebo were observed in the CCH 0.25-mg group for nodule hardness and consistency. However, greater improvement was observed at the two higher CCH doses (0.40 mg and 0.60 mg), with little apparent increase in the incidence of AEs. Furthermore, investigators noted \"very much\" or \"much\" improvement in most (83.3% with CCH 0.40 mg and 88.9% with CCH 0.60 mg) patients who received the two higher doses of CCH. Most patients also expressed a high degree of satisfaction with CCH treatment, indicating that they were \"very satisfied\" or \"quite satisfied\" with the two higher CCH doses. Based on these data, CCH doses greater than 0.25 mg appear to be more effective than lower doses for the treatment of Dupuytren nodules and warrant further investigation. Clinical trials have demonstrated the beneficial effect of CCH for the treatment of Dupuytren contracture [13, 14]. During these trials, joints with low baseline contracture severity had greater reduction in contracture to 0–5° of normal (primary end point) 30 days post-injection than joints with more severe contracture [13, 14], implying that earlier treatment may have an effect on the potential response to CCH. However, the current medical literature for the pharmacologic treatment of Dupuytren nodules is limited. In a 4-year study of patients with Dupuytren nodules (n = 75 hands), injection of triamcinolone acetonide (a corticosteroid) flattened and softened the injected nodules in most (97%) hands. However, multiple injections per site were performed (mean number of injections, 3.2), and the authors concluded that the initial injection of corticosteroids was more of a \"priming\" than a therapeutic dose [16]. The current study demonstrated that injection of CCH into nodules significantly improved nodule consistency and reduced hardness versus placebo within 4 weeks after a single injection. The overall safety profile of CCH was similar to that reported in phase 3 clinical trials of CCH for treatment of Dupuytren contracture [13, 14]. The most commonly reported AEs (ie, contusion/bruising, extremity pain, and local swelling) with the injection of CCH into nodules were similar to those previously reported with CCH injection for the treatment of Dupuytren contracture [13, 14]. Most patients (86.4–100.0%) had antibodies against AUX-I and AUX-II, which was consistent with the rate reported for patients receiving injection into a Dupuytren cord (82–95.2%) [13, 14]. Research has also shown that the presence of AUX-I and AUX-II antibodies has no impact on the efficacy or safety of later injections [17–19]. The current study is limited by its small sample size per treatment group, the administration of only one injection, the limited follow-up duration, and an inability to quantify changes in nodules accurately using ultrasound. Discordance between caliper and ultrasound measurements of nodule size was related to extreme outliers and lack of convergent validity with other efficacy measures. This was likely because of a lack of existing standards for use of ultrasound to measure nodules. Similar patterns of results were observed for both caliper and ultrasound measurements, with the CCH 0.40-mg and 0.60-mg groups showing greater reduction in nodule size compared with placebo, but the wide variability in the ultrasound measurements prevented computation of any significant treatment effect. Thus, we recommend that standard measurement rules be pre-specified in future studies using ultrasound measurements of nodules, and that personnel conducting ultrasound assessments undergo training to maximize measurement consistency. Some improvement was noted in the placebo group for all efficacy end points, which suggests that factors other than active treatment (eg, local injection of anesthesia, nodular massage alone, or patient expectation [placebo response effect]) may have impacted the results. However, the fact that significant improvements with CCH treatment were observed despite the high placebo rate may indicate that benefits of CCH are potentially greater than what has been reported in the current study. In addition, ratings of nodule consistency, nodule pain, and patient satisfaction were subjective; and although both the patient and investigators were blinded to treatment, it is possible that these end points were affected by individuals' desire for or anticipation of improvement. However, the consistency of the improvement observed among all subjective and non-subjective assessments (eg, nodule size as measured with calipers and durometer measurements of hardness) suggests the subjective measurements used in the current study accurately assessed an effect of treatment. Finally, practical use of a dynamometer to potentiate pressure on the affected nodule and then measure nodule pain had not been previously studied in this type of clinical scenario with Dupuytren disease. The positioning of the dynamometer against the nodule was not standardized; thus, patients may not have applied direct pressure to the nodule if it was painful. This variation to avoid pain may explain why no significant improvements in pain were observed with CCH versus placebo. Despite these issues, CCH treatment improved nodular pain by the end of the study and a treatment effect was observed in a post hoc analysis of patients with baseline pain scores ≥3.\n\nBODY.CONCLUSION:\nThis phase 2a, dose-ranging study demonstrated that a single injection of CCH 0.40 mg or 0.60 mg significantly decreased the size and hardness of palmar nodules in patients with Dupuytren disease and displayed a tolerable safety profile, similar to that reported with CCH treatment for Dupuytren contracture. Additional studies are needed to confirm these initial results and evaluate the long-term efficacy and safety of CCH for palmar nodules.\n\n**Question:** Compared to dose of 0.25 mg, 0.40 mg, or 0.60 mg (1:1:1 ratio) and then allocated placebo (4:1 ratio) what was the result of receive a dose of 0.25 mg (1:1:1 ratio) and then allocated to active treatment (CCH) on global assessment of improvement?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
613
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Biochemical markers of bone turnover in patients with spinal metastases after resistance training under radiotherapy – a randomized trial\n\n ABSTRACT.BACKGROUND:\nTo compare the effects of resistance training versus passive physical therapy on bone turnover markers (BTM) in the metastatic bone during radiation therapy (RT) in patients with spinal bone metastases. Secondly, to evaluate an association of BTM to local response, skeletal-related events (SRE), and number of metastases.\n\nABSTRACT.METHODS:\nIn this randomized trial, 60 patients were allocated from September 2011 to March 2013 into one of the two arms: resistance training (Arm A) or passive physical therapy (Arm B) with thirty patients in each arm during RT. Biochemical markers such as pyridinoline (PYD), desoxy-pyridinoline (DPD), bone alkaline phosphatase (BAP), total amino-terminal propeptide of type I collagen (PINP), beta-isomer of carboxy-terminal telopeptide of type I collagen (CTX-I), and cross-linked N-telopeptide of type I collagen (NTX) were analyzed at baseline, and three months after RT.\n\nABSTRACT.RESULTS:\nMean change values of PYD and CTX-I were significantly lower at 3 months after RT (p = 0.035 and p = 0.043) in Arm A. Importantly, all markers decreased in both arms, except of PYD and CTX-I in arm B, although significance was not reached for some biomarkers. In arm A, the local response was significantly higher (p = 0.003) and PINP could be identified as a predictor for survivors (OR 0.968, 95%CI 0.938–0.999, p = 0.043). BAP (OR 0.974, 95%CI 0.950–0.998, p = 0.034) and PINP (OR 1.025, 95%CI 1.001–1.049, p = 0.044) were related with an avoidance of SRE.\n\nABSTRACT.CONCLUSIONS:\nIn this group of patients with spinal bone metastases, we were able to show that patients with guided resistance training of the paravertebral muscles can influence BTM. PYD and CTX-I decreased significantly in arm A. PINP can be considered as a complementary tool for prediction of local response, and PINP as well as BAP for avoidance of SRE.\n\nABSTRACT.TRIAL REGISTRATION:\nClinical trial identifier NCT 01409720. August 2, 2011.\n\nBODY.BACKGROUND:\nSpinal bone metastases represent the most frequent site of skeletal metastasis [1], and radiotherapy (RT) is the most common treatment option of bone metastases in an advanced tumour disease [2]. As a result of the alteration in bone remodeling activity in patients with bone metastases, various markers of bone formation or resorption have been investigated as a measurement of activity of skeletal metastases. Balance between bone resorption and bone formation is required for maintenance of bone metabolism, and can be reflected by bone turnover markers (BTM). The usefulness of BTM as a tool for the diagnosis of bone metastases in many types of cancers has been investigated previously [3]. Previous studies have demonstrated that some BTM can indicate the existence of bone metastases [4], and have analyzed their relationship with clinical outcomes [5–9]. The two most clinically relevant markers of bone turnover in patients with skeletal metastases are bone-specific alkaline phosphatase (BAP) and N-terminal telopeptide of collagen type I (NTX). Total amino-terminal propeptide of type I collagen (PINP) and BAP are markers of bone formation; BAP has a linear relationship with osteoblast and osteoblastic precursor activity. NTX is a breakdown product of type I collagen produced by various proteolytic enzymes during bone resorption and dissolution of the organic bone matrix. Additionally, pyridinium cross-links pyridinoline (PYD) and desoxy-pyridinoline (DPD) are well-characterized markers for bone resorption. C-terminal cross-linking telopeptide of type I collagen (CTX-I) can be considered a complementary tool for prediction of clinical outcome as a marker of resorption. At the present time, although biochemical markers of bone turnover have shown some utility in clinical trials by predicting clinical outcomes such as death or development of SREs, they are not routinely used in clinical practice. Questions remain as to how clinicians should best use these markers to select and time appropriate treatments among patients with bone metastases. The use of these markers may, in the future, better allow physicians to selectively treat patients with bone metastases. In our recent work, we could show the feasibility of resistance training in patients with spinal bone metastases under RT [10]. Importantly, we demonstrated that the bone density in metastases of the resistance training arm was significantly higher than in the control arm after 3 months. Therefore, we hypothesized that resistance training concomitant to RT could influence bone metabolism, and would be reflected by BTM. The aim of this randomized trial was to compare the effect of resistance training concomitant to RT versus RT only on BTM, such as BAP, PINP, CTX-I, PYD, DPD, and NTX in patients with spinal bone metastases. Secondly, we evaluated an association of these markers as predicted factors for local response, prevention of SRE, and number of metastases.\n\nBODY.METHODS.SETTINGS AND PATIENTS:\nThis is a randomized, controlled, two-armed intervention trial. A block randomization approach with block size 6 was used to ensure that the two intervention groups were balanced. After the baseline measurements, the patients with stable bone metastases were assigned to the respective treatment groups on a 1:1 basis according to the randomization list. Arm A (intervention group, resistance training) and arm B (control group, passive physical therapy) each consisted of 30 patients. The blood and urine parameters were measured before start of RT (t0) (day of the first fraction), and after three months (t2) on an empty stomach. The primary endpoint was to compare BTM after 3 months in patients treated with resistance training concomitant to RT versus RT only in spinal bone metastases. Secondary endpoint was to evaluate predictive bone markers for local response, prevention of SRE, and number of metastases. Local response of metastasis was assessed on the basis of computed tomography. Positive local response was defined as complete or partial re-calcification on the basis of computed tomography observation at 3 months after RT. The definition of SRE was the first of any of the following events: pathological fractures, severe pain (increase of more than 2 points according to numeric rating scale), hypercalcaemia, and spinal cord compression. Number of metastases was classified in 1 or >1 (solitary vs. multiple). The data of the patient records were collected by the authors. Patient characteristics are shown in Table 1.Table 1Patient characteristics at baselineIntervention group (n = 30)Control group (n = 30)\nn\n%\nn\n%Age (years)Mean (SD)61.3 +/− 10.164.1 +/− 10.9GenderMale1446.71963.3Female1653.31136.7Karnofsky-index (median, range)80 (70–100)80 (70–100)Primary siteLung cancer129.2826.6Breast cancer516.7620.1Prostate cancer516.7930.1Melanoma13.313.3Renal cancer13.326.7Other620.1413.4Localization metastasesThoracic1756.71446.7Lumbar930.01343.3Thoracic and lumbar26.726.7Sacrum26.713.3Number metastasesMean (range)1.4 (2–4)1.7 (1–5)Solitary2273.31860.0Multiple826.71240.0Type of metastasesosteoblast930.01033.3osteolytic2170.02066.7Size of metastasisMean (SD)318.6 +/− 230.0380.7 +/− 193.6Distant metastases at baselineVisceral1240.0516.7brain310.0310.0lung723.3413.3tissue826.7620.0Hormonotherapy1033.31653.3Immunotherapy723.3516.7Chemotherapy2583.32066.7Previous SRE930.01343.3Abbreviation: SD standard deviation Inclusion criteria were an age of 18 to 80 years, a Karnofsky performance score [11] ≥ 70, written consent to participate, and already initiated bisphosphonate therapy. Patients were excluded if they presented with concomitant pathologies that could interfere in the evaluation of bone turnover markers, such as bone metabolic disorders, Paget`s disease of bone, hyperparathyroidism, thyroid abnormalities, abnormal intestinal absorption, or hepatic or renal dysfunction. In all cases, anticancer treatment could be changed as clinically indicated throughout the course of the study. The patients were subjected to a staging of their vertebral column within the context of the computed tomography (CT) designed to plan the radiation schedule prior to enrolment into the trial. In this examination metastases were classified as \"stable\" or \"unstable\". This was diagnosed independently by a specialist for radiology as well as by a specialist for orthopedic surgery. The specifications for an unstable vertebral body were tumor occupancy more than 60 % of the vertebral body, and pedicle destruction [12]. Only a metastasis classified by both specialists as \"stable\" was suggested eligible for inclusion. Patients with significant neurological or psychiatric disorders were excluded. The study was approved by the Heidelberg Ethics Committee (Nr. S-316/2011).\n\nBODY.METHODS.RADIOTHERAPY:\nRT was performed in the Radiooncology Department of the Heidelberg University Clinic. After virtual simulation was performed to plan the radiation schedule, RT was carried out over a dorsal photon field of the 6MV energy range. Primary target volume (PTV) covered the specific vertebral body affected as well as the ones immediately above and below. In Arm A, 24 patients (80 %) were treated with 10 × 3 Gy, three patients (10 %) with 14 × 2.5 Gy, and three patients (10 %) with 20 × 2 Gy. In Arm B the dose fractions for 28 patients (93.4 %) were 10 × 3 Gy, for one patient (3.3 %) 14 × 2.5 Gy, and for one patient (3.3 %) 20 × 2 Gy. The median individual dose in all patients was 3 Gy (range 2–3 Gy), the median total dose 30 Gy (range 20–35 Gy). The individual and total doses were decided separately for each individual patient, depending on the histology, the patient's general state of health, and on the current staging and the corresponding prognosis.\n\nBODY.METHODS.STUDY INTERVENTIONS:\nThe interventions commenced on the same day as RT and were performed on each day of RT treatment (Monday through Friday) over a 2-week period, independent of the number of fractions. During the 2-week RT period, the patients in the resistance training arm (Arm A) performed the exercises under the guidance of a physiotherapist. The patients were then instructed to practice the training in their homes three times a week and continued the resistance training themselves until the last investigation after three months, and conducted the documentation in form of a training diary. The resistance training lasted approx. 30 min, the passive physical therapy (Arm B) approx. 15 min. Since the site of the bone metastases differed from patient to patient, three different exercises were enacted to ensure an even isometric resistance training of the paravertebral muscles. Patients in the control arm (Arm B) received passive physical therapy in form of breathing exercises also for a period of 2 weeks. This was conducted so that these patients were not discouraged in comparison to the intervention arm, and for avoidance of a high drop-out rate. A detailed report of the intervention and its application has already been published [13].\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nBone marker values were presented in terms of mean and standard deviation (SD). The possible difference between arms at 3 months was calculated using ANCOVA with arm as factor and baseline value as covariate. Therefore as all surviving patients completed all surveys we assumed that 23 patients in Arm A and 24 patients in Arm B were eligible for the analysis. Multivariate binary logistic regression models were fitted to quantify the degree of association between potential predictors of markers at baseline according to local response (yes/no), prevention of SRE (yes/no), and number of metastases (1/more than one). Group had been included as a covariate in the analysis. Arm A with 23 survived patients was the reference. Level of significance was set to 0.05 for all tests. All statistical analyses were done using SAS software Version 9.4 (SAS Institute, Cary, NC, USA).\n\nBODY.METHODS.ANALYTIC METHODS:\nSamples were centrifuged at 3.500 rpm for 10 min after drawing, serum obtained and stored at −80°. First morning void of urine was collected, mixed and an aliquot of 10 ml stored at – 80 °C. Samples shipped on dry ice to the laboratory (Labor Limbach, Heidelberg, Germany) and again stored at −80 °C until analysis. Total aminoterminal propeptide of type I collagen (PINP; bone formation; interassay coefficient of variation [CV]: 2.7 %), C-terminal cross-linking telopeptide of type I collagen (CTX-I; bone resorption; CV: 3.1 %) and intact parathyroid hormone (iPTH; CV: 1.4 %) were measured by means of an automated electrochemiluminescence immunoassay (ECLIA; Modular Analytics E170, Roche Diagnostics, Penzberg, Germany). Bone-specific alkaline phosphatase (BAP; bone formation; CV: 5,2 %) was measured by means of a spectrophotometric immunoassay (IDS-ISYS Ostase BAP; Immunodiagnostic Systems Ltd [IDS Ltd], Boldon, Tyne & Wear, UK) on the fully automated immunoassay system (IDS-ISYS (Immunodiagnostic Systems Ltd [IDS Ltd], Boldon, Tyne & Wear, UK). Pyridinoline (PYD) and deoxypyridinoline (DPD; bone resorption; CV: 12.5 %) were assayed by high performance liquid chromatography (HPLC) [14, 15]. Analysis required first a sample extraction, hydrolysis and automated column-chromatographic pre-purification. To avoid any effect of different dilutions of urine, Pyr and Dpyr data are expressed against gram of creatinine. Cross-linked N-telopeptides of type I collagen (NTx; bone resorption; CV: 12.8 %) was determined with an commercially available ELISA (Osteomark Ntx; Wampole Laboratories, Princeton NJ, USA). All laboratory analyses were done in two batches after completion of the sample collection. To further reduce imprecision of measurement, all samples were analyzed utilizing one reagent lot. Tests and instruments were run strictly in accordance with the guidelines given by the manufacturer and were subject to continuous maintenance and service according to the laboratories standard operating procedures for good laboratory practice. Samples were thawed at the day of analysis at ambient temperature, mixed on a head-over-head mixer and centrifuged before measurement.\n\nBODY.RESULTS:\nFrom September 2011 to March 2013, consecutive 80 patients with a histologically confirmed cancer of any primary and spinal bone metastases of the thoracic or lumbar segments, or of the sacral region were considered in the Radiooncology Department of the Heidelberg University Clinic. Fifteen patients were excluded due to unstable metastases, and five patients declined to participate in the study. Sixty patients fulfilled the inclusion and were enrolled into the trial (Fig. 1). Arms were balanced at baseline without group differences, particularly number of metastases and tumor size (Table 1). Seven patients (23.3 %) died in arm A within the first 12 weeks following RT, six patients in arm B (20.0 %) died within 3 months. The mean follow-up was 3.3 months for both groups. All surviving patients completed all surveys. Mortality did not differ between groups.Fig. 1Flow of participants through the trial Mean change values of PYD and CTX-I were significantly lower at 3 months after RT (p = 0.035 and p = 0.043) in arm A. DPD showed a tendency with a lower mean change value, but not significant. No changes were seen between the arms in BAP, NTX, and PINP. Importantly, all markers decreased in both arms, except of PYD and CTX-I in arm B, although significance was not reached for some biomarkers (Table 2).Table 2Results of bone turnover markersArm AArm BDifference between armsbaseline, n=233 months, n=23baseline, n=243 months, n=24LS meansParameterReference valuemeanSDmeanSDmeanSDmeanSDDifference (95 % CI)\np-value*PYD160–280 μg/g Cr375.63206.20299.89173.88402.00199.01405.50187.32−90.92 (−175.19; −6.65)0.035DPD26–65 μg/g Cr67.3039.6451.2035.8186.1078.8572.8837.11−18.20 (−38.84; 2.45)0.082CTX-I<0.5484 ng/ml0.290.270.200.230.390.370.420.45−0.10 (−0.20; −0.003))0.043BAP6–15 μg/l56.8992.3131.4663.3144.1747.3236.5237.58−12.10 (−31.51; 7.31)0.215NTX5.4–24.2 nmol/l19.097.2117.427.9821.429.3620.389.81−0.87 (−3.84; 2.10)0.556PINP15–59 μg/l67.5440.6949.5041.4387.9651.9866.7739.18−6.94 (−26.81; 12.93)0.485*Results of ANCOVAThis table shows the results of bone turnover markers of both groups at baseline and 3 months after RT. Differences are presented within and between groupsAbbreviation: LS means least square means In arm A, the local response was significantly higher [73.9 % (n = 17) vs. 25 % (n = 6)] (p = 0.003). At first, PINP could be identified as a predictor of local response (p = 0.043). BAP (p = 0.034) and PINP (p = 0.044) could be identified as a predictor for avoidance of SRE. No marker could be detected for solitary metastasis (Table 3).Table 3Results of multivariate binary logistic regression analysis of bone markersLocal response (no local response)OR95 % CI (OR)\np-value Arm (A – reference)0.0330.004 – 0.3110.003 PYD1.0000.992 – 1.0080.986 DPD1.0230.974 – 1.0740.371 CTX-I10.5500.003 – >1000.569 BAP1.0110.996 – 1.0250.142 NTX0.8700.688 – 1.1010.245 PINP0.9680.938 – 0.9990.043Prevention of SRE (SRE = 0)OR95 % CI (OR)\np-value Arm (A – reference)3.3020.877 – 12.4310.077 PYD0.9980.994 – 1.0020.373 DPD1.0060.982 – 1.0310.633 CTX-I0.3230.001 – 81.3360.689 BAP0.9740.950 – 0.9980.034 NTX0.9880.861 – 1.1340.865 PINP1.0251.001 – 1.0490.044Solitary metastasis (n = 1)OR95 % CI (OR)\np-value Arm (A – reference)1.6920.477 – 6.0070.416 PYD1.0010.997 – 1.0050.512 DPD1.0040.980 – 1.0290.761 CTX-I0.3590.001 – >1000.723 BAP0.9970.985 – 1.0090.592 NTX1.0830.939 – 1.2490.275 PINP0.9980.981 – 1.0160.829Abbreviation: SRE skeletal-related events\n\nBODY.DISCUSSION:\nBone metastases are a very frequent secondary diagnosis associated with an advanced tumor disease, with the vertebral column being the most frequent localization [2, 10]. The usefulness of BTM as tool for the diagnosis of bone metastases in many types of cancers has been investigated previously [3]. Many studies have analyzed their relationship with clinical outcomes [7, 16] as well as their clinical importance [17, 18]. However, there is still no concensus among these studies as to which BTM is the ideal marker. In the current work, all BTM in arm A decreased after 3 months, especially the mean change values of PYD and CTX-I were significantly lower at 3 months after RT due to resistance training. BTM in arm B showed also decreased values after 3 months except of PYD and CTX-I, but not so distinctive as in arm A. Importantly, local response as re-calcification in metastasis was improved in arm A due to resistance training. In our recent work, we could show that bone density was significantly increased in metastasis 3 months after start of resistance training concomitant to RT [19]. This factor may influence the BTM and was demonstrated in our results. Therefore, PINP could be detected as a strong marker for bone formation after combined treatment with resistance training concomitant to RT. Determination of CTX-I is recommended for monitoring the efficacy of antiresorptive therapy. Patients with renal cell carcinoma who died or progressed had higher baseline B-CTX levels and those who experienced SRE during follow-up showed high BAP levels [20]. However, in our results we could not found any useful data in normal/abnormal values of BTM. A multicenter study found that increased values of BAP and NTX were associated with increased risk of SRE, and disease progression in patients with breast cancer, prostate cancer, and other solid tumors, treated with bisphosphonates [21]. These markers of bone turnover have been used clinically to predict the risk of SREs and disease outcomes. According our results, we could identify BAP and PINP for avoidance of SRE. In addition, biochemical markers of bone turnover may prove useful in the monitoring of patients on bisphosphonate treatment for bone metastases. One review [22] of 121 patients with skeletal metastases from variety of solid tumors revealed that mean values of NTX were consistently elevated in patients experiencing SREs compared with those who did not. An additional study [23] showed in 441 patients that patients with high NTX or BAP levels had a greater incidence of SREs compared with patients with low levels of NTX or BAP. Patients with increased NTX or BAP at baseline had an increased risk for SRE, shorter time to first event, disease progression and death. As NTX levels have been shown to correlate with response to bisphosphonate treatment. In our data, we could not show any correlation of NTX to local response, SRE, and number of metastases, but we were able to confirm the relation to BAP with prevention of SRE. Zoledronic acid normalizes or maintains normal NTX levels in most patients with bone metastases. All of our participants were treated with bisphosphonates. Our data presented no differences between arms of NTX. However, a PINP could be identified as a predictor for local response and avoidance of SRE. In this novel study, our results showed that resistance training concomitant to RT can even enhance an effect on BTM. Since all patients were in advanced stages of their cancer, 40 % of the patients in either group were lost to follow-up due to progressive disease and subsequently death. Further limitations of the study were the relatively small sample size, the variety of primary tumors and patient conditions, and the exclusion of patients presenting with cervical spine metastases. Among the strengths of our novel and original study were the randomized design and the very first presentation of bone turnover markers in combined treatment of resistance training concomitant to RT in patients with spinal bone metastases.\n\nBODY.CONCLUSION:\nIn this group of patients with spinal bone metastases, we were able to show that patients with guided resistance training of the paravertebral muscles can influence BTM. PYD and CTX-I decreased significantly in arm A. PINP can be considered as a complementary tool for prediction of local response, and PINP as well as BAP for avoidance of SRE. More studies in larger groups of patients are necessary for further confirmatory research.\n\nBODY.ETHICS APPROVAL:\nThe study was approved by the Heidelberg Ethics Committee (Nr. S-316/2011).\n\nBODY.CONSENT FOR PUBLICATION:\nNot applicable.\n\nBODY.AVAILABILITY OF DATA AND MATERIALS:\nThe dataset supporting the conclusions of this article is included within the article\n\n**Question:** Compared to passive physical therapy what was the result of resistance training dyrung radiation therapy on pyridinoline?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
486
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Rates of virological failure in patients treated in a home-based versus a facility-based HIV-care model in Jinja, southeast Uganda: a cluster-randomised equivalence trial\n\n ABSTRACT.SUMMARY.BACKGROUND:\nIdentification of new ways to increase access to antiretroviral therapy in Africa is an urgent priority. We assessed whether home-based HIV care was as effective as was facility-based care.\n\nABSTRACT.SUMMARY.METHODS:\nWe undertook a cluster-randomised equivalence trial in Jinja, Uganda. 44 geographical areas in nine strata, defined according to ratio of urban and rural participants and distance from the clinic, were randomised to home-based or facility-based care by drawing sealed cards from a box. The trial was integrated into normal service delivery. All patients with WHO stage IV or late stage III disease or CD4-cell counts fewer than 200 cells per μL who started antiretroviral therapy between Feb 15, 2005, and Dec 19, 2006, were eligible, apart from those living on islands. Follow-up continued until Jan 31, 2009. The primary endpoint was virological failure, defined as RNA more than 500 copies per mL after 6 months of treatment. The margin of equivalence was 9% (equivalence limits 0·69–1·45). Analyses were by intention to treat and adjusted for baseline CD4-cell count and study stratum. This trial is registered at http://isrctn.org, number ISRCTN 17184129.\n\nABSTRACT.SUMMARY.FINDINGS:\n859 patients (22 clusters) were randomly assigned to home and 594 (22 clusters) to facility care. During the first year, 93 (11%) receiving home care and 66 (11%) receiving facility care died, 29 (3%) receiving home and 36 (6%) receiving facility care withdrew, and 8 (1%) receiving home and 9 (2%) receiving facility care were lost to follow-up. 117 of 729 (16%) in home care had virological failure versus 80 of 483 (17%) in facility care: rates per 100 person-years were 8·19 (95% CI 6·84–9·82) for home and 8·67 (6·96–10·79) for facility care (rate ratio [RR] 1·04, 0·78–1·40; equivalence shown). Two patients from each group were immediately lost to follow-up. Mortality rates were similar between groups (0·95 [0·71–1·28]). 97 of 857 (11%) patients in home and 75 of 592 (13%) in facility care were admitted at least once (0·91, 0·64–1·28).\n\nABSTRACT.SUMMARY.INTERPRETATION:\nThis home-based HIV-care strategy is as effective as is a clinic-based strategy, and therefore could enable improved and equitable access to HIV treatment, especially in areas with poor infrastructure and access to clinic care.\n\nABSTRACT.SUMMARY.FUNDING:\nUS Centers for Disease Control and Prevention and UK Medical Research Council.\n\nBODY.INTRODUCTION:\nAntiretroviral drug therapy has been scaled up rapidly in Africa, and is now given to more than 2 million people.1 A global commitment has been made to provide universal coverage,2 but another 5 million people, mostly living in rural and semiurban areas, are estimated to need such treatment. Achievement of high coverage in these populations will be a challenge. Two major barriers to increasing coverage exist—a severe shortage of clinically qualified staff, which has reached crisis point in most of Africa,3 and difficulty for patients in accessing clinics because of high costs and poor availability of transport and low-cash incomes.4,5 WHO proposes decentralised antiretroviral therapy delivery,6,7 and so far services for such therapy have been provided through nurse-led centres with simplified protocols in several settings, including in Malawi,8,9 Zambia,10 Mozambique,11 Botswana,12 and South Africa.13 Good patient outcomes have been reported8,10 from short-term assessments done in some sites, but interpretation of this evidence is difficult because of poor retention rates.14 Furthermore, nursing staff as well as doctors are in very short supply3,15 and care needs to be delegated to non-clinical workers, although evidence for use of non-clinical workers in HIV care is scarce. In Tororo, Uganda, a home-based programme16,17 with lay workers has achieved good outcomes, but it consisted of home visits made every week with good access to clinical staff when needed—a model that would be difficult to scale up. No direct comparisons of hospital-based HIV care versus any form of decentralised HIV care have been done in Africa. We assessed home-based HIV care, with lay workers delivering antiretroviral therapy and monitoring patients, versus facility-based HIV care.\n\nBODY.METHODS.STUDY SETTING AND PATIENTS:\nWe undertook a trial based at the AIDS Support Organisation (TASO) clinic in Jinja district, southeast Uganda.18 TASO is a large non-governmental organisation with 11 centres in the country, offering counselling and social and clinical services to people with HIV. The Jinja district and surrounding area is poor, with inhabitants on low-cash incomes.18 TASO clinic serves a predominantly rural and semiurban population from a radius of about 100 km. Most TASO clients are subsistence farmers, and very few work in the formal sector earning wages. In accordance with guidelines from the Ugandan Ministry of Health, people with HIV were eligible to start antiretroviral therapy if they were assessed to be at WHO stage IV or late stage III disease, or if they had a CD4-cell count of fewer than 200 cells per μL. Eligible patients were prepared for therapy by TASO staff during three visits to clinic, which were usually spread over 4 weeks. Information and counselling were provided both in groups and in one-to-one sessions. Participants were given drugs for 28 days of treatment and issued with a pill box. A buffer supply for 2 days was provided. Patients were also strongly encouraged to identify a so-called medicine companion to provide support and reminders. Medicine companions were given information by TASO about the basic principles of antiretroviral therapy and adherence. All TASO patients older than 18 years who were starting on antiretroviral therapy for the first time were invited to join the trial, apart from those living on islands, which were about 100 km away and where provision of home-based care was not possible. All patients provided written informed consent. The trial protocol was approved by the Ugandan National Council of Science and Technology and the Institutional Review Boards of the Uganda Virus Research Institute, Centers for Disease Control and Prevention, and London School of Hygiene and Tropical Medicine. Patients were informed about their rights to refuse to join the trial or withdraw subsequently. Those who did were offered facility-based HIV care (including antiretroviral therapy) from TASO Jinja.\n\nBODY.METHODS.STUDY DESIGN:\nRecruitment began Feb 15, 2005, and ended Dec 19, 2006, and follow-up continued until Jan 31, 2009. Numbers of patients eligible for antiretroviral therapy were not known in advance—participants were identified after they were tested for CD4-cell counts and clinically assessed. The catchment area was divided into nine strata according to ratio of urban and rural participants and approximate distance from a central point to the TASO Jinja clinic. In every stratum, an even number of clusters (geographical areas) were defined for randomisation along subdistrict boundaries, or, in the case of a few large subdistricts, by known barriers within the subdistrict. Clusters in every stratum had a similar estimated number of people with HIV who were registered at TASO Jinja. Distribution of strata and clusters was as follows: (1) four clusters in urban areas or near the TASO Jinja facility; (2) eight in periurban intermediate distance; (3) eight in rural and far; (4) four in Kamuli district; (5) four in Mukono district near; (6) six in Mukono district far; (7) six in Mayuge district; (8) two in Iganga district near; and (9) two in Iganga district far. Strata and clusters were devised by two people with knowledge of the area (one TASO staff member and one researcher) and cross-checked independently by two other people on two separate occasions. For all patients, antiretroviral therapy was started at the TASO Jinja clinic, and thereafter patients received care according to the treatment to which their residential area had been assigned. After giving consent, patients were enrolled into the study by research staff, and their addresses were confirmed from TASO records. At every clinic visit, research staff interviewed participants in privacy in a separate building soon after their arrival and before they saw TASO staff.19\n\nBODY.METHODS.RANDOMISATION:\nClusters in each strata were allocated to either home-based or facility-based care by drawing cards from a concealed box. The cards were sealed in advance and labelled with the stratum number by the trial coordinator and TASO senior medical officer who organised the allocation event and placed the cards into the box for each stratum. Cards were drawn by two patient representatives, a TASO medical officer, TASO counsellor, and TASO field officer, each taking turns. This process was done in the presence of senior TASO staff, researchers, and local public health representatives.\n\nBODY.METHODS.MODELS OF CARE:\nThe trial was done in conditions similar to those of actual health services, with TASO staff responsible for service delivery.19 Numbers of counsellors, nurses, and laboratory and pharmacy staff in Jinja were similar to those at other TASO centres. The clinic had five medical officers but the number present usually varied between two and four, with some support from local part-time physicians during the trial. Most medical officers were newly qualified. Clinical staff were trained on antiretroviral therapy and supported by a senior medical officer. For the home-based group, trained field officers travelling on motorcycles visited patients at home every month to deliver drugs, monitor participants with a checklist that included signs and symptoms of drug toxicity or disease progression, and provide adherence support. Most field officers had degree qualifications or college diplomas and underwent 4 weeks of intensive training at the start of the study and yearly refresher courses thereafter about the principles of antiretroviral therapy and adherence support. They were supported at the TASO clinic by counsellors and medical officers. Field officers referred patients to a physician or counsellor at the TASO clinic when they judged referral to be necessary. They had mobile phones and could contact physicians when unsure about referral. At the end of every day, a medical officer reviewed the notes made by field officers and, when needed, asked officers to return to the patient's home to refer them. Patients who were not at home for their monthly appointment were visited again—usually the next day. If they were absent again, fieldworkers left a message for them to come to the clinic. All patients were invited to the clinic for routine reviews by a medical officer and a counsellor at 2 and 6 months after starting therapy and every 6 months thereafter. Drugs were not dispensed during clinic visits for those allocated to home-based case. Before antiretroviral therapy started, TASO offered free voluntary counselling and testing in the home to household members of participants. This offer was repeated during home visits for drug delivery for those who were absent previously. In the facility-based group, patients obtained drugs every month from the clinic and had routine reviews with a medical officer and counsellor that were scheduled at 2 and 3 months after start of treatment and every 3 months thereafter. Apart from scheduled reviews, patients were assessed during clinic visits by a nurse and referred to a doctor when necessary. When an appointment was missed, patients were followed up at home by a field officer (if patients had given permission for home visits), usually after 2–3 days, and reminded to attend clinic. Participants were also given vouchers for their household for free voluntary counselling and testing at TASO Jinja. Patients in both groups were asked to come to the clinic any time that they felt unwell. They were also given a telephone number to call for advice. In exceptional cases, and when TASO resources allowed, home care was provided by a team, including a physician, to patients who were bedridden. No financial or other incentives were provided to patients or staff and TASO clinical management procedures were identical for trial and non-trial participants.\n\nBODY.METHODS.PROCEDURES:\nIndependent research staff assessed adherence.19 Patients in both groups were interviewed during routine clinical and counselling visits at 2 months and 6 months after starting therapy and then every 6 months. Questionnaires were translated into the local language, Luganda, and then back into English by an independent person, and cross-checked by another researcher who was not involved with the trial. Clinical data were transcribed from patient notes. A change to a second-line regimen was decided by a TASO case conference, consisting of physicians and counsellors, and was made when a patient had one of the following criteria: (1) new or recurrent WHO clinical stage IV or advanced stage III disease; (2) clinical deterioration (eg, weight loss) and two or more consecutive CD4-cell counts less than baseline, or a fall to 50% less than peak CD4-cell count attained after the start of antiretroviral therapy; or (3) CD4-cell counts persistently fewer than 100 cells per μL. Survival status was established through home follow-ups or hospital records, dependent on where deaths took place. We established the status of participants who withdrew from TASO records. CD4-cell counts were monitored by TASO staff every 6 months for all patients as part of their clinical care. CD4-positive cells were measured with TriTEST reagents (Becton-Dickenson, Franklin Lakes, NJ, USA), according to an inhouse dual-platform protocol and MultiSET and Attractors software (version 2.2) with a FACScan flow cytometer (Becton-Dickinson, Franklin Lakes, NJ, USA). Additional blood was taken to measure plasma viral load, but this testing was for research reasons and done in batches later. Plasma was separated within 2 h and stored immediately at −80°C. HIV-1 RNA was tested with the VERSANT RNA 3.0 (Bayer, Bayer HealthCare, NY, USA) assay (with a lower limit of detection of 50 copies per mL) for baseline samples, and the Amplicor MONITOR 1.5 (Roche, Roche Molecular Systems, NJ, USA) for other samples (400 per copies per mL). After we established close correlation between results of the two assays, the Amplicor assay was used to keep costs to a minimum. Our economic analysis took a societal perspective and included recurrent and capital costs incurred by the provider, transport and other related costs, and income lost by patients while accessing care. We reported all costs in 2008 US$; the mean exchange rate from 2005 to 2008 was 1732 Ugandan shillings to $1. Cost data and all data for care provided by TASO were obtained from TASO accounts. We used three steps to allocate costs. First, we established the proportion of all TASO clients who were receiving antiretroviral therapy. Second, we calculated the percentage of TASO clients on therapy who entered the trial. Both percentages changed over time, rising initially as numbers of patients who were put on therapy increased, and then falling when recruitment stopped. To capture this dynamic situation, we gathered and aggregated monthly cost data every 6 months, and converted data to US$ with the prevailing exchange rate, with adjustment for inflation. Third, we allocated costs to facility and home groups. When possible, we used actual service data—eg, information about numbers of doctor visits was used to allocate staff time. We assigned antiretroviral therapy costs proportionally by patient numbers in both groups for that period. Drug prices included purchase cost, insurance, and freight to Uganda and were adjusted to account for substantial price reductions that occurred early in the project. We established costs incurred by patients through a questionnaire. Health-services costs consisted of: staff costs (doctors, field officers, cousellors, and other staff), transport (motorcycle and vehicle costs of fuel and maintenance, and other transport costs); all drugs; laboratory and clinical expenses (radiograph, ultrasound, and laboratory and CD4 tests); sensitisation (AIDS education via radio, other media, and drama); training, teambuilding, and workshops; utilities (electricity, telephone, postage, and security), supervision and overheads (stationery, repairs, overheads, and supervision costs), and capital costs (buildings, furniture, vehicles, equipment, and inventory). Buildings depreciated over 50 years and other elements 5 years (eg, The AIDS Support Organisation practice). Patient costs consisted of: cost of transport (including transport of medicine companion), childcare, and lunches, if applicable, median weighted by proportion ($2·88 for women and $3·46 for men); and lost work time, estimated 1 day for clinic visits and 0·5 days for home visits, valued at Uganda mean per head gross domestic product from 2005–08 (World Bank data) for 300 working days per year. The primary endpoint was rate of virological failure, defined as time (starting from 6 months) to a plasma RNA viral load of more than 500 copies per mL. The secondary outcome measures were time to either detectable plasma viral load of more than 500 copies per mL at any visit from 12 months onwards in patients with viral loads of fewer than 500 copies per mL at 6 months, or an increase of 1000 copies per mL between two consecutive tests in those not achieving a viral load of fewer than 500 copies per mL at 6 months. Other secondary outcomes were all-cause mortality; virological failure as defined in the primary outcome or death; time to first admission; death, admission, or change to second-line antiretroviral therapy; outpatient attendance; adherence during the previous 28 days (measured with a standardised questionnaire); and costs incurred by the health service and patients.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nWe designed the study as an equivalence trial. Virological failure time was taken as halfway between the last measure of RNA of 500 copies per mL or fewer and the first of more than 500 copies per mL. Testing was repeated in patients who had viral loads between 500 and 1000 copies per mL to exclude the possibility of small transient increases. We assumed that in one group the rate of virological failure during follow-up would be about 20%,20–22 and that the other group could be regarded as equivalent if the rate of virological failure did not exceed 20% by more than 9%—ie, 29% or less. Thus, the upper limit of our equivalence interval was 29/20 or 1·45, and by symmetry the lower limit was 20/29 or 0·69. A sample size of 20 clusters per group with a total of 1200 participants gave more than 95% power to show equivalence, on the assumption of a between-cluster coefficient of variation of 0·2. Analysis was by intention to treat, in which all participants were regarded as randomly assigned to the group corresponding to the cluster in which they lived. Analyses were done for the individual by fitting generalised linear mixed models with a log-link and poisson distribution, with every patient contributing an outcome of 1 if they had virological failure and 0 if they did not. The model had fixed terms for study regions, baseline CD4-cell counts (categorised as a four-level factor with counts of 0–49, 50–99, 100–149, and 150 or more cells per μL), and study groups, with the log of exposure time included as an offset variable, and a random term for study cluster. The model was fitted with the assumption that the random cluster effects followed a γ distribution. For the primary endpoint, exposure time was calculated from the 6-month visit to midway between the last date on which the patient did not have virological failure and the date of virological failure. For other endpoints, exposure time was calculated from enrolment. Those who withdrew or were lost to follow-up before 12 months were excluded from the primary endpoint analysis, and for other endpoints they were censored on the last date seen.\n\nBODY.METHODS.ROLE OF THE FUNDING SOURCE:\nSponsor staff had a role in the study design, data collection, data analysis, data interpretation, and writing of the report. The corresponding author had full access to the data and had final responsibility for the decision to submit for publication.\n\nBODY.RESULTS:\nFigure 1 shows the trial profile. The two groups were well balanced according to baseline characteristics apart from CD4-cell count, which was lower in the home-based than in the facility-based group (table 1). The median cluster size for home-based care was 36 people (range 6–84) and for facility-based care was 25 (2–65). Overall, 1403 patients (97%) were taking co-trimoxazole prophylaxis and 101 (7%) were being treated for tuberculosis. 119 patients withdrew during the course of the trial. Their status at the end of the trial was: three (3%, one from the facility and two from the home group) had died, 98 (82%, 48 facility and 50 home) were receiving antiretroviral therapy, one (<1%, facility) was alive and not receiving antiretroviral therapy, and 17 (15%, eight home and nine facility) were no longer in contact with TASO. The median follow-up of survivors on home-based care was 28 months (IQR 18–35) and on facility-based care was 27 months (13–34). Table 2 shows rates of virological failure, death, and hospital admission by group. Figure 2 shows HIV-RNA virological suppression and survival over time by study group. Rates of detection of plasma viral loads of more than 500 copies per mL after a 6-month visit were much the same in both groups. Also similar were the composite rates of either plasma RNA viral loads of more than 500 copies per mL after a 6-month visit in those who had undetectable viral loads at 6 months, or an increase in plasma RNA viral load of 1000 copies per mL between two consecutive tests in those who had detectable viral loads at 6 months. 184 (24%) patients having home and 145 (27%) facility care either had virological failure, were lost to follow-up, or withdrew from the trial (adjusted rate ratio [RR] 0·88, 95% CI 0·70–1·10). Mortality rates were much the same in the two groups during the study (figure 2). Combined mortality rates per 100 person-years were 16·47 (95% CI 13·69–19·82) during the first 5 months after treatment started, 6·69 (4·94–9·05) for 6–11 months, 2·71 (1·92–3·84) for 12–23 months, and 0·97 (0·54–1·76) for 24 months and after. By the end of the study, 566 (66%) participants in the home group and 377 (63%) in the facility group were alive, receiving follow-up, and had undetectable plasma viral loads. Admission diagnoses were similar in both groups (table 3). 20 (13%) patients who were admitted died (15 on home and five on facility care) and eight (5%) worsened and requested discharge (six on home and two on facility care)—seven died subsequently. Table 4 shows frequency of outpatient attendance at clinic, number of presentations in which a new diagnosis was made, and new diagnoses by number and type. Distribution of diagnoses was similar between groups and more than half were infectious and parasitic disease. CD4-cell counts increased rapidly in both groups (figure 3). 748 (87%) participants in home care and 521 (88%) in facility care were tested for CD4-cell count at least once after starting treatment, with median intervals between baseline and final tests of 32 months (IQR 25–39) for home and 29 months (23–35) for facility. 608 (81%) in home and 419 (80%) in facility had CD4-cell counts of greater than 200 cells per μL at the final visit. Counts at this visit were lower than baseline in 32 (4%) of those in home compared with 29 (6%) in facility care. At routine clinical and counselling reviews, home participants reported complete adherence to therapy in the past 28 days in 3698 of 3951 (94%) visits compared with 2527 of 2768 (91%) visits made by facility participants (figure 4). Patients were too sick to be interviewed in a further 78 (2%) home-group and 39 (1%) facility-group visits. Only two patients, both in home-based care, refused to answer adherence questions—saying they were in a hurry to return home. 138 (16%) of patients in home care had a drug substitution at a median 9 months (IQR 2–24) versus 123 (21%) in facility care at 8 months (3–22) after treatment started. Most substitutions were because of adverse reactions to antiretroviral therapy (table 5). Only one person in home-based and two in facility-based care had their first-line treatment changed to second-line. Table 6 shows mean yearly health services cost per patient calculated during 4 years, (including capital and recurrent expenses, and those of the starting phase and subsequent years). A large proportion of the costs were for drugs and staff salaries. The main cause of excess expenditure for the facility-based group was the increased number of contacts with health staff—especially with nurses and medical officers. These costs outweighed those of transport for field officers in the home-based group. Patient costs (transport of patient and companion, lunches, child care, and time lost from work) were much higher for the facility-based than for the home-based group (table 6). During the first year, when many visits were needed to start antiretroviral therapy, median yearly costs incurred by every patient were higher in facility than in home (table 6). Much of this expense was for transport. After the first year, patient costs for the home-based group were fairly low but remained high for the facility-based group, showing the economic burden of monthly clinic visits. Overall, the median cost of a clinic visit was $2·30—about 13% of reported monthly cash incomes for men and 20% for women.\n\nBODY.DISCUSSION:\nWe have shown that a home-based HIV-care strategy with trained lay workers supporting drug delivery and monitoring patients was as effective as was a nurse-led and doctor-led clinic-based strategy for prevention of virological failure, mortality, and other adverse outcomes. For our primary endpoint of virological failure, the adjusted RR was contained between the pre-specified equivalence limits of 0·69 to 1·45. Results were similar for other endpoints. The home-based strategy did not result in higher costs for the health service. Moreover, home-based care was slightly cheaper than facility-based care by about $45 per patient per year, or 6% of the total cost. Costs incurred by patients to access care were much less for those in the home group than for those receiving facility-based care. We have identified a strategy to provide effective HIV care in the many settings in Africa in which clinical staff are scarce and patient access to clinics is difficult. Our findings were achieved in a standard resource-constrained health-service setting. Mortality rates in our facility-based group of about six deaths per 100 person-years and virological failure rates of nine per 100 person-years were better than or at least as good as were those reported from most other settings. Other researchers8,10,16,21,24–26 have reported mortality rates ranging from six to more than 15 deaths per 100 person-years and virological failure rates20–22,27,28 from 15% to more than 40% for 12–24 months. Thus, findings from our home-based care strategy were compared with a well functioning facility-based model and identified to be equivalent. Mortality rates in developed countries are about two deaths per 100 person-years27 and most of the increased mortality in Africa takes place during the first year of follow-up,29 as we identified. This mortality rate could be reduced through starting of antiretroviral therapy earlier than it is at present, but how people with HIV infection who need treatment can be identified early and encouraged to seek care is less clear, and needs to be investigated. Our study shows that community-based approaches would be important. We transferred care from the clinic to trained lay workers visiting homes of patients. The costs of the home visits were offset by the savings from reduced attendence at clinic—thus, 75% fewer clinic visits were made by patients in the home-based group, and 50% fewer consultations with a doctor took place when a new clinical disorder was recorded. We recorded no negative effect on survival, plasma viral load, or other outcomes. Patients had regular counselling and adherence support, especially in the home group in which support was personalised and often provided by the same individual. This support could have had a major positive effect on outcomes. Such an approach should be achievable throughout Africa since counsellors and other support staff are more easily available and rapidly trained than are clinical staff and incur much less expense for health services. A large randomised trial30 at two sites in Uganda and one in Zimbabwe recorded health-service costs of $846 (2008 exchange rate) for a model of laboratory and clinical monitoring at a health facility, which is similar to $793 in our home group and $838 in our facility group. Costs of access to care are a major burden for most African people, especially for those living in rural areas, because cash incomes are very low. In our study, one clinic visit was 15–20% of monthly earnings for most people. In Africa, high travel costs relative to income are major determinants of poor access to care, late presentation, poor adherence, and low retention of people in antiretroviral-therapy programmes.4,14,31 Our study shows that home-based care could substantially reduce costs for patients and this outcome might have a major beneficial effect on their long-term adherence and retention. In our study, TASO changed treatment to second-line therapy for three people only, which was substantially fewer than those who had falls in CD4-cell counts to less than their baseline or virological failure, showing the major differences in the diagnostic accuracy of clinical and laboratory assessments. When to change HIV treatment is a dilemma in many settings in Africa because of poor availability and high costs of second-line regimens and the absence of information about resistance to antiretroviral therapy—a situation that is unlikely to greatly change in the near future. We should, therefore, identify means to achieve the best possible adherence to extend the life of existing drugs. Our results suggest that community-based support of patients receiving antiretroviral therapy could lead to high adherence. Very few studies have been done in which models of care are randomly assigned because of strong preferences of some individuals for a specific method of care and the role of stigma, which might result from HIV status disclosure—eg, if a field worker from a known AIDS support organisation visits a patient in the community. We overcame these difficulties by developing a partnership with the service provider, the community, and with patients from the beginning when the research question was defined, and then held regular meetings with stakeholders to discuss difficulties and provide information. No monetary incentives were provided to either the service provider or patients. Only 41 (3%) of participants refused to join the trial or later withdrew and cited stigma as a reason. All received antiretrovirals from TASO or other providers. The importance and effects of stigma in the long term when patients have sustained improved health and, for example, resumed normal relationships, is unclear. However, we have shown that community-based HIV care is feasible and that stigma is probably not an impediment to increasing coverage in settings in which trust and good relations between service providers and the community are present. Our study could have been affected by selection bias, but numbers of refusals and withdrawals were low and almost identical in both groups. Most people who withdrew were alive at the end of the study—survival status was unknown for just 51 (4%) of participants. More were recruited in the home group than in the facility group but many more in the home group were screened, suggesting that this imbalance arose by chance. Median baseline CD4-cell count was also lower in the home group than in the facility group, but again this finding was probably attributable to chance (and was adjusted for in the analysis). These imbalances show the weakness of cluster-randomised trials32 in achievement of balance through randomisation, even in trials such as ours in which a large number of clusters were randomised. We have shown that home-based HIV care with antiretroviral therapy is an effective strategy, which relies less on clinical staff and hospital services than does facility-based care and provides large savings for patients. Such community-based strategies could enable improved and equitable access to HIV treatment—especially in areas in which clinical infrastructure is scarce and patient access to clinic-based care is poor.\n\n**Question:** Compared to Facility-based HIV-care strategy what was the result of Home-based HIV-care strategy on Mortality rates?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
488
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Rates of virological failure in patients treated in a home-based versus a facility-based HIV-care model in Jinja, southeast Uganda: a cluster-randomised equivalence trial\n\n ABSTRACT.SUMMARY.BACKGROUND:\nIdentification of new ways to increase access to antiretroviral therapy in Africa is an urgent priority. We assessed whether home-based HIV care was as effective as was facility-based care.\n\nABSTRACT.SUMMARY.METHODS:\nWe undertook a cluster-randomised equivalence trial in Jinja, Uganda. 44 geographical areas in nine strata, defined according to ratio of urban and rural participants and distance from the clinic, were randomised to home-based or facility-based care by drawing sealed cards from a box. The trial was integrated into normal service delivery. All patients with WHO stage IV or late stage III disease or CD4-cell counts fewer than 200 cells per μL who started antiretroviral therapy between Feb 15, 2005, and Dec 19, 2006, were eligible, apart from those living on islands. Follow-up continued until Jan 31, 2009. The primary endpoint was virological failure, defined as RNA more than 500 copies per mL after 6 months of treatment. The margin of equivalence was 9% (equivalence limits 0·69–1·45). Analyses were by intention to treat and adjusted for baseline CD4-cell count and study stratum. This trial is registered at http://isrctn.org, number ISRCTN 17184129.\n\nABSTRACT.SUMMARY.FINDINGS:\n859 patients (22 clusters) were randomly assigned to home and 594 (22 clusters) to facility care. During the first year, 93 (11%) receiving home care and 66 (11%) receiving facility care died, 29 (3%) receiving home and 36 (6%) receiving facility care withdrew, and 8 (1%) receiving home and 9 (2%) receiving facility care were lost to follow-up. 117 of 729 (16%) in home care had virological failure versus 80 of 483 (17%) in facility care: rates per 100 person-years were 8·19 (95% CI 6·84–9·82) for home and 8·67 (6·96–10·79) for facility care (rate ratio [RR] 1·04, 0·78–1·40; equivalence shown). Two patients from each group were immediately lost to follow-up. Mortality rates were similar between groups (0·95 [0·71–1·28]). 97 of 857 (11%) patients in home and 75 of 592 (13%) in facility care were admitted at least once (0·91, 0·64–1·28).\n\nABSTRACT.SUMMARY.INTERPRETATION:\nThis home-based HIV-care strategy is as effective as is a clinic-based strategy, and therefore could enable improved and equitable access to HIV treatment, especially in areas with poor infrastructure and access to clinic care.\n\nABSTRACT.SUMMARY.FUNDING:\nUS Centers for Disease Control and Prevention and UK Medical Research Council.\n\nBODY.INTRODUCTION:\nAntiretroviral drug therapy has been scaled up rapidly in Africa, and is now given to more than 2 million people.1 A global commitment has been made to provide universal coverage,2 but another 5 million people, mostly living in rural and semiurban areas, are estimated to need such treatment. Achievement of high coverage in these populations will be a challenge. Two major barriers to increasing coverage exist—a severe shortage of clinically qualified staff, which has reached crisis point in most of Africa,3 and difficulty for patients in accessing clinics because of high costs and poor availability of transport and low-cash incomes.4,5 WHO proposes decentralised antiretroviral therapy delivery,6,7 and so far services for such therapy have been provided through nurse-led centres with simplified protocols in several settings, including in Malawi,8,9 Zambia,10 Mozambique,11 Botswana,12 and South Africa.13 Good patient outcomes have been reported8,10 from short-term assessments done in some sites, but interpretation of this evidence is difficult because of poor retention rates.14 Furthermore, nursing staff as well as doctors are in very short supply3,15 and care needs to be delegated to non-clinical workers, although evidence for use of non-clinical workers in HIV care is scarce. In Tororo, Uganda, a home-based programme16,17 with lay workers has achieved good outcomes, but it consisted of home visits made every week with good access to clinical staff when needed—a model that would be difficult to scale up. No direct comparisons of hospital-based HIV care versus any form of decentralised HIV care have been done in Africa. We assessed home-based HIV care, with lay workers delivering antiretroviral therapy and monitoring patients, versus facility-based HIV care.\n\nBODY.METHODS.STUDY SETTING AND PATIENTS:\nWe undertook a trial based at the AIDS Support Organisation (TASO) clinic in Jinja district, southeast Uganda.18 TASO is a large non-governmental organisation with 11 centres in the country, offering counselling and social and clinical services to people with HIV. The Jinja district and surrounding area is poor, with inhabitants on low-cash incomes.18 TASO clinic serves a predominantly rural and semiurban population from a radius of about 100 km. Most TASO clients are subsistence farmers, and very few work in the formal sector earning wages. In accordance with guidelines from the Ugandan Ministry of Health, people with HIV were eligible to start antiretroviral therapy if they were assessed to be at WHO stage IV or late stage III disease, or if they had a CD4-cell count of fewer than 200 cells per μL. Eligible patients were prepared for therapy by TASO staff during three visits to clinic, which were usually spread over 4 weeks. Information and counselling were provided both in groups and in one-to-one sessions. Participants were given drugs for 28 days of treatment and issued with a pill box. A buffer supply for 2 days was provided. Patients were also strongly encouraged to identify a so-called medicine companion to provide support and reminders. Medicine companions were given information by TASO about the basic principles of antiretroviral therapy and adherence. All TASO patients older than 18 years who were starting on antiretroviral therapy for the first time were invited to join the trial, apart from those living on islands, which were about 100 km away and where provision of home-based care was not possible. All patients provided written informed consent. The trial protocol was approved by the Ugandan National Council of Science and Technology and the Institutional Review Boards of the Uganda Virus Research Institute, Centers for Disease Control and Prevention, and London School of Hygiene and Tropical Medicine. Patients were informed about their rights to refuse to join the trial or withdraw subsequently. Those who did were offered facility-based HIV care (including antiretroviral therapy) from TASO Jinja.\n\nBODY.METHODS.STUDY DESIGN:\nRecruitment began Feb 15, 2005, and ended Dec 19, 2006, and follow-up continued until Jan 31, 2009. Numbers of patients eligible for antiretroviral therapy were not known in advance—participants were identified after they were tested for CD4-cell counts and clinically assessed. The catchment area was divided into nine strata according to ratio of urban and rural participants and approximate distance from a central point to the TASO Jinja clinic. In every stratum, an even number of clusters (geographical areas) were defined for randomisation along subdistrict boundaries, or, in the case of a few large subdistricts, by known barriers within the subdistrict. Clusters in every stratum had a similar estimated number of people with HIV who were registered at TASO Jinja. Distribution of strata and clusters was as follows: (1) four clusters in urban areas or near the TASO Jinja facility; (2) eight in periurban intermediate distance; (3) eight in rural and far; (4) four in Kamuli district; (5) four in Mukono district near; (6) six in Mukono district far; (7) six in Mayuge district; (8) two in Iganga district near; and (9) two in Iganga district far. Strata and clusters were devised by two people with knowledge of the area (one TASO staff member and one researcher) and cross-checked independently by two other people on two separate occasions. For all patients, antiretroviral therapy was started at the TASO Jinja clinic, and thereafter patients received care according to the treatment to which their residential area had been assigned. After giving consent, patients were enrolled into the study by research staff, and their addresses were confirmed from TASO records. At every clinic visit, research staff interviewed participants in privacy in a separate building soon after their arrival and before they saw TASO staff.19\n\nBODY.METHODS.RANDOMISATION:\nClusters in each strata were allocated to either home-based or facility-based care by drawing cards from a concealed box. The cards were sealed in advance and labelled with the stratum number by the trial coordinator and TASO senior medical officer who organised the allocation event and placed the cards into the box for each stratum. Cards were drawn by two patient representatives, a TASO medical officer, TASO counsellor, and TASO field officer, each taking turns. This process was done in the presence of senior TASO staff, researchers, and local public health representatives.\n\nBODY.METHODS.MODELS OF CARE:\nThe trial was done in conditions similar to those of actual health services, with TASO staff responsible for service delivery.19 Numbers of counsellors, nurses, and laboratory and pharmacy staff in Jinja were similar to those at other TASO centres. The clinic had five medical officers but the number present usually varied between two and four, with some support from local part-time physicians during the trial. Most medical officers were newly qualified. Clinical staff were trained on antiretroviral therapy and supported by a senior medical officer. For the home-based group, trained field officers travelling on motorcycles visited patients at home every month to deliver drugs, monitor participants with a checklist that included signs and symptoms of drug toxicity or disease progression, and provide adherence support. Most field officers had degree qualifications or college diplomas and underwent 4 weeks of intensive training at the start of the study and yearly refresher courses thereafter about the principles of antiretroviral therapy and adherence support. They were supported at the TASO clinic by counsellors and medical officers. Field officers referred patients to a physician or counsellor at the TASO clinic when they judged referral to be necessary. They had mobile phones and could contact physicians when unsure about referral. At the end of every day, a medical officer reviewed the notes made by field officers and, when needed, asked officers to return to the patient's home to refer them. Patients who were not at home for their monthly appointment were visited again—usually the next day. If they were absent again, fieldworkers left a message for them to come to the clinic. All patients were invited to the clinic for routine reviews by a medical officer and a counsellor at 2 and 6 months after starting therapy and every 6 months thereafter. Drugs were not dispensed during clinic visits for those allocated to home-based case. Before antiretroviral therapy started, TASO offered free voluntary counselling and testing in the home to household members of participants. This offer was repeated during home visits for drug delivery for those who were absent previously. In the facility-based group, patients obtained drugs every month from the clinic and had routine reviews with a medical officer and counsellor that were scheduled at 2 and 3 months after start of treatment and every 3 months thereafter. Apart from scheduled reviews, patients were assessed during clinic visits by a nurse and referred to a doctor when necessary. When an appointment was missed, patients were followed up at home by a field officer (if patients had given permission for home visits), usually after 2–3 days, and reminded to attend clinic. Participants were also given vouchers for their household for free voluntary counselling and testing at TASO Jinja. Patients in both groups were asked to come to the clinic any time that they felt unwell. They were also given a telephone number to call for advice. In exceptional cases, and when TASO resources allowed, home care was provided by a team, including a physician, to patients who were bedridden. No financial or other incentives were provided to patients or staff and TASO clinical management procedures were identical for trial and non-trial participants.\n\nBODY.METHODS.PROCEDURES:\nIndependent research staff assessed adherence.19 Patients in both groups were interviewed during routine clinical and counselling visits at 2 months and 6 months after starting therapy and then every 6 months. Questionnaires were translated into the local language, Luganda, and then back into English by an independent person, and cross-checked by another researcher who was not involved with the trial. Clinical data were transcribed from patient notes. A change to a second-line regimen was decided by a TASO case conference, consisting of physicians and counsellors, and was made when a patient had one of the following criteria: (1) new or recurrent WHO clinical stage IV or advanced stage III disease; (2) clinical deterioration (eg, weight loss) and two or more consecutive CD4-cell counts less than baseline, or a fall to 50% less than peak CD4-cell count attained after the start of antiretroviral therapy; or (3) CD4-cell counts persistently fewer than 100 cells per μL. Survival status was established through home follow-ups or hospital records, dependent on where deaths took place. We established the status of participants who withdrew from TASO records. CD4-cell counts were monitored by TASO staff every 6 months for all patients as part of their clinical care. CD4-positive cells were measured with TriTEST reagents (Becton-Dickenson, Franklin Lakes, NJ, USA), according to an inhouse dual-platform protocol and MultiSET and Attractors software (version 2.2) with a FACScan flow cytometer (Becton-Dickinson, Franklin Lakes, NJ, USA). Additional blood was taken to measure plasma viral load, but this testing was for research reasons and done in batches later. Plasma was separated within 2 h and stored immediately at −80°C. HIV-1 RNA was tested with the VERSANT RNA 3.0 (Bayer, Bayer HealthCare, NY, USA) assay (with a lower limit of detection of 50 copies per mL) for baseline samples, and the Amplicor MONITOR 1.5 (Roche, Roche Molecular Systems, NJ, USA) for other samples (400 per copies per mL). After we established close correlation between results of the two assays, the Amplicor assay was used to keep costs to a minimum. Our economic analysis took a societal perspective and included recurrent and capital costs incurred by the provider, transport and other related costs, and income lost by patients while accessing care. We reported all costs in 2008 US$; the mean exchange rate from 2005 to 2008 was 1732 Ugandan shillings to $1. Cost data and all data for care provided by TASO were obtained from TASO accounts. We used three steps to allocate costs. First, we established the proportion of all TASO clients who were receiving antiretroviral therapy. Second, we calculated the percentage of TASO clients on therapy who entered the trial. Both percentages changed over time, rising initially as numbers of patients who were put on therapy increased, and then falling when recruitment stopped. To capture this dynamic situation, we gathered and aggregated monthly cost data every 6 months, and converted data to US$ with the prevailing exchange rate, with adjustment for inflation. Third, we allocated costs to facility and home groups. When possible, we used actual service data—eg, information about numbers of doctor visits was used to allocate staff time. We assigned antiretroviral therapy costs proportionally by patient numbers in both groups for that period. Drug prices included purchase cost, insurance, and freight to Uganda and were adjusted to account for substantial price reductions that occurred early in the project. We established costs incurred by patients through a questionnaire. Health-services costs consisted of: staff costs (doctors, field officers, cousellors, and other staff), transport (motorcycle and vehicle costs of fuel and maintenance, and other transport costs); all drugs; laboratory and clinical expenses (radiograph, ultrasound, and laboratory and CD4 tests); sensitisation (AIDS education via radio, other media, and drama); training, teambuilding, and workshops; utilities (electricity, telephone, postage, and security), supervision and overheads (stationery, repairs, overheads, and supervision costs), and capital costs (buildings, furniture, vehicles, equipment, and inventory). Buildings depreciated over 50 years and other elements 5 years (eg, The AIDS Support Organisation practice). Patient costs consisted of: cost of transport (including transport of medicine companion), childcare, and lunches, if applicable, median weighted by proportion ($2·88 for women and $3·46 for men); and lost work time, estimated 1 day for clinic visits and 0·5 days for home visits, valued at Uganda mean per head gross domestic product from 2005–08 (World Bank data) for 300 working days per year. The primary endpoint was rate of virological failure, defined as time (starting from 6 months) to a plasma RNA viral load of more than 500 copies per mL. The secondary outcome measures were time to either detectable plasma viral load of more than 500 copies per mL at any visit from 12 months onwards in patients with viral loads of fewer than 500 copies per mL at 6 months, or an increase of 1000 copies per mL between two consecutive tests in those not achieving a viral load of fewer than 500 copies per mL at 6 months. Other secondary outcomes were all-cause mortality; virological failure as defined in the primary outcome or death; time to first admission; death, admission, or change to second-line antiretroviral therapy; outpatient attendance; adherence during the previous 28 days (measured with a standardised questionnaire); and costs incurred by the health service and patients.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nWe designed the study as an equivalence trial. Virological failure time was taken as halfway between the last measure of RNA of 500 copies per mL or fewer and the first of more than 500 copies per mL. Testing was repeated in patients who had viral loads between 500 and 1000 copies per mL to exclude the possibility of small transient increases. We assumed that in one group the rate of virological failure during follow-up would be about 20%,20–22 and that the other group could be regarded as equivalent if the rate of virological failure did not exceed 20% by more than 9%—ie, 29% or less. Thus, the upper limit of our equivalence interval was 29/20 or 1·45, and by symmetry the lower limit was 20/29 or 0·69. A sample size of 20 clusters per group with a total of 1200 participants gave more than 95% power to show equivalence, on the assumption of a between-cluster coefficient of variation of 0·2. Analysis was by intention to treat, in which all participants were regarded as randomly assigned to the group corresponding to the cluster in which they lived. Analyses were done for the individual by fitting generalised linear mixed models with a log-link and poisson distribution, with every patient contributing an outcome of 1 if they had virological failure and 0 if they did not. The model had fixed terms for study regions, baseline CD4-cell counts (categorised as a four-level factor with counts of 0–49, 50–99, 100–149, and 150 or more cells per μL), and study groups, with the log of exposure time included as an offset variable, and a random term for study cluster. The model was fitted with the assumption that the random cluster effects followed a γ distribution. For the primary endpoint, exposure time was calculated from the 6-month visit to midway between the last date on which the patient did not have virological failure and the date of virological failure. For other endpoints, exposure time was calculated from enrolment. Those who withdrew or were lost to follow-up before 12 months were excluded from the primary endpoint analysis, and for other endpoints they were censored on the last date seen.\n\nBODY.METHODS.ROLE OF THE FUNDING SOURCE:\nSponsor staff had a role in the study design, data collection, data analysis, data interpretation, and writing of the report. The corresponding author had full access to the data and had final responsibility for the decision to submit for publication.\n\nBODY.RESULTS:\nFigure 1 shows the trial profile. The two groups were well balanced according to baseline characteristics apart from CD4-cell count, which was lower in the home-based than in the facility-based group (table 1). The median cluster size for home-based care was 36 people (range 6–84) and for facility-based care was 25 (2–65). Overall, 1403 patients (97%) were taking co-trimoxazole prophylaxis and 101 (7%) were being treated for tuberculosis. 119 patients withdrew during the course of the trial. Their status at the end of the trial was: three (3%, one from the facility and two from the home group) had died, 98 (82%, 48 facility and 50 home) were receiving antiretroviral therapy, one (<1%, facility) was alive and not receiving antiretroviral therapy, and 17 (15%, eight home and nine facility) were no longer in contact with TASO. The median follow-up of survivors on home-based care was 28 months (IQR 18–35) and on facility-based care was 27 months (13–34). Table 2 shows rates of virological failure, death, and hospital admission by group. Figure 2 shows HIV-RNA virological suppression and survival over time by study group. Rates of detection of plasma viral loads of more than 500 copies per mL after a 6-month visit were much the same in both groups. Also similar were the composite rates of either plasma RNA viral loads of more than 500 copies per mL after a 6-month visit in those who had undetectable viral loads at 6 months, or an increase in plasma RNA viral load of 1000 copies per mL between two consecutive tests in those who had detectable viral loads at 6 months. 184 (24%) patients having home and 145 (27%) facility care either had virological failure, were lost to follow-up, or withdrew from the trial (adjusted rate ratio [RR] 0·88, 95% CI 0·70–1·10). Mortality rates were much the same in the two groups during the study (figure 2). Combined mortality rates per 100 person-years were 16·47 (95% CI 13·69–19·82) during the first 5 months after treatment started, 6·69 (4·94–9·05) for 6–11 months, 2·71 (1·92–3·84) for 12–23 months, and 0·97 (0·54–1·76) for 24 months and after. By the end of the study, 566 (66%) participants in the home group and 377 (63%) in the facility group were alive, receiving follow-up, and had undetectable plasma viral loads. Admission diagnoses were similar in both groups (table 3). 20 (13%) patients who were admitted died (15 on home and five on facility care) and eight (5%) worsened and requested discharge (six on home and two on facility care)—seven died subsequently. Table 4 shows frequency of outpatient attendance at clinic, number of presentations in which a new diagnosis was made, and new diagnoses by number and type. Distribution of diagnoses was similar between groups and more than half were infectious and parasitic disease. CD4-cell counts increased rapidly in both groups (figure 3). 748 (87%) participants in home care and 521 (88%) in facility care were tested for CD4-cell count at least once after starting treatment, with median intervals between baseline and final tests of 32 months (IQR 25–39) for home and 29 months (23–35) for facility. 608 (81%) in home and 419 (80%) in facility had CD4-cell counts of greater than 200 cells per μL at the final visit. Counts at this visit were lower than baseline in 32 (4%) of those in home compared with 29 (6%) in facility care. At routine clinical and counselling reviews, home participants reported complete adherence to therapy in the past 28 days in 3698 of 3951 (94%) visits compared with 2527 of 2768 (91%) visits made by facility participants (figure 4). Patients were too sick to be interviewed in a further 78 (2%) home-group and 39 (1%) facility-group visits. Only two patients, both in home-based care, refused to answer adherence questions—saying they were in a hurry to return home. 138 (16%) of patients in home care had a drug substitution at a median 9 months (IQR 2–24) versus 123 (21%) in facility care at 8 months (3–22) after treatment started. Most substitutions were because of adverse reactions to antiretroviral therapy (table 5). Only one person in home-based and two in facility-based care had their first-line treatment changed to second-line. Table 6 shows mean yearly health services cost per patient calculated during 4 years, (including capital and recurrent expenses, and those of the starting phase and subsequent years). A large proportion of the costs were for drugs and staff salaries. The main cause of excess expenditure for the facility-based group was the increased number of contacts with health staff—especially with nurses and medical officers. These costs outweighed those of transport for field officers in the home-based group. Patient costs (transport of patient and companion, lunches, child care, and time lost from work) were much higher for the facility-based than for the home-based group (table 6). During the first year, when many visits were needed to start antiretroviral therapy, median yearly costs incurred by every patient were higher in facility than in home (table 6). Much of this expense was for transport. After the first year, patient costs for the home-based group were fairly low but remained high for the facility-based group, showing the economic burden of monthly clinic visits. Overall, the median cost of a clinic visit was $2·30—about 13% of reported monthly cash incomes for men and 20% for women.\n\nBODY.DISCUSSION:\nWe have shown that a home-based HIV-care strategy with trained lay workers supporting drug delivery and monitoring patients was as effective as was a nurse-led and doctor-led clinic-based strategy for prevention of virological failure, mortality, and other adverse outcomes. For our primary endpoint of virological failure, the adjusted RR was contained between the pre-specified equivalence limits of 0·69 to 1·45. Results were similar for other endpoints. The home-based strategy did not result in higher costs for the health service. Moreover, home-based care was slightly cheaper than facility-based care by about $45 per patient per year, or 6% of the total cost. Costs incurred by patients to access care were much less for those in the home group than for those receiving facility-based care. We have identified a strategy to provide effective HIV care in the many settings in Africa in which clinical staff are scarce and patient access to clinics is difficult. Our findings were achieved in a standard resource-constrained health-service setting. Mortality rates in our facility-based group of about six deaths per 100 person-years and virological failure rates of nine per 100 person-years were better than or at least as good as were those reported from most other settings. Other researchers8,10,16,21,24–26 have reported mortality rates ranging from six to more than 15 deaths per 100 person-years and virological failure rates20–22,27,28 from 15% to more than 40% for 12–24 months. Thus, findings from our home-based care strategy were compared with a well functioning facility-based model and identified to be equivalent. Mortality rates in developed countries are about two deaths per 100 person-years27 and most of the increased mortality in Africa takes place during the first year of follow-up,29 as we identified. This mortality rate could be reduced through starting of antiretroviral therapy earlier than it is at present, but how people with HIV infection who need treatment can be identified early and encouraged to seek care is less clear, and needs to be investigated. Our study shows that community-based approaches would be important. We transferred care from the clinic to trained lay workers visiting homes of patients. The costs of the home visits were offset by the savings from reduced attendence at clinic—thus, 75% fewer clinic visits were made by patients in the home-based group, and 50% fewer consultations with a doctor took place when a new clinical disorder was recorded. We recorded no negative effect on survival, plasma viral load, or other outcomes. Patients had regular counselling and adherence support, especially in the home group in which support was personalised and often provided by the same individual. This support could have had a major positive effect on outcomes. Such an approach should be achievable throughout Africa since counsellors and other support staff are more easily available and rapidly trained than are clinical staff and incur much less expense for health services. A large randomised trial30 at two sites in Uganda and one in Zimbabwe recorded health-service costs of $846 (2008 exchange rate) for a model of laboratory and clinical monitoring at a health facility, which is similar to $793 in our home group and $838 in our facility group. Costs of access to care are a major burden for most African people, especially for those living in rural areas, because cash incomes are very low. In our study, one clinic visit was 15–20% of monthly earnings for most people. In Africa, high travel costs relative to income are major determinants of poor access to care, late presentation, poor adherence, and low retention of people in antiretroviral-therapy programmes.4,14,31 Our study shows that home-based care could substantially reduce costs for patients and this outcome might have a major beneficial effect on their long-term adherence and retention. In our study, TASO changed treatment to second-line therapy for three people only, which was substantially fewer than those who had falls in CD4-cell counts to less than their baseline or virological failure, showing the major differences in the diagnostic accuracy of clinical and laboratory assessments. When to change HIV treatment is a dilemma in many settings in Africa because of poor availability and high costs of second-line regimens and the absence of information about resistance to antiretroviral therapy—a situation that is unlikely to greatly change in the near future. We should, therefore, identify means to achieve the best possible adherence to extend the life of existing drugs. Our results suggest that community-based support of patients receiving antiretroviral therapy could lead to high adherence. Very few studies have been done in which models of care are randomly assigned because of strong preferences of some individuals for a specific method of care and the role of stigma, which might result from HIV status disclosure—eg, if a field worker from a known AIDS support organisation visits a patient in the community. We overcame these difficulties by developing a partnership with the service provider, the community, and with patients from the beginning when the research question was defined, and then held regular meetings with stakeholders to discuss difficulties and provide information. No monetary incentives were provided to either the service provider or patients. Only 41 (3%) of participants refused to join the trial or later withdrew and cited stigma as a reason. All received antiretrovirals from TASO or other providers. The importance and effects of stigma in the long term when patients have sustained improved health and, for example, resumed normal relationships, is unclear. However, we have shown that community-based HIV care is feasible and that stigma is probably not an impediment to increasing coverage in settings in which trust and good relations between service providers and the community are present. Our study could have been affected by selection bias, but numbers of refusals and withdrawals were low and almost identical in both groups. Most people who withdrew were alive at the end of the study—survival status was unknown for just 51 (4%) of participants. More were recruited in the home group than in the facility group but many more in the home group were screened, suggesting that this imbalance arose by chance. Median baseline CD4-cell count was also lower in the home group than in the facility group, but again this finding was probably attributable to chance (and was adjusted for in the analysis). These imbalances show the weakness of cluster-randomised trials32 in achievement of balance through randomisation, even in trials such as ours in which a large number of clusters were randomised. We have shown that home-based HIV care with antiretroviral therapy is an effective strategy, which relies less on clinical staff and hospital services than does facility-based care and provides large savings for patients. Such community-based strategies could enable improved and equitable access to HIV treatment—especially in areas in which clinical infrastructure is scarce and patient access to clinic-based care is poor.\n\n**Question:** Compared to Facility-based HIV-care strategy what was the result of Home-based HIV-care strategy on Admission diagnoses?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
489
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Rates of virological failure in patients treated in a home-based versus a facility-based HIV-care model in Jinja, southeast Uganda: a cluster-randomised equivalence trial\n\n ABSTRACT.SUMMARY.BACKGROUND:\nIdentification of new ways to increase access to antiretroviral therapy in Africa is an urgent priority. We assessed whether home-based HIV care was as effective as was facility-based care.\n\nABSTRACT.SUMMARY.METHODS:\nWe undertook a cluster-randomised equivalence trial in Jinja, Uganda. 44 geographical areas in nine strata, defined according to ratio of urban and rural participants and distance from the clinic, were randomised to home-based or facility-based care by drawing sealed cards from a box. The trial was integrated into normal service delivery. All patients with WHO stage IV or late stage III disease or CD4-cell counts fewer than 200 cells per μL who started antiretroviral therapy between Feb 15, 2005, and Dec 19, 2006, were eligible, apart from those living on islands. Follow-up continued until Jan 31, 2009. The primary endpoint was virological failure, defined as RNA more than 500 copies per mL after 6 months of treatment. The margin of equivalence was 9% (equivalence limits 0·69–1·45). Analyses were by intention to treat and adjusted for baseline CD4-cell count and study stratum. This trial is registered at http://isrctn.org, number ISRCTN 17184129.\n\nABSTRACT.SUMMARY.FINDINGS:\n859 patients (22 clusters) were randomly assigned to home and 594 (22 clusters) to facility care. During the first year, 93 (11%) receiving home care and 66 (11%) receiving facility care died, 29 (3%) receiving home and 36 (6%) receiving facility care withdrew, and 8 (1%) receiving home and 9 (2%) receiving facility care were lost to follow-up. 117 of 729 (16%) in home care had virological failure versus 80 of 483 (17%) in facility care: rates per 100 person-years were 8·19 (95% CI 6·84–9·82) for home and 8·67 (6·96–10·79) for facility care (rate ratio [RR] 1·04, 0·78–1·40; equivalence shown). Two patients from each group were immediately lost to follow-up. Mortality rates were similar between groups (0·95 [0·71–1·28]). 97 of 857 (11%) patients in home and 75 of 592 (13%) in facility care were admitted at least once (0·91, 0·64–1·28).\n\nABSTRACT.SUMMARY.INTERPRETATION:\nThis home-based HIV-care strategy is as effective as is a clinic-based strategy, and therefore could enable improved and equitable access to HIV treatment, especially in areas with poor infrastructure and access to clinic care.\n\nABSTRACT.SUMMARY.FUNDING:\nUS Centers for Disease Control and Prevention and UK Medical Research Council.\n\nBODY.INTRODUCTION:\nAntiretroviral drug therapy has been scaled up rapidly in Africa, and is now given to more than 2 million people.1 A global commitment has been made to provide universal coverage,2 but another 5 million people, mostly living in rural and semiurban areas, are estimated to need such treatment. Achievement of high coverage in these populations will be a challenge. Two major barriers to increasing coverage exist—a severe shortage of clinically qualified staff, which has reached crisis point in most of Africa,3 and difficulty for patients in accessing clinics because of high costs and poor availability of transport and low-cash incomes.4,5 WHO proposes decentralised antiretroviral therapy delivery,6,7 and so far services for such therapy have been provided through nurse-led centres with simplified protocols in several settings, including in Malawi,8,9 Zambia,10 Mozambique,11 Botswana,12 and South Africa.13 Good patient outcomes have been reported8,10 from short-term assessments done in some sites, but interpretation of this evidence is difficult because of poor retention rates.14 Furthermore, nursing staff as well as doctors are in very short supply3,15 and care needs to be delegated to non-clinical workers, although evidence for use of non-clinical workers in HIV care is scarce. In Tororo, Uganda, a home-based programme16,17 with lay workers has achieved good outcomes, but it consisted of home visits made every week with good access to clinical staff when needed—a model that would be difficult to scale up. No direct comparisons of hospital-based HIV care versus any form of decentralised HIV care have been done in Africa. We assessed home-based HIV care, with lay workers delivering antiretroviral therapy and monitoring patients, versus facility-based HIV care.\n\nBODY.METHODS.STUDY SETTING AND PATIENTS:\nWe undertook a trial based at the AIDS Support Organisation (TASO) clinic in Jinja district, southeast Uganda.18 TASO is a large non-governmental organisation with 11 centres in the country, offering counselling and social and clinical services to people with HIV. The Jinja district and surrounding area is poor, with inhabitants on low-cash incomes.18 TASO clinic serves a predominantly rural and semiurban population from a radius of about 100 km. Most TASO clients are subsistence farmers, and very few work in the formal sector earning wages. In accordance with guidelines from the Ugandan Ministry of Health, people with HIV were eligible to start antiretroviral therapy if they were assessed to be at WHO stage IV or late stage III disease, or if they had a CD4-cell count of fewer than 200 cells per μL. Eligible patients were prepared for therapy by TASO staff during three visits to clinic, which were usually spread over 4 weeks. Information and counselling were provided both in groups and in one-to-one sessions. Participants were given drugs for 28 days of treatment and issued with a pill box. A buffer supply for 2 days was provided. Patients were also strongly encouraged to identify a so-called medicine companion to provide support and reminders. Medicine companions were given information by TASO about the basic principles of antiretroviral therapy and adherence. All TASO patients older than 18 years who were starting on antiretroviral therapy for the first time were invited to join the trial, apart from those living on islands, which were about 100 km away and where provision of home-based care was not possible. All patients provided written informed consent. The trial protocol was approved by the Ugandan National Council of Science and Technology and the Institutional Review Boards of the Uganda Virus Research Institute, Centers for Disease Control and Prevention, and London School of Hygiene and Tropical Medicine. Patients were informed about their rights to refuse to join the trial or withdraw subsequently. Those who did were offered facility-based HIV care (including antiretroviral therapy) from TASO Jinja.\n\nBODY.METHODS.STUDY DESIGN:\nRecruitment began Feb 15, 2005, and ended Dec 19, 2006, and follow-up continued until Jan 31, 2009. Numbers of patients eligible for antiretroviral therapy were not known in advance—participants were identified after they were tested for CD4-cell counts and clinically assessed. The catchment area was divided into nine strata according to ratio of urban and rural participants and approximate distance from a central point to the TASO Jinja clinic. In every stratum, an even number of clusters (geographical areas) were defined for randomisation along subdistrict boundaries, or, in the case of a few large subdistricts, by known barriers within the subdistrict. Clusters in every stratum had a similar estimated number of people with HIV who were registered at TASO Jinja. Distribution of strata and clusters was as follows: (1) four clusters in urban areas or near the TASO Jinja facility; (2) eight in periurban intermediate distance; (3) eight in rural and far; (4) four in Kamuli district; (5) four in Mukono district near; (6) six in Mukono district far; (7) six in Mayuge district; (8) two in Iganga district near; and (9) two in Iganga district far. Strata and clusters were devised by two people with knowledge of the area (one TASO staff member and one researcher) and cross-checked independently by two other people on two separate occasions. For all patients, antiretroviral therapy was started at the TASO Jinja clinic, and thereafter patients received care according to the treatment to which their residential area had been assigned. After giving consent, patients were enrolled into the study by research staff, and their addresses were confirmed from TASO records. At every clinic visit, research staff interviewed participants in privacy in a separate building soon after their arrival and before they saw TASO staff.19\n\nBODY.METHODS.RANDOMISATION:\nClusters in each strata were allocated to either home-based or facility-based care by drawing cards from a concealed box. The cards were sealed in advance and labelled with the stratum number by the trial coordinator and TASO senior medical officer who organised the allocation event and placed the cards into the box for each stratum. Cards were drawn by two patient representatives, a TASO medical officer, TASO counsellor, and TASO field officer, each taking turns. This process was done in the presence of senior TASO staff, researchers, and local public health representatives.\n\nBODY.METHODS.MODELS OF CARE:\nThe trial was done in conditions similar to those of actual health services, with TASO staff responsible for service delivery.19 Numbers of counsellors, nurses, and laboratory and pharmacy staff in Jinja were similar to those at other TASO centres. The clinic had five medical officers but the number present usually varied between two and four, with some support from local part-time physicians during the trial. Most medical officers were newly qualified. Clinical staff were trained on antiretroviral therapy and supported by a senior medical officer. For the home-based group, trained field officers travelling on motorcycles visited patients at home every month to deliver drugs, monitor participants with a checklist that included signs and symptoms of drug toxicity or disease progression, and provide adherence support. Most field officers had degree qualifications or college diplomas and underwent 4 weeks of intensive training at the start of the study and yearly refresher courses thereafter about the principles of antiretroviral therapy and adherence support. They were supported at the TASO clinic by counsellors and medical officers. Field officers referred patients to a physician or counsellor at the TASO clinic when they judged referral to be necessary. They had mobile phones and could contact physicians when unsure about referral. At the end of every day, a medical officer reviewed the notes made by field officers and, when needed, asked officers to return to the patient's home to refer them. Patients who were not at home for their monthly appointment were visited again—usually the next day. If they were absent again, fieldworkers left a message for them to come to the clinic. All patients were invited to the clinic for routine reviews by a medical officer and a counsellor at 2 and 6 months after starting therapy and every 6 months thereafter. Drugs were not dispensed during clinic visits for those allocated to home-based case. Before antiretroviral therapy started, TASO offered free voluntary counselling and testing in the home to household members of participants. This offer was repeated during home visits for drug delivery for those who were absent previously. In the facility-based group, patients obtained drugs every month from the clinic and had routine reviews with a medical officer and counsellor that were scheduled at 2 and 3 months after start of treatment and every 3 months thereafter. Apart from scheduled reviews, patients were assessed during clinic visits by a nurse and referred to a doctor when necessary. When an appointment was missed, patients were followed up at home by a field officer (if patients had given permission for home visits), usually after 2–3 days, and reminded to attend clinic. Participants were also given vouchers for their household for free voluntary counselling and testing at TASO Jinja. Patients in both groups were asked to come to the clinic any time that they felt unwell. They were also given a telephone number to call for advice. In exceptional cases, and when TASO resources allowed, home care was provided by a team, including a physician, to patients who were bedridden. No financial or other incentives were provided to patients or staff and TASO clinical management procedures were identical for trial and non-trial participants.\n\nBODY.METHODS.PROCEDURES:\nIndependent research staff assessed adherence.19 Patients in both groups were interviewed during routine clinical and counselling visits at 2 months and 6 months after starting therapy and then every 6 months. Questionnaires were translated into the local language, Luganda, and then back into English by an independent person, and cross-checked by another researcher who was not involved with the trial. Clinical data were transcribed from patient notes. A change to a second-line regimen was decided by a TASO case conference, consisting of physicians and counsellors, and was made when a patient had one of the following criteria: (1) new or recurrent WHO clinical stage IV or advanced stage III disease; (2) clinical deterioration (eg, weight loss) and two or more consecutive CD4-cell counts less than baseline, or a fall to 50% less than peak CD4-cell count attained after the start of antiretroviral therapy; or (3) CD4-cell counts persistently fewer than 100 cells per μL. Survival status was established through home follow-ups or hospital records, dependent on where deaths took place. We established the status of participants who withdrew from TASO records. CD4-cell counts were monitored by TASO staff every 6 months for all patients as part of their clinical care. CD4-positive cells were measured with TriTEST reagents (Becton-Dickenson, Franklin Lakes, NJ, USA), according to an inhouse dual-platform protocol and MultiSET and Attractors software (version 2.2) with a FACScan flow cytometer (Becton-Dickinson, Franklin Lakes, NJ, USA). Additional blood was taken to measure plasma viral load, but this testing was for research reasons and done in batches later. Plasma was separated within 2 h and stored immediately at −80°C. HIV-1 RNA was tested with the VERSANT RNA 3.0 (Bayer, Bayer HealthCare, NY, USA) assay (with a lower limit of detection of 50 copies per mL) for baseline samples, and the Amplicor MONITOR 1.5 (Roche, Roche Molecular Systems, NJ, USA) for other samples (400 per copies per mL). After we established close correlation between results of the two assays, the Amplicor assay was used to keep costs to a minimum. Our economic analysis took a societal perspective and included recurrent and capital costs incurred by the provider, transport and other related costs, and income lost by patients while accessing care. We reported all costs in 2008 US$; the mean exchange rate from 2005 to 2008 was 1732 Ugandan shillings to $1. Cost data and all data for care provided by TASO were obtained from TASO accounts. We used three steps to allocate costs. First, we established the proportion of all TASO clients who were receiving antiretroviral therapy. Second, we calculated the percentage of TASO clients on therapy who entered the trial. Both percentages changed over time, rising initially as numbers of patients who were put on therapy increased, and then falling when recruitment stopped. To capture this dynamic situation, we gathered and aggregated monthly cost data every 6 months, and converted data to US$ with the prevailing exchange rate, with adjustment for inflation. Third, we allocated costs to facility and home groups. When possible, we used actual service data—eg, information about numbers of doctor visits was used to allocate staff time. We assigned antiretroviral therapy costs proportionally by patient numbers in both groups for that period. Drug prices included purchase cost, insurance, and freight to Uganda and were adjusted to account for substantial price reductions that occurred early in the project. We established costs incurred by patients through a questionnaire. Health-services costs consisted of: staff costs (doctors, field officers, cousellors, and other staff), transport (motorcycle and vehicle costs of fuel and maintenance, and other transport costs); all drugs; laboratory and clinical expenses (radiograph, ultrasound, and laboratory and CD4 tests); sensitisation (AIDS education via radio, other media, and drama); training, teambuilding, and workshops; utilities (electricity, telephone, postage, and security), supervision and overheads (stationery, repairs, overheads, and supervision costs), and capital costs (buildings, furniture, vehicles, equipment, and inventory). Buildings depreciated over 50 years and other elements 5 years (eg, The AIDS Support Organisation practice). Patient costs consisted of: cost of transport (including transport of medicine companion), childcare, and lunches, if applicable, median weighted by proportion ($2·88 for women and $3·46 for men); and lost work time, estimated 1 day for clinic visits and 0·5 days for home visits, valued at Uganda mean per head gross domestic product from 2005–08 (World Bank data) for 300 working days per year. The primary endpoint was rate of virological failure, defined as time (starting from 6 months) to a plasma RNA viral load of more than 500 copies per mL. The secondary outcome measures were time to either detectable plasma viral load of more than 500 copies per mL at any visit from 12 months onwards in patients with viral loads of fewer than 500 copies per mL at 6 months, or an increase of 1000 copies per mL between two consecutive tests in those not achieving a viral load of fewer than 500 copies per mL at 6 months. Other secondary outcomes were all-cause mortality; virological failure as defined in the primary outcome or death; time to first admission; death, admission, or change to second-line antiretroviral therapy; outpatient attendance; adherence during the previous 28 days (measured with a standardised questionnaire); and costs incurred by the health service and patients.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nWe designed the study as an equivalence trial. Virological failure time was taken as halfway between the last measure of RNA of 500 copies per mL or fewer and the first of more than 500 copies per mL. Testing was repeated in patients who had viral loads between 500 and 1000 copies per mL to exclude the possibility of small transient increases. We assumed that in one group the rate of virological failure during follow-up would be about 20%,20–22 and that the other group could be regarded as equivalent if the rate of virological failure did not exceed 20% by more than 9%—ie, 29% or less. Thus, the upper limit of our equivalence interval was 29/20 or 1·45, and by symmetry the lower limit was 20/29 or 0·69. A sample size of 20 clusters per group with a total of 1200 participants gave more than 95% power to show equivalence, on the assumption of a between-cluster coefficient of variation of 0·2. Analysis was by intention to treat, in which all participants were regarded as randomly assigned to the group corresponding to the cluster in which they lived. Analyses were done for the individual by fitting generalised linear mixed models with a log-link and poisson distribution, with every patient contributing an outcome of 1 if they had virological failure and 0 if they did not. The model had fixed terms for study regions, baseline CD4-cell counts (categorised as a four-level factor with counts of 0–49, 50–99, 100–149, and 150 or more cells per μL), and study groups, with the log of exposure time included as an offset variable, and a random term for study cluster. The model was fitted with the assumption that the random cluster effects followed a γ distribution. For the primary endpoint, exposure time was calculated from the 6-month visit to midway between the last date on which the patient did not have virological failure and the date of virological failure. For other endpoints, exposure time was calculated from enrolment. Those who withdrew or were lost to follow-up before 12 months were excluded from the primary endpoint analysis, and for other endpoints they were censored on the last date seen.\n\nBODY.METHODS.ROLE OF THE FUNDING SOURCE:\nSponsor staff had a role in the study design, data collection, data analysis, data interpretation, and writing of the report. The corresponding author had full access to the data and had final responsibility for the decision to submit for publication.\n\nBODY.RESULTS:\nFigure 1 shows the trial profile. The two groups were well balanced according to baseline characteristics apart from CD4-cell count, which was lower in the home-based than in the facility-based group (table 1). The median cluster size for home-based care was 36 people (range 6–84) and for facility-based care was 25 (2–65). Overall, 1403 patients (97%) were taking co-trimoxazole prophylaxis and 101 (7%) were being treated for tuberculosis. 119 patients withdrew during the course of the trial. Their status at the end of the trial was: three (3%, one from the facility and two from the home group) had died, 98 (82%, 48 facility and 50 home) were receiving antiretroviral therapy, one (<1%, facility) was alive and not receiving antiretroviral therapy, and 17 (15%, eight home and nine facility) were no longer in contact with TASO. The median follow-up of survivors on home-based care was 28 months (IQR 18–35) and on facility-based care was 27 months (13–34). Table 2 shows rates of virological failure, death, and hospital admission by group. Figure 2 shows HIV-RNA virological suppression and survival over time by study group. Rates of detection of plasma viral loads of more than 500 copies per mL after a 6-month visit were much the same in both groups. Also similar were the composite rates of either plasma RNA viral loads of more than 500 copies per mL after a 6-month visit in those who had undetectable viral loads at 6 months, or an increase in plasma RNA viral load of 1000 copies per mL between two consecutive tests in those who had detectable viral loads at 6 months. 184 (24%) patients having home and 145 (27%) facility care either had virological failure, were lost to follow-up, or withdrew from the trial (adjusted rate ratio [RR] 0·88, 95% CI 0·70–1·10). Mortality rates were much the same in the two groups during the study (figure 2). Combined mortality rates per 100 person-years were 16·47 (95% CI 13·69–19·82) during the first 5 months after treatment started, 6·69 (4·94–9·05) for 6–11 months, 2·71 (1·92–3·84) for 12–23 months, and 0·97 (0·54–1·76) for 24 months and after. By the end of the study, 566 (66%) participants in the home group and 377 (63%) in the facility group were alive, receiving follow-up, and had undetectable plasma viral loads. Admission diagnoses were similar in both groups (table 3). 20 (13%) patients who were admitted died (15 on home and five on facility care) and eight (5%) worsened and requested discharge (six on home and two on facility care)—seven died subsequently. Table 4 shows frequency of outpatient attendance at clinic, number of presentations in which a new diagnosis was made, and new diagnoses by number and type. Distribution of diagnoses was similar between groups and more than half were infectious and parasitic disease. CD4-cell counts increased rapidly in both groups (figure 3). 748 (87%) participants in home care and 521 (88%) in facility care were tested for CD4-cell count at least once after starting treatment, with median intervals between baseline and final tests of 32 months (IQR 25–39) for home and 29 months (23–35) for facility. 608 (81%) in home and 419 (80%) in facility had CD4-cell counts of greater than 200 cells per μL at the final visit. Counts at this visit were lower than baseline in 32 (4%) of those in home compared with 29 (6%) in facility care. At routine clinical and counselling reviews, home participants reported complete adherence to therapy in the past 28 days in 3698 of 3951 (94%) visits compared with 2527 of 2768 (91%) visits made by facility participants (figure 4). Patients were too sick to be interviewed in a further 78 (2%) home-group and 39 (1%) facility-group visits. Only two patients, both in home-based care, refused to answer adherence questions—saying they were in a hurry to return home. 138 (16%) of patients in home care had a drug substitution at a median 9 months (IQR 2–24) versus 123 (21%) in facility care at 8 months (3–22) after treatment started. Most substitutions were because of adverse reactions to antiretroviral therapy (table 5). Only one person in home-based and two in facility-based care had their first-line treatment changed to second-line. Table 6 shows mean yearly health services cost per patient calculated during 4 years, (including capital and recurrent expenses, and those of the starting phase and subsequent years). A large proportion of the costs were for drugs and staff salaries. The main cause of excess expenditure for the facility-based group was the increased number of contacts with health staff—especially with nurses and medical officers. These costs outweighed those of transport for field officers in the home-based group. Patient costs (transport of patient and companion, lunches, child care, and time lost from work) were much higher for the facility-based than for the home-based group (table 6). During the first year, when many visits were needed to start antiretroviral therapy, median yearly costs incurred by every patient were higher in facility than in home (table 6). Much of this expense was for transport. After the first year, patient costs for the home-based group were fairly low but remained high for the facility-based group, showing the economic burden of monthly clinic visits. Overall, the median cost of a clinic visit was $2·30—about 13% of reported monthly cash incomes for men and 20% for women.\n\nBODY.DISCUSSION:\nWe have shown that a home-based HIV-care strategy with trained lay workers supporting drug delivery and monitoring patients was as effective as was a nurse-led and doctor-led clinic-based strategy for prevention of virological failure, mortality, and other adverse outcomes. For our primary endpoint of virological failure, the adjusted RR was contained between the pre-specified equivalence limits of 0·69 to 1·45. Results were similar for other endpoints. The home-based strategy did not result in higher costs for the health service. Moreover, home-based care was slightly cheaper than facility-based care by about $45 per patient per year, or 6% of the total cost. Costs incurred by patients to access care were much less for those in the home group than for those receiving facility-based care. We have identified a strategy to provide effective HIV care in the many settings in Africa in which clinical staff are scarce and patient access to clinics is difficult. Our findings were achieved in a standard resource-constrained health-service setting. Mortality rates in our facility-based group of about six deaths per 100 person-years and virological failure rates of nine per 100 person-years were better than or at least as good as were those reported from most other settings. Other researchers8,10,16,21,24–26 have reported mortality rates ranging from six to more than 15 deaths per 100 person-years and virological failure rates20–22,27,28 from 15% to more than 40% for 12–24 months. Thus, findings from our home-based care strategy were compared with a well functioning facility-based model and identified to be equivalent. Mortality rates in developed countries are about two deaths per 100 person-years27 and most of the increased mortality in Africa takes place during the first year of follow-up,29 as we identified. This mortality rate could be reduced through starting of antiretroviral therapy earlier than it is at present, but how people with HIV infection who need treatment can be identified early and encouraged to seek care is less clear, and needs to be investigated. Our study shows that community-based approaches would be important. We transferred care from the clinic to trained lay workers visiting homes of patients. The costs of the home visits were offset by the savings from reduced attendence at clinic—thus, 75% fewer clinic visits were made by patients in the home-based group, and 50% fewer consultations with a doctor took place when a new clinical disorder was recorded. We recorded no negative effect on survival, plasma viral load, or other outcomes. Patients had regular counselling and adherence support, especially in the home group in which support was personalised and often provided by the same individual. This support could have had a major positive effect on outcomes. Such an approach should be achievable throughout Africa since counsellors and other support staff are more easily available and rapidly trained than are clinical staff and incur much less expense for health services. A large randomised trial30 at two sites in Uganda and one in Zimbabwe recorded health-service costs of $846 (2008 exchange rate) for a model of laboratory and clinical monitoring at a health facility, which is similar to $793 in our home group and $838 in our facility group. Costs of access to care are a major burden for most African people, especially for those living in rural areas, because cash incomes are very low. In our study, one clinic visit was 15–20% of monthly earnings for most people. In Africa, high travel costs relative to income are major determinants of poor access to care, late presentation, poor adherence, and low retention of people in antiretroviral-therapy programmes.4,14,31 Our study shows that home-based care could substantially reduce costs for patients and this outcome might have a major beneficial effect on their long-term adherence and retention. In our study, TASO changed treatment to second-line therapy for three people only, which was substantially fewer than those who had falls in CD4-cell counts to less than their baseline or virological failure, showing the major differences in the diagnostic accuracy of clinical and laboratory assessments. When to change HIV treatment is a dilemma in many settings in Africa because of poor availability and high costs of second-line regimens and the absence of information about resistance to antiretroviral therapy—a situation that is unlikely to greatly change in the near future. We should, therefore, identify means to achieve the best possible adherence to extend the life of existing drugs. Our results suggest that community-based support of patients receiving antiretroviral therapy could lead to high adherence. Very few studies have been done in which models of care are randomly assigned because of strong preferences of some individuals for a specific method of care and the role of stigma, which might result from HIV status disclosure—eg, if a field worker from a known AIDS support organisation visits a patient in the community. We overcame these difficulties by developing a partnership with the service provider, the community, and with patients from the beginning when the research question was defined, and then held regular meetings with stakeholders to discuss difficulties and provide information. No monetary incentives were provided to either the service provider or patients. Only 41 (3%) of participants refused to join the trial or later withdrew and cited stigma as a reason. All received antiretrovirals from TASO or other providers. The importance and effects of stigma in the long term when patients have sustained improved health and, for example, resumed normal relationships, is unclear. However, we have shown that community-based HIV care is feasible and that stigma is probably not an impediment to increasing coverage in settings in which trust and good relations between service providers and the community are present. Our study could have been affected by selection bias, but numbers of refusals and withdrawals were low and almost identical in both groups. Most people who withdrew were alive at the end of the study—survival status was unknown for just 51 (4%) of participants. More were recruited in the home group than in the facility group but many more in the home group were screened, suggesting that this imbalance arose by chance. Median baseline CD4-cell count was also lower in the home group than in the facility group, but again this finding was probably attributable to chance (and was adjusted for in the analysis). These imbalances show the weakness of cluster-randomised trials32 in achievement of balance through randomisation, even in trials such as ours in which a large number of clusters were randomised. We have shown that home-based HIV care with antiretroviral therapy is an effective strategy, which relies less on clinical staff and hospital services than does facility-based care and provides large savings for patients. Such community-based strategies could enable improved and equitable access to HIV treatment—especially in areas in which clinical infrastructure is scarce and patient access to clinic-based care is poor.\n\n**Question:** Compared to Facility-based HIV-care strategy what was the result of Home-based HIV-care strategy on Increase in CD4-cell counts?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
618
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: The effects of multi-strain probiotic compound on symptoms and quality-of-life in patients with irritable bowel syndrome: A randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEvidence has shown beneficial effects of probiotics in the treatment of irritable bowel syndrome (IBS); however, there is still a lack of data in this regard. We evaluated the efficacy of a multi-strain probiotic compound on IBS symptoms and quality-of-life (QOL).\n\nABSTRACT.MATERIALS AND METHODS:\nAdult IBS patients (n = 132) were randomized to receive a probiotic compound containing seven bacteria species including Lactobacillus strains, Bifidobacterium strains and Streptococcus thermophiles or similar placebo, twice daily after a meal for 14 consecutive days. Improvement of IBS symptoms was assessed in categories of abdominal pain and distension and improvement of bowel habit. Improvement in patients QOL was assessed by the IBS-QOL instrument. Patients were evaluated for symptoms and QOL at baseline and then 1 month after completion of the treatment.\n\nABSTRACT.RESULTS:\nAfter treatment, there was a decrease in abdominal pain and distension severity in both probiotic and the placebo groups (P<0.001), but there was no difference between the two groups in this regard (P>0.05). Improvement in bowel habit was observed in 33.3% of the probiotic and 36.5% of the placebo group (P = 0.910). There was no significant difference between the two groups in QOL after the treatment (P >0.05).\n\nABSTRACT.CONCLUSIONS:\nWe found no beneficial effects over placebo for a 2-week treatment with the above mentioned multi-strain probiotic compound in the treatment of IBS. Further, trials are yet required before a clear conclusion in this regards.\n\nBODY.INTRODUCTION:\nIrritable bowel syndrome (IBS) is the most common functional bowel disorder characterized by abdominal pain/discomfort accompanying with disturbed bowel habits. It is estimated that 3-15% of the general population have IBS world-wide, modestly more prevalent in women than in men.[1] IBS possesses a chronic nature and affects patients physically, psychologically and economically and therefore, it is associated with impaired quality-of-life (QOL) and causes a major economic burden.[2] The pathophysiology of IBS is still not completely understood. Studies have shown that the etiology is most likely multifactorial and abnormal brain-gut interaction, food intolerance; altered microflora, post-infectious or inflammatory changes and genetic and psychological factors contribute to the pathogenesis of IBS.[34] Heterogeneous pathophysiology and nature of IBS has a substantial impact on the efficacy of therapies for IBS. Only few therapies have been found to be effective in IBS treatment and treatments are not satisfactory in about half of the patients.[5] The role of altered gut microbiota in the pathogenesis of IBS is highlighted by evidences showing changes in fecal and mucosa associated microflora, post-infectious IBS phenomenon and the link with intestinal bacterial overgrowth and dysregulation of mucosal immune system. Therefore, investigators have tried to see the effects of alterations in the intestinal microflora on IBS symptoms.[6] In this regard, the role of probiotics for intestinal functions and altered bowel microbiota, found in patients with IBS, has drawn attention toward these agents. Previous studies have shown beneficial effects of probiotics in the treatment of IBS and their safety has also contributed in to their popularity.[789] However, the benefits are likely to be strain-specific[10] and Bifidobacterium infantis has resulted in significant improvement in almost all IBS symptoms.[9] Based on some evidence, a mixture of probiotics that contains several species of bacteria could be more effective than a single species of bacteria in the treatment of some gastrointestinal diseases. It is assumed that multi-strain probiotics have synergistic effects that increase their effectiveness.[1112] However, whether a probiotic mixture is more effective than a single agent in treatment of IBS is remained un-answered yet. Another remained concern is the world-wide generalizability of current studies results. Almost all clinical studies with microbial therapies are carried out with people from developed countries.[789] Since, there is a variety in gut flora between different world's regions[1314] the efficacy of probiotics may be affected by different ethnic groups of patients from different countries. There is no published report about probiotics efficacy on IBS treatment in Iran yet. Moreover, most of the previous studies are limited by small sample size.[15] Considering the above mentioned questions and lack of qualified studies, the purpose of our study was to evaluate the efficacy of a multi-strain probiotic compound, Balance® (Protexin Co., Somerset, UK), in the treatment of Iranian IBS patients. Balance® contains seven species of bacteria including Lactobacillus and Bifidobacterium species that separately have been shown helpful for treatment of IBS.[916] We hypothesized that this probiotic compound would decrease symptoms of IBS and increase the QOL.\n\nBODY.MATERIALS AND METHODS.PATIENTS AND SETTING:\nThis randomized placebo-controlled triple-blinded study was conducted on adult patients with IBS referred to gastroenterology clinics of Alzahra University Hospital in Isfahan City (central Iran). IBS was diagnosed by a single gastroenterologist according to the Rome II criteria (reference is needed). Patients with symptoms presented at least for 2 days/week in the preceding 2 weeks were included. Those with any infectious diseases before or during the study that need antibiotic therapy, immune-deficient disease, history of surgery on the gastrointestinal tract and history of using antibiotics or probiotics within 4 weeks before the study were not included. Considering type I error = 0.05, study power = 0.8 and expecting 10 point increase in the QOL score,[17] the study sample size was calculated as 66 cases per group. The study was approved by the Ethics Committee of Isfahan University of Medical Sciences and registered in the U.S. National Institutes of Health Protocol Registration System (available at clinicaltrials.gov NCT01837472). Informed consent was obtained from all patients after full explanation of the study aim and protocol.\n\nBODY.MATERIALS AND METHODS.INTERVENTION:\nPatients were randomized into probiotic and placebo groups based on random table list. Patients in the probiotic group received the probiotic compound Balance® (Protexin Co., Somerset, UK), twice daily after a meal for 14 consecutive days. Balance® capsules contain seven bacteria species including Lactobacillus strains (Lactobacillus casei, Lactobacillus rhamnosus, Lactobacillus acidophilus and Lactobacillus bulgaricus), Bifidobacterium strains (Bifidobacterium breve and Bifidobacterium longum) and Streptococcus thermophiles. Total viable count is 1 × 108 CFU/per capsule. Other Ingredients are Fructo-oligosaccharide as prebiotic, magnesium stearate and hydroxypropyl methyl cellulose. Those in the placebo group received placebo capsules with the same order as probiotic group. No other treatment was prescribed for patients during the study period.\n\nBODY.MATERIALS AND METHODS.ASSESSMENTS:\nPrimary outcome of this study was improvement of IBS symptoms that was assessed in categories of abdominal pain and distension (from 0: No symptom to 3: Severe symptom) and improvement of bowel habit (get worse, no change, get better). Secondary outcome was improvement in patients QOL that was assessed by applying the IBS-QOL instrument. The IBS-QOL is a reliable and valid instrument for the assessment of IBS patients' QOL. It contains 34 items with 5-point response scale (1: No problem to 5: Extreme problem). The total score is converted into 0-100 points for better interpretation.[17] The Persian version of the IBS-QOL with sufficient psychometric properties was used in this study.[18] Patients were evaluated for symptoms and QOL at baseline and then 1 month after completion of the treatment.\n\nBODY.MATERIALS AND METHODS.STATISTICAL ANALYSES:\nThis study was designed as a triple-blind study and attending physicians, patients, principal investigators as well as data analyzer were all unaware about the treatment arms and drug codes. A third colleague who coded the probiotic and placebo capsules clarified the codes after data analyses. Data were analyzed using the SPSS software for windows version 16.0. Quantitative data and qualitative data were compared between the two groups with independent sample t-test and Chi-square/Mann-Whitney U tests, respectively. Paired t-test and Wilcoxon test were applied to assess changes in QOL score and symptoms severity within each group, respectively. A P value of less than 0.05 was considered as indicating a statistical significant difference in all analyses.\n\nBODY.RESULTS:\nA total of 160 patients were evaluated during the study period. Twenty eight patients were not included owing to unwillingness to participate, receiving antibiotics or probiotics at the time of the study. Thus, 132 patients were randomized into the probiotic and placebo groups. Three patients from the placebo group did not come for follow-up evaluations, not due to drug side effects. Thus, 129 patients completed the trial; 66 patients in the probiotic and 63 ones in the placebo group. Mean age was 36.2 ± 9.3 years and 85 (65.9%) cases were female. The two groups were similar regarding demographic and baseline clinical characteristics [Table 1]. Table 1 Comparison of the two groups with regards to demographic and baseline clinical characteristics After the treatment period, there was a significant decrease in abdominal pain severity in both the probiotic (P < 0.001) and the placebo (P = 0.001) groups. There was no difference between the two groups in this regard (P = 0.558). Furthermore, distension severity decreased significantly in both probiotic (P < 0.001) and the placebo (P < 0.001) groups, but no difference was observed between the two groups in this regard (P = 0.673). Improvement in bowel habit was observed in 33.3% of the probiotic and 36.5% of the placebo group (P = 0.910). With regard to QOL, an improvement was observed in the probiotic (P = 0.008), but not in the placebo group (P = 0.175); though, there was no significant difference between the two groups in this regard (P = 0.372), Table 2. Further analysis in each subgroup of bowel habit did not change these results. Table 2 Comparison of the two groups with regards to symptoms and quality-of-life after treatment In the probiotic group, three patients experienced mild abdominal pain and nausea at the beginning of therapy, which disappeared by continuing the drug. No specific side-effect was reported in the placebo group.\n\nBODY.DISCUSSION:\nThe aim of the present study was to evaluate the efficacy of a multi-strain probiotic compound, which contains seven species of bacteria including Lactobacillus and Bifidobacterium species in the treatment of Iranian IBS patients. We found no beneficial effects for this probiotic compound over placebo in reliving IBS symptoms. Although there was a statistically significant improvement in QOL score in the probiotic group, this change was not clinically important, which might be due to short duration of the study. Previous studies on the efficacy of multi-strain probiotic compounds in the treatment of IBS have provided different results. Two small studies by Kim et al. on a probiotic compound containing Bifidobacterium, Lactobacillus and Streptococcus salivarius species for 4-8 weeks found beneficial effects of these probiotics over placebo only for bloating and flatulence symptoms.[1920] Ki Cha et al. have evaluated a probiotic mixture containing Lactobacillus and Bifidobacterium and S. thermophilus for 8 weeks and found an overall response rate of 48% versus 12% with placebo; though, it had no significant effect on individual symptoms.[21] The study by Williams et al. on a combination of Lactobacillus and Bifidobacterium species also found greater improvement in IBS symptom severity and also in QOL compared with placebo over the 8-week intervention period.[22] Two other studies by Kajander et al. showed that a probiotic mixture of Lactobacillus and Bifidobacterium species for 5 months can stabilize the intestinal microbiota and alleviate IBS symptoms.[2324] In contrast to these reports, the study by Søndergaard on a probiotic fermented milk containing Lactobacillus and Bifidobacterium species has found no special effect over acidified milk for 8 weeks.[25] A similar study by Simrén et al. also found no positive effect of such treatment.[26] Our study also found no beneficial effects of multi-strain probiotic over placebo in the treatment of IBS. According to systematic reviews and meta-analyses on this subject, there is a considerable heterogeneity among previous clinical trials regarding study design, which prevent a clear conclusion. Studies are different considering the duration of treatment (2 weeks to 5 months), outcome assessments and the type and amount (drug dose) of intervention. A publication bias toward positive results also should be considered.[9] Future studies should follow Rome Committee recommendations for appropriate design of clinical trials in this field.[27] There are some limitations for this study. We assessed abdominal pain, the most important IBS symptom for patients as well as other symptoms with a Likert scale. This type of assessment is based on clinical importance of change; however, it might not detect small changes. Therefore, it is better for future studies to apply more comprehensive evaluation of symptoms.[28] Furthermore, the IBS-QOL evaluates QOL of the patient in the preceding 30 days; thus, 1 month was not an appropriate interval for expecting change in QOL and the study needed longer follow-up for evaluation of changes in QOL.\n\nBODY.CONCLUSIONS:\nWe found no beneficial effects for a 2-weeks treatment with a multi-strain probiotic compound containing Lactobacillus and Bifidobacterium species over placebo in the treatment of Iranian IBS patients. Further trials with longer duration of treatment and follow-ups are yet required before a clear conclusion in this regards. Such research should also focus on the type, optimal dose of probiotics and the subgroups of patients who are likely to benefit the most.\n\n**Question:** Compared to similar placebo, twice daily after a meal for 14 consecutive days what was the result of receive a probiotic compound containing seven bacteria species including Lactobacillus strains, Bifidobacterium strains and Streptococcus thermophiles on decrease in abdominal pain and distension severity?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
490
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Interferon-gamma in the first-line therapy of ovarian cancer: a randomized phase III trial\n\n ABSTRACT:\nIntraperitoneal treatment with interferon-γ (IFN-γ) has been shown to achieve surgically documented responses in the second-line therapy of ovarian cancer. To assess its efficacy in the first-line therapy, we conducted a randomized controlled trial with 148 patients who had undergone primary surgery for FIGO stage Ic–IIIc ovarian cancer. In the control arm women received 100 mg m−2cisplatin and 600 mg m−2cyclophosphamide, the experimental arm included the above regimen with IFN-γ 0.1 mg subcutaneously on days 1, 3, 5, 15, 17 and 19 of each 28-day cycle. Progression-free survival at 3 years was improved from 38% in controls to 51% in the treatment group corresponding to median times to progression of 17 and 48 months (P = 0.031, relative risk of progression 0.48, confidence interval 0.28–0.82). Three-year overall survival was 58% and 74% accordingly (n.s., median not yet reached). Complete clinical responses were observed in 68% with IFN-γ versus 56% in controls (n.s.). Toxicity was comparable in both groups except for a mild flu-like syndrome, experienced by most patients after administration of IFN-γ. Thus, with acceptable toxicity, the inclusion of IFN-γ in the first-line chemotherapy of ovarian cancer yielded a benefit in prolonging progression-free survival. © 2000 Cancer Research Campaign\n\n**Question:** Compared to Cisplatin and Cyclophosphamide what was the result of Cisplatin and Cyclophosphamide, plus subcutaneous IFN-γ on Progression-free survival after 3 years?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
504
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Oral mucositis and selective elimination of oral flora in head and neck cancer patients receiving radiotherapy: a double-blind randomised clinical trial\n\n ABSTRACT:\n\n\nBODY:\nRadiotherapy in head and neck cancer patients can induce oral mucositis, which is an acute inflammation of the oral mucosa. Until now no effective intervention has been developed to prevent oral mucositis in radiotherapy (Sutherland and Browman, 2001). This prevention is even more relevant now because altered fractionation schedules for the treatment of head and neck malignancies induce more severe mucositis (Kaanders et al, 1999). All patients receiving radiotherapy in the head and neck region develop oral mucositis to some extent, depending on radiation schedule, radiation field, radiation volume and cumulative dose (Miralbell et al, 1999). Clinically, mucositis appears in a conventional radiation scheme after a cumulative radiation dose of 10–20 Gy as a white discoloration of the mucosa because of hyperkeratinisation. The next stage is a deepening erythema followed by the development of pseudomembranes and ulcerations. Severe mucositis, appearing as pseudomembranes, will develop at the end of the third week of radiation, after about 30 Gy (Baker, 1982; Spijkervet et al, 1989b). Prevention of severe mucositis is important because mucositis affects the patient's feeding status, physical and mental well-being and it can influence the course of radiotherapy (Sutherland and Browman, 2001). Further oral pain because of mucositis has a serious impact on the quality of life of patients (Miralbell et al, 1999). Several mechanisms are supposed to play a role in the development of mucositis: changes at the cellular level of the basal cell layer, inflammatory process in the epithelium and influence of bacteria on mucosal surface. Changed oral flora, colonising the oral mucosa, may aggravate the mucosa reaction because of radiation (Van Saene and Martin, 1990). The carriage and colonisation of aerobic Gram-negative bacilli are thought to play a role in the pathogenesis of irradiation mucositis (Bernhoft and Skaug, 1985). A hypothesis has been proposed on the development of mucositis in four consecutive phases, in which the ulcerative/bacterial phase is thought to play a role in the development of fibrous pseudomembranes of the oral mucosa (Sonis, 1998). A pilot study in 15 patients reported the protective effect of an antibiotic lozenge for selective elimination of the oral flora (Spijkervet et al, 1990). Less severe mucositis and a less mean mucositis score compared to a historical control group was observed. None of the PTA-(polymyxin E 2 mg, tobramycin 1.8 mg and amphotericin B 10 mg) treated patients needed nasogastric tube feeding. In a cohort study including 36 patients, it was found that PTA lozenges may reduce irradiation mucositis (Kaanders et al, 1995). In contrast, randomised studies reported conflicting effects on mucositis by selective oral flora elimination (Symonds et al, 1996; Okuno et al, 1997; Wijers et al, 2001). The aim of this study was to evaluate in a randomised, double-blind, placebo-controlled trial the effects of selective oral flora elimination on the development of irradiation-induced oral mucositis, feeding, weight loss and colonisation of aerobic Gram-negative bacilli and yeast.\n\nBODY.PATIENTS AND METHODS.PROTOCOL:\nPatients with a malignant tumour in the head and neck regions to be treated with primary curative or postoperative radiotherapy were eligible for this study. Inclusion criteria for the study were: external bilateral irradiation via parallel-opposed portals by a linear accelerator (4–6 MeV), fractionation of 2 Gy daily, five times a week, with a prescribed dose of at least 50 Gy and at least 50% of the oral mucosa in the field of radiation. The dose specification was in line with ICRU 50 recommendations (Anonymous, 1993). Criteria for exclusion were: (1) an oral mucosa defect other than related to tumour surgery; (2) need for an obturator or resection prosthesis and; (3) treatment with antibiotics for an oral infection the last 2 weeks before the start of irradiation. As a standard procedure all patients were evaluated before radiation treatment for potential risk factors for oral complications by means of a thorough oral and dental evaluation, including a radiographic examination. All potential risk factors were eliminated appropriately before the start of radiotherapy. The supportive oral care regimen consisted of a daily protocol of cleansing the oral cavity by means of spraying with saline by the dental hygienist, and mouth rinsing by the patients with a salt–baking soda solution at least eight times a day to remove sticky saliva and debris. Dentate patients applied a neutral fluoride gel every second day with custom-made trays and edentulous patients were not allowed to wear their dentures during the course of radiotherapy (Jansma et al, 1992). The Medical Ethical Committee approved the study and all eligible patients gave written informed consent.\n\nBODY.PATIENTS AND METHODS.ASSIGNMENT:\nThe eligible patients were randomised to receive active lozenges of 1 g containing polymyxin E 2 mg, tobramycin 1.8 mg and amphotericin B 10 mg (PTA) or placebo lozenges. The ingredients of the placebo lozenge were identical with the PTA lozenge except the active drugs. The colour, taste and form of the PTA and placebo lozenges were identical as well. Randomisation was performed by the hospital pharmacist according to a computer-generated, randomised allocation schedule. Patients, clinicians, dental hygienists and microbiologists were blind for who was taking antibiotics. The patients used a PTA or placebo lozenge four times daily starting the first day of irradiation during the total radiation period.\n\nBODY.PATIENTS AND METHODS.ASSESSMENTS:\nThe study period included only the first 5 weeks of radiation because of the wide range of field changes above 50 Gy of radiation. During the study period mucositis, feeding and body weight scores were performed at the start of radiotherapy and twice weekly (Monday–Thursday). The assessments were performed by an assigned dental hygienist. For each patient a mean weekly score was calculated on the basis of these two scores. These mean scores were used for further statistical analyses. Twice weekly (Monday–Thursday) and two times before the start of radiation oral washings were obtained to examine the oral flora for Gram-negative bacilli, Candida species, viridans streptococci, Enterococci, Staphylococcus aureus and coagulase-negative Staphylococci.\n\nBODY.PATIENTS AND METHODS.ASSESSMENTS.MUCOSITIS:\nThe mean mucositis was scored by using qualitative and quantitative parameters (Spijkervet et al, 1989b). Four different local signs of mucositis (k) might be distinguished: 1=white discoloration; 2=erythema; 3=formation of pseudomembranes; 4=ulceration. Mucositis of the oral cavity was determined for maximally eight distinguishable irradiated areas of the mouth: buccal mucosa (left and right), soft and hard palates, dorsum and border of the tongue (left and right), and the floor of the mouth. The degree of mucositis of each area was scored according to the local signs of mucositis. The length (E) of the local sign of mucositis was measured: 1=⩽1 cm; 2=1–2 cm; 3=2–4 cm; 4=⩾4 cm. The degree of mucositis was defined as the product of the values k and E. The mucositis score was defined as the mean of the scores assigned to the irradiated areas. The mucositis was also scored according to the WHO score (grade 0=normal, no mucositis; grade 1=soreness and erythema; grade 2=erythema, ulcers, can eat solids; grade 3=ulcers, requires liquid diet only; grade 4=alimentation not possible) (Anonymous, 1979).\n\nBODY.PATIENTS AND METHODS.ASSESSMENTS.FEEDING:\nThe quality of feeding was scored (0=normal, no changes; 1=symptoms without medication; 2=symptoms with medication; 3=liquid diet only; 4=nasogastric tube feeding) and body weight was determined. Afterwards the changes in weight were scored.\n\nBODY.PATIENTS AND METHODS.ASSESSMENTS.MICROBIOLOGICAL METHODS:\nTo acquire an oral washing, patients gargled and rinsed their mouth with 10 ml sterile saline for 30 s, and spit it into a sterile vial. One millilitre of the sample was diluted in 9 ml of Brain Heart infusion (BHI) (Oxoid, Basingstoke, England) and this suspension was serially diluted in BHI. The suspensions were than plated out onto 5% sheep blood agar, McConkey-3 agar (Oxoid) and Yeast morphology agar (Merck, Darmstadt, Germany). The agar plates and BHI broth cultures tubes were incubated overnight aerobically at 37°C. If an agar plate did not show growth and the corresponding BHI broth culture of the dilution series did show turbidity, then this suspension was plated again onto the agars mentioned above. With this enrichment step even low numbers of Candida species and Gram-negative bacilli could be detected (Spijkervet et al, 1989a). By reading and counting the plates after incubation the viable numbers of microorganisms per millilitre was estimated. The identification was performed by standard microbiological techniques.\n\nBODY.PATIENTS AND METHODS.ASSESSMENTS.DEFINITIONS:\nCarriage of a particular microorganism was defined as the condition in which a patient showed a minimum of two consecutive oral washings positive for that organism. Colonisation index of the oral cavity was defined as the sum of logarithms of the concentrations of a particular microorganism isolated from 1 ml of oral-washing specimens divided by the number of oral washings.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSIS:\nSample size calculation of this study was based on the study by Spijkervet (Spijkervet et al, 1990). A two-sided α of 5% and a power of 80% were used. Additionally, a 50% reduction of mucositis in the PTA group was determined as clinically relevant with a normal incidence of mucositis of 80%. Based on these assumptions, 27 patients in each group would be sufficient. Intention-to-treat analysis was performed. The difference of dropouts between both groups was analysed using Fisher's exact test. The results were analysed, with respect to mean mucositis, the loss of weight, and colonisation numbers for five different microorganisms (t-test for independent samples) and the WHO mucositis score and feeding (Mann–Whitney U test). Two-sided tests, performed at the 5% level of significance, were used.\n\nBODY.RESULTS:\nPatient characteristics are shown in Table 1\n Table 1Patient characteristicsPatients characteristicsPlaceboPTAP-valueaAge mean±sd (years)54 (10.8)56 (12.5)0.36Gender: male/female (n)22/1024/90.79 Tumor site Oral cavity (n)17230.41 Oropharynx (n)108 Hypopharynx (n)11 Unknown primary(n)41 Histology Squamous (n)31321.0 Other (n)11 T-stage T1 (n)450.25 T2 (n)65 T3 (n)88 T4 (n)914 bTx (n)51 N-stage N0 (n)10140.12 N1 (n)610 N2a (n)21 N2b (n)93 N2c (n)13 N3 (n)42 Surgery Yes (n)21270.17 No (n)116 Dentures Yes (n)20250.29 No (n)128 All differences between the groups were analysed using χ2 test exceptain which t-test was used.bSix patients with an unknown primary tumour.. From January 1994 to February 1997, 65 patients were included, 33 patients received PTA lozenges and 32 the placebo lozenges. Out of the 65 included patients, 58 patients were evaluable for the total evaluation period of 5 weeks. Seven patients (11%) dropped out earlier from the study, five of the PTA group (15%) and two of the placebo group (6%). The difference of dropouts between both groups was not significant. One patient (PTA) developed a skin reaction, unlikely caused by the PTA lozenges, and one patient (placebo) could not suck the lozenges because of the tumour surgery of his tongue. The other five dropped out for reasons not related to one of the lozenges. Of the seven dropouts, one patient stopped after 1 week, two patients after 2 weeks, one patient after 3 weeks and three patients after 4 weeks radiation.\n\nBODY.RESULTS.MUCOSITIS:\nThe mean mucositis was the same in the PTA group and the placebo group during the study period (P>0.2) (Figure 1Figure 1The mean mucositis score (±s.d.) for the PTA group (▵) and the placebo group (□).). During the 5-week observation period 89% of the patients in the PTA group developed pseudomembranes and in the placebo group 94%. The mucositis according to the WHO score did not differ throughout the study period between both groups (P>0.5). In the PTA group, 80% of the patients developed grades 3 and 4 mucositis according to the WHO score, and in the placebo group 90%. The appearance of pseudomembranes was for both groups at a similar radiation status; after 30 Gy of radiation.\n\nBODY.RESULTS.FEEDING:\nSix patients (19%) in the placebo group (n=32) and two patients (6%) in the PTA group (n=33) needed nasogastric tube feeding during the evaluation period (P=0.08).\n\nBODY.RESULTS.BODY WEIGHT:\nThe mean weight loss after 5 weeks of radiation was less in the PTA group by 1.3 kg (s.d. 3.0) than in the placebo group 2.8 kg (s.d. 2.9) (P=0.05).\n\nBODY.RESULTS.MICROORGANISMS:\nFor viridans streptococci, Enterococci, Staphylococcus aureus and coagulase-negative Staphylococci, a similar pattern of carriage and colonisation was found in both groups. The colonisation and carriage of Candida species at baseline was equal in both groups (P>0.8). During the first two radiation weeks the colonisation for Candida species showed an increase in the placebo group and a decrease in the PTA group. After 2 weeks, an increase in both groups was found but the difference between the two groups remained significant during the total study period (P<0.05) (Figure 2Figure 2Percentage of patients colonised for Candida species for the PTA group (lines) and the placebo group (solid).). During the first 4 weeks a significant difference was found for the carriage of Candida species (P<0.03). The colonisation and carriage of aerobic Gram-negative bacilli at baseline was equal in both groups (P=0.9). During the radiation period the colonisation in the PTA group was less than in the placebo group, but the difference was only significant in the second week of radiation (P=0.05) (Figure 3Figure 3Percentage of patients colonised for aerobic Gram-negative bacilli for the PTA group (lines) and the placebo group (solid).). During the first 2 weeks the carriage of aerobic Gram-negative bacilli was reduced in the PTA group (P<0.04). In weeks 3–5 the difference was no longer significant. All results are summarised in Table 2\n Table 2Results of the PTA–placebo group for mean mucositis, weight loss, carriage and colonisation index of Candida species and aerobic Gram-negative bacilli 012345 WeekXs.d.Xs.d.Xs.d.Xs.d.Xs.d.Xs.d.Mean mucositis PTA000.50.72.21.74.62.74.52.75.02.3 Placebo000.30.42.62.04.82.34.92.55.22.8 Weight loss PTA00−0.31.00.41.30.62.11.02.71.33.0 Placebo000.30.9a0.61.21.31.72.22.32.82.9a Candida col. Index PTA1.01.30.40.80.50.90.60.90.81.51.01.5 Placebo1.11.31.21.6a1.61.7a1.71.7a2.01.7a1.91.8a Candida carriage PTA (%)48 23.5 17.6 31.8 30.8 36 Placebo (%)52 76.5b 82.4b 68.2b 69.2b 64 Aerobic Gram-negative bac. col. Index PTA0.71.20.40.80.40.90.61.20.51.00.40.9 Placebo0.71.40.81.10.91.1a0.81.00.81.40.81.5 Aerobic Gram-negative bac. Carriage PTA (%)52.4 23.1 25 42.9 54.5 40 Placebo (%)47.6 76.9b 75b 57.1 45.5 60 aRepresents a significant difference between the PTA and placebo group using an independent sample t-test.bRepresents a significant difference between the PTA and placebo group using χ2 test..\n\nBODY.DISCUSSION:\nIn this study, no effect of selective oral flora elimination on mucositis was observed. The development of mucositis follows the same pattern as reported in an earlier cohort study (Spijkervet et al, 1989c). According to the WHO score, 80% of the patients in the PTA group and 90% in the placebo group developed mucositis grades 3 and 4. This severity of mucositis is in accordance with the outcomes of Okuno et al (1997). In other studies, different outcomes are reported. A significant reduction of mucositis in the PTA group was found by two groups (Spijkervet et al, 1990; Kaanders et al, 1995). Both studies are nonrandomised clinical trials and the PTA group is compared with a historical control group. A reduction in mucositis distribution and affected area, dysphagia and weight loss in the PTA group is reported by Symonds et al. (1996). From a total of 221 patients in that study, 98 (44%) patients had a larynx carcinoma (PTA=57, placebo=41). Of these patients, the radiation field included only a minor part of the oral mucosa, in which mucositis could develop. In the study of Okuno et al only a subjective patient-reported amelioration of mucositis was reported but no reduction was found in clinically observed mucositis (Okuno et al, 1997). The PTA group (n=54) in that study consisted of an unblinded (n=29) and a blinded (n=26) group. Only in the unblinded PTA group the mean mucositis, reported by the patients was lower than the placebo group. Recently, it was shown in a randomised study including 77 patients that selective oral flora elimination does not reduce radiation mucositis (Wijers et al, 2001). A problem in that study is the short evaluation time of only the first 3 weeks of radiotherapy. Whereas normally development of severe mucositis starts after 3 weeks of radiation (Kaanders et al, 1999). A complicating factor in comparing outcomes from different studies is the assessment method of mucositis. All studies used different scoring methods. Therefore, two scoring methods were used in the current study. The WHO score is a widely accepted method, but this score is a combination of local mucositis signs and general complaints (Anonymous, 1979). The other scoring method in the current study is based only on mucosal signs of mucositis (Spijkervet et al, 1989b). It therefore provides a more precise estimation of the mucositis development at the mucosal level. It further makes a comparison possible with outcomes of earlier publications (Spijkervet et al, 1989b; Parulekar et al, 1998). For future studies, we recommend the use of the OMAS-score from the mucositis study group because this scoring method is a reliable, well-validated and widely accepted method (Sonis et al, 1999). This scoring method was published later than the start of the current study and was therefore not used as a scoring method in this study. In the current study, patients who received PTA lozenges had less weight loss than patients receiving placebo lozenges, assuming a better feeding status of the PTA-group patients (mean difference 1.5 kg). Owing to the minimal effect of PTA on the mucositis level, we found the feeding outcome of minor clinical relevance. In our study, carriage and colonisation of aerobic Gram-negative bacilli and Candida species decreased in the PTA group but was not totally eradicated. These findings are in line with the findings of other studies (Spijkervet et al, 1990; Kaanders et al, 1995; Symonds et al, 1996; Wijers et al, 2001). Based on these findings and the development and severity of mucositis it can be concluded that the presence of Candida species and aerobic Gram-negative bacilli has no influence on the development of radiation-induced mucositis. The increase of the carriage and colonisation of Candida species and aerobic Gram-negative bacilli after 3 weeks of radiation may be explained by the development of xerostomia, which makes dissolving of the lozenges more difficult. Wijers et al tried to overcome this problem by using a paste instead of a lozenge. However, the paste appeared to be an unsuccessful form of application because already after randomisation 32% of the patients refused further participation and 77% of the patients dropped out after four study weeks because of bad taste and unpleasant sensation of the paste texture in the mouth (Wijers et al, 2001). In conclusion, PTA lozenges have a positive effect on the quality of feeding and the amount of weight loss but cannot prevent severe mucositis. The presence of Candida species and aerobic Gram-negative bacilli has no effect on the development and severity of radiation-induced mucositis. Based on our findings of this randomised clinical trial, we do not recommend this type of supportive care for the reduction or prevention of radiation mucositis.\n\n**Question:** Compared to Placebo lozenge what was the result of PTA lozenge on Need of feeding tube?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
506
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Oral mucositis and selective elimination of oral flora in head and neck cancer patients receiving radiotherapy: a double-blind randomised clinical trial\n\n ABSTRACT:\n\n\nBODY:\nRadiotherapy in head and neck cancer patients can induce oral mucositis, which is an acute inflammation of the oral mucosa. Until now no effective intervention has been developed to prevent oral mucositis in radiotherapy (Sutherland and Browman, 2001). This prevention is even more relevant now because altered fractionation schedules for the treatment of head and neck malignancies induce more severe mucositis (Kaanders et al, 1999). All patients receiving radiotherapy in the head and neck region develop oral mucositis to some extent, depending on radiation schedule, radiation field, radiation volume and cumulative dose (Miralbell et al, 1999). Clinically, mucositis appears in a conventional radiation scheme after a cumulative radiation dose of 10–20 Gy as a white discoloration of the mucosa because of hyperkeratinisation. The next stage is a deepening erythema followed by the development of pseudomembranes and ulcerations. Severe mucositis, appearing as pseudomembranes, will develop at the end of the third week of radiation, after about 30 Gy (Baker, 1982; Spijkervet et al, 1989b). Prevention of severe mucositis is important because mucositis affects the patient's feeding status, physical and mental well-being and it can influence the course of radiotherapy (Sutherland and Browman, 2001). Further oral pain because of mucositis has a serious impact on the quality of life of patients (Miralbell et al, 1999). Several mechanisms are supposed to play a role in the development of mucositis: changes at the cellular level of the basal cell layer, inflammatory process in the epithelium and influence of bacteria on mucosal surface. Changed oral flora, colonising the oral mucosa, may aggravate the mucosa reaction because of radiation (Van Saene and Martin, 1990). The carriage and colonisation of aerobic Gram-negative bacilli are thought to play a role in the pathogenesis of irradiation mucositis (Bernhoft and Skaug, 1985). A hypothesis has been proposed on the development of mucositis in four consecutive phases, in which the ulcerative/bacterial phase is thought to play a role in the development of fibrous pseudomembranes of the oral mucosa (Sonis, 1998). A pilot study in 15 patients reported the protective effect of an antibiotic lozenge for selective elimination of the oral flora (Spijkervet et al, 1990). Less severe mucositis and a less mean mucositis score compared to a historical control group was observed. None of the PTA-(polymyxin E 2 mg, tobramycin 1.8 mg and amphotericin B 10 mg) treated patients needed nasogastric tube feeding. In a cohort study including 36 patients, it was found that PTA lozenges may reduce irradiation mucositis (Kaanders et al, 1995). In contrast, randomised studies reported conflicting effects on mucositis by selective oral flora elimination (Symonds et al, 1996; Okuno et al, 1997; Wijers et al, 2001). The aim of this study was to evaluate in a randomised, double-blind, placebo-controlled trial the effects of selective oral flora elimination on the development of irradiation-induced oral mucositis, feeding, weight loss and colonisation of aerobic Gram-negative bacilli and yeast.\n\nBODY.PATIENTS AND METHODS.PROTOCOL:\nPatients with a malignant tumour in the head and neck regions to be treated with primary curative or postoperative radiotherapy were eligible for this study. Inclusion criteria for the study were: external bilateral irradiation via parallel-opposed portals by a linear accelerator (4–6 MeV), fractionation of 2 Gy daily, five times a week, with a prescribed dose of at least 50 Gy and at least 50% of the oral mucosa in the field of radiation. The dose specification was in line with ICRU 50 recommendations (Anonymous, 1993). Criteria for exclusion were: (1) an oral mucosa defect other than related to tumour surgery; (2) need for an obturator or resection prosthesis and; (3) treatment with antibiotics for an oral infection the last 2 weeks before the start of irradiation. As a standard procedure all patients were evaluated before radiation treatment for potential risk factors for oral complications by means of a thorough oral and dental evaluation, including a radiographic examination. All potential risk factors were eliminated appropriately before the start of radiotherapy. The supportive oral care regimen consisted of a daily protocol of cleansing the oral cavity by means of spraying with saline by the dental hygienist, and mouth rinsing by the patients with a salt–baking soda solution at least eight times a day to remove sticky saliva and debris. Dentate patients applied a neutral fluoride gel every second day with custom-made trays and edentulous patients were not allowed to wear their dentures during the course of radiotherapy (Jansma et al, 1992). The Medical Ethical Committee approved the study and all eligible patients gave written informed consent.\n\nBODY.PATIENTS AND METHODS.ASSIGNMENT:\nThe eligible patients were randomised to receive active lozenges of 1 g containing polymyxin E 2 mg, tobramycin 1.8 mg and amphotericin B 10 mg (PTA) or placebo lozenges. The ingredients of the placebo lozenge were identical with the PTA lozenge except the active drugs. The colour, taste and form of the PTA and placebo lozenges were identical as well. Randomisation was performed by the hospital pharmacist according to a computer-generated, randomised allocation schedule. Patients, clinicians, dental hygienists and microbiologists were blind for who was taking antibiotics. The patients used a PTA or placebo lozenge four times daily starting the first day of irradiation during the total radiation period.\n\nBODY.PATIENTS AND METHODS.ASSESSMENTS:\nThe study period included only the first 5 weeks of radiation because of the wide range of field changes above 50 Gy of radiation. During the study period mucositis, feeding and body weight scores were performed at the start of radiotherapy and twice weekly (Monday–Thursday). The assessments were performed by an assigned dental hygienist. For each patient a mean weekly score was calculated on the basis of these two scores. These mean scores were used for further statistical analyses. Twice weekly (Monday–Thursday) and two times before the start of radiation oral washings were obtained to examine the oral flora for Gram-negative bacilli, Candida species, viridans streptococci, Enterococci, Staphylococcus aureus and coagulase-negative Staphylococci.\n\nBODY.PATIENTS AND METHODS.ASSESSMENTS.MUCOSITIS:\nThe mean mucositis was scored by using qualitative and quantitative parameters (Spijkervet et al, 1989b). Four different local signs of mucositis (k) might be distinguished: 1=white discoloration; 2=erythema; 3=formation of pseudomembranes; 4=ulceration. Mucositis of the oral cavity was determined for maximally eight distinguishable irradiated areas of the mouth: buccal mucosa (left and right), soft and hard palates, dorsum and border of the tongue (left and right), and the floor of the mouth. The degree of mucositis of each area was scored according to the local signs of mucositis. The length (E) of the local sign of mucositis was measured: 1=⩽1 cm; 2=1–2 cm; 3=2–4 cm; 4=⩾4 cm. The degree of mucositis was defined as the product of the values k and E. The mucositis score was defined as the mean of the scores assigned to the irradiated areas. The mucositis was also scored according to the WHO score (grade 0=normal, no mucositis; grade 1=soreness and erythema; grade 2=erythema, ulcers, can eat solids; grade 3=ulcers, requires liquid diet only; grade 4=alimentation not possible) (Anonymous, 1979).\n\nBODY.PATIENTS AND METHODS.ASSESSMENTS.FEEDING:\nThe quality of feeding was scored (0=normal, no changes; 1=symptoms without medication; 2=symptoms with medication; 3=liquid diet only; 4=nasogastric tube feeding) and body weight was determined. Afterwards the changes in weight were scored.\n\nBODY.PATIENTS AND METHODS.ASSESSMENTS.MICROBIOLOGICAL METHODS:\nTo acquire an oral washing, patients gargled and rinsed their mouth with 10 ml sterile saline for 30 s, and spit it into a sterile vial. One millilitre of the sample was diluted in 9 ml of Brain Heart infusion (BHI) (Oxoid, Basingstoke, England) and this suspension was serially diluted in BHI. The suspensions were than plated out onto 5% sheep blood agar, McConkey-3 agar (Oxoid) and Yeast morphology agar (Merck, Darmstadt, Germany). The agar plates and BHI broth cultures tubes were incubated overnight aerobically at 37°C. If an agar plate did not show growth and the corresponding BHI broth culture of the dilution series did show turbidity, then this suspension was plated again onto the agars mentioned above. With this enrichment step even low numbers of Candida species and Gram-negative bacilli could be detected (Spijkervet et al, 1989a). By reading and counting the plates after incubation the viable numbers of microorganisms per millilitre was estimated. The identification was performed by standard microbiological techniques.\n\nBODY.PATIENTS AND METHODS.ASSESSMENTS.DEFINITIONS:\nCarriage of a particular microorganism was defined as the condition in which a patient showed a minimum of two consecutive oral washings positive for that organism. Colonisation index of the oral cavity was defined as the sum of logarithms of the concentrations of a particular microorganism isolated from 1 ml of oral-washing specimens divided by the number of oral washings.\n\nBODY.PATIENTS AND METHODS.STATISTICAL ANALYSIS:\nSample size calculation of this study was based on the study by Spijkervet (Spijkervet et al, 1990). A two-sided α of 5% and a power of 80% were used. Additionally, a 50% reduction of mucositis in the PTA group was determined as clinically relevant with a normal incidence of mucositis of 80%. Based on these assumptions, 27 patients in each group would be sufficient. Intention-to-treat analysis was performed. The difference of dropouts between both groups was analysed using Fisher's exact test. The results were analysed, with respect to mean mucositis, the loss of weight, and colonisation numbers for five different microorganisms (t-test for independent samples) and the WHO mucositis score and feeding (Mann–Whitney U test). Two-sided tests, performed at the 5% level of significance, were used.\n\nBODY.RESULTS:\nPatient characteristics are shown in Table 1\n Table 1Patient characteristicsPatients characteristicsPlaceboPTAP-valueaAge mean±sd (years)54 (10.8)56 (12.5)0.36Gender: male/female (n)22/1024/90.79 Tumor site Oral cavity (n)17230.41 Oropharynx (n)108 Hypopharynx (n)11 Unknown primary(n)41 Histology Squamous (n)31321.0 Other (n)11 T-stage T1 (n)450.25 T2 (n)65 T3 (n)88 T4 (n)914 bTx (n)51 N-stage N0 (n)10140.12 N1 (n)610 N2a (n)21 N2b (n)93 N2c (n)13 N3 (n)42 Surgery Yes (n)21270.17 No (n)116 Dentures Yes (n)20250.29 No (n)128 All differences between the groups were analysed using χ2 test exceptain which t-test was used.bSix patients with an unknown primary tumour.. From January 1994 to February 1997, 65 patients were included, 33 patients received PTA lozenges and 32 the placebo lozenges. Out of the 65 included patients, 58 patients were evaluable for the total evaluation period of 5 weeks. Seven patients (11%) dropped out earlier from the study, five of the PTA group (15%) and two of the placebo group (6%). The difference of dropouts between both groups was not significant. One patient (PTA) developed a skin reaction, unlikely caused by the PTA lozenges, and one patient (placebo) could not suck the lozenges because of the tumour surgery of his tongue. The other five dropped out for reasons not related to one of the lozenges. Of the seven dropouts, one patient stopped after 1 week, two patients after 2 weeks, one patient after 3 weeks and three patients after 4 weeks radiation.\n\nBODY.RESULTS.MUCOSITIS:\nThe mean mucositis was the same in the PTA group and the placebo group during the study period (P>0.2) (Figure 1Figure 1The mean mucositis score (±s.d.) for the PTA group (▵) and the placebo group (□).). During the 5-week observation period 89% of the patients in the PTA group developed pseudomembranes and in the placebo group 94%. The mucositis according to the WHO score did not differ throughout the study period between both groups (P>0.5). In the PTA group, 80% of the patients developed grades 3 and 4 mucositis according to the WHO score, and in the placebo group 90%. The appearance of pseudomembranes was for both groups at a similar radiation status; after 30 Gy of radiation.\n\nBODY.RESULTS.FEEDING:\nSix patients (19%) in the placebo group (n=32) and two patients (6%) in the PTA group (n=33) needed nasogastric tube feeding during the evaluation period (P=0.08).\n\nBODY.RESULTS.BODY WEIGHT:\nThe mean weight loss after 5 weeks of radiation was less in the PTA group by 1.3 kg (s.d. 3.0) than in the placebo group 2.8 kg (s.d. 2.9) (P=0.05).\n\nBODY.RESULTS.MICROORGANISMS:\nFor viridans streptococci, Enterococci, Staphylococcus aureus and coagulase-negative Staphylococci, a similar pattern of carriage and colonisation was found in both groups. The colonisation and carriage of Candida species at baseline was equal in both groups (P>0.8). During the first two radiation weeks the colonisation for Candida species showed an increase in the placebo group and a decrease in the PTA group. After 2 weeks, an increase in both groups was found but the difference between the two groups remained significant during the total study period (P<0.05) (Figure 2Figure 2Percentage of patients colonised for Candida species for the PTA group (lines) and the placebo group (solid).). During the first 4 weeks a significant difference was found for the carriage of Candida species (P<0.03). The colonisation and carriage of aerobic Gram-negative bacilli at baseline was equal in both groups (P=0.9). During the radiation period the colonisation in the PTA group was less than in the placebo group, but the difference was only significant in the second week of radiation (P=0.05) (Figure 3Figure 3Percentage of patients colonised for aerobic Gram-negative bacilli for the PTA group (lines) and the placebo group (solid).). During the first 2 weeks the carriage of aerobic Gram-negative bacilli was reduced in the PTA group (P<0.04). In weeks 3–5 the difference was no longer significant. All results are summarised in Table 2\n Table 2Results of the PTA–placebo group for mean mucositis, weight loss, carriage and colonisation index of Candida species and aerobic Gram-negative bacilli 012345 WeekXs.d.Xs.d.Xs.d.Xs.d.Xs.d.Xs.d.Mean mucositis PTA000.50.72.21.74.62.74.52.75.02.3 Placebo000.30.42.62.04.82.34.92.55.22.8 Weight loss PTA00−0.31.00.41.30.62.11.02.71.33.0 Placebo000.30.9a0.61.21.31.72.22.32.82.9a Candida col. Index PTA1.01.30.40.80.50.90.60.90.81.51.01.5 Placebo1.11.31.21.6a1.61.7a1.71.7a2.01.7a1.91.8a Candida carriage PTA (%)48 23.5 17.6 31.8 30.8 36 Placebo (%)52 76.5b 82.4b 68.2b 69.2b 64 Aerobic Gram-negative bac. col. Index PTA0.71.20.40.80.40.90.61.20.51.00.40.9 Placebo0.71.40.81.10.91.1a0.81.00.81.40.81.5 Aerobic Gram-negative bac. Carriage PTA (%)52.4 23.1 25 42.9 54.5 40 Placebo (%)47.6 76.9b 75b 57.1 45.5 60 aRepresents a significant difference between the PTA and placebo group using an independent sample t-test.bRepresents a significant difference between the PTA and placebo group using χ2 test..\n\nBODY.DISCUSSION:\nIn this study, no effect of selective oral flora elimination on mucositis was observed. The development of mucositis follows the same pattern as reported in an earlier cohort study (Spijkervet et al, 1989c). According to the WHO score, 80% of the patients in the PTA group and 90% in the placebo group developed mucositis grades 3 and 4. This severity of mucositis is in accordance with the outcomes of Okuno et al (1997). In other studies, different outcomes are reported. A significant reduction of mucositis in the PTA group was found by two groups (Spijkervet et al, 1990; Kaanders et al, 1995). Both studies are nonrandomised clinical trials and the PTA group is compared with a historical control group. A reduction in mucositis distribution and affected area, dysphagia and weight loss in the PTA group is reported by Symonds et al. (1996). From a total of 221 patients in that study, 98 (44%) patients had a larynx carcinoma (PTA=57, placebo=41). Of these patients, the radiation field included only a minor part of the oral mucosa, in which mucositis could develop. In the study of Okuno et al only a subjective patient-reported amelioration of mucositis was reported but no reduction was found in clinically observed mucositis (Okuno et al, 1997). The PTA group (n=54) in that study consisted of an unblinded (n=29) and a blinded (n=26) group. Only in the unblinded PTA group the mean mucositis, reported by the patients was lower than the placebo group. Recently, it was shown in a randomised study including 77 patients that selective oral flora elimination does not reduce radiation mucositis (Wijers et al, 2001). A problem in that study is the short evaluation time of only the first 3 weeks of radiotherapy. Whereas normally development of severe mucositis starts after 3 weeks of radiation (Kaanders et al, 1999). A complicating factor in comparing outcomes from different studies is the assessment method of mucositis. All studies used different scoring methods. Therefore, two scoring methods were used in the current study. The WHO score is a widely accepted method, but this score is a combination of local mucositis signs and general complaints (Anonymous, 1979). The other scoring method in the current study is based only on mucosal signs of mucositis (Spijkervet et al, 1989b). It therefore provides a more precise estimation of the mucositis development at the mucosal level. It further makes a comparison possible with outcomes of earlier publications (Spijkervet et al, 1989b; Parulekar et al, 1998). For future studies, we recommend the use of the OMAS-score from the mucositis study group because this scoring method is a reliable, well-validated and widely accepted method (Sonis et al, 1999). This scoring method was published later than the start of the current study and was therefore not used as a scoring method in this study. In the current study, patients who received PTA lozenges had less weight loss than patients receiving placebo lozenges, assuming a better feeding status of the PTA-group patients (mean difference 1.5 kg). Owing to the minimal effect of PTA on the mucositis level, we found the feeding outcome of minor clinical relevance. In our study, carriage and colonisation of aerobic Gram-negative bacilli and Candida species decreased in the PTA group but was not totally eradicated. These findings are in line with the findings of other studies (Spijkervet et al, 1990; Kaanders et al, 1995; Symonds et al, 1996; Wijers et al, 2001). Based on these findings and the development and severity of mucositis it can be concluded that the presence of Candida species and aerobic Gram-negative bacilli has no influence on the development of radiation-induced mucositis. The increase of the carriage and colonisation of Candida species and aerobic Gram-negative bacilli after 3 weeks of radiation may be explained by the development of xerostomia, which makes dissolving of the lozenges more difficult. Wijers et al tried to overcome this problem by using a paste instead of a lozenge. However, the paste appeared to be an unsuccessful form of application because already after randomisation 32% of the patients refused further participation and 77% of the patients dropped out after four study weeks because of bad taste and unpleasant sensation of the paste texture in the mouth (Wijers et al, 2001). In conclusion, PTA lozenges have a positive effect on the quality of feeding and the amount of weight loss but cannot prevent severe mucositis. The presence of Candida species and aerobic Gram-negative bacilli has no effect on the development and severity of radiation-induced mucositis. Based on our findings of this randomised clinical trial, we do not recommend this type of supportive care for the reduction or prevention of radiation mucositis.\n\n**Question:** Compared to Placebo lozenge what was the result of PTA lozenge on Candida sp. colonisation during the study?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
508
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Improvements in survival of the uncemented Nottingham Total Shoulder prosthesis: a prospective comparative study\n\n ABSTRACT.BACKGROUND:\nThe uncemented Nottingham Total Shoulder Replacement prosthesis system (Nottingham TSR) was developed from the previous BioModular® shoulder prosthesis taking into consideration the causes of the initial implant's failure. We investigated the impact of changes in the design of Nottingham TSR prosthesis on its survivorship rate.\n\nABSTRACT.METHODS:\nSurvivorship analyses of three types of uncemented total shoulder arthroplasty prostheses (BioModular®, initial Nottingham TSR and current Nottingham TSR systems with 11, 8 and 4 year survivorship data respectively) were compared. All these prostheses were implanted for the treatment of disabling pain in the shoulder due to primary and secondary osteoarthritis or rheumatoid arthritis. Each type of the prosthesis studied was implanted in consecutive group of patients – 90 patients with BioModular® system, 103 with the initial Nottingham TSR and 34 patients with the current Nottingham TSR system. The comparison of the annual cumulative survivorship values in the compatible time range between the three groups was done according to the paired t test.\n\nABSTRACT.RESULTS:\nThe 8-year and 11-year survivorship rates for the initially used modified BioModular® uncemented prosthesis were relatively low (75.6% and 71.7% respectively) comparing to the reported survivorship of the conventional cemented implants. The 8-year survivorship for the uncemented Nottingham TSR prosthesis was significantly higher (81.8%), but still not in the desired range of above 90%, that is found in other cemented designs. Glenoid component loosening was the main factor of prosthesis failure in both prostheses and mainly occurred in the first 4 postoperative years. The 4-year survivorship of the currently re-designed Nottingham TSR prosthesis, with hydroxylapatite coating of the glenoid baseplate, was significantly higher, 93.1% as compared to 85.1% of the previous Nottingham TSR.\n\nABSTRACT.CONCLUSION:\nThe initial Nottingham shoulder prosthesis showed significantly higher survivorship than the BioModular® uncemented prosthesis, but lower than expected. Subsequently re-designed Nottingham TSR system presented a high short term survivorship rate that encourages its ongoing use\n\nBODY.BACKGROUND:\nInflammatory or degenerative processes of glenohumeral joint lead to pain and restriction of movements of the shoulder. Prosthetic replacement of the glenohumeral joint has gained in popularity because of its efficacy in relieving pain. The pioneering successful prostheses for total shoulder arthroplasty have been based on an unconstrained design, i.e. a metal spherical head component fixed to a metal intramedullary stem articulating with a high-density polyethylene socket (Table 1). These components are stabilized in the adjacent bone using polymethylmethacrylate bone cement [1]. The important cause for failure of the cemented prostheses was related to the glenoid component, with a 0.01–6% rate of loosening [2-4]. Table 1 Long term survivorship data on cemented and the outcome of a large series of a cementless total shoulder replacement prostheses Reference Type of prosthesis No. of Patients Survivorship End point criteria Glenoid failure rate Overall failure rate Tarchia, Cofield & Settergren [5] Neer I & II cemented 113 [31 = OA, 36 = RA 12 = 2ary OA] 10years = 93% 15years = 87% Revision – severe pain, abd < 90°, ext rot < 20° 7/113 14/113 Brenner, Perlic, Clayton & Dennis [8] Neer II & Gristina cemented 51 [37 = OA 14 = RA] 11years = 75% Severe pain, radiographic evidence of component loosening 3/51 6/51 Cofield [6] Cofield cementless 180 [110 = OA 28 =RA 30 = 2ary OA 12 = revisions] Not calculated Revision 5/180 12/180 Pfahler et al [4] Aequalis cemented 705 [418 = OA 107 = RA 180 = 2ary OA] Not calculated Revision 9/705 43/705 OA = osteoarthritis, RA = rheumatoid arthritis The long term survivorship of the prosthesis developed by C. Neer for the cemented total shoulder arthroplasty (TSA) is almost the single one with well documented outcomes [5] with 87% fifteen year survivorship rate for Neer I & II cemented shoulder prostheses. This implant has become the gold standard, against which all the successive prosthetic designs are compared. Further developments of TSA implants have been aimed at enhancing longevity by addressing the following three most critical issues: (1) Improving the incorporation of the glenoid component using a more \"biological\" type of fixation in order to reduce the rate of mechanical loosening; (2) Designing a better glenoid component to achieve the lowest possible rate of wear; (3) Finding the best method for the fixation of the humeral component while allowing good preservation of the humeral bone stock, taking into consideration need for possible future revision surgery. These goals can potentially be achieved using an uncemented design, with press fit and/or tissue in-growth porous coating of the metal, at its bone interface. There is evidence that the porous coating at the proximal part of the stem is superior to the press fit design [6], possibly because of lesser stress shielding of the proximal humerus and subsequently less bone resorption, and preservation of the proximal humeral bone stock. Biological fixation of the glenoid component currently requires the use of a metal backing or metal base-plate that serves as the \"bone in-growth\" surface and results in a more even distribution of the compression forces on the bone. On this baseplate a high-density polyethylene insert is mounted, either molded onto the metal or fixed using some form of fastening mechanism at the time of surgery. This bearing should be at least 3 mm thick (at its thinnest part) to reduce polyethylene wear [2,7]. Currently there are very few long-term peer reviewed large series survivorship data on cemented TSAs [5,8] and no survivorship data on cementless designs (Table 1). Survivorship studies with commonly acceptable clinical outcome criteria are important, but currently there is no uniform agreement on these types of criteria. Most authors consider revision of the prosthesis an end point in its survivorship [9]. Furthermore published reports on single prosthetic designs so far have only provided short-term postoperative follow-up data or a small number of patients. All these factors result in wide confidence intervals in survivorship tables and lead to difficulty in drawing a meaningful interpretation of the results [9]. In spite of these problems we can reach some tentative conclusions from TSA outcome by different authors (Table 1). The best long-term outcome is that reported for the Neer II cemented prosthesis, with a 93% ten years survivorship. Short-term glenoid failure, requiring implant removal, reaches the rate of around 6% for cemented designs and 3% for cementless designs. Glenoid failure is the cause of between 20% – 50% of all failed TSAs, cemented or cementless. Survivorship of cemented TSA is highest in patients with rheumatoid arthritis. We are nor aware of survivorship data available for rheumatoid patients with cementless designs. It is logical to conclude that any cementless prosthetic design should possess at least the best survivorship characteristics of the cemented prostheses in order to be considered as an alternative. In order to achieve the goal of the desired survivorship rates of cementless TSA a chain of modification of the initial BioModular® prosthesis was employed with eventual evolvement of the current Nottingham TSR design. The main characteristics of this prosthesis are: (1) The use of an indexable offset modular head, to improve the anatomical configuration of the implant and the optimal soft tissue balancing [10,11]. (2) A porous proximal stem in order to eliminate the stress shielding effect. (3) Conformed radii of humeral and glenoid components in order to reduce point loading and point wear of the polyethylene glenoid liner [12]. (4) Hydroxyapatite lining of the glenoid baseplate-bone interface in order to provide a \"biologic\" milieu to improve an osseo-integration [13]. (5) An improved capture mechanism for holding the polyethylene bearing onto the base-plate in order to reduce the liner disengagement rate. Following these design changes we hypothesize that the TSA with cementless implantation will present improved survivorship rates. Therefore in order to estimate the improvement in a performance of the prostheses design we have compared survivorship data of the BioModular® prosthesis – with or without the \"Wallace\" prototype offset head (Fig 1) – with the survivorship of the initial design of the Nottingham TSR (Fig 2) and the latest design of the Nottingham TSR with the glenoid component base-plate covered by hydroxyapatite (Fig 3). We show that Nottingham TSR uncemented prosthesis has better short and midterm survivorship than the BioModular® uncemented design. Figure 1The BioModular® total shoulder arthroplasty prosthetic design is shown. (A) A titanium BioModular® stem. (B) An offset \"Wallace\" head. (C) The glenoid trays: on the right – the low-profile version, top row – view from the side, bottom row – view into the tray, showing the glenoid liner capture mechanisms. Figure 2The Nottingham TSR total shoulder arthroplasty prosthetic design is shown. (A) A chrome cobalt stem. (B) A glenoid tray showing the capture mechanism for the polyethylene liner. (C) A glenoid tray seen from the back, showing the areas for bone in-growth. (D) An off-set head with a morse taper assembling interface. Figure 3The Nottingham TSR total shoulder arthroplasty prosthetic design with glenoid base-plate coated with hydroxyapatite. (A) A lateral view of the base-plate with fixation screws and with mounted polyethylene liner. (B) A view on the bone interface side of the base-plate covered by hydroxyapatite.\n\nBODY.METHODS:\nSurvivorship analyses of three types of uncemented TSA prostheses, implanted for the treatment of disabling pain in the shoulder due to primary and secondary osteoarthritis or rheumatoid arthritis, were compared. Each type of the prosthesis studied was implanted in consecutive group of patients, i.e. Group 1: the BioModular® TSA prosthesis, Group 2: The initial Nottingham TSR prosthesis and Group 3: The most recently redesigned Nottingham TSR prosthesis. The indication for surgery and criteria for inclusion in the study were pain in the shoulder with functional disability combined with radiographic evidence of an advanced destruction of the humeral and glenoid articular surfaces. Patients compatible with these criteria but who were medically unfit for surgery, due to advanced systemic disease, were not offered the procedure and were therefore excluded from the study. Group 1 was comprised of 90 patients who were operated between 1989–1994 (15 men and 75 women, mean age 61 years, range 19 – 92 years). These patients had the uncemented BioModular® Total Shoulder Prostheses implanted, either with the standard non-offset head or the prototype (\"Wallace\") offset humeral head. The mean follow up period in this group was 8.8 years. Group 2 patients were treated with the initial Nottingham TSR cementless prosthesis where the glenoid component had no hydroxyapatite backing. This group included 103 patients – 12 men and 91 women, average age of 58 years (range: 20–84 years). This design has been used between 1994 and 1997 and the patients had a mean follow up period of 6.4 years. Group 3 comprised of 34 patients, who had a hydroxyapatite coated glenoid component base plate implanted, as part of their most recent Nottingham TSR. In this group there were two men and 32 women, with a mean age of 64 years (range 31–89 years). These patients were operated in 1998–99 and had a mean follow up of 3.2 years. The characteristics of the different groups of patients are given in the Table 2. All these patients were included in the survivorship analyses. Table 2 Characteristics of the study groups Study Group Age (years) Male/Female Mean follow up (years) OA RA 2 nd ary OA Total Number Group 1 Mean: 61 Range: 19–92 15/75 8.8 48 (1 with RC tear) 31 (2 with RC tear) 11 90 Group 2 Mean: 58 Range: 20–84 12/91 6.4 47 36 (2 with RC tear) 20 103 Group 3 Mean: 64 Range: 31–89 2/32 3.2 19 12 (1 with RC tear) 3 34 OA = osteoarthritis, RA = rheumatoid arthritis, RC – rotator cuff muscle For the comparison of the three TSA prostheses' clinical outcome we used a survivorship analysis according to the method described by Murray et al [14] which is based on Rothman's formula for the confidence limits determination. The criterion for failure in this series was revision surgery requiring removal or exchange of either part of or a whole prosthesis. The indications for these re-operations were: (1) An increased level of pain during follow-up, that appeared to be related to the implant, with restriction of external rotation to under 20° and abduction to under 60° and/or newly developed radiolucency around the glenoid peg or complete peri-prosthetic radiolucency at the metal-bone interface, more then 2 mm in width, around either the humeral or glenoid components [7]. The radiographic evaluation was done by the surgical team and by the radiologist; (2) Deep wound infection; (3) Migration of any of the prosthetic components. For the purpose of postoperative follow up and identification of the possible failure of the implants the patients were monitored annually. This review evaluation included estimation of the level of pain using a Visual Analog Scale, a clinical examination of the range of movements of the shoulder and radiographic evaluation of the shoulder with an anterior – posterior view and an axillary view to allow assessment of the alignment and position of the components, the presence of any change in position over time and measurement of any radiolucency at the prosthesis-bone interface. Information on patients who died during the follow up period, which is included in the survivorship analysis, was obtained either from the Registrar for Births, Marriages and Deaths or from the hospitals' registration systems and through direct contact with General Practitioners or relatives. The comparison of the annual cumulative survivorship values (quantitative type of variables) in the compatible time range between the three groups was done according to the paired t test and the p < 0.05 was considered significant. The TSA operations were performed through a proximally extended deltopectoral approach with a longitudinal clavicle osteotomy and a lesser tuberosity osteotomy [15]. This approach was used to facilitate glenoid exposure and to ensure stable deltoid and subscapularis muscle reattachment, that allows early postoperative shoulder mobilization [16]. The authors prefer this surgical approach also because it protects the deltoid muscle during retraction. After humeral head resection, humeral stem alignment was established using the anatomical neck as a guide to prosthesis placement, preserving the rotator cuff. Humeral medullary canal and glenoid surface preparation were carried out using specially designed reamers. With the standard BioModular® stems either a standard or an offset prototype modular head was used. The head geometry, apart from the off-set feature, was identical in the two types of prostetic heads used with the BioModular® implant. In the Nottingham TSR system humeral stems in four sizes, offset modular heads in five sizes and glenoid bearings in three thicknesses were available for optimal component fitting and soft tissue balancing. In six patients (three in the Group 1, two in the Group 2 and one patient in the Group 3 – Table 2) tears in rotator cuff muscles were identified and firmly repaired. Five of six patients with rotator cuff muscles tears suffered from the rheumatoid arthritis. During the first three months postoperatively every patient underwent intensive physiotherapy following a standard programme aimed at improving strength and range of movements. Since the surgical procedure was carried out through a deltopectoral approach with a lesser tuberosity osteotomy and its strong reattachment, an immediate postoperative rehabilitation was possible with very few limitations. Usually a work on external rotation and elevation was commenced from the first postoperative day with isometrics, passive and active elevation and external rotation up to the level of movement achieved during the surgery. Patients used the broad arm sling intermittently only during the first 2–3 postoperative days. The exercise programme was increased as the patients gain confidence and pain relief aiming to achieve a maximal possible active and passive range of movements.\n\nBODY.RESULTS:\nThe eight year survivorship of the initial Nottingham TSR design (Group 2) was higher (p < 0.001) than observed in Group 1 patients with implanted BioModular® prostheses (Fig 4,5). The eight-year cumulative survivorship in the Group 2 was 81.8% and remained constant from the sixth postoperative year (Fig 5). The eight – and ten- year cumulative survival rates of Group 1 (BioModular® prosthesis) were 75.6% and 71.7% (Fig 4). The main causes of failure of the BioModular® prosthesis were related to the glenoid component, i.e. aseptic glenoid component loosening in 13 patients and uncoupling of the polyethylene bearing liner in 4 patients, overall 71% of failed cases (Table 3). Seventy one percent of the failed cases occurred during the first four postoperative years (Table 3) showing four year cumulative survivorship rate of 80.9% (Fig 4). The main drop in survivorship of the initial Nottingham TSR occurred also during the initial four postoperative years and was mainly due to glenoid component failure (11 of the 17 failed cases, Table 4). About half of the failures in Group 2 during the eight years of the survivorship analysis were due to aseptic loosening of the glenoid base-plate in eight patients, six of these patients were treated for primary or secondary osteoarthritis (Table 5). Table 3 Time distribution of the occurrence of prostheses failure in the Group 1 (patients operated in 1989 – 94 with BioModular ® uncemented TSA) according to the mode of failure Year Post Op Glenoid Loosening Bearing failure Infection Dislocation 1 3 1 0 1 2 1 1 0 1 3 0 0 1 3 4 3 1 1 0 5 1 0 0 0 6 2 0 0 0 7 2 0 0 0 8 0 0 0 0 9 1 0 0 0 10 0 1 0 0 11 0 0 0 0 Total 13 4 2 5 Table 4 Time distribution of the occurrence of prostheses failure in the Group 2 (patients operated in 1994 – 97 with the initial Nottingham TSR prosthesis) according to the mode of failure Year Post Op Glenoid Loosening Bearing failure Infection Dislocation 1 0 1 0 0 2 0 3 0 1 3 2 1 0 2 4 4 0 0 1 5 0 0 0 0 6 1 0 0 0 7 1 0 0 0 8 0 0 0 0 Total 8 5 0 4 Figure 4This graph shows the survival results of BioModular® total shoulder arthroplasty (vertical bars represent 95% confidence intervals). Figure 5This graph shows the survival rate of the initial design for the Nottingham TSR (vertical bars represent 95% confidence intervals). Table 5 Failed uncemented Nottingham TSR prostheses in Group 2 (patients operated in 1994 – 97) according to their mode of failure Component Mode of Failure Loosening Infection Malposition: bearing failure/head dislocation, stem malposition Glenoid 8 (OA = 4, RA = 2, 2 nd ary OA = 2) 0 7 [OA = 4, 2 nd ary OA = 3] Humeral 0 0 2 [2 nd ary OA = 2] OA = osteoarthritis, RA = rheumatoid arthritis Survivorship in patients with rheumatoid arthritis (RA) in both groups 1 and 2 was higher (p < 0.001) than in patients with osteoarthritis. The patients with RA who had the BioModular® prosthesis implanted, presented a 96.8% and 93.1% cumulative five and eight year survivorships respectively (Fig 6) and the RA patients with the initial Nottingham TSR had presented a constant 94.4% cumulative survivorships from the fourth to eights year postoperatively (Fig 7). Figure 6This graph shows the survival rates of the BioModular® total shoulder arthroplasty in patients with RA (vertical bars represent 95% confidence intervals). Figure 7This graph shows the survival rate of the initial design of the Nottingham TSR in patients with RA (vertical bars represent 95% confidence intervals). The initial Nottingham TSR prostheses showed higher eight year survivorship than BioModular® prostheses in patients with OA (p < 0.01). Survivorship of the BioModular® prosthesis in patients with primary osteoarthritis was 70.9% and 64.3% at five and eight years respectively and for the initial Nottingham TSR these values were 84.5% and 80.4% (Fig 8,9). Figure 8This graph shows the survival rate of the initial design for the Nottingham TSR in patients with OA (vertical bars represent 95% confidence intervals). Figure 9This graph shows the survival results of the BioModular® total shoulder arthroplasty in patients with OA (vertical bars represent 95% confidence intervals). The observed four-year survivorship of the patients in Group 3 was also significantly higher than the survivorship rates of the BioModular® prosthesis observed after the first four years after implantation (p = 0.02), with a 93.1% cumulative four year survivorship of the re-designed Nottingham TSR (Fig 10) comparing to the 80.9% of cumulative four year survivorship of the BioModular® prosthesis (Fig 4). Among the Group 3 patients only two prostheses failed, both in patients with osteoarthritis (Table 6). One failure was due to glenoid bearing disassembly, two years after the operation, and the other due to glenohumeral dislocation three years after the operation (Table 7). Table 6 Failed uncemented Nottingham TSR prostheses in the Group 3 (patients operated in 1998 -99) according to the mode of failure Component Mode of Failure Loosening Infection Malposition: bearing failure/head dislocation Glenoid 0 0 2 (OA = 2) Humeral 0 0 0 OA = osteoarthritis Table 7 Time distribution of the occurrence of prostheses failures in the Group 3 (patients operated in 1998 – 99 with the current Nottingham TSR prosthesis) according to the mode of failure Year Post Op Glenoid Loosening Bearing failure Infection Dislocation 1 0 0 0 0 2 0 1 0 0 3 0 0 0 1 4 0 0 0 0 Total 0 1 0 1 Figure 10This graph shows the survival of the current Nottingham TSR with a hydroxyapatite coated glenoid baseplate (vertical bars represent 95% confidence intervals).\n\nBODY.DISCUSSION:\nThe evolving cementless TSA prostheses should present longevity that is comparable with or better than conventionally used cemented implants. We evaluated the short and midterm survivorship of the Nottingham TSR cementless prosthesis, with comparison to the survivorship of the BioModular® TSA prosthesis from which the Nottingham TSR evolved, in order to estimate the ability of these implants to achieve the desirable survivorship rates. The transitions from one design to another occurred following recognition of causes of implant failure. The use of the offset head on the standard BioModular® stem design did not prevent a considerably high loosening rate. The subsequent change to a conforming design with an identical radii of curvature of the humeral head component and glenoid component and to a different glenoid component with a conical peg, allowing press-fit implantation, led to significant improvement in the middle term survivorship among the patients who had an implant of the initial Nottingham TSR design. We are aware of suggestions by other authors, that full conformity between the components may lead to an enhanced stress on the globoid rim due to loss of the humeral head translation possible in the normal shoulder joint, and as a consequence a higher risk for prosthetic loosening. [12,17]. Since this hypothesis has been raised following cadaveric studies and in vivo radiographic evaluation and has been never confirmed in clinical trials and since the exact degree of optimal mismatch of the glenoid and the humeral head radii is not known, the authors preferred the conforming design. This choice of conformity is based on the hypothesis that mismatch of the glenoid and humeral component curvature can lead to a considerable rate of polyethylene wear due to uneven force distribution between the components and point loading and point wear of the polyethylene [12]. The midterm survivorship in the Group 2 patients shows that the original Nottingham TSR had less favorable results when compared with the existing published survivorship studies on the Neer I & II cemented implants [5], with the outcome studies of the Cofield uncemented prostheses [6] and with the \"Aequalis\" cemented prosthesis [4], but is comparable with the study on the Neer II and Gristina prostheses [8]. The comparison with the latter study is more realistic because the groups of patients are more comparable to our patients, i.e.both series consist mainly of patients with primary osteoarthritis, smaller groups of patients with rheumatoid arthritis and some patients with secondary osteoarthritis, and they have similar indications for failure recognition. Although the midterm survivorship of the initial Nottingham TSR design showed a significant improvement over the survivorship rate of the BioModular® prosthesis, especially in the patients with osteoarthritis, this improvement did not reach the desired values of survivorship above 90% that has been reported for the cemented Neer I&II prostheses. We note that the overall lower than desired midterm survivorship rates in the Group 2 patients are due to less favorable performance of the Nottingham TSR prosthesis in patients with primary osteoarthritis, who had an eight year survivorship rate of only 80.4%. The interesting finding is the evidence of a significantly higher (and in the desirable range of above 90%) survivorship in patients with rheumatoid arthritis compared to the patients with osteoarthritis in both Group 1 and Group 2. The difference in the survivorship between patients with osteoarthritis and rheumatoid arthritis is consistent with observations in other reports on other prosthetic shoulder arthroplasty systems [8] and can be explained by the lower level of demand placed on a shoulder prostheses in a rheumatoid patient. In spite of the improved survivorship in the initial design of the Nottingham TSR it still showed an unsatisfactory short term loosening rate. It should be realized that the two most serious complications of any prosthetic surgery, e.g. deep wound infection and periprosthetic fracture, did not occur among any of the patients treated by the initial design of the Nottingham TSR. This can probably be attributed to the use of an appropriate surgical technique and instrumentation for the prosthesis implantation. The glenohumeral dislocation rate appeared to be similarly low in Group 1, five of 90 patients, and Group 2, four of 103 patients, (Tables 3,4). This finding shows that the tissue balancing technique for the Nottingham TSR prosthesis implantation, i.e. systematic intraoperative evaluation of an adequate free subacromial space, flush and stable alignment of the glenoid and humeral components with correct offset of the humeral head, adequate anterior – posterior laxity and ability to reattach the lesser tuberosity with the arm in external rotation without loosing of the desired glenohumeral reduction, was effective. The main mode of failure of the prostheses in Group 2 patients was aseptic loosening of the glenoid component predominantly occurring in the first four postoperative years and the second most important cause of failure cause bearing disassembly during the same postoperative period (Table 4). After having identified the two main causes of failure for the intermediate design of the Nottingham TSR prosthesis, steps were taken to change of the design of the metal base-plate of the glenoid component. To achieve an optimal bone osseointegration coating of the implant with hydroxyapatite was introduced. In order to eliminate glenoid bearing disassembly improvement of the capture mechanism for the glenoid bearing was implimented. When looking at the data for Group 3, the addition of hydroxyapatite to the porous coating of the glenoid base-plate has eliminated the original 3.9–5.6% rate of aseptic glenoid loosening from the second to the fourth postoperative years (Tables 3, 4, 7). Additionally by improving the capture mechanism of the glenoid bearing its disassembly has now became rare (Tables 3, 4, 7). Following these changes in design the four-year survivorship of the Nottingham TSR prostheses in the Group 3 patients showed a satisfactory 93.1 % rate, which is significantly higher than the four-year survivorship rates of the BioModular® system. Since in the Groups 1 and 2 the deterioration in the survivorships occurred predominantly in the first four postoperative years, the present high four-year survivorship rate of the newly designed prosthesis might indicate on a sustained long-term improvement of the prosthesis survivorship. Since Group 3 comprised of only 34 patients we have not subdivided and compared the subgroups according to the underlying pathology as we did in Groups 1 and 2. Furthermore, because the number of patients in Group 3 is not sufficient for the adequate power of the statistical comparison with the survivorship in Group 2 patients we can only suggest that the further improvement of the present Nottingham TSR system survivorship is likely to be seen. Future long-term survivorship studies will verify this point more precisely. However, with regard to its initial design (Group 2), there is a clear evidence that the cementless Nottingham TSR system led to a significant improvement in its midterm survivorship comparing to its predecessor, the BioModular® prosthesis.\n\nBODY.CONCLUSION:\nWe have shown that the discussed cementless TSA prosthesis design (Nottingham TSR), following a chain of modifications according to recognition of previous causes of failure, have reached short term survivorship rates that are comparable to the conventional cemented designs. Therefore, in the light of potential long term \"biological\" advantages of uncemented implants, these results are encouraging for the ongoing use and development of this type of prosthesis.\n\nBODY.ABBREVIATIONS:\nTSA – total shoulder arthroplasty TSR – total shoulder replacemen\n\nBODY.COMPETING INTERESTS:\nThe authors has received research funding from Biomet Merck Ltd.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nNR – processed the data and wrote the paper. LN – collected and analyzed the data. AM – collected the data. IJM – collected the data. WAW – collected and analyzed the data.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here:\n\n**Question:** Compared to BioModular® shoulder prosthesis what was the result of Initial Nottingham TSR design prosthesis on 8-year survivorship?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
513
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Comparative Study of Low Doses of Rosuvastatin and Atorvastatin on Lipid and Glycemic Control in Patients with Metabolic Syndrome and Hypercholesterolemia\n\n ABSTRACT.BACKGROUND/AIMS:\nThis multicenter, open-labeled, randomized trial was performed to compare the effects of rosuvastatin 10 mg and atorvastatin 10 mg on lipid and glycemic control in Korean patients with nondiabetic metabolic syndrome.\n\nABSTRACT.METHODS:\nIn total, 351 patients who met the modified National Cholesterol Education Program Adult Treatment Panel III (NCEP ATP III) criteria for metabolic syndrome with low-density lipoprotein cholesterol (LDL-C) levels ≥ 130 mg/dL were randomized to receive either rosuvastatin 10 mg (n = 173) or atorvastatin 10 mg (n = 178) for over 6 weeks.\n\nABSTRACT.RESULTS:\nAfter 6 weeks of treatment, greater reductions in total cholesterol (- 35.94 ± 11.38 vs. - 30.07 ± 10.46%, p < 0.001), LDL-C (48.04 ± 14.45 vs. 39.52 ± 14.42%, p < 0.001), non-high-density lipoprotein cholesterol (- 42.93 ± 13.15 vs. - 35.52 ± 11.76%, p < 0.001), and apolipoprotein-B (- 38.7 ± 18.85 vs. - 32.57 ± 17.56%, p = 0.002) levels were observed in the rosuvastatin group as compared to the atorvastatin group. Overall, the percentage of patients attaining the NCEP ATP III goal was higher with rosuvastatin as compared to atorvastatin (87.64 vs. 69.88%, p < 0.001). Changes in glucose and insulin levels, and homeostasis model assessment of insulin resistance index were not significantly different between the two groups. The safety and tolerability of the two agents were similar.\n\nABSTRACT.CONCLUSIONS:\nRosuvastatin 10 mg was more effective than atorvastatin 10 mg in achieving NCEP ATP III LDL-C goals in patients with nondiabetic metabolic syndrome, especially in those with lower NCEP ATP III target level goals.\n\nBODY.INTRODUCTION:\nMetabolic syndrome consists of a group of cardiovascular risk factors, namely dyslipidemia, high blood pressure (BP), abdominal obesity, and insulin intolerance, whose concurrent appearance increases the risk of atherosclerotic cardiovascular disease [1]. Using the modified National Cholesterol Education Program (NCEP) Expert Panel on Detection, Evaluation, and Treatment of High Blood Cholesterol in Adults (Adult Treatment Panel III [ATP III]) criteria, the prevalence of atherosclerotic cardiovascular disease is estimated to be as high as 24.8% in Korea and is continuing to rapidly increase to epidemic proportions [2]. Elevated cholesterol levels have also been shown to be a strong risk factor for the development of coronary heart disease (CHD). This clustering of risk factors may interact synergistically to affect atherosclerosis and cardiovascular events [3]. Current guidelines for lipid management stress the importance of low-density lipoprotein cholesterol (LDL-C) levels as the primary goal of therapy [4]; however, a high proportion of patients, especially those having high lipid levels, do not achieve their target LDL-C levels despite lipid-lowering therapy [5,6]. Statins effectively lower blood cholesterol levels and reduce the risk of cardiovascular events in many patient types, and are therefore recommended as first-line agents for lowering LDL-C levels [4,7]. Statins also improve other aspects of the lipid profile, such as increasing high-density lipoprotein cholesterol (HDL-C) and lowering triglyceride levels to some extent. Rosuvastatin is a highly effective HMG-CoA reductase inhibitor, which was registered in 2002 in Korea. Rosuvastatin use has been previously shown in numerous studies to be associated with greater LDL-C level reductions as compared to atorvastatin, simvastatin, or pravastatin use [8-10]. The primary objective of the current trial was to compare the effects of rosuvastatin 10 mg with that of atorvastatin 10 mg, which are the lowest-dose tablets available, on the percentage of patients who reach the NCEP ATP III LDL-C goal and safety in subjects with nondiabetic metabolic syndrome after 6 weeks of treatment. The secondary objective was to compare the effects of rosuvastatin with that of atorvastatin on glucose control and insulin resistance.\n\nBODY.METHODS.STUDY DESIGN:\nThis 6-week, multicenter, randomized, open-label, parallel-group, single-dose trial (NCT00335699) was designed to compare the efficacy of a single dose of rosuvastatin and atorvastatin in patients having nondiabetic metabolic syndrome with dyslipidemia (Fig. 1). The study was conducted from August 2005 to January 2006 at 20 medical centers in Korea. The study included a 6-week dietary run-in period before randomization, followed by a 6-week treatment phase. Subjects entering the run-in period were asked to follow the NCEP Step I diet and required to discontinue any previous lipid lowering therapy. Following the dietary lead-in period, patients with fasting LDL-C levels ≥ 130 mg/dL to < 220 mg/dL were selected and randomly assigned to two parallel treatment groups. At baseline, eligible subjects were randomized 1 : 1 to receive either rosuvastatin (Astra-Zeneca Korea, Seoul, Korea) 10 mg or atorvastatin (Pfizer Pharmaceuticals Korea, Seoul, Korea) 10 mg once daily at bedtime for 6 weeks. The study drug was discontinued and subjects were removed from the study if they withdrew informed consent, became pregnant, or developed creatine kinase levels greater than 10 times the upper normal limit. The ethics committees and institutional review boards at each participating hospital approved the study protocol. All patients provided informed consent to participate in this study.\n\nBODY.METHODS.SUBJECTS:\nPatients were ≥ 18 years of age and had nondiabetic metabolic syndrome. Metabolic syndrome was defined according to the modified NCEP ATP III criteria [11], which requires at least three of the following: abdominal obesity (waist circumference): men > 90 cm (36 inches), women > 80 cm (32 inches); triglyceride levels ≥ 150 mg/dL (1.70 mmol/L); HDL-C levels: men < 40 mg/dL (1.04 mmol/L) and women < 50 mg/dL (1.3 mmol/L); BP ≥ 130 / ≥ 85 mmHg or subject receiving antihypertensive treatment; and fasting blood glucose 110 mg/dL (6.11 mmol/L) to 125 mg/dL (6.94 mmol/L). Patients were excluded if they were pregnant or had malignancy. Additional exclusion criteria included diabetes, and active arterial disease such as unstable angina, myocardial infarction, cerebrovascular accident, coronary artery bypass surgery, or angioplasty within 2 months prior to enrollment. After completing the 6-week dietary run-in period, fasting LDL-C concentrations were required to be ≥ 130 mg/dL (3.36 mmol/L) to < 220 mg/dL (5.69 mmol/L) and fasting triglyceride levels were required to be < 400 mg/dL (4.52 mmol/L).\n\nBODY.METHODS.ASSESSMENTS:\nSample analysis for efficacy endpoints was performed in the Green Cross Reference Laboratory, Yongin, Korea, which was certified by the American College of Pathology (LAP No. 6708401) and the National Committee for Clinical Laboratory Standards. Blood samples from patients who had fasted for 12 hours were collected at all investigational sites and delivered by courier to the central laboratory within 24 hours of blood draw. To assess the primary efficacy endpoint, lipid parameters such as total cholesterol, LDL-C, HDL-C, and triglyceride levels were measured during the dietary lead-in period, at randomization, and 6 weeks after treatment. Additionally, levels of apolipoprotein A-1 and B, high-sensitivity C-reactive protein (hsCRP), insulin, glucose, and hemoglobin A1c (HbA1c) were measured at randomization and at 6 weeks after treatment. LDL-C levels were calculated using the Friedewald equation (LDL-C = total cholesterol - (HDL-C + triglyceride/5). The insulin resistance index was estimated using the homeostasis model assessment (HOMA) for insulin resistance based on the following formula: fasting serum insulin (μU/mL) × fasting plasma glucose (mmol/L)/22.5. According to the NCEP ATP III guidelines, the goal LDL-C level for each patient and the proportion of patients achieving the goal in each group was assessed. Persons with CHD or CHD risk equivalent (Framingham 10-year CHD risk > 20%) had a LDL-C level goal of < 100 mg/dL. Those with multiple risk factors had a LDL cholesterol level goal of < 130 mg/dL and those with 0 - 1 risk factor (s) had a goal LDL cholesterol of < 160 mg/dL. Individual demographic data, physical findings, vital signs, and adverse events were evaluated and recorded in the given case record form. To evaluate adverse events, various laboratory assessments including blood counts, and hemoglobin, aspartate aminotransferase, alanine aminotransferase, creatine kinase, electrolyte, and creatinine levels were performed at each time point.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nOne-hundred and forty-three evaluable subjects per treatment group were required to achieve 95% power for detecting a clinically significant difference of 6% at the 5% two-sided level in percentage change from baseline in LDL-C levels at 6 weeks with an assumed standard deviation of 14% [12]. Assuming a dropout rate of 20% during the randomized treatment period, approximately 180 subjects were recruited to each active treatment group. To obtain the required number of randomized subjects (360 in total), approximately 900 subjects were assumed to be needed for screening based on a screening failure rate of 60%. The primary analysis population was the last observation carried forward on the intention-to-treat population. This included all subjects with a baseline and at least one post-baseline lipid level measurement. All numeric variables were expressed as the mean ± SEM (standard error of the mean). Efficacy endpoints were analyzed using the unpaired t-test for continuous variables and Pearson's chi-square test for frequencies with 95% confidence intervals. Multivariate logistic regression analysis was used to evaluate the predictors for reaching target NCEP ATP III LDL-C levels after treatment. Variables used for analysis included the statin used, presence of coronary artery disease and hypertension, body mass index, gender, age, waist circumference, and lipid parameters. On the basis of the actual treatment received, safety data were evaluated for all patients who received at least one dose of study medication.\n\nBODY.RESULTS.SUBJECT CHARACTERISTICS:\nIn total, 645 subjects were screened for participation in this study. Of them, 370 patients entered the dietary lead-in phase and 351 patients met the inclusion criteria and were randomly assigned to treatment with either rosuvastatin 10 mg or atorvastatin 10 mg (Fig. 1). One patient was lost to follow-up and had no safety assessment. Table 1 shows demographic data and baseline characteristics of all 350 subjects who took at least one dose of the study drug at baseline. In terms of demographic data and baseline characteristics, no statistically significant differences existed between the two treatment groups. Patients had a mean age of 60 years in the rosuvastatin group and 58 years in the atorvastatin group. Mean body weights were 66 kg in the rosuvastatin group and 66 kg in the atorvastatin group. Mean systolic and diastolic BP and waist circumstance were comparable between the two groups (Table 1). A total of five patients dropped out before efficacy assessment. Data from 346 patients were analyzed for efficacy in the intention-to-treat population defined as those who took at least one dose of study drug and had lipid levels checked at baseline and follow-up. Safety assessments were performed in 350 patients who were randomized and available for follow-up.\n\nBODY.RESULTS.CHANGES IN METABOLIC PARAMETERS:\nLipid levels, glucose levels, insulin resistance indices, and hsCRP levels at baseline and 6 weeks are shown in Table 2. In each group, atherogenic lipid parameters including total cholesterol, LDL-C, triglyceride, non-HDL-C, and apolipoprotein B had significantly decreased after 6 weeks of treatment (p < 0.001 vs. baseline). Only the atorvastatin treatment produced a modest decrease in HDL-C. Rosuvastatin treatment significantly increased HbA1c and the HOMA index; however, no significant change occurred in the atorvastatin group. Data from two groups were analyzed for an efficacy comparison in the intention-to-treat population. Baseline values of all parameters were similar between the two groups. At 6 weeks after treatment, rosuvastatin 10 mg produced a significantly greater reduction in total cholesterol, LDL-C, non-HDL-C, and apolipoprotein B levels. Otherwise, no significant differences were detected in HDL-C and apolipoprotein A-1 levels between the two groups. In addition, no significant differences were observed with respect to glucose, HbA1c, and hsCRP levels, and HOMA index between the rosuvastatin and atorvastatin groups at 6 weeks (Table 2). At 6 weeks, LDL-C absolute values decreased by 48.04 ± 14.45 mg/dL in the rosuvastatin group and by 39.52 ± 14.42 mg/dL in the atorvastatin group; the former reduction associated with rosuvastatin use was significantly larger than that with atorvastatin (p < 0.0001). Percent changes from baseline in lipid profiles after treatment for 6 weeks, including LDL-C, are shown in Fig. 2. Reductions in total cholesterol (- 35.94 ± 11.38 vs. - 30.07 ± 10.46%, p < 0.0001), non-HDL-C (- 42.93 ± 13.15 vs. - 35.52 ± 11.76%, p < 0.0001), and apolipoprotein B (- 38.7 ± 18.85 vs. - 32.57 ± 17.56%, p = 0.0019) levels were larger in the rosuvastatin group as compared to the atorvastatin group (Fig. 2).\n\nBODY.RESULTS.LDL-C TARGET ACHIEVEMENT:\nAccording to the reported CHD or/and CHD risk equivalents and/or number of risk factors and/or Framingham 10-year risk, the NCEP ATP III LDL-C target goal was determined in each patient and the success rate in reaching their target goal was analyzed after 6 weeks in each group. The percentage of patients who reached their ATP III LDL-C level goals was higher in the rosuvastatin group (87.6 vs. 69.9%, p < 0.001). Among them, patients having LDL-C target cholesterol level goals of < 100 mg and < 130 mg reached their LDL-C target level goals more frequently in the rosuvastatin group as compared to the atorvastatin group. In contrast, in patients with a LDL-C target level goal < 160 mg, more than 96% reached their target goal without a significant difference between the rosuvastatin- and atorvastatin-treated groups (Fig. 3). The overall achievement rate for NCEP non-HDL-C level target goals after 6 weeks of treatment was 76.08% in the rosuvastatin group and 58.92% in the atorvastatin group (p = 0.067).\n\nBODY.RESULTS.PERCENT CHANGES IN GLUCOSE LEVELS AND INSULIN RESISTANCE:\nPercent changes in glucose levels and insulin resistance at 6 weeks are summarized in Table 3. Changes in glucose and insulin levels were not significantly different between the two groups; however, HbA1c levels were slightly higher in the rosuvastatin group with marginal significance. To evaluate insulin resistance in the two groups, the HOMA index was calculated. At 6 weeks, the HOMA index increased in both groups and the difference between groups was not significant.\n\nBODY.RESULTS.SAFETY:\nBoth rosuvastatin 10 mg and atorvastatin 10 mg were well tolerated, with similar incidences of adverse events. During the treatment period, 13 subjects in the rosuvastatin group and 9 subjects in the atorvastatin group reported adverse events (Table 4). The most frequent adverse events in the rosuvastatin group were edema and dizziness, both with incidences of 1.16%. Only five adverse events were reported in the atorvastatin group as related to the study drug; myalgia was reported in one case (0.56%). All adverse events were mild, developed within 2 weeks after starting treatment, had no action taken, and resolved spontaneously. No drug-related adverse effects were observed in the rosuvastatin group. Also, no patient had an increase in alanine aminotransferase level > 3 times the upper limit of normal or rhabdomyolysis.\n\nBODY.RESULTS.PREDICTORS FOR LDL-C LEVEL GOAL ACHIEVEMENT AT 6 WEEKS:\nOverall, the percentage of patients who reached NCEP ATP III LDL-C target level goals was higher in the rosuvastatin group as compared to the atorvastatin group. Univariate analysis showed that patients with target LDL-C levels at 6 weeks tended to be rosuvastatin-treated and have coronary artery disease. Multivariate logistic regression analyses that included age, gender, statin, coronary artery disease, hypertension, body mass index, waist circumference, baseline total cholesterol levels, and triglyceride levels showed that rosuvastatin treatment, the presence of coronary artery disease, female gender, lower total cholesterol level, and lower LDL-C levels at baseline were independent predictors for achievement of target LDL-C levels at 6 weeks (Table 5).\n\nBODY.DISCUSSION:\nThis study evaluated the comparative efficacy of the lowest doses available for two effective statins, rosuvastatin and atorvastatin, in Korean patients with nondiabetic metabolic syndrome. Rosuvastatin 10 mg was more effective than atorvastatin 10 mg in reducing LDL-C levels in subjects with nondiabetic metabolic syndrome after 6 weeks of treatment. Consistent with the greater reductions in LDL-C levels, more patients in the rosuvastatin group achieved LDL-C level goals as compared to the atorvastatin group. Otherwise, no significant difference was observed in glucose levels and insulin resistance. Metabolic syndrome, especially in the presence of high LDL-C levels, is already known to increase the risk of cardiovascular mortality and morbidity [13]. Statins are effective in decreasing LDL-C levels in patients with dyslipidemia. Survey studies have demonstrated that in real-world settings, only 67% of patients with treated dyslipidemia reach their LDL-C target level goals [14]. In this study, rosuvastatin treatment was associated with reaching recommended LDL-C level goals in a higher percentage of patients overall as compared to atorvastatin (87.6 vs. 69.9%). In particular, rosuvastatin was more effective in patients requiring more intensive LDL-C level lowering to less than 100 or 130 mg/dL. In high-risk patients with stronger targets of LDL-C levels < 100 mg/dL, rosuvastatin brought 83% of patients in this trial to the ATP III LDL-C level goal, which was higher than achieved in other studies conducted in South-Asian (76%) and Hispanic-American (61%) patients [15,16]. Both statins, however, were effective in patients with high target LDL-C level goals < 160 mg/dL. These data highlight the importance of using highly effective statins in high-risk patients to enable them to achieve their lower NCEP ATP III LDL-C level goals. With respect to other elements of the lipid profile, improvements in total cholesterol, apolipoprotein B, and non-HDL-C levels were also significantly greater with rosuvastatin as compared to atorvastatin, whereas changes in HDL-C, triglyceride, and apolipoprotein A1 levels were similar in both treatment groups. Unlike other studies in which rosuvastatin effectively raised HDL-C levels [9,15], HDL-C levels in this study were not effectively improved in either group [9]. Metabolic syndrome is associated with an increased risk of both insulin resistance and diabetes [17]. Additionally, changes in the insulin resistance index were investigated by evaluating the HOMA index, which is a positive predictor of metabolic syndrome [18]. Studies in an animal model of insulin resistance suggest that rosuvastatin treatment increases whole-body and peripheral tissue insulin sensitivity via improved cellular insulin signal transduction [19]. In contrast, in our study conducted in nondiabetic subjects, a tendency was detected for an increased HOMA index in both treatment arms. Major changes in this parameter were attributable to high increases in insulin concentrations. The degrees of percent change in fasting glucose, insulin concentrations, and HOMA index were not significantly different between the rosuvastatin and atorvastatin treatment groups. Thus, further studies are needed to elucidate the effects of statins on glucose metabolism, insulin secretion, and insulin sensitivity under diabetic or nondiabetic conditions. A multivariate analysis was performed to determine independent predictors of LDL-C goal achievement at 6 weeks. Overall, sex, the presence of coronary artery disease, LDL-C levels, and rosuvastatin treatment were predictive of target LDL-C achievement. Among these factors, rosuvastatin was the strongest predictor, with an odds ratio of 3.26. Moreover, the presence of coronary artery disease was an independent predictor of achieving target LDL-C levels. These patients were assumed to have been more likely to take interest in diet control or exercise than patients without coronary artery disease. Although the findings of this study are provocative, this study has important limitations. Recently, intensive regimens with 80 mg of atorvastatin or 20 mg of rosuvastatin have become available in Korea and produce greater reductions in atherosclerotic lipoprotein levels, which is particularly useful in patients with established coronary artery disease or acute coronary syndrome. Further studies comparing statins across dose ranges in patients not reaching their target goal with low-dose statins are required. Additionally, although changes metabolic parameters were not the primary endpoint of this study, a trend toward differences in blood glucose levels was observed between the two statins. Further studies are needed to elucidate the metabolic effects of statins. In conclusion, this study demonstrated that rosuvastatin 10 mg is significantly more effective than atorvastatin 10 mg in reducing LDL-C levels in patients with nondiabetic metabolic syndrome, especially among those with lower NCEP ATP III target level goals. Both statins were well tolerated.\n\n**Question:** Compared to Atorvastatin what was the result of Rosuvastatin on Levels of non-high-density lipoprotein cholesterol after 6 weeks of treatment?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
516
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Comparative Study of Low Doses of Rosuvastatin and Atorvastatin on Lipid and Glycemic Control in Patients with Metabolic Syndrome and Hypercholesterolemia\n\n ABSTRACT.BACKGROUND/AIMS:\nThis multicenter, open-labeled, randomized trial was performed to compare the effects of rosuvastatin 10 mg and atorvastatin 10 mg on lipid and glycemic control in Korean patients with nondiabetic metabolic syndrome.\n\nABSTRACT.METHODS:\nIn total, 351 patients who met the modified National Cholesterol Education Program Adult Treatment Panel III (NCEP ATP III) criteria for metabolic syndrome with low-density lipoprotein cholesterol (LDL-C) levels ≥ 130 mg/dL were randomized to receive either rosuvastatin 10 mg (n = 173) or atorvastatin 10 mg (n = 178) for over 6 weeks.\n\nABSTRACT.RESULTS:\nAfter 6 weeks of treatment, greater reductions in total cholesterol (- 35.94 ± 11.38 vs. - 30.07 ± 10.46%, p < 0.001), LDL-C (48.04 ± 14.45 vs. 39.52 ± 14.42%, p < 0.001), non-high-density lipoprotein cholesterol (- 42.93 ± 13.15 vs. - 35.52 ± 11.76%, p < 0.001), and apolipoprotein-B (- 38.7 ± 18.85 vs. - 32.57 ± 17.56%, p = 0.002) levels were observed in the rosuvastatin group as compared to the atorvastatin group. Overall, the percentage of patients attaining the NCEP ATP III goal was higher with rosuvastatin as compared to atorvastatin (87.64 vs. 69.88%, p < 0.001). Changes in glucose and insulin levels, and homeostasis model assessment of insulin resistance index were not significantly different between the two groups. The safety and tolerability of the two agents were similar.\n\nABSTRACT.CONCLUSIONS:\nRosuvastatin 10 mg was more effective than atorvastatin 10 mg in achieving NCEP ATP III LDL-C goals in patients with nondiabetic metabolic syndrome, especially in those with lower NCEP ATP III target level goals.\n\nBODY.INTRODUCTION:\nMetabolic syndrome consists of a group of cardiovascular risk factors, namely dyslipidemia, high blood pressure (BP), abdominal obesity, and insulin intolerance, whose concurrent appearance increases the risk of atherosclerotic cardiovascular disease [1]. Using the modified National Cholesterol Education Program (NCEP) Expert Panel on Detection, Evaluation, and Treatment of High Blood Cholesterol in Adults (Adult Treatment Panel III [ATP III]) criteria, the prevalence of atherosclerotic cardiovascular disease is estimated to be as high as 24.8% in Korea and is continuing to rapidly increase to epidemic proportions [2]. Elevated cholesterol levels have also been shown to be a strong risk factor for the development of coronary heart disease (CHD). This clustering of risk factors may interact synergistically to affect atherosclerosis and cardiovascular events [3]. Current guidelines for lipid management stress the importance of low-density lipoprotein cholesterol (LDL-C) levels as the primary goal of therapy [4]; however, a high proportion of patients, especially those having high lipid levels, do not achieve their target LDL-C levels despite lipid-lowering therapy [5,6]. Statins effectively lower blood cholesterol levels and reduce the risk of cardiovascular events in many patient types, and are therefore recommended as first-line agents for lowering LDL-C levels [4,7]. Statins also improve other aspects of the lipid profile, such as increasing high-density lipoprotein cholesterol (HDL-C) and lowering triglyceride levels to some extent. Rosuvastatin is a highly effective HMG-CoA reductase inhibitor, which was registered in 2002 in Korea. Rosuvastatin use has been previously shown in numerous studies to be associated with greater LDL-C level reductions as compared to atorvastatin, simvastatin, or pravastatin use [8-10]. The primary objective of the current trial was to compare the effects of rosuvastatin 10 mg with that of atorvastatin 10 mg, which are the lowest-dose tablets available, on the percentage of patients who reach the NCEP ATP III LDL-C goal and safety in subjects with nondiabetic metabolic syndrome after 6 weeks of treatment. The secondary objective was to compare the effects of rosuvastatin with that of atorvastatin on glucose control and insulin resistance.\n\nBODY.METHODS.STUDY DESIGN:\nThis 6-week, multicenter, randomized, open-label, parallel-group, single-dose trial (NCT00335699) was designed to compare the efficacy of a single dose of rosuvastatin and atorvastatin in patients having nondiabetic metabolic syndrome with dyslipidemia (Fig. 1). The study was conducted from August 2005 to January 2006 at 20 medical centers in Korea. The study included a 6-week dietary run-in period before randomization, followed by a 6-week treatment phase. Subjects entering the run-in period were asked to follow the NCEP Step I diet and required to discontinue any previous lipid lowering therapy. Following the dietary lead-in period, patients with fasting LDL-C levels ≥ 130 mg/dL to < 220 mg/dL were selected and randomly assigned to two parallel treatment groups. At baseline, eligible subjects were randomized 1 : 1 to receive either rosuvastatin (Astra-Zeneca Korea, Seoul, Korea) 10 mg or atorvastatin (Pfizer Pharmaceuticals Korea, Seoul, Korea) 10 mg once daily at bedtime for 6 weeks. The study drug was discontinued and subjects were removed from the study if they withdrew informed consent, became pregnant, or developed creatine kinase levels greater than 10 times the upper normal limit. The ethics committees and institutional review boards at each participating hospital approved the study protocol. All patients provided informed consent to participate in this study.\n\nBODY.METHODS.SUBJECTS:\nPatients were ≥ 18 years of age and had nondiabetic metabolic syndrome. Metabolic syndrome was defined according to the modified NCEP ATP III criteria [11], which requires at least three of the following: abdominal obesity (waist circumference): men > 90 cm (36 inches), women > 80 cm (32 inches); triglyceride levels ≥ 150 mg/dL (1.70 mmol/L); HDL-C levels: men < 40 mg/dL (1.04 mmol/L) and women < 50 mg/dL (1.3 mmol/L); BP ≥ 130 / ≥ 85 mmHg or subject receiving antihypertensive treatment; and fasting blood glucose 110 mg/dL (6.11 mmol/L) to 125 mg/dL (6.94 mmol/L). Patients were excluded if they were pregnant or had malignancy. Additional exclusion criteria included diabetes, and active arterial disease such as unstable angina, myocardial infarction, cerebrovascular accident, coronary artery bypass surgery, or angioplasty within 2 months prior to enrollment. After completing the 6-week dietary run-in period, fasting LDL-C concentrations were required to be ≥ 130 mg/dL (3.36 mmol/L) to < 220 mg/dL (5.69 mmol/L) and fasting triglyceride levels were required to be < 400 mg/dL (4.52 mmol/L).\n\nBODY.METHODS.ASSESSMENTS:\nSample analysis for efficacy endpoints was performed in the Green Cross Reference Laboratory, Yongin, Korea, which was certified by the American College of Pathology (LAP No. 6708401) and the National Committee for Clinical Laboratory Standards. Blood samples from patients who had fasted for 12 hours were collected at all investigational sites and delivered by courier to the central laboratory within 24 hours of blood draw. To assess the primary efficacy endpoint, lipid parameters such as total cholesterol, LDL-C, HDL-C, and triglyceride levels were measured during the dietary lead-in period, at randomization, and 6 weeks after treatment. Additionally, levels of apolipoprotein A-1 and B, high-sensitivity C-reactive protein (hsCRP), insulin, glucose, and hemoglobin A1c (HbA1c) were measured at randomization and at 6 weeks after treatment. LDL-C levels were calculated using the Friedewald equation (LDL-C = total cholesterol - (HDL-C + triglyceride/5). The insulin resistance index was estimated using the homeostasis model assessment (HOMA) for insulin resistance based on the following formula: fasting serum insulin (μU/mL) × fasting plasma glucose (mmol/L)/22.5. According to the NCEP ATP III guidelines, the goal LDL-C level for each patient and the proportion of patients achieving the goal in each group was assessed. Persons with CHD or CHD risk equivalent (Framingham 10-year CHD risk > 20%) had a LDL-C level goal of < 100 mg/dL. Those with multiple risk factors had a LDL cholesterol level goal of < 130 mg/dL and those with 0 - 1 risk factor (s) had a goal LDL cholesterol of < 160 mg/dL. Individual demographic data, physical findings, vital signs, and adverse events were evaluated and recorded in the given case record form. To evaluate adverse events, various laboratory assessments including blood counts, and hemoglobin, aspartate aminotransferase, alanine aminotransferase, creatine kinase, electrolyte, and creatinine levels were performed at each time point.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nOne-hundred and forty-three evaluable subjects per treatment group were required to achieve 95% power for detecting a clinically significant difference of 6% at the 5% two-sided level in percentage change from baseline in LDL-C levels at 6 weeks with an assumed standard deviation of 14% [12]. Assuming a dropout rate of 20% during the randomized treatment period, approximately 180 subjects were recruited to each active treatment group. To obtain the required number of randomized subjects (360 in total), approximately 900 subjects were assumed to be needed for screening based on a screening failure rate of 60%. The primary analysis population was the last observation carried forward on the intention-to-treat population. This included all subjects with a baseline and at least one post-baseline lipid level measurement. All numeric variables were expressed as the mean ± SEM (standard error of the mean). Efficacy endpoints were analyzed using the unpaired t-test for continuous variables and Pearson's chi-square test for frequencies with 95% confidence intervals. Multivariate logistic regression analysis was used to evaluate the predictors for reaching target NCEP ATP III LDL-C levels after treatment. Variables used for analysis included the statin used, presence of coronary artery disease and hypertension, body mass index, gender, age, waist circumference, and lipid parameters. On the basis of the actual treatment received, safety data were evaluated for all patients who received at least one dose of study medication.\n\nBODY.RESULTS.SUBJECT CHARACTERISTICS:\nIn total, 645 subjects were screened for participation in this study. Of them, 370 patients entered the dietary lead-in phase and 351 patients met the inclusion criteria and were randomly assigned to treatment with either rosuvastatin 10 mg or atorvastatin 10 mg (Fig. 1). One patient was lost to follow-up and had no safety assessment. Table 1 shows demographic data and baseline characteristics of all 350 subjects who took at least one dose of the study drug at baseline. In terms of demographic data and baseline characteristics, no statistically significant differences existed between the two treatment groups. Patients had a mean age of 60 years in the rosuvastatin group and 58 years in the atorvastatin group. Mean body weights were 66 kg in the rosuvastatin group and 66 kg in the atorvastatin group. Mean systolic and diastolic BP and waist circumstance were comparable between the two groups (Table 1). A total of five patients dropped out before efficacy assessment. Data from 346 patients were analyzed for efficacy in the intention-to-treat population defined as those who took at least one dose of study drug and had lipid levels checked at baseline and follow-up. Safety assessments were performed in 350 patients who were randomized and available for follow-up.\n\nBODY.RESULTS.CHANGES IN METABOLIC PARAMETERS:\nLipid levels, glucose levels, insulin resistance indices, and hsCRP levels at baseline and 6 weeks are shown in Table 2. In each group, atherogenic lipid parameters including total cholesterol, LDL-C, triglyceride, non-HDL-C, and apolipoprotein B had significantly decreased after 6 weeks of treatment (p < 0.001 vs. baseline). Only the atorvastatin treatment produced a modest decrease in HDL-C. Rosuvastatin treatment significantly increased HbA1c and the HOMA index; however, no significant change occurred in the atorvastatin group. Data from two groups were analyzed for an efficacy comparison in the intention-to-treat population. Baseline values of all parameters were similar between the two groups. At 6 weeks after treatment, rosuvastatin 10 mg produced a significantly greater reduction in total cholesterol, LDL-C, non-HDL-C, and apolipoprotein B levels. Otherwise, no significant differences were detected in HDL-C and apolipoprotein A-1 levels between the two groups. In addition, no significant differences were observed with respect to glucose, HbA1c, and hsCRP levels, and HOMA index between the rosuvastatin and atorvastatin groups at 6 weeks (Table 2). At 6 weeks, LDL-C absolute values decreased by 48.04 ± 14.45 mg/dL in the rosuvastatin group and by 39.52 ± 14.42 mg/dL in the atorvastatin group; the former reduction associated with rosuvastatin use was significantly larger than that with atorvastatin (p < 0.0001). Percent changes from baseline in lipid profiles after treatment for 6 weeks, including LDL-C, are shown in Fig. 2. Reductions in total cholesterol (- 35.94 ± 11.38 vs. - 30.07 ± 10.46%, p < 0.0001), non-HDL-C (- 42.93 ± 13.15 vs. - 35.52 ± 11.76%, p < 0.0001), and apolipoprotein B (- 38.7 ± 18.85 vs. - 32.57 ± 17.56%, p = 0.0019) levels were larger in the rosuvastatin group as compared to the atorvastatin group (Fig. 2).\n\nBODY.RESULTS.LDL-C TARGET ACHIEVEMENT:\nAccording to the reported CHD or/and CHD risk equivalents and/or number of risk factors and/or Framingham 10-year risk, the NCEP ATP III LDL-C target goal was determined in each patient and the success rate in reaching their target goal was analyzed after 6 weeks in each group. The percentage of patients who reached their ATP III LDL-C level goals was higher in the rosuvastatin group (87.6 vs. 69.9%, p < 0.001). Among them, patients having LDL-C target cholesterol level goals of < 100 mg and < 130 mg reached their LDL-C target level goals more frequently in the rosuvastatin group as compared to the atorvastatin group. In contrast, in patients with a LDL-C target level goal < 160 mg, more than 96% reached their target goal without a significant difference between the rosuvastatin- and atorvastatin-treated groups (Fig. 3). The overall achievement rate for NCEP non-HDL-C level target goals after 6 weeks of treatment was 76.08% in the rosuvastatin group and 58.92% in the atorvastatin group (p = 0.067).\n\nBODY.RESULTS.PERCENT CHANGES IN GLUCOSE LEVELS AND INSULIN RESISTANCE:\nPercent changes in glucose levels and insulin resistance at 6 weeks are summarized in Table 3. Changes in glucose and insulin levels were not significantly different between the two groups; however, HbA1c levels were slightly higher in the rosuvastatin group with marginal significance. To evaluate insulin resistance in the two groups, the HOMA index was calculated. At 6 weeks, the HOMA index increased in both groups and the difference between groups was not significant.\n\nBODY.RESULTS.SAFETY:\nBoth rosuvastatin 10 mg and atorvastatin 10 mg were well tolerated, with similar incidences of adverse events. During the treatment period, 13 subjects in the rosuvastatin group and 9 subjects in the atorvastatin group reported adverse events (Table 4). The most frequent adverse events in the rosuvastatin group were edema and dizziness, both with incidences of 1.16%. Only five adverse events were reported in the atorvastatin group as related to the study drug; myalgia was reported in one case (0.56%). All adverse events were mild, developed within 2 weeks after starting treatment, had no action taken, and resolved spontaneously. No drug-related adverse effects were observed in the rosuvastatin group. Also, no patient had an increase in alanine aminotransferase level > 3 times the upper limit of normal or rhabdomyolysis.\n\nBODY.RESULTS.PREDICTORS FOR LDL-C LEVEL GOAL ACHIEVEMENT AT 6 WEEKS:\nOverall, the percentage of patients who reached NCEP ATP III LDL-C target level goals was higher in the rosuvastatin group as compared to the atorvastatin group. Univariate analysis showed that patients with target LDL-C levels at 6 weeks tended to be rosuvastatin-treated and have coronary artery disease. Multivariate logistic regression analyses that included age, gender, statin, coronary artery disease, hypertension, body mass index, waist circumference, baseline total cholesterol levels, and triglyceride levels showed that rosuvastatin treatment, the presence of coronary artery disease, female gender, lower total cholesterol level, and lower LDL-C levels at baseline were independent predictors for achievement of target LDL-C levels at 6 weeks (Table 5).\n\nBODY.DISCUSSION:\nThis study evaluated the comparative efficacy of the lowest doses available for two effective statins, rosuvastatin and atorvastatin, in Korean patients with nondiabetic metabolic syndrome. Rosuvastatin 10 mg was more effective than atorvastatin 10 mg in reducing LDL-C levels in subjects with nondiabetic metabolic syndrome after 6 weeks of treatment. Consistent with the greater reductions in LDL-C levels, more patients in the rosuvastatin group achieved LDL-C level goals as compared to the atorvastatin group. Otherwise, no significant difference was observed in glucose levels and insulin resistance. Metabolic syndrome, especially in the presence of high LDL-C levels, is already known to increase the risk of cardiovascular mortality and morbidity [13]. Statins are effective in decreasing LDL-C levels in patients with dyslipidemia. Survey studies have demonstrated that in real-world settings, only 67% of patients with treated dyslipidemia reach their LDL-C target level goals [14]. In this study, rosuvastatin treatment was associated with reaching recommended LDL-C level goals in a higher percentage of patients overall as compared to atorvastatin (87.6 vs. 69.9%). In particular, rosuvastatin was more effective in patients requiring more intensive LDL-C level lowering to less than 100 or 130 mg/dL. In high-risk patients with stronger targets of LDL-C levels < 100 mg/dL, rosuvastatin brought 83% of patients in this trial to the ATP III LDL-C level goal, which was higher than achieved in other studies conducted in South-Asian (76%) and Hispanic-American (61%) patients [15,16]. Both statins, however, were effective in patients with high target LDL-C level goals < 160 mg/dL. These data highlight the importance of using highly effective statins in high-risk patients to enable them to achieve their lower NCEP ATP III LDL-C level goals. With respect to other elements of the lipid profile, improvements in total cholesterol, apolipoprotein B, and non-HDL-C levels were also significantly greater with rosuvastatin as compared to atorvastatin, whereas changes in HDL-C, triglyceride, and apolipoprotein A1 levels were similar in both treatment groups. Unlike other studies in which rosuvastatin effectively raised HDL-C levels [9,15], HDL-C levels in this study were not effectively improved in either group [9]. Metabolic syndrome is associated with an increased risk of both insulin resistance and diabetes [17]. Additionally, changes in the insulin resistance index were investigated by evaluating the HOMA index, which is a positive predictor of metabolic syndrome [18]. Studies in an animal model of insulin resistance suggest that rosuvastatin treatment increases whole-body and peripheral tissue insulin sensitivity via improved cellular insulin signal transduction [19]. In contrast, in our study conducted in nondiabetic subjects, a tendency was detected for an increased HOMA index in both treatment arms. Major changes in this parameter were attributable to high increases in insulin concentrations. The degrees of percent change in fasting glucose, insulin concentrations, and HOMA index were not significantly different between the rosuvastatin and atorvastatin treatment groups. Thus, further studies are needed to elucidate the effects of statins on glucose metabolism, insulin secretion, and insulin sensitivity under diabetic or nondiabetic conditions. A multivariate analysis was performed to determine independent predictors of LDL-C goal achievement at 6 weeks. Overall, sex, the presence of coronary artery disease, LDL-C levels, and rosuvastatin treatment were predictive of target LDL-C achievement. Among these factors, rosuvastatin was the strongest predictor, with an odds ratio of 3.26. Moreover, the presence of coronary artery disease was an independent predictor of achieving target LDL-C levels. These patients were assumed to have been more likely to take interest in diet control or exercise than patients without coronary artery disease. Although the findings of this study are provocative, this study has important limitations. Recently, intensive regimens with 80 mg of atorvastatin or 20 mg of rosuvastatin have become available in Korea and produce greater reductions in atherosclerotic lipoprotein levels, which is particularly useful in patients with established coronary artery disease or acute coronary syndrome. Further studies comparing statins across dose ranges in patients not reaching their target goal with low-dose statins are required. Additionally, although changes metabolic parameters were not the primary endpoint of this study, a trend toward differences in blood glucose levels was observed between the two statins. Further studies are needed to elucidate the metabolic effects of statins. In conclusion, this study demonstrated that rosuvastatin 10 mg is significantly more effective than atorvastatin 10 mg in reducing LDL-C levels in patients with nondiabetic metabolic syndrome, especially among those with lower NCEP ATP III target level goals. Both statins were well tolerated.\n\n**Question:** Compared to Atorvastatin what was the result of Rosuvastatin on Changes in glucose and insulin levels?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.