id
int64 1
263
| prompt
listlengths 1
1
| completion
listlengths 1
1
| Label
stringclasses 10
values |
|---|---|---|---|
1
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n \n\n## Background Limited information has been published regarding how specific processes for event adjudication can affect event rates in trials. We reviewed nonfatal myocardial infarctions (MIs) reported by site investigators in the international Platelet Glycoprotein IIb/IIIa in Unstable Angina: Receptor Suppression Using Integrilin (Eptifibatide) Therapy (PURSUIT) trial and those adjudicated by a central clinical events committee (CEC) to determine the reasons for differences in event rates. \n\n## Methods The PURSUIT trial randomised 10,948 patients with acute coronary syndromes to receive eptifibatide or placebo. The primary end-point was death or post-enrolment MI at 30 days as assessed by the CEC; this end-point was also constructed using site-reported events. The CEC identified suspected MIs by systematic review of clinical, cardiac enzyme, and electrocardiographic data. \n\n## Results The CEC identified 5005 (46%) suspected events, of which 1415 (28%) were adjudicated as MI. The site investigator and CEC assessments of whether a MI had occurred disagreed in 983 (20%) of the 5005 patients with suspected MI, mostly reflecting site misclassification of post-enrolment MIs (as enrolment MIs) or underreported periprocedural MIs. Patients for whom the CEC and site investigator agreed that no end-point MI had occurred had the lowest mortality at 30 days and between 30 days and 6 months, and those with agreement that a MI had occurred had the highest mortality. \n\n## Conclusion CEC adjudication provides a standard, systematic, independent, and unbiased assessment of end-points, particularly for trials that span geographic regions and clinical practice settings. Understanding the review process and reasons for disagreement between CEC and site investigator assessments of MI is important to design future trials and interpret event rates between trials. # Results \n\n## Incidence of disagreement Overall, 5005 (46%) patients with possible or suspected MI were identified and adjudicated by the CEC. The CEC identified more patients with end-point events than did the site investigators (13.6% versus 7.7% for placebo, 12.6% versus 6.2% for eptifibatide). The CEC and site investigator assessments of MI disagreed for 9% of all patients enrolled in the PURSUIT trial. The CEC identified MIs in 1415 of the 5005 patients with suspected MI. The site investigator and the CEC assessments disagreed in 983 (20%) of the 5005 patients. Of these 983 patients with disagreements, 816 patients had a MI identified by the CEC but not the site investigator, and 167 patients had a MI identified by site investigator but not the CEC. The proportion of patients with disagreement was similar among regions. \n\n## Reasons for disagreement Most often, when the site investigator had identified a MI and the CEC had not, the investigator had misclassified a MI at enrolment as an end-point MI, although by protocol these were not end-point events (Table [1](#)). Recurrent ischemic events without elevated cardiac enzymes or ECG evidence of MI were also incorrectly identified by site investigators as MIs (Table [1](#)). In cases where the CEC had identified a MI and the site investigators had not, one-third of those identified were MIs defined by enzyme elevations without clinical or ECG evidence of ischemia or infarction (Table [2](#)). Enzyme elevations after bypass surgery accounted for 25% of these cases. Patients with clinically evident ischemia reported by the site investigator and associated with cardiac enzyme elevations were not reported as MIs by investigators in 27% of the cases of disagreement (Table [2](#)). Few infarctions based on new Q waves without clinical evidence of reinfarction were identified by the CEC and not by site investigators. ::::table-wrap\n\n::: caption\nMyocardial infarctions identified by site investigators but not\nconfirmed by the clinical events committee\n:::\n\n```\n Eastern Europe Latin America North America Western Europe Overall\n```\n\n______________________________________________________________________\n\nClinical scenario (*n* = 24) (*n* = 8) (*n* = 57) (*n* = 78) (*n* = 167)\nEnrolment myocardial infarction^\\*^ 8 (33) 4 (50) 24 (42) 28 (36) 64 (38)\nIschemic event without infarction^†^ 7 (29) 0 (0) 8 (14) 19 (24) 34 (20)\nPeri-death infarction^‡^ 6 (25) 2 (25) 13 (23) 8 (10) 29 (17)\nPercutaneous coronary intervention related 0 (0) 1 (12.5) 6 (11) 10 (13) 17 (10)\nCoronary artery bypass surgery related 2 (8) 1 (12.5) 5 (9) 7 (9) 15 (9)\nMiscellaneous 1 (4) 0 (0) 1 (2) 6 (8) 8 (5)\n\nData presented as *n* (%). ^\\*^ Not an end-point event per protocol. ^†^\nClinical evidence of ischemia without electrocardiography (ECG) or\ncardiac enzyme evidence of infarction. ^‡^ Infarction suspected at the\ntime of death without supporting clinical, ECG, or cardiac enzyme data.:::: ::::table-wrap\n::: caption\nMyocardial infarctions identified by the clinical events committee but\nnot the site investigator\n:::\n\n```\n Eastern Europe Latin America North America Western Europe Overall\n```\n\n______________________________________________________________________\n\nClinical scenario (*n* = 182) (*n* = 44) (*n* = 299) (*n* = 291) (*n* = 816)\nAsymptomatic CK-MB elevation^\\*^ 83 (46) 23 (52) 37 (12) 128 (44) 271 (33)\nIschemic event^†^ 89 (49) 12 (27) 48 (16) 68 (23) 217 (27)\nCoronary artery bypass graft-related 6 (3) 6 (14) 138 (46) 52 (18) 202 (25)\nPCI-related 2 (1) 1 (2) 62 (21) 22 (8) 87 (11)\nEarly myocardial infarction^‡^ 1 (1) 0 (0.0) 3 (1) 3 (1) 7 (1)\nIsolated electrocardiogram (Q waves)^§^ 1 (1) 1 (2) 5 (2) 4 (1) 11 (1)\nPeri-death^¶^ 0 (0) 1 (2) 1 (0.3) 4 (1) 6 (1)\nMiscellaneous 0 (0) 0 (0) 5 (2) 10 (3) 15 (2)\n\nData presented as *n* (%). CK-MB, CK-MB = creatine kinase-myocardial\nband; PCI, percutaneous coronary intervention. ^*^ No clinical symptoms\nor electrocardiography (ECG) evidence of ischemia. ^†^ Clinical evidence\nof ischemia and ECG/cardiac enzyme evidence of infarction. ^‡^ Cardiac\nenzyme or ECG evidence of infarction < 24 hours after enrolment,\ndifferent from the enrolment event. ^§^ Identified by systematic review\nof ECGs without clinical evidence of reinfarction. ^¶^ Myocardial\ninfarction at the time of death with clinical, ECG, or cardiac enzyme\nevidence.:::: Table [3](#) presents the cardiac enzyme elevation for MIs that the CEC identified and the site investigators did not. These data exclude MIs associated with PCI or bypass surgery; by definition, those types of MI required enzyme elevations greater than three or five times the upper limit of normal (ULN), respectively. The ratio of creatine kinase-myocardial band (CK-MB) to its ULN was highest in North America (median [25^th^, 75^th^] 1.6 [1.2, 2.9]). Enzymes were similarly elevated between patients with MIs defined only by enzyme elevations (without symptoms or ECG changes) and patients with elevations associated with ECG or clinical evidence of ischemia. ::::table-wrap\n::: caption\nEnzyme elevations in patients with myocardial infarction identified by\nthe clinical events committee but not the site investigator^*^\n:::\n\n```\n Median peak CK/ULN Median peak CK-MB/ULN\n```\n\n______________________________________________________________________\n\nRegion *n* (25th, 75th percentiles) *n* (25th, 75th percentiles)\nEastern Europe 172 0.6 (0.3, 1.2) 167 1.4 (1.2, 1.9)\nLatin America 34 0.7 (0.4, 1.2) 34 2.0 (1.3, 2.6)\nNorth America 112 1.6 (1.0, 3.1) 106 2.9 (1.5, 5.5)\nWestern Europe 202 0.7 (0.4, 2.0) 196 1.7 (1.2, 3.0)\nOverall 520 0.9 (0.4, 1.9) 503 1.6 (1.2, 2.9):::: Table [4](#) presents the level of clinical certainty for MIs not associated with PCI or bypass surgery, as identified by the CEC but not the site investigators. Overall, 98 (18%) of these patients were assigned a low level of clinical certainty. The proportion of patients assigned a low level of clinical certainty varied among the regions, with the lowest in North America. ::::table-wrap\n::: caption\nLevel of clinical certainty^\\*^ for myocardial infarction identified by\nthe clinical events committee but not the site investigator\n:::\n\n```\n High certainty Low certainty Total\n```\n\n______________________________________________________________________\n\nEastern Europe 133 (76) 42 (24) 175\nLatin America 21 (58) 15 (42) 36\nNorth America 111 (98) 2 (2) 113\nWestern Europe 177 (82) 39 (18) 216\nOverall 442 (82) 98 (18) 540\n\nData presented as *n* (%). ^\\*^ See Methods.:::: \n\n## Effect of disagreement on outcomes The 30-day CEC rates of MI and death or MI overall are presented in Table [5](#) by geographic region. The event rates are also shown for the analyses in which the 98 patients assigned a low level of certainty were reclassified as no infarction. ::::table-wrap\n::: caption\nClinical events committee event rates (%) at 30 days\n:::\n\n```\n All patients With reclassification^*^ \n```\n\n______________________________________________________________________\n\nEvent Eptifibatide Placebo *P* Eptifibatide Placebo *P*\nDeath or myocardial infarction\\\nEastern Europe 21.0 19.7 18.0 17.9\\\nLatin America 16.1 15.7 14.1 13.2\\\nNorth America 11.7 15.0 11.7 15.0\\\nWestern Europe 13.8 14.8 12.9 13.7\\\nOverall 14.2 15.7 0.042 13.3 14.9 0.021\n\nMyocardial infarction\\\nEastern Europe 18.8 17.3 15.8 15.3\\\nLatin America 11.6 11.7 9.6 9.1\\\nNorth America 10.1 12.9 10.1 12.9\\\nWestern Europe 12.6 12.9 11.7 11.8\\\nOverall 12.6 13.6 0.137 11.6 12.7 0.08\n\n^\\*^See Methods; 98 patients with low clinical certainty reclassified as\nhaving no infarction.:::: The lowest mortality rates were in patients for whom the CEC and site investigators agreed that no MI had occurred by 30 days (Table [6](#)). The highest rates were in patients for whom there was agreement that a MI had occurred. Mortality was high in the group with MI identified by the site investigators but not the CEC; however, many of these patients had suspected sudden cardiac death as the event identified as a MI by the investigator (Table [1](#)). The absolute increase in mortality between 30 days and 6 months was greater in patients with CEC-determined MIs not identified by the site investigators than in patients with MI identified by the site investigators but not the CEC. ::::table-wrap\n::: caption\nMortality (30 days and 6 months) for cases of disagreement\n:::\n\n```\n Mortality (%) \n```\n\n______________________________________________________________________\n\n```\n *n* 30 days 30 days--6 months 6 months\n```\n\nCEC no / site no 9366 1.7 2.1 3.8\nCEC yes / site yes 599 22.0 5.7 27.7\nCEC yes / site no 816 7.2 5.4 12.6\nCEC no / site yes 167 24.0 2.3 26.3\n\nCEC, Clinical events committee.::::\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** eptifibatide\n**Comparator:** placebo\n**Outcome:** Death or myocardial infarction\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: x\n group_size: x\ncomparator:\n events: x\n group_size: x"
}
] |
intervention:
events: x
group_size: x
comparator:
events: x
group_size: x
|
2
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n \n\n## Background Limited information has been published regarding how specific processes for event adjudication can affect event rates in trials. We reviewed nonfatal myocardial infarctions (MIs) reported by site investigators in the international Platelet Glycoprotein IIb/IIIa in Unstable Angina: Receptor Suppression Using Integrilin (Eptifibatide) Therapy (PURSUIT) trial and those adjudicated by a central clinical events committee (CEC) to determine the reasons for differences in event rates. \n\n## Methods The PURSUIT trial randomised 10,948 patients with acute coronary syndromes to receive eptifibatide or placebo. The primary end-point was death or post-enrolment MI at 30 days as assessed by the CEC; this end-point was also constructed using site-reported events. The CEC identified suspected MIs by systematic review of clinical, cardiac enzyme, and electrocardiographic data. \n\n## Results The CEC identified 5005 (46%) suspected events, of which 1415 (28%) were adjudicated as MI. The site investigator and CEC assessments of whether a MI had occurred disagreed in 983 (20%) of the 5005 patients with suspected MI, mostly reflecting site misclassification of post-enrolment MIs (as enrolment MIs) or underreported periprocedural MIs. Patients for whom the CEC and site investigator agreed that no end-point MI had occurred had the lowest mortality at 30 days and between 30 days and 6 months, and those with agreement that a MI had occurred had the highest mortality. \n\n## Conclusion CEC adjudication provides a standard, systematic, independent, and unbiased assessment of end-points, particularly for trials that span geographic regions and clinical practice settings. Understanding the review process and reasons for disagreement between CEC and site investigator assessments of MI is important to design future trials and interpret event rates between trials. # Results \n\n## Incidence of disagreement Overall, 5005 (46%) patients with possible or suspected MI were identified and adjudicated by the CEC. The CEC identified more patients with end-point events than did the site investigators (13.6% versus 7.7% for placebo, 12.6% versus 6.2% for eptifibatide). The CEC and site investigator assessments of MI disagreed for 9% of all patients enrolled in the PURSUIT trial. The CEC identified MIs in 1415 of the 5005 patients with suspected MI. The site investigator and the CEC assessments disagreed in 983 (20%) of the 5005 patients. Of these 983 patients with disagreements, 816 patients had a MI identified by the CEC but not the site investigator, and 167 patients had a MI identified by site investigator but not the CEC. The proportion of patients with disagreement was similar among regions. \n\n## Reasons for disagreement Most often, when the site investigator had identified a MI and the CEC had not, the investigator had misclassified a MI at enrolment as an end-point MI, although by protocol these were not end-point events (Table [1](#)). Recurrent ischemic events without elevated cardiac enzymes or ECG evidence of MI were also incorrectly identified by site investigators as MIs (Table [1](#)). In cases where the CEC had identified a MI and the site investigators had not, one-third of those identified were MIs defined by enzyme elevations without clinical or ECG evidence of ischemia or infarction (Table [2](#)). Enzyme elevations after bypass surgery accounted for 25% of these cases. Patients with clinically evident ischemia reported by the site investigator and associated with cardiac enzyme elevations were not reported as MIs by investigators in 27% of the cases of disagreement (Table [2](#)). Few infarctions based on new Q waves without clinical evidence of reinfarction were identified by the CEC and not by site investigators. ::::table-wrap\n\n::: caption\nMyocardial infarctions identified by site investigators but not\nconfirmed by the clinical events committee\n:::\n\n```\n Eastern Europe Latin America North America Western Europe Overall\n```\n\n______________________________________________________________________\n\nClinical scenario (*n* = 24) (*n* = 8) (*n* = 57) (*n* = 78) (*n* = 167)\nEnrolment myocardial infarction^\\*^ 8 (33) 4 (50) 24 (42) 28 (36) 64 (38)\nIschemic event without infarction^†^ 7 (29) 0 (0) 8 (14) 19 (24) 34 (20)\nPeri-death infarction^‡^ 6 (25) 2 (25) 13 (23) 8 (10) 29 (17)\nPercutaneous coronary intervention related 0 (0) 1 (12.5) 6 (11) 10 (13) 17 (10)\nCoronary artery bypass surgery related 2 (8) 1 (12.5) 5 (9) 7 (9) 15 (9)\nMiscellaneous 1 (4) 0 (0) 1 (2) 6 (8) 8 (5)\n\nData presented as *n* (%). ^\\*^ Not an end-point event per protocol. ^†^\nClinical evidence of ischemia without electrocardiography (ECG) or\ncardiac enzyme evidence of infarction. ^‡^ Infarction suspected at the\ntime of death without supporting clinical, ECG, or cardiac enzyme data.:::: ::::table-wrap\n::: caption\nMyocardial infarctions identified by the clinical events committee but\nnot the site investigator\n:::\n\n```\n Eastern Europe Latin America North America Western Europe Overall\n```\n\n______________________________________________________________________\n\nClinical scenario (*n* = 182) (*n* = 44) (*n* = 299) (*n* = 291) (*n* = 816)\nAsymptomatic CK-MB elevation^\\*^ 83 (46) 23 (52) 37 (12) 128 (44) 271 (33)\nIschemic event^†^ 89 (49) 12 (27) 48 (16) 68 (23) 217 (27)\nCoronary artery bypass graft-related 6 (3) 6 (14) 138 (46) 52 (18) 202 (25)\nPCI-related 2 (1) 1 (2) 62 (21) 22 (8) 87 (11)\nEarly myocardial infarction^‡^ 1 (1) 0 (0.0) 3 (1) 3 (1) 7 (1)\nIsolated electrocardiogram (Q waves)^§^ 1 (1) 1 (2) 5 (2) 4 (1) 11 (1)\nPeri-death^¶^ 0 (0) 1 (2) 1 (0.3) 4 (1) 6 (1)\nMiscellaneous 0 (0) 0 (0) 5 (2) 10 (3) 15 (2)\n\nData presented as *n* (%). CK-MB, CK-MB = creatine kinase-myocardial\nband; PCI, percutaneous coronary intervention. ^*^ No clinical symptoms\nor electrocardiography (ECG) evidence of ischemia. ^†^ Clinical evidence\nof ischemia and ECG/cardiac enzyme evidence of infarction. ^‡^ Cardiac\nenzyme or ECG evidence of infarction < 24 hours after enrolment,\ndifferent from the enrolment event. ^§^ Identified by systematic review\nof ECGs without clinical evidence of reinfarction. ^¶^ Myocardial\ninfarction at the time of death with clinical, ECG, or cardiac enzyme\nevidence.:::: Table [3](#) presents the cardiac enzyme elevation for MIs that the CEC identified and the site investigators did not. These data exclude MIs associated with PCI or bypass surgery; by definition, those types of MI required enzyme elevations greater than three or five times the upper limit of normal (ULN), respectively. The ratio of creatine kinase-myocardial band (CK-MB) to its ULN was highest in North America (median [25^th^, 75^th^] 1.6 [1.2, 2.9]). Enzymes were similarly elevated between patients with MIs defined only by enzyme elevations (without symptoms or ECG changes) and patients with elevations associated with ECG or clinical evidence of ischemia. ::::table-wrap\n::: caption\nEnzyme elevations in patients with myocardial infarction identified by\nthe clinical events committee but not the site investigator^*^\n:::\n\n```\n Median peak CK/ULN Median peak CK-MB/ULN\n```\n\n______________________________________________________________________\n\nRegion *n* (25th, 75th percentiles) *n* (25th, 75th percentiles)\nEastern Europe 172 0.6 (0.3, 1.2) 167 1.4 (1.2, 1.9)\nLatin America 34 0.7 (0.4, 1.2) 34 2.0 (1.3, 2.6)\nNorth America 112 1.6 (1.0, 3.1) 106 2.9 (1.5, 5.5)\nWestern Europe 202 0.7 (0.4, 2.0) 196 1.7 (1.2, 3.0)\nOverall 520 0.9 (0.4, 1.9) 503 1.6 (1.2, 2.9):::: Table [4](#) presents the level of clinical certainty for MIs not associated with PCI or bypass surgery, as identified by the CEC but not the site investigators. Overall, 98 (18%) of these patients were assigned a low level of clinical certainty. The proportion of patients assigned a low level of clinical certainty varied among the regions, with the lowest in North America. ::::table-wrap\n::: caption\nLevel of clinical certainty^\\*^ for myocardial infarction identified by\nthe clinical events committee but not the site investigator\n:::\n\n```\n High certainty Low certainty Total\n```\n\n______________________________________________________________________\n\nEastern Europe 133 (76) 42 (24) 175\nLatin America 21 (58) 15 (42) 36\nNorth America 111 (98) 2 (2) 113\nWestern Europe 177 (82) 39 (18) 216\nOverall 442 (82) 98 (18) 540\n\nData presented as *n* (%). ^\\*^ See Methods.:::: \n\n## Effect of disagreement on outcomes The 30-day CEC rates of MI and death or MI overall are presented in Table [5](#) by geographic region. The event rates are also shown for the analyses in which the 98 patients assigned a low level of certainty were reclassified as no infarction. ::::table-wrap\n::: caption\nClinical events committee event rates (%) at 30 days\n:::\n\n```\n All patients With reclassification^*^ \n```\n\n______________________________________________________________________\n\nEvent Eptifibatide Placebo *P* Eptifibatide Placebo *P*\nDeath or myocardial infarction\\\nEastern Europe 21.0 19.7 18.0 17.9\\\nLatin America 16.1 15.7 14.1 13.2\\\nNorth America 11.7 15.0 11.7 15.0\\\nWestern Europe 13.8 14.8 12.9 13.7\\\nOverall 14.2 15.7 0.042 13.3 14.9 0.021\n\nMyocardial infarction\\\nEastern Europe 18.8 17.3 15.8 15.3\\\nLatin America 11.6 11.7 9.6 9.1\\\nNorth America 10.1 12.9 10.1 12.9\\\nWestern Europe 12.6 12.9 11.7 11.8\\\nOverall 12.6 13.6 0.137 11.6 12.7 0.08\n\n^\\*^See Methods; 98 patients with low clinical certainty reclassified as\nhaving no infarction.:::: The lowest mortality rates were in patients for whom the CEC and site investigators agreed that no MI had occurred by 30 days (Table [6](#)). The highest rates were in patients for whom there was agreement that a MI had occurred. Mortality was high in the group with MI identified by the site investigators but not the CEC; however, many of these patients had suspected sudden cardiac death as the event identified as a MI by the investigator (Table [1](#)). The absolute increase in mortality between 30 days and 6 months was greater in patients with CEC-determined MIs not identified by the site investigators than in patients with MI identified by the site investigators but not the CEC. ::::table-wrap\n::: caption\nMortality (30 days and 6 months) for cases of disagreement\n:::\n\n```\n Mortality (%) \n```\n\n______________________________________________________________________\n\n```\n *n* 30 days 30 days--6 months 6 months\n```\n\nCEC no / site no 9366 1.7 2.1 3.8\nCEC yes / site yes 599 22.0 5.7 27.7\nCEC yes / site no 816 7.2 5.4 12.6\nCEC no / site yes 167 24.0 2.3 26.3\n\nCEC, Clinical events committee.::::\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** eptifibatide\n**Comparator:** placebo\n**Outcome:** Myocardial infarction\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: x\n group_size: x\ncomparator:\n events: x\n group_size: x"
}
] |
intervention:
events: x
group_size: x
comparator:
events: x
group_size: x
|
56
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n \n\n## Background: Hernia is an abnormal protrusion of an organ or tissue through a defect in its surrounding walls which most commonly involves the abdominal wall, particularly the inguinal region. The treatment options for hernia ranges from simple exercises to modern surgeries. The effect of yoga therapy is not scientifically examined for reversible inguinal hernia and hence this study is undertaken with the aim to test the effect of selected asanas in reversible inguinal hernia. \n\n## Materials and Methods: A quasi experimental trail of 19 males through consecutive sampling was done with selected asanas for three months and the outcome was measured by a questionnaire focusing on pain, aggravating factors, relieving factors and frequency of occurrence of symptoms of hernia. \n\n## Results: The pre and post interventional data were compared statistically and found significant reduction of symptoms with *P*≤0.001 in pain, frequency of occurrence and aggravating factors. The relieving factors showed significant increase with *P*≤0.001. \n\n## Conclusion: Yoga therapy with selected asanas is effective in the treatment of reversible inguinal hernia. # Data analysis and results The pre-intervention and post-intervention assessments were carried out by using the hernia questionnaire designed for this study. This includes the details about intensity of pain, relieving factors, aggravating factors and frequency of occurrence in last two weeks which were used for analysis along with the general information. Schedule method of data collection was used. Data analysis including descriptive analysis and inferential analysis were done by using computerized software (SPSS-11.5) Statistical package for social sciences, Version 11.5 for windows. # Descriptive statistics Descriptive statistics includes measures of central tendency specifically the median and measures of dispersion namely minimum, maximum, first quartile, third quartile and quartile deviation for all the studied dependent variables before and after intervention. # Inferential statistics Inferential statistics of significance testing was done by using Wilcoxon signed-rank test with asymptomatic two tailed z test for paired observations i.e. before and after intervention for all studied variables. # General information Nineteen subjects participated in the study. General information like age, side of bulge, first occurrence of symptoms, activity during first occurrence and effect of rest were also recorded for all participants as applicable. # Age group Age of the subjects ranged from 24 to 46 years, with the mean of 36.26 years and standard deviation of 7.43 years. # Side involved Out of nineteen subjects studied, ten presented with left side hernia, eight with right side hernia and remaining one presented with hernia on both sides. # First occurrence of the problem Out of nineteen studied, eleven subjects were not able to retrieve any detail about first occurrence of the problem. For six subjects, the problem occurred during activity and taking rest relieved it. Remaining two was not clear about the exact activity during occurrence, but they gave the approximate duration of their problem. For all the subjects, there was no history of previous hernia. # Pain Intensity of pain was measured with numeric pain rating scale starting from zero to ten where zero indicates no pain and ten indicates maximum tolerable pain, which was a part of the hernia questionnaire. Pain intensity before intervention ranged from three to eight with median of six and quartile deviation of one. Pain intensity after intervention was from zero to three with median of one and quartile deviation of one \\[[Table 1](#), [Figure 1](#)\\]. The z value of Wilcoxon signed-rank test which is equal to --3.864 with *P* value\\<0.001 denotes that there is statistically significant reduction in pain after intervention. ::::table-wrap\n\n::: caption\nData analysis for pain before and after intervention\n:::\n\n:::: <figure> <p><img src=\"\" /></p> <figcaption>Pre-treatment and post-treatment values of pain, aggravating factors, relieving factors and frequency of occurrence of symptoms. Pain - Maximum score 10; Agg. fac. (aggravating factors) aximum score 5; Rel. fac. (relieving factors) aximum score 3; Freq. (frequency) epending on individual</figcaption> </figure> # Aggravating factors The participants were asked which of the five most common activities exacerbate the problem. The activities are exercise/walking, bowel movement, bladder activity, lifting and coughing/sneezing. Out of nineteen participated, 9 showed the presence of three activities, 6 showed the presence of four activities and remaining 4 showed the presence of all five activities before intervention. After three months of intervention with selected yogasanas, 14 subjects presented with the presence of two activities to increase the problem, 1 presented with one activity and the remaining 4 subjects presented with no activity to increase the problem out of the five commonly found activities. Wilcoxon signed-rank test z value of --3.875 with *P*\\<0.001 denotes that there is statistically significant reduction in aggravating factors after yogic practice \\[[Table 2](#), [Figure 1](#)\\]. ::::table-wrap\n::: caption\nData analysis for aggravating factors before and after intervention\n:::\n\n:::: # Reliving factors The symptoms of inguinal hernia may be relieved by three activities which reduce the intra-abdominal pressure viz. sleeping, lying down and sitting which were also asked for its presence. Out of nineteen subjects participated, seven showed the presence of one relieving factor, another seven showed the presence of two relieving factors and the remaining five showed the presence of al three relieving factors before intervention. All nineteen subjects showed the presence of all three relieving factors after intervention \\[Table [Table 3](#), [Figure 1](#)\\]. ::::table-wrap\n::: caption\nData analysis for reliving factors before and after intervention\n:::\n\n:::: The z value of Wilcoxon signed-rank test which is equal to 3.391 with *P*\\<0.001 denotes that there is statistically significant increase in relieving factors of inguinal hernia after intervention. # Frequency of occurrence Frequency of occurrence of the hernia i.e. number of times in last two weeks were also analyzed before and after intervention. The median for frequency of occurrence before intervention is twelve times with range from nine to fourteen times per two weeks. Frequency of occurrence reduced from zero to six times with median of two times after practise of yoga. The z value of Wilcoxon signed-rank test which is equal to --3.835 with *P* value\\<0.001 denotes that there is statistically significant reduction in frequency of occurrence of symptoms of hernia after intervention \\[[Table 4](#), [Figure 1](#)\\]. ::::table-wrap\n::: caption\nData analysis for frequency of occurrence of hernial bulge before and\nafter intervention\n:::\n\n::::\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** post-Yoga\n**Comparator:** pre-Yoga\n**Outcome:** effective in the treatment of reversible inguinal hernia\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: x\n group_size: 19\ncomparator:\n events: x\n group_size: 19"
}
] |
intervention:
events: x
group_size: 19
comparator:
events: x
group_size: 19
|
120
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n \n\n## Background: Anderson-Hynes dismembered pyeloplasty is the gold standard therapeutic approach to ureteropelvic junction obstruction (UPJO). Use of a drainage method to protect the suture line from leakage is a matter of controversy. \n\n## Objectives: We have compared the surgical outcome of Anderson-Hynes dismembered pyeloplasty for UPJO repair, with or without internal stenting. \n\n## Patients and Methods: Eighty-two patients with UPJO were evaluated from 1996 to 2002. Complicated or emergent cases were excluded. Classic standard dismembered pyeloplasty was performed. Internal drainage, with a double j catheter, was performed in several patients, randomly. Another drain was also placed in the retroperitoneal space. The follow-up of patients was planned weekly, with patient visits and urine analysis and intravenous pyelography (IVP) and diethylene-triamine-pentaacetate (DTPA) scan after one month. \n\n## Results: The study group consisted of 51 male and 31 female patients, who were mostly in the age range of 20 - 40 years. Comparing the two techniques of pyeloplasty with or without internal drainage, there was no significant difference between groups regarding extravasation and anastomosis complications, such as leakage, stenosis, urinoma formation or evidence of obstruction on postoperative IVP or DTPA scan. However, a higher incidence of catheter related urinary symptoms and flank pain was reported among those with internal stent. \n\n## Conclusions: Pyeloplasty, with adequate spatulation, hemostasis and a watertight anastomosis, represents the mainstay of successful pyeloplasty and there may be no significant benefit for urethral stenting, especially in non-complicated cases. # 4. Results Double stenting was used in 30 cases and pyeloplasty without internal drainage was performed in 52 patients. Both groups were similar in age and sex distribution. The most common symptom was severe flank pain, which was present in 69% of patients. History of urinary tract infection was detected in 47% and 51% reported associated gastrointestinal symptoms. Pyuria was seen in 58% and only 36% of patients had positive urine culture, with *Escherichia coli* (*E. coli*) as the most common pathogen (60%). The preoperative sonographic evaluation and IVP results are shown in [Table 1](#). Intraoperative assessments showed ureteropelvic junction segmental atresia in 45 cases and aberrant vessels in 25 patients. The postoperative course was compared in two groups of patients, with and without internal drainage ([Table 2](#)). Among patients with extravasation in DTPA scan in the stent free group, retrograde DJ stent was inserted in four cases that had unacceptable drainage due to inflammation. One patient had distal ureter obstruction because of distal ureter stone, that was treated by Trans-ureteral lithotripsy (TULP) and stent support. Three other cases had no anatomical abnormality, and they were followed and extravasation resolved spontaneously at control IVP after one month. Removal of DJ stent was planned in one month after operation. However, eight cases missed the time and late stent removal was accompanied with several complications, such as stone formation on the tip of catheter in the bladder of a patient that needed TULP before stent removal. ::::table-wrap\n\n::: caption\n\n\n\n##\n\n##\n\n## Results of Preoperative Ultrasonography and Intravenous Pyelography Evaluation ^[a](#), [b](#)^\n\n:::\n\nImaging Method Right Kidney Left Kidney\n\n______________________________________________________________________\n\n**Sonography**\\\nSevere hydronephrosis 28 (34.6) 35 (43.2)\nModerate hydronephrosis 8 (9.9) 9 (11.1)\nMild hydronephrosis 6 (7.4) 3 (3.7)\nWithout hydronephrosis 39 (48) 34 (42)\n**IVP**\\\nNo secretion 6 (7.3) 9 (11)\nDelayed secretion 33 (40.2) 38 (46.3)\nNormal secretion 43 (52.4) 35 (42.7)\n\n^a^Abbreviation: IVP, intravenous pyelography\n\n^b^Data are presented as No. (%).:::: ::::table-wrap\n::: caption\n\n\n\n##\n\n##\n\n## Comparing Postoperative Course Between Patients who Underwent Pyeloplasty With or Without Internal Drainage ^[a](#), [b](#)^\n\n:::\n\nPost-Operative Course With Stent (n = 30) Without Stent (n = 52) P Value\n\n______________________________________________________________________\n\n**Drain removal**\\\nIn 48 hours 12 (40) 17 (32.7) 0.583\nAfter 2 days 18 (60) 34 (65.4) 0.632\n**Mean hospital stay, d** 36 ± 1.74 3.4 ± 1.30 0.841\n**Urine analysis** ^**[c](#)**^\\\nHematuria 19/27 32/32 0.001\nPyuria 12/27 20/32 0.008\n**Post-operative IVP (one month later)**\\\nExtravasation 2 (6.7) 8 (15.3) 0.209\nDelayed secretion 19 (63.3) 25 (48.1) 0.124\nVisible ureter 18 (60) 41 (78.8) 0.633\n**DTPA scan**^**[d](#)**^\\\nPartial obstruction 8/20 13/44 0.716\n**Urinary symptoms** 24 (80) 2 (3.8) 0.005\n**Urinoma** 0 (0) 1 (1.9) 0.324\n**Recurrence of stenosis**\\\nreoperation 0 (0) 1 (1.9) 0.324\n**Stent remnants** 2 (6.7) 0 (0) 0.041\n**Flank pain at voiding** 10 (33.3) 0 (0) 0.001\n\n^a^Abbreviations: IVP, intravenous pyelography; DTPA,\ndiethylene-triamine-pentaacetate.\n\n^b^Data are presented as No. (%).\n\n^c^Urine analysis was done in 27 patients of the stent group and 32\ncases of the stent free group.\n\n^d^DTPA scan was done in 20 patients of stent group and 32 cases of\nstent free group.::::\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** internal drainage group\n**Comparator:** stentless cases\n**Outcome:** ureteropelvic junction obstruction\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: 8\n group_size: 20\ncomparator:\n events: 13.0\n group_size: 44"
}
] |
intervention:
events: 8
group_size: 20
comparator:
events: 13.0
group_size: 44
|
190
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n \n\n## Background Little information is available about whether the use of self-assessment instruments in primary care affects depression course and outcome. The purpose was to evaluate whether using a depression self-rating scale in recurrent person-centred GP consultations affected depression severity, quality of life, medication use, and sick leave frequency. \n\n## Methods Patients in the intervention group met their GP regularly at least 4 times during the 3 months intervention. In addition to treatment as usual (TAU), patients completed a self-assessment instrument (Montgomery-Asberg Depression Rating Scale) on each occasion, and then GPs used the completed instrument as the basis for a person-centred discussion of changes in depression symptoms. The control group received TAU. Frequency of visits in the TAU arm was the result of the GPs' and patients' joint assessments of care need in each case. Depression severity was measured with Beck Depression Inventory-II (BDI-II), quality of life with EQ-5D, and psychological well-being with the General Health Questionnaire-12 (GHQ-12). Data on sick leave, antidepressant and sedatives use, and care contacts were collected from electronic patient records. All variables were measured at baseline and 3, 6, and 12 months. Mean intra-individual changes were compared between the intervention and TAU group. \n\n## Results There were no significant differences between the intervention and control group in depression severity reduction or remission rate, change in quality of life, psychological well-being, sedative prescriptions, or sick leave during the whole 12-month follow-up. However, significantly more patients in the intervention group continued antidepressants until the 6 month follow-up (86/125 vs 78/133, *p* \\< 0.05). \n\n## Conclusions When GPs used a depression self-rating scale in recurrent consultations, patients more often continued antidepressant medication according to guidelines, compared to TAU patients. However, reduction of depressive symptoms, remission rate, quality of life, psychological well-being, sedative use, sick leave, and health care use 4-12 months was not significantly different from the TAU group. These findings suggest that frequent use of depression rating scales in person-centred primary care consultations has no further additional effect on patients' depression or well-being, sick leave, or health care use. \n\n## Trial registration ClinicalTrials.gov Identifier: [NCT01402206](#). Registered June 27 2011(retrospectively registered). \n\n## Electronic supplementary material The online version of this article (doi:10.1186/s12875-016-0578-9) contains supplementary material, which is available to authorized users. # Results Of the 91 participating GPs, 45 were randomised into a group that provided the intervention and 46 into a group that provided TAU. The participating GPs enrolled 258 patients, and the flow of the patients through the study is shown in Fig. [1](#) \\[[23](#)\\]. There was no significant difference in participation rate in the patients in the intervention and control groups at the 3-, 6- or 12-months follow-ups. <figure> <p><img src=\"\" /></p> <figcaption>PRI-SMA-Study (CONSORT Flowchart)</figcaption> </figure> Table [1](#) presents the background characteristics of the study population. No significant differences were found between the participants in the intervention and TAU groups at baseline. ::::table-wrap\n\n::: caption\nBaseline characteristics of participants in the PRI-SMA trial\n(*n* = 258)\n:::\n\n______________________________________________________________________\n\nCharacteristics Total Intervention TAU^¤^ *p*\n*n* (%) *n* (%) *n* (%)\n\n______________________________________________________________________\n\nParticipants 258 125 133\n\nAge (years, mean ) 43.48 44.84 42.19 0.2\n\nmen 76 (29.5) 31 (24.8) 45 (33.8)\n\nwomen 182 (70.5) 94 (75.2) 88 (66.2) 0.1\n\nMarital status\n\nsingle 118 (45.7) 61 (48.8) 57 (42.9)\n\nmarried/cohabiting 140 (54.3) 64 (51.2) 76 (57.1)\n\nchildren \\<18 years at home 82 (43.2) 36 (40.4) 46 (45.5) 0.5\n\nLower educational level 34 (13.2) 17 (13.7) 17 (12.8)\n\nMiddle educational level 115 (44.7) 61 (49.2) 54 (40.6)\n\nHigh educational level 108 (42.0) 46 (37.1) 62 (46.6) 0.3\n\nEmployment\n\nworking/studying 181 (80.8) 90 (81.1) 91 (80.5)\n\nunemployed/retired 43 (19.2) 21 (18.9) 22 (19.5) 0.9\n\nBorn outside the Nordic countries 41 (16) 19 (15.3) 22 (16.7) 0.8\n\nSmoking (yes or sometimes) 75 (29.4) 36 (29.3) 39 (29.5) 0.9\n\nLeisure-time physical activity\n\nnever 109 (42.4) 57 (46) 52 (39.1)\n\nat least 4 hrs/week 124 (48.2) 55 (44.4) 69 (51.9)\n\nintensive 24 (9.3) 12 (9.7) 12 (9,0) 0.5\n\nDepression\n\nmild (BDI-II 12-19) 32 (13) 16 (13.6) 16 (12.4)\n\nmoderate (BDI-II 20-28) 82 (33.2) 39 (33.1) 43 (33.3)\n\n\n\n## high moderate (BDI-II 29-36) 68 (27.5) 35 (29.7) 33 (25.6) 0.9\n\n^¤^*TAU* treatment as usual:::: There was a statistically significant difference between participants and drop-outs during the study concerning age (mean age 44.3 in participants, mean age 37.3 in drop-outs, *p* = 0.02), gender (male 14/62, 22.6%, female 16/166, 9.6%, *p* = 0.034), and ethnicity (born in Sweden 21/194, 10.8%, and born outside Sweden 9/32, 28.1%, *p* = 0.035) Figures [2](#), [3](#), and [4](#) shows depression symptoms (BDI-II), quality of life (EQ-5D), and overall psychological well-being (GHQ-12) in intervention and TAU groups at baseline and 3, 6, and 12 months (boxplots). All patients who participated in the study, both those in the intervention and those in the TAU group, improved in all three variables between baseline and 3 months but there were no significant differences in mean changes (mean of intra-individual ∆) between the groups. Improvements were substantial in both groups; at the 3-month follow-up, nearly half the patients no longer had depression (BDI \\<13) (49% in the intervention and 47.3% in the TAU group, *p* = 0.89). We also performed logistic regression analyses. The models showed that at the 12-month follow-up, older age was associated with improved BDI-II score (OR 1.05, CI 1.01-1.99), and a higher level of education was associated with improved EQ-5D score (OR 3.9, CI 1.77-8.73). The factors added to the model (sex, age, education, antidepressant medication, and participation in the intervention or TAU group) explained the same amount of variation in both the intervention and TAU groups. Thus, the difference between the groups remained non-significant (data not shown). No adverse events were reported from intervention or TAU group. <figure> <p><img src=\"\" /></p> <figcaption>Depression severity (BDI-II values) in the intervention and TAU groups. Boxplots for baseline, 3-months follow up, 6-months follow up, and 12-months follow up. The outcome variable is presented as box plot with medians, minimum and maximum values and lower and upper quartiles. Y-axis: BDI-II, X-axis: time 0, 3, 6, 12 months. Outliers (<em>circle</em>) are cases with values between 1.5 and 3 times the interquartile range (5 cases with BDI-II ≥50 in patients with difficulties in Swedish language, where complementary diagnostic procedure by the GP ended up on medium depressive disorder)</figcaption> </figure> <figure> <p><img src=\"\" /></p> <figcaption>Quality of life (EQ-5D values) in the intervention and TAU groups. Boxplots for baseline, 3-months follow up, 6-months follow up, and 12-months follow up. The outcome variable is presented as box plot with medians, minimum and maximum values and lower and upper quartiles. Y-axis: EQ-5D, X-axis: time 0, 3, 6, 12 months. Outliers (<em>circle</em>) are cases with values between 1.5 and 3 times the interquartile range, extremes (<em>star</em>) are cases with values more than 3 times the interquartile range</figcaption> </figure> <figure> <p><img src=\"\" /></p> <figcaption>Overall psychological well-being (GHQ-12 values) in the intervention and TAU groups. Boxplots for baseline, 3-months follow up, 6-months follow up, and 12-months follow up. The outcome variable is presented as box plot with medians, minimum and maximum values and lower and upper quartiles. Y-axis: GHQ-12, X-axis: time 0, 3, 6, 12 months. Outliers (<em>circle</em>) are cases with values between 1.5 and 3 times the interquartile range</figcaption> </figure> Table [2](#) shows differences between the intervention and TAU groups in the percent of patients who had prescriptions for antidepressants and sedatives. At baseline, 22% of patients in the intervention group and 32% of patients in the TAU group were on maintenance antidepressant medication. After 3 months, the proportion of patients with prescriptions for antidepressant medication was 72% in both the intervention and the TAU group. At the 6-month follow-up, the proportion of patients taking antidepressants had dropped to 69% in the intervention group and 59% in the TAU group (p = 0.007). At the 12-month follow-up, there were no significant differences in the percent of patients who had prescriptions for antidepressants or sedatives in the intervention and TAU groups (Table [2](#)). ::::table-wrap\n::: caption\nNumber and percent of patients who had prescriptions for antidepressants\nand sedatives and stated medication at baseline and 3-, 6-, and\n12-months follow up, respectively, in the intervention and TAU groups\n:::\n\n```\n Baseline 3 months follow-up 6 months follow-up 12 months follow-up \n```\n\n______________________________________________________________________\n\n*n* (%) *n* (%) *n* (% ) *n* (%)\\\nAntidepressants\\\nIntervention (n = 125) 27 (22) 90 (72) 86 (69)\\*\\* 74 (59)\nTAU (n = 133) 43 (32) 96 (72) 78 (59) 77 (58)\nSedatives\\\nIntervention 26 (21) 64 (51) 53 (42) 52 (42)\nTAU^¤^ 32 (24) 73 (55) 56 (42) 51 (38)\n\n^¤^*TAU* treatment as usual\n\n\\*\\*Significantly higher proportion of patients in intervention group\nstill on antidepressants after 6 months, *p* = 0.007:::: Table [3](#) shows the mean number of days of sick leave by patient group. There were no significant differences in the percentage of patients on sick leave in the intervention and TAU groups between baseline and 3 months, or 4 -12 months, or during the entire study period. The mean total duration of sick leave (days) was not significantly different between the intervention and TAU groups (Table [3](#)). ::::table-wrap\n::: caption\nNumber and percent of individuals on sick leave, mean days of sick\nleave, and p-values for difference in mean days of sick leave between\nparticipants in intervention and TAU groups, based on information\nobtained from electronic patient records\n:::\n\n```\n Intervention TAU \n```\n\n______________________________________________________________________\n\n*n* (%) Mean days of sick leave SD *n* (%) Mean days of sick leave SD *P* for difference mean days\\\n0-3 months 31(25) 63.1 29.8 48 (36) 55.8 27.7 0.221\n4-12 months 35(28) 100.8 87.3 47(35) 102.7 85 0.922\nTotal 0-12 months 49(39) 124.8 102.5 64 (48) 123.3 85.0 0.942:::: \n\n## Health care use Mean number of visits at the PHCC, including visits to GP, nurse, psychologist/therapist and total visits to PHCC, was compared between intervention and TAU groups. All information was obtained from EPRs (Table [4](#)). We also compared the total number of visits. There were no significant differences between the intervention and TAU groups regarding these outcomes, during the total 12-month follow-up period. However, during the 0-3 month period, the TAU group made significantly more visits to psychologists/psychotherapists than the intervention group and the intervention group made significantly more total visits to the PHCC than the TAU group. ::::table-wrap\n::: caption\nNumber of patients' contacts with GPs, nurses, and psychologists between\nbaseline to 3 months, and 4 to12 months for intervention and TAU groups,\nbased on information obtained from electronic patient records\n:::\n\n______________________________________________________________________\n\nProfession Type of contact Intervention 0-3 months m (SD) TAU 0-3 months m (SD) *p*\nGP visit 3.44 (1.214) 2.59 (1.354) 0.066\nNurse visit 0.32 (0.829) 0.32 (0.875) 0.878\nPsychologist/Therapist visit 0.40 (1.320) 0.89 (1.776) **0. 0001**\nTotal visits to PHCC visit 4.16 (2.398) 3.81 (2.692) **0.006**\nIntervention 4-12 months m (SD) TAU 4-12 months m (SD) *p*\nGP visit 2. 54 (2.337) 2.38 (2.595) 0.301\nNurse visit 0. 68 (1.484) 0.62 (1.551) 0.581\nPsychologist/Therapist visit 0. 90 (2.504) 0.83 (1.908) 0.401\nTotal visits to PHCC visit 4. 11 (4.586) 3.83 (4.403) 0.619\nIntervention total 0-12 months m (SD) TAU total 0-12 months m (SD) *p*\nGP visit 8.26 (5.842) 7.64 (5.976) 0.304\nNurse visit 0.99 (1.978) 0.94 (2.088) 0.967\nPsychologist/Therapist visit 1.30 (3.129) 1.73 (3.222) 0.167\nTotal visits to PHCC visit 8.26 (5.842) 7.64 (5.976) 0.812\n\n______________________________________________________________________\n\nBold numeral indicates statistically significant *p*-value::::\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** person-centred general practitioners (GP) consultations\n**Comparator:** treatment as usual (TAU)\n**Outcome:** sedative prescriptions\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: 52\n group_size: 125\ncomparator:\n events: 51.0\n group_size: 133"
}
] |
intervention:
events: 52
group_size: 125
comparator:
events: 51.0
group_size: 133
|
191
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n \n\n## Background Little information is available about whether the use of self-assessment instruments in primary care affects depression course and outcome. The purpose was to evaluate whether using a depression self-rating scale in recurrent person-centred GP consultations affected depression severity, quality of life, medication use, and sick leave frequency. \n\n## Methods Patients in the intervention group met their GP regularly at least 4 times during the 3 months intervention. In addition to treatment as usual (TAU), patients completed a self-assessment instrument (Montgomery-Asberg Depression Rating Scale) on each occasion, and then GPs used the completed instrument as the basis for a person-centred discussion of changes in depression symptoms. The control group received TAU. Frequency of visits in the TAU arm was the result of the GPs' and patients' joint assessments of care need in each case. Depression severity was measured with Beck Depression Inventory-II (BDI-II), quality of life with EQ-5D, and psychological well-being with the General Health Questionnaire-12 (GHQ-12). Data on sick leave, antidepressant and sedatives use, and care contacts were collected from electronic patient records. All variables were measured at baseline and 3, 6, and 12 months. Mean intra-individual changes were compared between the intervention and TAU group. \n\n## Results There were no significant differences between the intervention and control group in depression severity reduction or remission rate, change in quality of life, psychological well-being, sedative prescriptions, or sick leave during the whole 12-month follow-up. However, significantly more patients in the intervention group continued antidepressants until the 6 month follow-up (86/125 vs 78/133, *p* \\< 0.05). \n\n## Conclusions When GPs used a depression self-rating scale in recurrent consultations, patients more often continued antidepressant medication according to guidelines, compared to TAU patients. However, reduction of depressive symptoms, remission rate, quality of life, psychological well-being, sedative use, sick leave, and health care use 4-12 months was not significantly different from the TAU group. These findings suggest that frequent use of depression rating scales in person-centred primary care consultations has no further additional effect on patients' depression or well-being, sick leave, or health care use. \n\n## Trial registration ClinicalTrials.gov Identifier: [NCT01402206](#). Registered June 27 2011(retrospectively registered). \n\n## Electronic supplementary material The online version of this article (doi:10.1186/s12875-016-0578-9) contains supplementary material, which is available to authorized users. # Results Of the 91 participating GPs, 45 were randomised into a group that provided the intervention and 46 into a group that provided TAU. The participating GPs enrolled 258 patients, and the flow of the patients through the study is shown in Fig. [1](#) \\[[23](#)\\]. There was no significant difference in participation rate in the patients in the intervention and control groups at the 3-, 6- or 12-months follow-ups. <figure> <p><img src=\"\" /></p> <figcaption>PRI-SMA-Study (CONSORT Flowchart)</figcaption> </figure> Table [1](#) presents the background characteristics of the study population. No significant differences were found between the participants in the intervention and TAU groups at baseline. ::::table-wrap\n\n::: caption\nBaseline characteristics of participants in the PRI-SMA trial\n(*n* = 258)\n:::\n\n______________________________________________________________________\n\nCharacteristics Total Intervention TAU^¤^ *p*\n*n* (%) *n* (%) *n* (%)\n\n______________________________________________________________________\n\nParticipants 258 125 133\n\nAge (years, mean ) 43.48 44.84 42.19 0.2\n\nmen 76 (29.5) 31 (24.8) 45 (33.8)\n\nwomen 182 (70.5) 94 (75.2) 88 (66.2) 0.1\n\nMarital status\n\nsingle 118 (45.7) 61 (48.8) 57 (42.9)\n\nmarried/cohabiting 140 (54.3) 64 (51.2) 76 (57.1)\n\nchildren \\<18 years at home 82 (43.2) 36 (40.4) 46 (45.5) 0.5\n\nLower educational level 34 (13.2) 17 (13.7) 17 (12.8)\n\nMiddle educational level 115 (44.7) 61 (49.2) 54 (40.6)\n\nHigh educational level 108 (42.0) 46 (37.1) 62 (46.6) 0.3\n\nEmployment\n\nworking/studying 181 (80.8) 90 (81.1) 91 (80.5)\n\nunemployed/retired 43 (19.2) 21 (18.9) 22 (19.5) 0.9\n\nBorn outside the Nordic countries 41 (16) 19 (15.3) 22 (16.7) 0.8\n\nSmoking (yes or sometimes) 75 (29.4) 36 (29.3) 39 (29.5) 0.9\n\nLeisure-time physical activity\n\nnever 109 (42.4) 57 (46) 52 (39.1)\n\nat least 4 hrs/week 124 (48.2) 55 (44.4) 69 (51.9)\n\nintensive 24 (9.3) 12 (9.7) 12 (9,0) 0.5\n\nDepression\n\nmild (BDI-II 12-19) 32 (13) 16 (13.6) 16 (12.4)\n\nmoderate (BDI-II 20-28) 82 (33.2) 39 (33.1) 43 (33.3)\n\n\n\n## high moderate (BDI-II 29-36) 68 (27.5) 35 (29.7) 33 (25.6) 0.9\n\n^¤^*TAU* treatment as usual:::: There was a statistically significant difference between participants and drop-outs during the study concerning age (mean age 44.3 in participants, mean age 37.3 in drop-outs, *p* = 0.02), gender (male 14/62, 22.6%, female 16/166, 9.6%, *p* = 0.034), and ethnicity (born in Sweden 21/194, 10.8%, and born outside Sweden 9/32, 28.1%, *p* = 0.035) Figures [2](#), [3](#), and [4](#) shows depression symptoms (BDI-II), quality of life (EQ-5D), and overall psychological well-being (GHQ-12) in intervention and TAU groups at baseline and 3, 6, and 12 months (boxplots). All patients who participated in the study, both those in the intervention and those in the TAU group, improved in all three variables between baseline and 3 months but there were no significant differences in mean changes (mean of intra-individual ∆) between the groups. Improvements were substantial in both groups; at the 3-month follow-up, nearly half the patients no longer had depression (BDI \\<13) (49% in the intervention and 47.3% in the TAU group, *p* = 0.89). We also performed logistic regression analyses. The models showed that at the 12-month follow-up, older age was associated with improved BDI-II score (OR 1.05, CI 1.01-1.99), and a higher level of education was associated with improved EQ-5D score (OR 3.9, CI 1.77-8.73). The factors added to the model (sex, age, education, antidepressant medication, and participation in the intervention or TAU group) explained the same amount of variation in both the intervention and TAU groups. Thus, the difference between the groups remained non-significant (data not shown). No adverse events were reported from intervention or TAU group. <figure> <p><img src=\"\" /></p> <figcaption>Depression severity (BDI-II values) in the intervention and TAU groups. Boxplots for baseline, 3-months follow up, 6-months follow up, and 12-months follow up. The outcome variable is presented as box plot with medians, minimum and maximum values and lower and upper quartiles. Y-axis: BDI-II, X-axis: time 0, 3, 6, 12 months. Outliers (<em>circle</em>) are cases with values between 1.5 and 3 times the interquartile range (5 cases with BDI-II ≥50 in patients with difficulties in Swedish language, where complementary diagnostic procedure by the GP ended up on medium depressive disorder)</figcaption> </figure> <figure> <p><img src=\"\" /></p> <figcaption>Quality of life (EQ-5D values) in the intervention and TAU groups. Boxplots for baseline, 3-months follow up, 6-months follow up, and 12-months follow up. The outcome variable is presented as box plot with medians, minimum and maximum values and lower and upper quartiles. Y-axis: EQ-5D, X-axis: time 0, 3, 6, 12 months. Outliers (<em>circle</em>) are cases with values between 1.5 and 3 times the interquartile range, extremes (<em>star</em>) are cases with values more than 3 times the interquartile range</figcaption> </figure> <figure> <p><img src=\"\" /></p> <figcaption>Overall psychological well-being (GHQ-12 values) in the intervention and TAU groups. Boxplots for baseline, 3-months follow up, 6-months follow up, and 12-months follow up. The outcome variable is presented as box plot with medians, minimum and maximum values and lower and upper quartiles. Y-axis: GHQ-12, X-axis: time 0, 3, 6, 12 months. Outliers (<em>circle</em>) are cases with values between 1.5 and 3 times the interquartile range</figcaption> </figure> Table [2](#) shows differences between the intervention and TAU groups in the percent of patients who had prescriptions for antidepressants and sedatives. At baseline, 22% of patients in the intervention group and 32% of patients in the TAU group were on maintenance antidepressant medication. After 3 months, the proportion of patients with prescriptions for antidepressant medication was 72% in both the intervention and the TAU group. At the 6-month follow-up, the proportion of patients taking antidepressants had dropped to 69% in the intervention group and 59% in the TAU group (p = 0.007). At the 12-month follow-up, there were no significant differences in the percent of patients who had prescriptions for antidepressants or sedatives in the intervention and TAU groups (Table [2](#)). ::::table-wrap\n::: caption\nNumber and percent of patients who had prescriptions for antidepressants\nand sedatives and stated medication at baseline and 3-, 6-, and\n12-months follow up, respectively, in the intervention and TAU groups\n:::\n\n```\n Baseline 3 months follow-up 6 months follow-up 12 months follow-up \n```\n\n______________________________________________________________________\n\n*n* (%) *n* (%) *n* (% ) *n* (%)\\\nAntidepressants\\\nIntervention (n = 125) 27 (22) 90 (72) 86 (69)\\*\\* 74 (59)\nTAU (n = 133) 43 (32) 96 (72) 78 (59) 77 (58)\nSedatives\\\nIntervention 26 (21) 64 (51) 53 (42) 52 (42)\nTAU^¤^ 32 (24) 73 (55) 56 (42) 51 (38)\n\n^¤^*TAU* treatment as usual\n\n\\*\\*Significantly higher proportion of patients in intervention group\nstill on antidepressants after 6 months, *p* = 0.007:::: Table [3](#) shows the mean number of days of sick leave by patient group. There were no significant differences in the percentage of patients on sick leave in the intervention and TAU groups between baseline and 3 months, or 4 -12 months, or during the entire study period. The mean total duration of sick leave (days) was not significantly different between the intervention and TAU groups (Table [3](#)). ::::table-wrap\n::: caption\nNumber and percent of individuals on sick leave, mean days of sick\nleave, and p-values for difference in mean days of sick leave between\nparticipants in intervention and TAU groups, based on information\nobtained from electronic patient records\n:::\n\n```\n Intervention TAU \n```\n\n______________________________________________________________________\n\n*n* (%) Mean days of sick leave SD *n* (%) Mean days of sick leave SD *P* for difference mean days\\\n0-3 months 31(25) 63.1 29.8 48 (36) 55.8 27.7 0.221\n4-12 months 35(28) 100.8 87.3 47(35) 102.7 85 0.922\nTotal 0-12 months 49(39) 124.8 102.5 64 (48) 123.3 85.0 0.942:::: \n\n## Health care use Mean number of visits at the PHCC, including visits to GP, nurse, psychologist/therapist and total visits to PHCC, was compared between intervention and TAU groups. All information was obtained from EPRs (Table [4](#)). We also compared the total number of visits. There were no significant differences between the intervention and TAU groups regarding these outcomes, during the total 12-month follow-up period. However, during the 0-3 month period, the TAU group made significantly more visits to psychologists/psychotherapists than the intervention group and the intervention group made significantly more total visits to the PHCC than the TAU group. ::::table-wrap\n::: caption\nNumber of patients' contacts with GPs, nurses, and psychologists between\nbaseline to 3 months, and 4 to12 months for intervention and TAU groups,\nbased on information obtained from electronic patient records\n:::\n\n______________________________________________________________________\n\nProfession Type of contact Intervention 0-3 months m (SD) TAU 0-3 months m (SD) *p*\nGP visit 3.44 (1.214) 2.59 (1.354) 0.066\nNurse visit 0.32 (0.829) 0.32 (0.875) 0.878\nPsychologist/Therapist visit 0.40 (1.320) 0.89 (1.776) **0. 0001**\nTotal visits to PHCC visit 4.16 (2.398) 3.81 (2.692) **0.006**\nIntervention 4-12 months m (SD) TAU 4-12 months m (SD) *p*\nGP visit 2. 54 (2.337) 2.38 (2.595) 0.301\nNurse visit 0. 68 (1.484) 0.62 (1.551) 0.581\nPsychologist/Therapist visit 0. 90 (2.504) 0.83 (1.908) 0.401\nTotal visits to PHCC visit 4. 11 (4.586) 3.83 (4.403) 0.619\nIntervention total 0-12 months m (SD) TAU total 0-12 months m (SD) *p*\nGP visit 8.26 (5.842) 7.64 (5.976) 0.304\nNurse visit 0.99 (1.978) 0.94 (2.088) 0.967\nPsychologist/Therapist visit 1.30 (3.129) 1.73 (3.222) 0.167\nTotal visits to PHCC visit 8.26 (5.842) 7.64 (5.976) 0.812\n\n______________________________________________________________________\n\nBold numeral indicates statistically significant *p*-value::::\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** person-centred general practitioners (GP) consultations\n**Comparator:** treatment as usual (TAU)\n**Outcome:** sick leave\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: 49\n group_size: 125\ncomparator:\n events: 64.0\n group_size: 133"
}
] |
intervention:
events: 49
group_size: 125
comparator:
events: 64.0
group_size: 133
|
192
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n \n\n## Background Little information is available about whether the use of self-assessment instruments in primary care affects depression course and outcome. The purpose was to evaluate whether using a depression self-rating scale in recurrent person-centred GP consultations affected depression severity, quality of life, medication use, and sick leave frequency. \n\n## Methods Patients in the intervention group met their GP regularly at least 4 times during the 3 months intervention. In addition to treatment as usual (TAU), patients completed a self-assessment instrument (Montgomery-Asberg Depression Rating Scale) on each occasion, and then GPs used the completed instrument as the basis for a person-centred discussion of changes in depression symptoms. The control group received TAU. Frequency of visits in the TAU arm was the result of the GPs' and patients' joint assessments of care need in each case. Depression severity was measured with Beck Depression Inventory-II (BDI-II), quality of life with EQ-5D, and psychological well-being with the General Health Questionnaire-12 (GHQ-12). Data on sick leave, antidepressant and sedatives use, and care contacts were collected from electronic patient records. All variables were measured at baseline and 3, 6, and 12 months. Mean intra-individual changes were compared between the intervention and TAU group. \n\n## Results There were no significant differences between the intervention and control group in depression severity reduction or remission rate, change in quality of life, psychological well-being, sedative prescriptions, or sick leave during the whole 12-month follow-up. However, significantly more patients in the intervention group continued antidepressants until the 6 month follow-up (86/125 vs 78/133, *p* \\< 0.05). \n\n## Conclusions When GPs used a depression self-rating scale in recurrent consultations, patients more often continued antidepressant medication according to guidelines, compared to TAU patients. However, reduction of depressive symptoms, remission rate, quality of life, psychological well-being, sedative use, sick leave, and health care use 4-12 months was not significantly different from the TAU group. These findings suggest that frequent use of depression rating scales in person-centred primary care consultations has no further additional effect on patients' depression or well-being, sick leave, or health care use. \n\n## Trial registration ClinicalTrials.gov Identifier: [NCT01402206](#). Registered June 27 2011(retrospectively registered). \n\n## Electronic supplementary material The online version of this article (doi:10.1186/s12875-016-0578-9) contains supplementary material, which is available to authorized users. # Results Of the 91 participating GPs, 45 were randomised into a group that provided the intervention and 46 into a group that provided TAU. The participating GPs enrolled 258 patients, and the flow of the patients through the study is shown in Fig. [1](#) \\[[23](#)\\]. There was no significant difference in participation rate in the patients in the intervention and control groups at the 3-, 6- or 12-months follow-ups. <figure> <p><img src=\"\" /></p> <figcaption>PRI-SMA-Study (CONSORT Flowchart)</figcaption> </figure> Table [1](#) presents the background characteristics of the study population. No significant differences were found between the participants in the intervention and TAU groups at baseline. ::::table-wrap\n\n::: caption\nBaseline characteristics of participants in the PRI-SMA trial\n(*n* = 258)\n:::\n\n______________________________________________________________________\n\nCharacteristics Total Intervention TAU^¤^ *p*\n*n* (%) *n* (%) *n* (%)\n\n______________________________________________________________________\n\nParticipants 258 125 133\n\nAge (years, mean ) 43.48 44.84 42.19 0.2\n\nmen 76 (29.5) 31 (24.8) 45 (33.8)\n\nwomen 182 (70.5) 94 (75.2) 88 (66.2) 0.1\n\nMarital status\n\nsingle 118 (45.7) 61 (48.8) 57 (42.9)\n\nmarried/cohabiting 140 (54.3) 64 (51.2) 76 (57.1)\n\nchildren \\<18 years at home 82 (43.2) 36 (40.4) 46 (45.5) 0.5\n\nLower educational level 34 (13.2) 17 (13.7) 17 (12.8)\n\nMiddle educational level 115 (44.7) 61 (49.2) 54 (40.6)\n\nHigh educational level 108 (42.0) 46 (37.1) 62 (46.6) 0.3\n\nEmployment\n\nworking/studying 181 (80.8) 90 (81.1) 91 (80.5)\n\nunemployed/retired 43 (19.2) 21 (18.9) 22 (19.5) 0.9\n\nBorn outside the Nordic countries 41 (16) 19 (15.3) 22 (16.7) 0.8\n\nSmoking (yes or sometimes) 75 (29.4) 36 (29.3) 39 (29.5) 0.9\n\nLeisure-time physical activity\n\nnever 109 (42.4) 57 (46) 52 (39.1)\n\nat least 4 hrs/week 124 (48.2) 55 (44.4) 69 (51.9)\n\nintensive 24 (9.3) 12 (9.7) 12 (9,0) 0.5\n\nDepression\n\nmild (BDI-II 12-19) 32 (13) 16 (13.6) 16 (12.4)\n\nmoderate (BDI-II 20-28) 82 (33.2) 39 (33.1) 43 (33.3)\n\n\n\n## high moderate (BDI-II 29-36) 68 (27.5) 35 (29.7) 33 (25.6) 0.9\n\n^¤^*TAU* treatment as usual:::: There was a statistically significant difference between participants and drop-outs during the study concerning age (mean age 44.3 in participants, mean age 37.3 in drop-outs, *p* = 0.02), gender (male 14/62, 22.6%, female 16/166, 9.6%, *p* = 0.034), and ethnicity (born in Sweden 21/194, 10.8%, and born outside Sweden 9/32, 28.1%, *p* = 0.035) Figures [2](#), [3](#), and [4](#) shows depression symptoms (BDI-II), quality of life (EQ-5D), and overall psychological well-being (GHQ-12) in intervention and TAU groups at baseline and 3, 6, and 12 months (boxplots). All patients who participated in the study, both those in the intervention and those in the TAU group, improved in all three variables between baseline and 3 months but there were no significant differences in mean changes (mean of intra-individual ∆) between the groups. Improvements were substantial in both groups; at the 3-month follow-up, nearly half the patients no longer had depression (BDI \\<13) (49% in the intervention and 47.3% in the TAU group, *p* = 0.89). We also performed logistic regression analyses. The models showed that at the 12-month follow-up, older age was associated with improved BDI-II score (OR 1.05, CI 1.01-1.99), and a higher level of education was associated with improved EQ-5D score (OR 3.9, CI 1.77-8.73). The factors added to the model (sex, age, education, antidepressant medication, and participation in the intervention or TAU group) explained the same amount of variation in both the intervention and TAU groups. Thus, the difference between the groups remained non-significant (data not shown). No adverse events were reported from intervention or TAU group. <figure> <p><img src=\"\" /></p> <figcaption>Depression severity (BDI-II values) in the intervention and TAU groups. Boxplots for baseline, 3-months follow up, 6-months follow up, and 12-months follow up. The outcome variable is presented as box plot with medians, minimum and maximum values and lower and upper quartiles. Y-axis: BDI-II, X-axis: time 0, 3, 6, 12 months. Outliers (<em>circle</em>) are cases with values between 1.5 and 3 times the interquartile range (5 cases with BDI-II ≥50 in patients with difficulties in Swedish language, where complementary diagnostic procedure by the GP ended up on medium depressive disorder)</figcaption> </figure> <figure> <p><img src=\"\" /></p> <figcaption>Quality of life (EQ-5D values) in the intervention and TAU groups. Boxplots for baseline, 3-months follow up, 6-months follow up, and 12-months follow up. The outcome variable is presented as box plot with medians, minimum and maximum values and lower and upper quartiles. Y-axis: EQ-5D, X-axis: time 0, 3, 6, 12 months. Outliers (<em>circle</em>) are cases with values between 1.5 and 3 times the interquartile range, extremes (<em>star</em>) are cases with values more than 3 times the interquartile range</figcaption> </figure> <figure> <p><img src=\"\" /></p> <figcaption>Overall psychological well-being (GHQ-12 values) in the intervention and TAU groups. Boxplots for baseline, 3-months follow up, 6-months follow up, and 12-months follow up. The outcome variable is presented as box plot with medians, minimum and maximum values and lower and upper quartiles. Y-axis: GHQ-12, X-axis: time 0, 3, 6, 12 months. Outliers (<em>circle</em>) are cases with values between 1.5 and 3 times the interquartile range</figcaption> </figure> Table [2](#) shows differences between the intervention and TAU groups in the percent of patients who had prescriptions for antidepressants and sedatives. At baseline, 22% of patients in the intervention group and 32% of patients in the TAU group were on maintenance antidepressant medication. After 3 months, the proportion of patients with prescriptions for antidepressant medication was 72% in both the intervention and the TAU group. At the 6-month follow-up, the proportion of patients taking antidepressants had dropped to 69% in the intervention group and 59% in the TAU group (p = 0.007). At the 12-month follow-up, there were no significant differences in the percent of patients who had prescriptions for antidepressants or sedatives in the intervention and TAU groups (Table [2](#)). ::::table-wrap\n::: caption\nNumber and percent of patients who had prescriptions for antidepressants\nand sedatives and stated medication at baseline and 3-, 6-, and\n12-months follow up, respectively, in the intervention and TAU groups\n:::\n\n```\n Baseline 3 months follow-up 6 months follow-up 12 months follow-up \n```\n\n______________________________________________________________________\n\n*n* (%) *n* (%) *n* (% ) *n* (%)\\\nAntidepressants\\\nIntervention (n = 125) 27 (22) 90 (72) 86 (69)\\*\\* 74 (59)\nTAU (n = 133) 43 (32) 96 (72) 78 (59) 77 (58)\nSedatives\\\nIntervention 26 (21) 64 (51) 53 (42) 52 (42)\nTAU^¤^ 32 (24) 73 (55) 56 (42) 51 (38)\n\n^¤^*TAU* treatment as usual\n\n\\*\\*Significantly higher proportion of patients in intervention group\nstill on antidepressants after 6 months, *p* = 0.007:::: Table [3](#) shows the mean number of days of sick leave by patient group. There were no significant differences in the percentage of patients on sick leave in the intervention and TAU groups between baseline and 3 months, or 4 -12 months, or during the entire study period. The mean total duration of sick leave (days) was not significantly different between the intervention and TAU groups (Table [3](#)). ::::table-wrap\n::: caption\nNumber and percent of individuals on sick leave, mean days of sick\nleave, and p-values for difference in mean days of sick leave between\nparticipants in intervention and TAU groups, based on information\nobtained from electronic patient records\n:::\n\n```\n Intervention TAU \n```\n\n______________________________________________________________________\n\n*n* (%) Mean days of sick leave SD *n* (%) Mean days of sick leave SD *P* for difference mean days\\\n0-3 months 31(25) 63.1 29.8 48 (36) 55.8 27.7 0.221\n4-12 months 35(28) 100.8 87.3 47(35) 102.7 85 0.922\nTotal 0-12 months 49(39) 124.8 102.5 64 (48) 123.3 85.0 0.942:::: \n\n## Health care use Mean number of visits at the PHCC, including visits to GP, nurse, psychologist/therapist and total visits to PHCC, was compared between intervention and TAU groups. All information was obtained from EPRs (Table [4](#)). We also compared the total number of visits. There were no significant differences between the intervention and TAU groups regarding these outcomes, during the total 12-month follow-up period. However, during the 0-3 month period, the TAU group made significantly more visits to psychologists/psychotherapists than the intervention group and the intervention group made significantly more total visits to the PHCC than the TAU group. ::::table-wrap\n::: caption\nNumber of patients' contacts with GPs, nurses, and psychologists between\nbaseline to 3 months, and 4 to12 months for intervention and TAU groups,\nbased on information obtained from electronic patient records\n:::\n\n______________________________________________________________________\n\nProfession Type of contact Intervention 0-3 months m (SD) TAU 0-3 months m (SD) *p*\nGP visit 3.44 (1.214) 2.59 (1.354) 0.066\nNurse visit 0.32 (0.829) 0.32 (0.875) 0.878\nPsychologist/Therapist visit 0.40 (1.320) 0.89 (1.776) **0. 0001**\nTotal visits to PHCC visit 4.16 (2.398) 3.81 (2.692) **0.006**\nIntervention 4-12 months m (SD) TAU 4-12 months m (SD) *p*\nGP visit 2. 54 (2.337) 2.38 (2.595) 0.301\nNurse visit 0. 68 (1.484) 0.62 (1.551) 0.581\nPsychologist/Therapist visit 0. 90 (2.504) 0.83 (1.908) 0.401\nTotal visits to PHCC visit 4. 11 (4.586) 3.83 (4.403) 0.619\nIntervention total 0-12 months m (SD) TAU total 0-12 months m (SD) *p*\nGP visit 8.26 (5.842) 7.64 (5.976) 0.304\nNurse visit 0.99 (1.978) 0.94 (2.088) 0.967\nPsychologist/Therapist visit 1.30 (3.129) 1.73 (3.222) 0.167\nTotal visits to PHCC visit 8.26 (5.842) 7.64 (5.976) 0.812\n\n______________________________________________________________________\n\nBold numeral indicates statistically significant *p*-value::::\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** person-centred general practitioners (GP) consultations\n**Comparator:** treatment as usual (TAU)\n**Outcome:** continued antidepressants until the 6-month\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: 86\n group_size: 125\ncomparator:\n events: 78.0\n group_size: 133"
}
] |
intervention:
events: 86
group_size: 125
comparator:
events: 78.0
group_size: 133
|
260
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n # Abstract\n\n ***Objectives:*** To evaluate the short-term efficacy and safety of desvenlafaxine (25--50 mg/d) compared with placebo in children and adolescents with major depressive disorder (MDD). ***Methods:*** Outpatient children (7--11 years) and adolescents (12--17 years) who met DSM-IV-TR criteria for MDD and had screening and baseline Children's Depression Rating Scale--Revised (CDRS-R) total scores >40 were randomly assigned to 8-week treatment with placebo, desvenlafaxine (25, 35, or 50 mg/d based on baseline weight), or fluoxetine (20 mg/d). The primary efficacy endpoint was change from baseline in CDRS-R total score at week 8, analyzed using a mixed-effects model for repeated measures. Secondary efficacy endpoints included week 8 Clinical Global Impressions--Severity, Clinical Global Impressions--Improvement (CGI-I), and response (CGI-I ≤ 2). Safety assessments included adverse events, physical and vital sign measurements, laboratory evaluations, electrocardiogram, and the Columbia-Suicide Severity Rating Scale. ***Results:*** The safety population included 339 patients (children, *n* = 130; adolescents, *n* = 209). The primary endpoint, change from baseline in CDRS-R total score at week 8, did not statistically separate from placebo, for either desvenlafaxine (adjusted mean [standard error] change, −22.6 [1.17]) or fluoxetine (−24.8 [1.17]; placebo, −23.1 [1.18]). Week 8 CGI-I response rates were significantly greater for fluoxetine (78.2%; *p* = 0.017) than for placebo (62.6%); desvenlafaxine (68.7%) did not differ from placebo. Other secondary outcomes were consistent with those obtained with CDRS-R. Rates of treatment-emergent adverse events were comparable among treatment groups (desvenlafaxine, 60.0%; placebo, 70.5%; and fluoxetine, 64.3%). ***Conclusion:*** Desvenlafaxine did not demonstrate efficacy for treating MDD in children and adolescents in this trial. Because neither desvenlafaxine nor the reference medication, fluoxetine, demonstrated a statistically significant difference from placebo on the primary endpoint, this was considered a failed trial and no efficacy conclusions can be drawn. Desvenlafaxine 25--50 mg/d was generally safe and well tolerated in children and adolescents in this study. # Results \n\n## Study population A total of 340 patients were randomly assigned to treatment; 339 patients (children, *n* = 130; adolescents, *n* = 209) were included in the safety population (desvenlafaxine, *n* = 115; fluoxetine, *n* = 112; placebo, *n* = 112). The ITT population included 130 children and 207 adolescents. A total of 42 (12%) patients discontinued early (desvenlafaxine, 16 [14%]; fluoxetine, 13 [12%]; and placebo, 13 [12%]). Lost to follow-up was the most common reason for discontinuation from the desvenlafaxine and placebo groups; in the fluoxetine group, the most common reason for discontinuation was \"no longer willing to participate\" ([Fig. 1](#)). <figure> <p><img src=\"\" /></p> <figcaption>Study flow. <sup>a</sup>One patient was screened and, although not randomized, received a total of eight blinded placebo doses. The patient was discontinued after the week 1 visit once the error was identified and listed as a protocol violation.</figcaption> </figure> Demographic and baseline characteristics were comparable among treatment groups for both children and adolescents ([Table 1](#)). Mean (SD) CDRS-R Total Score at baseline was 56.5 (8.9), mean (SD) CGI-S score was 4.5 (0.6), and the duration of the most recent depressive episode ranged from 1 to 96 months (median, 7; mean [SD], 13.4 [15.1]). Overall, 30.4% (103) of patients in the safety population had a prior or active psychiatric condition other than MDD in their medical history (desvenlafaxine, 31.3%; fluoxetine, 25.9%; and placebo, 33.9%). The most common psychiatric conditions (reported by ≥2% of patients) included attention-deficit/hyperactivity disorder (desvenlafaxine, 12.2%; fluoxetine, 13.4%; and placebo, 5.4%), nonsuicidal self-injurious behavior (desvenlafaxine, 7.0%; fluoxetine, 8.0%; and placebo, 12.5%), insomnia (desvenlafaxine, 7.0%; fluoxetine, 6.3%; and placebo, 8.0%), generalized anxiety disorder (desvenlafaxine, 0.9%; fluoxetine, 6.3%; and placebo, 0), and oppositional defiant disorder (desvenlafaxine, 3.5%; fluoxetine, 3.6%; and placebo, 0). ::::table-wrap\n\n::: caption\n\\[Demographic and Baseline Characteristics, Safety\nPopulation\\]{.smallcaps}\n:::\n\n*Children* *Adolescents*\n\n______________________________________________________________________\n\n*Placebo (*n* = 42)* *Fluoxetine (*n* = 45)* *Desvenlafaxine (*n* = 43)* *Total (*n* = 130)* *Placebo (*n* = 70)* *Fluoxetine (*n* = 67)* *Desvenlafaxine (*n* = 72)* *Total (*n* = 209)*\nAge, mean (SD), years 9.4 (1.3) 9.6 (1.3) 9.3 (1.4) 9.4 (1.3) 14.6 (1.5) 14.7 (1.6) 15.0 (1.5) 14.8 (1.5)\nSex, *n* (%)\\\nFemale 23 (55) 14 (31) 20 (47) 57 (44) 41 (59) 43 (64) 43 (60) 127 (61)\nMale 19 (45) 31 (69) 23 (53) 73 (56) 29 (41) 24 (36) 29 (40) 82 (39)\nRace, *n* (%)\\\nAsian 1 (2) 0 1 (2) 2 (2) 0 2 (3) 0 2 (1)\nBlack 15 (36) 15 (33) 14 (33) 44 (34) 10 (14) 19 (28) 18 (25) 47 (22)\nWhite 25 (60) 26 (58) 23 (53) 74 (57) 56 (80) 41 (61) 49 (68) 146 (70)\nOther 1 (2) 4 (9) 5 (12) 10 (8) 4 (6) 5 (7) 5 (7) 14 (7)\nHeight, mean (SD), cm 140.5 (10.6) 141.3 (11.2) 144.3 (11.5) 142.0 (11.1) 164.5 (9.8) 165.8 (8.4) 167.3 (9.1) 165.9 (9.2)\nWeight, mean (SD), kg 39.4 (14.0) 44.0 (18.9) 46.0 (15.2) 43.2 (16.3) 68.0 (19.1) 73.3 (21.8) 71.7 (19.0) 71.0 (20.0)\nBMI, mean (SD), kg/m^2^ 19.5 (4.7) 21.3 (6.4) 21.6 (5.0) 20.8 (5.5) 25.0 (6.0) 26.5 (6.9) 25.5 (5.8) 25.6 (6.3)\nDuration of most recent episode, median (range), months 11 (1--57) 6 (1--42) 8 (1--71) 7 (1--71) 8 (1--69) 7 (1--96) 7 (1--61) 7 (1--96)\nCDRS-R total score, mean (SD) 57.0 (8.6) 55.0 (8.7) 56.4 (10.9) 56.1 (9.4) 57.1 (9.1) 57.0 (8.1) 56.3 (8.8) 56.8 (8.7)\n\nBMI, body mass index; CDRS-R, Children's Depression Rating\nScale--Revised; SD, standard deviation.:::: \n\n## Efficacy Statistical separation from placebo was not observed on the primary efficacy endpoint for either desvenlafaxine or for the fluoxetine reference group. Adjusted mean (standard error) change from baseline in CDRS-R total score at week 8 was −22.6 (1.17) and −23.1 (1.18) for the desvenlafaxine and placebo groups, respectively, and for fluoxetine was −24.8 (1.17) ([Fig. 2](#)). The change from baseline in CDRS-R over the 8-week treatment phase was similar for the three arms. Point differences were statistically significant between desvenlafaxine and placebo at week 2 and between fluoxetine and placebo at weeks 1 and 2; no significant differences were observed at any other time points. Results were similar for the child and adolescent groups in an exploratory analysis of change from baseline in CDRS-R total score ([Supplementary Fig. S1](#)). <figure> <p><img src=\"\" /></p> <figcaption>Adjusted mean (SE) change from baseline in CDRS-R total score in children and adolescents; MMRM analysis, ITT population. \\*<em>p</em> \\< 0.01, fluoxetine versus placebo. <sup>†</sup><em>p</em> \\< 0.05, fluoxetine versus placebo and desvenlafaxine versus placebo. CDRS-R, Children's Depression Rating Scale–Revised; CI, confidence interval; ITT, intent-to-treat; MMRM, mixed-effects model for repeated measures; SE, standard error.</figcaption> </figure> At week 8, the CGI-I response rate for fluoxetine (78.2%) was significantly greater compared with placebo (62.6%; *p* = 0.017). Week 8 CGI-I response rate for desvenlafaxine (68.7%) was also greater than placebo, although this comparison did not reach statistical significance (*p* = 0.343). Results for CGI-S and CGI-I scores were otherwise consistent with those for CDRS-R total score, with no statistically significant difference from placebo for either desvenlafaxine or fluoxetine at week 8 ([Table 2](#)). ::::table-wrap\n::: caption\n[Summary of Secondary Efficacy Outcomes at Week 8]{.smallcaps}\n:::\n\n*CGI-S* n *Adjusted mean change (SE) from baseline*^[a](#)^ *Difference in adjusted means (placebo-active)* *95% CI* p\n\n______________________________________________________________________\n\nPlacebo 99 −1.71 (0.12) --- --- ---\nFluoxetine 101 −1.88 (0.12) 0.18 −0.11 to 0.46 0.224\nDesvenlafaxine 99 −1.70 (0.11) −0.01 −0.29 to 0.27 0.944\n\n*CGI-I*^[b](#)^ n *Very much improved (%)* *Much improved (%)* *Minimally improved (%)* *No change (%)* *CMH test*^[c](#)^ p\\*-value\\*\n\n______________________________________________________________________\n\nPlacebo 99 27.3 35.4 32.3 4.0 ---\nFluoxetine 101 30.7 47.5 16.8 4.0 0.095\nDesvenlafaxine 99 23.2 45.5 21.2 9.1 0.852\n\n*CGI-I response*^[d](#)^ *Proportion responders* *%* *Adjusted odds ratio*^[e](#)^ *Wald 95% CI* p\n\n______________________________________________________________________\n\nPlacebo 62/99 62.6 --- --- ---\nFluoxetine 79/101 78.2 0.465 0.249 to 0.871 0.017\nDesvenlafaxine 68/99 68.7 0.751 0.415 to 1.357 0.343\n\nEstimates of adjusted mean, SE, difference in means, 95% CI, and\n*p*-values were based on a mixed-effects model for repeated measures for\nthe change from baseline in CGI-S with terms for treatment, week,\ninteraction of treatment and week, age group, country, gender, and\nbaseline CGI-S total score.\n\nCGI-I scored as 1, very much improved; 2, much improved; 3, minimally\nimproved; 4, no change; 5, minimally worse; 6, much worse; 7, very much\nworse. No patients scored 5--7 at week 8.\n\nCMH test was controlled for age group and country.\n\nCGI-I response was defined as CGI-I score of 1 (very much improved) or 2\n(much improved).\n\nEstimates of odds ratios, 95% CI, and *p*-values were based on a\nlogistic regression model of the response rate, with terms for treatment\ngroup, age group, and country.\n\nCGI-I, Clinical Global Impressions--Improvement; CGI-S, Clinical Global\nImpressions--Severity; CI, confidence interval; CMH,\nCochran--Mantel--Haenszel; SE, standard error.:::: \n\n## Safety \n\n### Adverse events A total of 220/339 (64.9%) patients experienced AEs during the on-therapy period (desvenlafaxine, 69/115 [60.0%]; fluoxetine, 72/112 [64.3%]; and placebo, 79/112 [70.5%]). Most AEs were mild or moderate in severity. AEs considered by the investigator to be related to study medication were reported by 31.9% of patients (desvenlafaxine, 28.7%; fluoxetine, 32.1%; and placebo, 34.8%). Severe AEs (those that interfered significantly with patients' usual function) considered by the investigator to be unrelated to study medication were reported by 3.5% of patients (desvenlafaxine, 1.7%; fluoxetine, 5.4%; and placebo, 3.6%). In three patients, severe AEs were considered related to study medication: One desvenlafaxine-treated patient reported severe pruritus and severe macular rash and discontinued treatment. One placebo-treated patient reported severe agitation and severe anger, and a second reported severe insomnia; neither was discontinued due to those AEs. Five adolescents (0 children) discontinued due to AEs, two each from the desvenlafaxine (disinhibition; macular rash and pruritus) and placebo (vomiting; headache) groups and one from the fluoxetine group (suicidal ideation). \n\n### Treatment-emergent adverse events Treatment-emergent adverse events (TEAEs) reported by more than 10% of patients in any group were headache, upper abdominal pain, and nausea. [Table 3](#) shows the most frequent (≥5% in any group) TEAEs by age group, and overall. There were no statistically significant differences between desvenlafaxine or fluoxetine and placebo in the incidence of any prespecified TEAEs of clinical interest for desvenlafaxine (tier-1 TEAEs) ([Supplementary Table S2](#)). ::::table-wrap\n::: caption\n\\[Number (%) of Patients Reporting Treatment-Emergent Adverse Events with\nIncidence ≥5% in Any Group, On-Therapy Period, Safety\nPopulation\\]{.smallcaps}\n:::\n\n*Children* *Adolescents* *Overall*\n\n______________________________________________________________________\n\n*Placebo (*n* = 42)* *Fluoxetine (*n* = 45)* *Desvenlafaxine (*n* = 43)* *Placebo (*n* = 70)* *Fluoxetine (*n* = 67)* *Desvenlafaxine (*n* = 72)* *Placebo (*n* = 112)* *Desvenlafaxine (*n* = 112)* *Desvenlafaxine (*n* = 115)*\nAny TEAE 27 (64.3) 29 (64.4) 22 (51.2) 52 (74.3) 43 (64.2) 47 (65.3) 79 (70.5) 72 (64.3) 69 (60.0)\nHeadache 8 (19.0) 3 (6.7) 5 (11.6) 13 (18.6) 13 (19.4) 14 (19.4) 21 (18.8) 16 (14.3) 19 (16.5)\nAbdominal pain upper 2 (4.8) 1 (2.2) 6 (14.0) 5 (7.1) 8 (11.9) 9 (12.5) 7 (6.3) 9 (8.0) 15 (13.0)\nNausea 3 (7.1) 4 (8.9) 2 (4.7) 7 (10.0) 9 (13.4) 6 (8.3) 10 (8.9) 13 (11.6) 8 (7.0)\nDizziness 3 (7.1) 1 (2.2) 2 (4.7) 3 (4.3) 2 (3.0) 5 (6.9) 6 (5.4) 3 (2.7) 7 (6.1)\nInfluenza 0 2 (4.4) 2 (4.7) 0 0 4 (5.6) 0 2 (1.8) 6 (5.2)\nNasopharyngitis 4 (9.5) 2 (4.4) 1 (2.3) 4 (5.7) 5 (7.5) 5 (6.9) 8 (7.1) 7 (6.3) 6 (5.2)\nUpper respiratory tract infection 2 (4.8) 3 (6.7) 1 (2.3) 4 (5.7) 1 (1.5) 5 (6.9) 6 (5.4) 4 (3.6) 6 (5.2)\nVomiting 1 (2.4) 5 (11.1) 1 (2.3) 3 (4.3) 2 (3.0) 4 (5.6) 4 (3.6) 7 (6.3) 5 (4.3)\nDiarrhea 1 (2.4) 0 4 (9.3) 2 (2.9) 3 (4.5) 1 (1.4) 3 (2.7) 3 (2.7) 5 (4.3)\nInsomnia 1 (2.4) 1 (2.2) 0 2 (2.9) 4 (6.0) 4 (5.6) 3 (2.7) 5 (4.5) 4 (3.5)\nFatigue 1 (2.4) 3 (6.7) 0 1 (1.4) 3 (4.5) 2 (2.8) 2 (1.8) 6 (5.4) 2 (1.7)\nPharyngitis 2 (4.8) 3 (6.7) 1 (2.3) 0 1 (1.5) 1 (1.4) 2 (1.8) 4 (3.6) 2 (1.7)\nRash 0 3 (6.7) 0 0 1 (1.5) 1 (1.4) 0 4 (3.6) 1 (0.9)\nArthralgia 3 (7.1) 1 (2.2) 1 (2.3) 1 (1.4) 2 (3.0) 0 4 (3.6) 3 (2.7) 1 (0.9)\nFall 2 (4.8) 4 (8.9) 0 0 1 (1.5) 0 2 (1.8) 5 (4.5) 0\nConstipation 3 (7.1) 0 0 1 (1.4) 0 0 4 (3.6) 0 0\n\nTEAE, treatment-emergent adverse event.:::: \n\n### Deaths and serious AEs There were no deaths during the study. Five randomized patients experienced serious AEs: two assigned to fluoxetine (suicidal ideation [acute suicidality; discontinued] and suicide attempt [occurred poststudy], one patient each), three assigned to desvenlafaxine (suicidal ideation [discontinued due to lack of confidence in caregiver reliability to report patient status], disinhibition [discontinued], and postpartum hemorrhage with anemia and endometritis [occurred poststudy], one patient each), and no placebo-treated patients. The desvenlafaxine-treated patient with postpartum hemorrhage had been withdrawn from the study following a positive pregnancy test at the final treatment phase visit and delivered a healthy full-term infant. \n\n### Suicidality A summary of C-SSRS results for treatment-emergent suicidal ideation or behavior is presented for the safety population in [Table 4](#) (full C-SSRS results are presented in [Supplementary Table S3](#)). Treatment-emergent suicidal ideation or suicidal behavior, which included both new-onset and worsening suicidal ideation or behavior, was reported for 29 (8.6%) of 337 patients who had a C-SSRS assessment at baseline and at 1 or more postbaseline time points. A total of 29/337 (8.6%) patients had treatment-emergent suicidal ideation, and 1 patient (0.3%) also had treatment-emergent suicidal behavior. The suicidal behavior event was categorized as a preparatory act toward imminent suicidal behavior (preparatory acts or behavior; interrupted attempt) and was reported in a fluoxetine-treated adolescent ([Supplementary Table S3](#)). The patient was discontinued due to a serious AE of acute suicidality (described in \"Deaths and Serious AEs\" section). ::::table-wrap\n::: caption\n\\[Summary of Treatment-Emergent Suicidal Ideation and Behavior Reported\non the Columbia-Suicide Severity Rating Scale at Any Postbaseline\nAssessment, Safety Population\\]{.smallcaps}\n:::\n\n*Placebo (*N* = 112)* *Fluoxetine (*N* = 110)* *Desvenlafaxine (*N* = 115)* *Total (*N* = 337)*\n\n______________________________________________________________________\n\nTreatment-emergent SIB^[a](#)^ 8/112 (7.1) 12/110 (10.9) 9/115 (7.8) 29/337 (8.6)\nNew-onset SIB^[b](#)^ 7/104 (6.7) 10/97 (10.3) 8/102 (7.8) 25/303 (8.3)\nWorsening SIB^[c](#)^ 1/8 (12.5) 2/13 (15.4) 1/13 (7.7) 4/34 (11.8)\nTreatment-emergent SI^[d](#)^ 8/112 (7.1) 12/110 (10.9) 9/115 (7.8) 29/337 (8.6)\nNew-onset SI^[e](#)^ 7/104 (6.7) 10/97 (10.3) 8/102 (7.8) 25/303 (8.3)\nWish to be dead 5 4 3 12\nNonspecific active suicidal thoughts 1 1 1 3\nActive SI with any methods (no plan) without intent to act 1 5 4 10\nWorsening SI^[f](#)^ 1/8 (12.5) 2/13 (15.4) 1/13 (7.7) 4/34 (11.8)\nShift to nonspecific active suicidal thoughts 1 0 0 1\nShift to active SI with any methods (no plan) without intent to act 0 1 1 2\nShift to active SI with specific plan and intent 0 1 0 1\nTreatment-emergent SB^[g](#)^ 0/112 (0.0) 1/110 (0.9) 0/115 (0.0) 1/337 (0.3)\nNew-onset SB^[h](#)^ 0/112 (0.0) 1/110 (0.9) 0/115 (0.0) 1/337 (0.3)\nInterrupted attempt 0 1 0 1\nWorsening SB^[i](#)^ 0 0 0 0\n\nThere was one poststudy suicide attempt reported as a serious adverse\nevent that was not captured on the C-SSRS; C-SSRS was not performed\nfollowing that event. *N* represents the number of patients in this\nanalysis, that is, patients who had a baseline and a postbaseline C-SSRS\nassessment.\n\nTreatment-emergent SIB is defined as (1) new-onset SI or SB, (2)\nworsening SI or SB, or (3) postbaseline SB on patients reporting SI at\nbaseline.\n\nNew-onset SIB is defined as any SI or SB reported postbaseline on\npatients who reported no SI and no SB at baseline.\n\nWorsening SIB is defined as (1) shift from SI at baseline to a more\nsevere SI postbaseline, (2) shift from SI at baseline (and no SB at\nbaseline) to any SB postbaseline, or (3) shift from SB at baseline to a\nmore severe SB postbaseline.\n\nTreatment-emergent SI is defined as new-onset SI or worsening SI.\n\nNew-onset SI is defined as any SI reported postbaseline on patients who\nreported no SI at baseline.\n\nWorsening SI is defined as shift to a more severe SI postbaseline on\npatients reporting SI at baseline.\n\nTreatment-emergent SB is defined as new-onset SB or worsening SB.\n\nNew-onset SB is defined as any SB reported postbaseline on patients who\nreported no SB at baseline.\n\nWorsening SB is defined as shift to a more severe SB postbaseline on\npatients reporting SB at baseline.\n\nC-SSRS, Columbia-Suicide Severity Rating Scale; SB, suicidal behavior;\nSI, suicidal ideation; SIB, suicidal ideation or behavior.:::: New-onset self-injurious behavior without suicidal intent was reported in two (1.8%) fluoxetine-treated adolescents and one (0.9%) desvenlafaxine-treated adolescent. The suicide attempt reported as a serious AE in the \"Deaths and Serious AEs\" section was not captured on the C-SSRS because it occurred poststudy. \n\n### Other safety measures The frequencies of patients with on-therapy potentially clinically important (PCI) vital sign values can be found in [Supplementary Table S4](#). Upon review of patient data by the medical monitor, eight patients (all adolescents) were deemed to have clinically important vital sign results: postural hypotension in three desvenlafaxine-treated patients (35-, 35-, and 50-mg/d doses) and in four fluoxetine-treated patients, and increased supine systolic blood pressure in one desvenlafaxine-treated patient (122--126 mm Hg at weeks 3--6; baseline, 117 mm Hg). No patients assigned to placebo had clinically important vital sign findings, and the observed changes from baseline in body mass index (BMI) were negligible. Mean changes from baseline in BMI, blood pressure, and pulse measurements are reported by age group in [Supplementary Table S5](#). Expected shifts associated with development assessed by Tanner staging were observed during the study. Clinically important ECG findings were reported for one patient assigned to fluoxetine who had Wolff--Parkinson--White syndrome at study entry, with no change over the course of the study. The frequencies of on-therapy PCI laboratory findings are presented in [Supplementary Table S6](#). Findings in nine patients (four desvenlafaxine, five fluoxetine) were determined to be clinically important: three had elevated triglycerides (two desvenlafaxine, one fluoxetine), one high prolactin (desvenlafaxine), one low hematocrit and low hemoglobin (desvenlafaxine), three positive urine protein (fluoxetine), and one abnormal liver function test (fluoxetine). No clinically important laboratory values were observed in the placebo group. Mean changes from baseline for selected laboratory values are reported by age group and treatment in [Supplementary Table S7](#).\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** fluoxetine\n**Comparator:** placebo\n**Outcome:** CGI-I response rate\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: 79\n group_size: 101\ncomparator:\n events: 62.0\n group_size: 99"
}
] |
intervention:
events: 79
group_size: 101
comparator:
events: 62.0
group_size: 99
|
261
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n # Abstract\n\n ***Objectives:*** To evaluate the short-term efficacy and safety of desvenlafaxine (25--50 mg/d) compared with placebo in children and adolescents with major depressive disorder (MDD). ***Methods:*** Outpatient children (7--11 years) and adolescents (12--17 years) who met DSM-IV-TR criteria for MDD and had screening and baseline Children's Depression Rating Scale--Revised (CDRS-R) total scores >40 were randomly assigned to 8-week treatment with placebo, desvenlafaxine (25, 35, or 50 mg/d based on baseline weight), or fluoxetine (20 mg/d). The primary efficacy endpoint was change from baseline in CDRS-R total score at week 8, analyzed using a mixed-effects model for repeated measures. Secondary efficacy endpoints included week 8 Clinical Global Impressions--Severity, Clinical Global Impressions--Improvement (CGI-I), and response (CGI-I ≤ 2). Safety assessments included adverse events, physical and vital sign measurements, laboratory evaluations, electrocardiogram, and the Columbia-Suicide Severity Rating Scale. ***Results:*** The safety population included 339 patients (children, *n* = 130; adolescents, *n* = 209). The primary endpoint, change from baseline in CDRS-R total score at week 8, did not statistically separate from placebo, for either desvenlafaxine (adjusted mean [standard error] change, −22.6 [1.17]) or fluoxetine (−24.8 [1.17]; placebo, −23.1 [1.18]). Week 8 CGI-I response rates were significantly greater for fluoxetine (78.2%; *p* = 0.017) than for placebo (62.6%); desvenlafaxine (68.7%) did not differ from placebo. Other secondary outcomes were consistent with those obtained with CDRS-R. Rates of treatment-emergent adverse events were comparable among treatment groups (desvenlafaxine, 60.0%; placebo, 70.5%; and fluoxetine, 64.3%). ***Conclusion:*** Desvenlafaxine did not demonstrate efficacy for treating MDD in children and adolescents in this trial. Because neither desvenlafaxine nor the reference medication, fluoxetine, demonstrated a statistically significant difference from placebo on the primary endpoint, this was considered a failed trial and no efficacy conclusions can be drawn. Desvenlafaxine 25--50 mg/d was generally safe and well tolerated in children and adolescents in this study. # Results \n\n## Study population A total of 340 patients were randomly assigned to treatment; 339 patients (children, *n* = 130; adolescents, *n* = 209) were included in the safety population (desvenlafaxine, *n* = 115; fluoxetine, *n* = 112; placebo, *n* = 112). The ITT population included 130 children and 207 adolescents. A total of 42 (12%) patients discontinued early (desvenlafaxine, 16 [14%]; fluoxetine, 13 [12%]; and placebo, 13 [12%]). Lost to follow-up was the most common reason for discontinuation from the desvenlafaxine and placebo groups; in the fluoxetine group, the most common reason for discontinuation was \"no longer willing to participate\" ([Fig. 1](#)). <figure> <p><img src=\"\" /></p> <figcaption>Study flow. <sup>a</sup>One patient was screened and, although not randomized, received a total of eight blinded placebo doses. The patient was discontinued after the week 1 visit once the error was identified and listed as a protocol violation.</figcaption> </figure> Demographic and baseline characteristics were comparable among treatment groups for both children and adolescents ([Table 1](#)). Mean (SD) CDRS-R Total Score at baseline was 56.5 (8.9), mean (SD) CGI-S score was 4.5 (0.6), and the duration of the most recent depressive episode ranged from 1 to 96 months (median, 7; mean [SD], 13.4 [15.1]). Overall, 30.4% (103) of patients in the safety population had a prior or active psychiatric condition other than MDD in their medical history (desvenlafaxine, 31.3%; fluoxetine, 25.9%; and placebo, 33.9%). The most common psychiatric conditions (reported by ≥2% of patients) included attention-deficit/hyperactivity disorder (desvenlafaxine, 12.2%; fluoxetine, 13.4%; and placebo, 5.4%), nonsuicidal self-injurious behavior (desvenlafaxine, 7.0%; fluoxetine, 8.0%; and placebo, 12.5%), insomnia (desvenlafaxine, 7.0%; fluoxetine, 6.3%; and placebo, 8.0%), generalized anxiety disorder (desvenlafaxine, 0.9%; fluoxetine, 6.3%; and placebo, 0), and oppositional defiant disorder (desvenlafaxine, 3.5%; fluoxetine, 3.6%; and placebo, 0). ::::table-wrap\n\n::: caption\n\\[Demographic and Baseline Characteristics, Safety\nPopulation\\]{.smallcaps}\n:::\n\n*Children* *Adolescents*\n\n______________________________________________________________________\n\n*Placebo (*n* = 42)* *Fluoxetine (*n* = 45)* *Desvenlafaxine (*n* = 43)* *Total (*n* = 130)* *Placebo (*n* = 70)* *Fluoxetine (*n* = 67)* *Desvenlafaxine (*n* = 72)* *Total (*n* = 209)*\nAge, mean (SD), years 9.4 (1.3) 9.6 (1.3) 9.3 (1.4) 9.4 (1.3) 14.6 (1.5) 14.7 (1.6) 15.0 (1.5) 14.8 (1.5)\nSex, *n* (%)\\\nFemale 23 (55) 14 (31) 20 (47) 57 (44) 41 (59) 43 (64) 43 (60) 127 (61)\nMale 19 (45) 31 (69) 23 (53) 73 (56) 29 (41) 24 (36) 29 (40) 82 (39)\nRace, *n* (%)\\\nAsian 1 (2) 0 1 (2) 2 (2) 0 2 (3) 0 2 (1)\nBlack 15 (36) 15 (33) 14 (33) 44 (34) 10 (14) 19 (28) 18 (25) 47 (22)\nWhite 25 (60) 26 (58) 23 (53) 74 (57) 56 (80) 41 (61) 49 (68) 146 (70)\nOther 1 (2) 4 (9) 5 (12) 10 (8) 4 (6) 5 (7) 5 (7) 14 (7)\nHeight, mean (SD), cm 140.5 (10.6) 141.3 (11.2) 144.3 (11.5) 142.0 (11.1) 164.5 (9.8) 165.8 (8.4) 167.3 (9.1) 165.9 (9.2)\nWeight, mean (SD), kg 39.4 (14.0) 44.0 (18.9) 46.0 (15.2) 43.2 (16.3) 68.0 (19.1) 73.3 (21.8) 71.7 (19.0) 71.0 (20.0)\nBMI, mean (SD), kg/m^2^ 19.5 (4.7) 21.3 (6.4) 21.6 (5.0) 20.8 (5.5) 25.0 (6.0) 26.5 (6.9) 25.5 (5.8) 25.6 (6.3)\nDuration of most recent episode, median (range), months 11 (1--57) 6 (1--42) 8 (1--71) 7 (1--71) 8 (1--69) 7 (1--96) 7 (1--61) 7 (1--96)\nCDRS-R total score, mean (SD) 57.0 (8.6) 55.0 (8.7) 56.4 (10.9) 56.1 (9.4) 57.1 (9.1) 57.0 (8.1) 56.3 (8.8) 56.8 (8.7)\n\nBMI, body mass index; CDRS-R, Children's Depression Rating\nScale--Revised; SD, standard deviation.:::: \n\n## Efficacy Statistical separation from placebo was not observed on the primary efficacy endpoint for either desvenlafaxine or for the fluoxetine reference group. Adjusted mean (standard error) change from baseline in CDRS-R total score at week 8 was −22.6 (1.17) and −23.1 (1.18) for the desvenlafaxine and placebo groups, respectively, and for fluoxetine was −24.8 (1.17) ([Fig. 2](#)). The change from baseline in CDRS-R over the 8-week treatment phase was similar for the three arms. Point differences were statistically significant between desvenlafaxine and placebo at week 2 and between fluoxetine and placebo at weeks 1 and 2; no significant differences were observed at any other time points. Results were similar for the child and adolescent groups in an exploratory analysis of change from baseline in CDRS-R total score ([Supplementary Fig. S1](#)). <figure> <p><img src=\"\" /></p> <figcaption>Adjusted mean (SE) change from baseline in CDRS-R total score in children and adolescents; MMRM analysis, ITT population. \\*<em>p</em> \\< 0.01, fluoxetine versus placebo. <sup>†</sup><em>p</em> \\< 0.05, fluoxetine versus placebo and desvenlafaxine versus placebo. CDRS-R, Children's Depression Rating Scale–Revised; CI, confidence interval; ITT, intent-to-treat; MMRM, mixed-effects model for repeated measures; SE, standard error.</figcaption> </figure> At week 8, the CGI-I response rate for fluoxetine (78.2%) was significantly greater compared with placebo (62.6%; *p* = 0.017). Week 8 CGI-I response rate for desvenlafaxine (68.7%) was also greater than placebo, although this comparison did not reach statistical significance (*p* = 0.343). Results for CGI-S and CGI-I scores were otherwise consistent with those for CDRS-R total score, with no statistically significant difference from placebo for either desvenlafaxine or fluoxetine at week 8 ([Table 2](#)). ::::table-wrap\n::: caption\n[Summary of Secondary Efficacy Outcomes at Week 8]{.smallcaps}\n:::\n\n*CGI-S* n *Adjusted mean change (SE) from baseline*^[a](#)^ *Difference in adjusted means (placebo-active)* *95% CI* p\n\n______________________________________________________________________\n\nPlacebo 99 −1.71 (0.12) --- --- ---\nFluoxetine 101 −1.88 (0.12) 0.18 −0.11 to 0.46 0.224\nDesvenlafaxine 99 −1.70 (0.11) −0.01 −0.29 to 0.27 0.944\n\n*CGI-I*^[b](#)^ n *Very much improved (%)* *Much improved (%)* *Minimally improved (%)* *No change (%)* *CMH test*^[c](#)^ p\\*-value\\*\n\n______________________________________________________________________\n\nPlacebo 99 27.3 35.4 32.3 4.0 ---\nFluoxetine 101 30.7 47.5 16.8 4.0 0.095\nDesvenlafaxine 99 23.2 45.5 21.2 9.1 0.852\n\n*CGI-I response*^[d](#)^ *Proportion responders* *%* *Adjusted odds ratio*^[e](#)^ *Wald 95% CI* p\n\n______________________________________________________________________\n\nPlacebo 62/99 62.6 --- --- ---\nFluoxetine 79/101 78.2 0.465 0.249 to 0.871 0.017\nDesvenlafaxine 68/99 68.7 0.751 0.415 to 1.357 0.343\n\nEstimates of adjusted mean, SE, difference in means, 95% CI, and\n*p*-values were based on a mixed-effects model for repeated measures for\nthe change from baseline in CGI-S with terms for treatment, week,\ninteraction of treatment and week, age group, country, gender, and\nbaseline CGI-S total score.\n\nCGI-I scored as 1, very much improved; 2, much improved; 3, minimally\nimproved; 4, no change; 5, minimally worse; 6, much worse; 7, very much\nworse. No patients scored 5--7 at week 8.\n\nCMH test was controlled for age group and country.\n\nCGI-I response was defined as CGI-I score of 1 (very much improved) or 2\n(much improved).\n\nEstimates of odds ratios, 95% CI, and *p*-values were based on a\nlogistic regression model of the response rate, with terms for treatment\ngroup, age group, and country.\n\nCGI-I, Clinical Global Impressions--Improvement; CGI-S, Clinical Global\nImpressions--Severity; CI, confidence interval; CMH,\nCochran--Mantel--Haenszel; SE, standard error.:::: \n\n## Safety \n\n### Adverse events A total of 220/339 (64.9%) patients experienced AEs during the on-therapy period (desvenlafaxine, 69/115 [60.0%]; fluoxetine, 72/112 [64.3%]; and placebo, 79/112 [70.5%]). Most AEs were mild or moderate in severity. AEs considered by the investigator to be related to study medication were reported by 31.9% of patients (desvenlafaxine, 28.7%; fluoxetine, 32.1%; and placebo, 34.8%). Severe AEs (those that interfered significantly with patients' usual function) considered by the investigator to be unrelated to study medication were reported by 3.5% of patients (desvenlafaxine, 1.7%; fluoxetine, 5.4%; and placebo, 3.6%). In three patients, severe AEs were considered related to study medication: One desvenlafaxine-treated patient reported severe pruritus and severe macular rash and discontinued treatment. One placebo-treated patient reported severe agitation and severe anger, and a second reported severe insomnia; neither was discontinued due to those AEs. Five adolescents (0 children) discontinued due to AEs, two each from the desvenlafaxine (disinhibition; macular rash and pruritus) and placebo (vomiting; headache) groups and one from the fluoxetine group (suicidal ideation). \n\n### Treatment-emergent adverse events Treatment-emergent adverse events (TEAEs) reported by more than 10% of patients in any group were headache, upper abdominal pain, and nausea. [Table 3](#) shows the most frequent (≥5% in any group) TEAEs by age group, and overall. There were no statistically significant differences between desvenlafaxine or fluoxetine and placebo in the incidence of any prespecified TEAEs of clinical interest for desvenlafaxine (tier-1 TEAEs) ([Supplementary Table S2](#)). ::::table-wrap\n::: caption\n\\[Number (%) of Patients Reporting Treatment-Emergent Adverse Events with\nIncidence ≥5% in Any Group, On-Therapy Period, Safety\nPopulation\\]{.smallcaps}\n:::\n\n*Children* *Adolescents* *Overall*\n\n______________________________________________________________________\n\n*Placebo (*n* = 42)* *Fluoxetine (*n* = 45)* *Desvenlafaxine (*n* = 43)* *Placebo (*n* = 70)* *Fluoxetine (*n* = 67)* *Desvenlafaxine (*n* = 72)* *Placebo (*n* = 112)* *Desvenlafaxine (*n* = 112)* *Desvenlafaxine (*n* = 115)*\nAny TEAE 27 (64.3) 29 (64.4) 22 (51.2) 52 (74.3) 43 (64.2) 47 (65.3) 79 (70.5) 72 (64.3) 69 (60.0)\nHeadache 8 (19.0) 3 (6.7) 5 (11.6) 13 (18.6) 13 (19.4) 14 (19.4) 21 (18.8) 16 (14.3) 19 (16.5)\nAbdominal pain upper 2 (4.8) 1 (2.2) 6 (14.0) 5 (7.1) 8 (11.9) 9 (12.5) 7 (6.3) 9 (8.0) 15 (13.0)\nNausea 3 (7.1) 4 (8.9) 2 (4.7) 7 (10.0) 9 (13.4) 6 (8.3) 10 (8.9) 13 (11.6) 8 (7.0)\nDizziness 3 (7.1) 1 (2.2) 2 (4.7) 3 (4.3) 2 (3.0) 5 (6.9) 6 (5.4) 3 (2.7) 7 (6.1)\nInfluenza 0 2 (4.4) 2 (4.7) 0 0 4 (5.6) 0 2 (1.8) 6 (5.2)\nNasopharyngitis 4 (9.5) 2 (4.4) 1 (2.3) 4 (5.7) 5 (7.5) 5 (6.9) 8 (7.1) 7 (6.3) 6 (5.2)\nUpper respiratory tract infection 2 (4.8) 3 (6.7) 1 (2.3) 4 (5.7) 1 (1.5) 5 (6.9) 6 (5.4) 4 (3.6) 6 (5.2)\nVomiting 1 (2.4) 5 (11.1) 1 (2.3) 3 (4.3) 2 (3.0) 4 (5.6) 4 (3.6) 7 (6.3) 5 (4.3)\nDiarrhea 1 (2.4) 0 4 (9.3) 2 (2.9) 3 (4.5) 1 (1.4) 3 (2.7) 3 (2.7) 5 (4.3)\nInsomnia 1 (2.4) 1 (2.2) 0 2 (2.9) 4 (6.0) 4 (5.6) 3 (2.7) 5 (4.5) 4 (3.5)\nFatigue 1 (2.4) 3 (6.7) 0 1 (1.4) 3 (4.5) 2 (2.8) 2 (1.8) 6 (5.4) 2 (1.7)\nPharyngitis 2 (4.8) 3 (6.7) 1 (2.3) 0 1 (1.5) 1 (1.4) 2 (1.8) 4 (3.6) 2 (1.7)\nRash 0 3 (6.7) 0 0 1 (1.5) 1 (1.4) 0 4 (3.6) 1 (0.9)\nArthralgia 3 (7.1) 1 (2.2) 1 (2.3) 1 (1.4) 2 (3.0) 0 4 (3.6) 3 (2.7) 1 (0.9)\nFall 2 (4.8) 4 (8.9) 0 0 1 (1.5) 0 2 (1.8) 5 (4.5) 0\nConstipation 3 (7.1) 0 0 1 (1.4) 0 0 4 (3.6) 0 0\n\nTEAE, treatment-emergent adverse event.:::: \n\n### Deaths and serious AEs There were no deaths during the study. Five randomized patients experienced serious AEs: two assigned to fluoxetine (suicidal ideation [acute suicidality; discontinued] and suicide attempt [occurred poststudy], one patient each), three assigned to desvenlafaxine (suicidal ideation [discontinued due to lack of confidence in caregiver reliability to report patient status], disinhibition [discontinued], and postpartum hemorrhage with anemia and endometritis [occurred poststudy], one patient each), and no placebo-treated patients. The desvenlafaxine-treated patient with postpartum hemorrhage had been withdrawn from the study following a positive pregnancy test at the final treatment phase visit and delivered a healthy full-term infant. \n\n### Suicidality A summary of C-SSRS results for treatment-emergent suicidal ideation or behavior is presented for the safety population in [Table 4](#) (full C-SSRS results are presented in [Supplementary Table S3](#)). Treatment-emergent suicidal ideation or suicidal behavior, which included both new-onset and worsening suicidal ideation or behavior, was reported for 29 (8.6%) of 337 patients who had a C-SSRS assessment at baseline and at 1 or more postbaseline time points. A total of 29/337 (8.6%) patients had treatment-emergent suicidal ideation, and 1 patient (0.3%) also had treatment-emergent suicidal behavior. The suicidal behavior event was categorized as a preparatory act toward imminent suicidal behavior (preparatory acts or behavior; interrupted attempt) and was reported in a fluoxetine-treated adolescent ([Supplementary Table S3](#)). The patient was discontinued due to a serious AE of acute suicidality (described in \"Deaths and Serious AEs\" section). ::::table-wrap\n::: caption\n\\[Summary of Treatment-Emergent Suicidal Ideation and Behavior Reported\non the Columbia-Suicide Severity Rating Scale at Any Postbaseline\nAssessment, Safety Population\\]{.smallcaps}\n:::\n\n*Placebo (*N* = 112)* *Fluoxetine (*N* = 110)* *Desvenlafaxine (*N* = 115)* *Total (*N* = 337)*\n\n______________________________________________________________________\n\nTreatment-emergent SIB^[a](#)^ 8/112 (7.1) 12/110 (10.9) 9/115 (7.8) 29/337 (8.6)\nNew-onset SIB^[b](#)^ 7/104 (6.7) 10/97 (10.3) 8/102 (7.8) 25/303 (8.3)\nWorsening SIB^[c](#)^ 1/8 (12.5) 2/13 (15.4) 1/13 (7.7) 4/34 (11.8)\nTreatment-emergent SI^[d](#)^ 8/112 (7.1) 12/110 (10.9) 9/115 (7.8) 29/337 (8.6)\nNew-onset SI^[e](#)^ 7/104 (6.7) 10/97 (10.3) 8/102 (7.8) 25/303 (8.3)\nWish to be dead 5 4 3 12\nNonspecific active suicidal thoughts 1 1 1 3\nActive SI with any methods (no plan) without intent to act 1 5 4 10\nWorsening SI^[f](#)^ 1/8 (12.5) 2/13 (15.4) 1/13 (7.7) 4/34 (11.8)\nShift to nonspecific active suicidal thoughts 1 0 0 1\nShift to active SI with any methods (no plan) without intent to act 0 1 1 2\nShift to active SI with specific plan and intent 0 1 0 1\nTreatment-emergent SB^[g](#)^ 0/112 (0.0) 1/110 (0.9) 0/115 (0.0) 1/337 (0.3)\nNew-onset SB^[h](#)^ 0/112 (0.0) 1/110 (0.9) 0/115 (0.0) 1/337 (0.3)\nInterrupted attempt 0 1 0 1\nWorsening SB^[i](#)^ 0 0 0 0\n\nThere was one poststudy suicide attempt reported as a serious adverse\nevent that was not captured on the C-SSRS; C-SSRS was not performed\nfollowing that event. *N* represents the number of patients in this\nanalysis, that is, patients who had a baseline and a postbaseline C-SSRS\nassessment.\n\nTreatment-emergent SIB is defined as (1) new-onset SI or SB, (2)\nworsening SI or SB, or (3) postbaseline SB on patients reporting SI at\nbaseline.\n\nNew-onset SIB is defined as any SI or SB reported postbaseline on\npatients who reported no SI and no SB at baseline.\n\nWorsening SIB is defined as (1) shift from SI at baseline to a more\nsevere SI postbaseline, (2) shift from SI at baseline (and no SB at\nbaseline) to any SB postbaseline, or (3) shift from SB at baseline to a\nmore severe SB postbaseline.\n\nTreatment-emergent SI is defined as new-onset SI or worsening SI.\n\nNew-onset SI is defined as any SI reported postbaseline on patients who\nreported no SI at baseline.\n\nWorsening SI is defined as shift to a more severe SI postbaseline on\npatients reporting SI at baseline.\n\nTreatment-emergent SB is defined as new-onset SB or worsening SB.\n\nNew-onset SB is defined as any SB reported postbaseline on patients who\nreported no SB at baseline.\n\nWorsening SB is defined as shift to a more severe SB postbaseline on\npatients reporting SB at baseline.\n\nC-SSRS, Columbia-Suicide Severity Rating Scale; SB, suicidal behavior;\nSI, suicidal ideation; SIB, suicidal ideation or behavior.:::: New-onset self-injurious behavior without suicidal intent was reported in two (1.8%) fluoxetine-treated adolescents and one (0.9%) desvenlafaxine-treated adolescent. The suicide attempt reported as a serious AE in the \"Deaths and Serious AEs\" section was not captured on the C-SSRS because it occurred poststudy. \n\n### Other safety measures The frequencies of patients with on-therapy potentially clinically important (PCI) vital sign values can be found in [Supplementary Table S4](#). Upon review of patient data by the medical monitor, eight patients (all adolescents) were deemed to have clinically important vital sign results: postural hypotension in three desvenlafaxine-treated patients (35-, 35-, and 50-mg/d doses) and in four fluoxetine-treated patients, and increased supine systolic blood pressure in one desvenlafaxine-treated patient (122--126 mm Hg at weeks 3--6; baseline, 117 mm Hg). No patients assigned to placebo had clinically important vital sign findings, and the observed changes from baseline in body mass index (BMI) were negligible. Mean changes from baseline in BMI, blood pressure, and pulse measurements are reported by age group in [Supplementary Table S5](#). Expected shifts associated with development assessed by Tanner staging were observed during the study. Clinically important ECG findings were reported for one patient assigned to fluoxetine who had Wolff--Parkinson--White syndrome at study entry, with no change over the course of the study. The frequencies of on-therapy PCI laboratory findings are presented in [Supplementary Table S6](#). Findings in nine patients (four desvenlafaxine, five fluoxetine) were determined to be clinically important: three had elevated triglycerides (two desvenlafaxine, one fluoxetine), one high prolactin (desvenlafaxine), one low hematocrit and low hemoglobin (desvenlafaxine), three positive urine protein (fluoxetine), and one abnormal liver function test (fluoxetine). No clinically important laboratory values were observed in the placebo group. Mean changes from baseline for selected laboratory values are reported by age group and treatment in [Supplementary Table S7](#).\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** desvenlafaxine\n**Comparator:** placebo\n**Outcome:** CGI-I response rate\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: 68\n group_size: 99\ncomparator:\n events: 62.0\n group_size: 99"
}
] |
intervention:
events: 68
group_size: 99
comparator:
events: 62.0
group_size: 99
|
262
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n # Abstract\n\n ***Objectives:*** To evaluate the short-term efficacy and safety of desvenlafaxine (25--50 mg/d) compared with placebo in children and adolescents with major depressive disorder (MDD). ***Methods:*** Outpatient children (7--11 years) and adolescents (12--17 years) who met DSM-IV-TR criteria for MDD and had screening and baseline Children's Depression Rating Scale--Revised (CDRS-R) total scores >40 were randomly assigned to 8-week treatment with placebo, desvenlafaxine (25, 35, or 50 mg/d based on baseline weight), or fluoxetine (20 mg/d). The primary efficacy endpoint was change from baseline in CDRS-R total score at week 8, analyzed using a mixed-effects model for repeated measures. Secondary efficacy endpoints included week 8 Clinical Global Impressions--Severity, Clinical Global Impressions--Improvement (CGI-I), and response (CGI-I ≤ 2). Safety assessments included adverse events, physical and vital sign measurements, laboratory evaluations, electrocardiogram, and the Columbia-Suicide Severity Rating Scale. ***Results:*** The safety population included 339 patients (children, *n* = 130; adolescents, *n* = 209). The primary endpoint, change from baseline in CDRS-R total score at week 8, did not statistically separate from placebo, for either desvenlafaxine (adjusted mean [standard error] change, −22.6 [1.17]) or fluoxetine (−24.8 [1.17]; placebo, −23.1 [1.18]). Week 8 CGI-I response rates were significantly greater for fluoxetine (78.2%; *p* = 0.017) than for placebo (62.6%); desvenlafaxine (68.7%) did not differ from placebo. Other secondary outcomes were consistent with those obtained with CDRS-R. Rates of treatment-emergent adverse events were comparable among treatment groups (desvenlafaxine, 60.0%; placebo, 70.5%; and fluoxetine, 64.3%). ***Conclusion:*** Desvenlafaxine did not demonstrate efficacy for treating MDD in children and adolescents in this trial. Because neither desvenlafaxine nor the reference medication, fluoxetine, demonstrated a statistically significant difference from placebo on the primary endpoint, this was considered a failed trial and no efficacy conclusions can be drawn. Desvenlafaxine 25--50 mg/d was generally safe and well tolerated in children and adolescents in this study. # Results \n\n## Study population A total of 340 patients were randomly assigned to treatment; 339 patients (children, *n* = 130; adolescents, *n* = 209) were included in the safety population (desvenlafaxine, *n* = 115; fluoxetine, *n* = 112; placebo, *n* = 112). The ITT population included 130 children and 207 adolescents. A total of 42 (12%) patients discontinued early (desvenlafaxine, 16 [14%]; fluoxetine, 13 [12%]; and placebo, 13 [12%]). Lost to follow-up was the most common reason for discontinuation from the desvenlafaxine and placebo groups; in the fluoxetine group, the most common reason for discontinuation was \"no longer willing to participate\" ([Fig. 1](#)). <figure> <p><img src=\"\" /></p> <figcaption>Study flow. <sup>a</sup>One patient was screened and, although not randomized, received a total of eight blinded placebo doses. The patient was discontinued after the week 1 visit once the error was identified and listed as a protocol violation.</figcaption> </figure> Demographic and baseline characteristics were comparable among treatment groups for both children and adolescents ([Table 1](#)). Mean (SD) CDRS-R Total Score at baseline was 56.5 (8.9), mean (SD) CGI-S score was 4.5 (0.6), and the duration of the most recent depressive episode ranged from 1 to 96 months (median, 7; mean [SD], 13.4 [15.1]). Overall, 30.4% (103) of patients in the safety population had a prior or active psychiatric condition other than MDD in their medical history (desvenlafaxine, 31.3%; fluoxetine, 25.9%; and placebo, 33.9%). The most common psychiatric conditions (reported by ≥2% of patients) included attention-deficit/hyperactivity disorder (desvenlafaxine, 12.2%; fluoxetine, 13.4%; and placebo, 5.4%), nonsuicidal self-injurious behavior (desvenlafaxine, 7.0%; fluoxetine, 8.0%; and placebo, 12.5%), insomnia (desvenlafaxine, 7.0%; fluoxetine, 6.3%; and placebo, 8.0%), generalized anxiety disorder (desvenlafaxine, 0.9%; fluoxetine, 6.3%; and placebo, 0), and oppositional defiant disorder (desvenlafaxine, 3.5%; fluoxetine, 3.6%; and placebo, 0). ::::table-wrap\n\n::: caption\n\\[Demographic and Baseline Characteristics, Safety\nPopulation\\]{.smallcaps}\n:::\n\n*Children* *Adolescents*\n\n______________________________________________________________________\n\n*Placebo (*n* = 42)* *Fluoxetine (*n* = 45)* *Desvenlafaxine (*n* = 43)* *Total (*n* = 130)* *Placebo (*n* = 70)* *Fluoxetine (*n* = 67)* *Desvenlafaxine (*n* = 72)* *Total (*n* = 209)*\nAge, mean (SD), years 9.4 (1.3) 9.6 (1.3) 9.3 (1.4) 9.4 (1.3) 14.6 (1.5) 14.7 (1.6) 15.0 (1.5) 14.8 (1.5)\nSex, *n* (%)\\\nFemale 23 (55) 14 (31) 20 (47) 57 (44) 41 (59) 43 (64) 43 (60) 127 (61)\nMale 19 (45) 31 (69) 23 (53) 73 (56) 29 (41) 24 (36) 29 (40) 82 (39)\nRace, *n* (%)\\\nAsian 1 (2) 0 1 (2) 2 (2) 0 2 (3) 0 2 (1)\nBlack 15 (36) 15 (33) 14 (33) 44 (34) 10 (14) 19 (28) 18 (25) 47 (22)\nWhite 25 (60) 26 (58) 23 (53) 74 (57) 56 (80) 41 (61) 49 (68) 146 (70)\nOther 1 (2) 4 (9) 5 (12) 10 (8) 4 (6) 5 (7) 5 (7) 14 (7)\nHeight, mean (SD), cm 140.5 (10.6) 141.3 (11.2) 144.3 (11.5) 142.0 (11.1) 164.5 (9.8) 165.8 (8.4) 167.3 (9.1) 165.9 (9.2)\nWeight, mean (SD), kg 39.4 (14.0) 44.0 (18.9) 46.0 (15.2) 43.2 (16.3) 68.0 (19.1) 73.3 (21.8) 71.7 (19.0) 71.0 (20.0)\nBMI, mean (SD), kg/m^2^ 19.5 (4.7) 21.3 (6.4) 21.6 (5.0) 20.8 (5.5) 25.0 (6.0) 26.5 (6.9) 25.5 (5.8) 25.6 (6.3)\nDuration of most recent episode, median (range), months 11 (1--57) 6 (1--42) 8 (1--71) 7 (1--71) 8 (1--69) 7 (1--96) 7 (1--61) 7 (1--96)\nCDRS-R total score, mean (SD) 57.0 (8.6) 55.0 (8.7) 56.4 (10.9) 56.1 (9.4) 57.1 (9.1) 57.0 (8.1) 56.3 (8.8) 56.8 (8.7)\n\nBMI, body mass index; CDRS-R, Children's Depression Rating\nScale--Revised; SD, standard deviation.:::: \n\n## Efficacy Statistical separation from placebo was not observed on the primary efficacy endpoint for either desvenlafaxine or for the fluoxetine reference group. Adjusted mean (standard error) change from baseline in CDRS-R total score at week 8 was −22.6 (1.17) and −23.1 (1.18) for the desvenlafaxine and placebo groups, respectively, and for fluoxetine was −24.8 (1.17) ([Fig. 2](#)). The change from baseline in CDRS-R over the 8-week treatment phase was similar for the three arms. Point differences were statistically significant between desvenlafaxine and placebo at week 2 and between fluoxetine and placebo at weeks 1 and 2; no significant differences were observed at any other time points. Results were similar for the child and adolescent groups in an exploratory analysis of change from baseline in CDRS-R total score ([Supplementary Fig. S1](#)). <figure> <p><img src=\"\" /></p> <figcaption>Adjusted mean (SE) change from baseline in CDRS-R total score in children and adolescents; MMRM analysis, ITT population. \\*<em>p</em> \\< 0.01, fluoxetine versus placebo. <sup>†</sup><em>p</em> \\< 0.05, fluoxetine versus placebo and desvenlafaxine versus placebo. CDRS-R, Children's Depression Rating Scale–Revised; CI, confidence interval; ITT, intent-to-treat; MMRM, mixed-effects model for repeated measures; SE, standard error.</figcaption> </figure> At week 8, the CGI-I response rate for fluoxetine (78.2%) was significantly greater compared with placebo (62.6%; *p* = 0.017). Week 8 CGI-I response rate for desvenlafaxine (68.7%) was also greater than placebo, although this comparison did not reach statistical significance (*p* = 0.343). Results for CGI-S and CGI-I scores were otherwise consistent with those for CDRS-R total score, with no statistically significant difference from placebo for either desvenlafaxine or fluoxetine at week 8 ([Table 2](#)). ::::table-wrap\n::: caption\n[Summary of Secondary Efficacy Outcomes at Week 8]{.smallcaps}\n:::\n\n*CGI-S* n *Adjusted mean change (SE) from baseline*^[a](#)^ *Difference in adjusted means (placebo-active)* *95% CI* p\n\n______________________________________________________________________\n\nPlacebo 99 −1.71 (0.12) --- --- ---\nFluoxetine 101 −1.88 (0.12) 0.18 −0.11 to 0.46 0.224\nDesvenlafaxine 99 −1.70 (0.11) −0.01 −0.29 to 0.27 0.944\n\n*CGI-I*^[b](#)^ n *Very much improved (%)* *Much improved (%)* *Minimally improved (%)* *No change (%)* *CMH test*^[c](#)^ p\\*-value\\*\n\n______________________________________________________________________\n\nPlacebo 99 27.3 35.4 32.3 4.0 ---\nFluoxetine 101 30.7 47.5 16.8 4.0 0.095\nDesvenlafaxine 99 23.2 45.5 21.2 9.1 0.852\n\n*CGI-I response*^[d](#)^ *Proportion responders* *%* *Adjusted odds ratio*^[e](#)^ *Wald 95% CI* p\n\n______________________________________________________________________\n\nPlacebo 62/99 62.6 --- --- ---\nFluoxetine 79/101 78.2 0.465 0.249 to 0.871 0.017\nDesvenlafaxine 68/99 68.7 0.751 0.415 to 1.357 0.343\n\nEstimates of adjusted mean, SE, difference in means, 95% CI, and\n*p*-values were based on a mixed-effects model for repeated measures for\nthe change from baseline in CGI-S with terms for treatment, week,\ninteraction of treatment and week, age group, country, gender, and\nbaseline CGI-S total score.\n\nCGI-I scored as 1, very much improved; 2, much improved; 3, minimally\nimproved; 4, no change; 5, minimally worse; 6, much worse; 7, very much\nworse. No patients scored 5--7 at week 8.\n\nCMH test was controlled for age group and country.\n\nCGI-I response was defined as CGI-I score of 1 (very much improved) or 2\n(much improved).\n\nEstimates of odds ratios, 95% CI, and *p*-values were based on a\nlogistic regression model of the response rate, with terms for treatment\ngroup, age group, and country.\n\nCGI-I, Clinical Global Impressions--Improvement; CGI-S, Clinical Global\nImpressions--Severity; CI, confidence interval; CMH,\nCochran--Mantel--Haenszel; SE, standard error.:::: \n\n## Safety \n\n### Adverse events A total of 220/339 (64.9%) patients experienced AEs during the on-therapy period (desvenlafaxine, 69/115 [60.0%]; fluoxetine, 72/112 [64.3%]; and placebo, 79/112 [70.5%]). Most AEs were mild or moderate in severity. AEs considered by the investigator to be related to study medication were reported by 31.9% of patients (desvenlafaxine, 28.7%; fluoxetine, 32.1%; and placebo, 34.8%). Severe AEs (those that interfered significantly with patients' usual function) considered by the investigator to be unrelated to study medication were reported by 3.5% of patients (desvenlafaxine, 1.7%; fluoxetine, 5.4%; and placebo, 3.6%). In three patients, severe AEs were considered related to study medication: One desvenlafaxine-treated patient reported severe pruritus and severe macular rash and discontinued treatment. One placebo-treated patient reported severe agitation and severe anger, and a second reported severe insomnia; neither was discontinued due to those AEs. Five adolescents (0 children) discontinued due to AEs, two each from the desvenlafaxine (disinhibition; macular rash and pruritus) and placebo (vomiting; headache) groups and one from the fluoxetine group (suicidal ideation). \n\n### Treatment-emergent adverse events Treatment-emergent adverse events (TEAEs) reported by more than 10% of patients in any group were headache, upper abdominal pain, and nausea. [Table 3](#) shows the most frequent (≥5% in any group) TEAEs by age group, and overall. There were no statistically significant differences between desvenlafaxine or fluoxetine and placebo in the incidence of any prespecified TEAEs of clinical interest for desvenlafaxine (tier-1 TEAEs) ([Supplementary Table S2](#)). ::::table-wrap\n::: caption\n\\[Number (%) of Patients Reporting Treatment-Emergent Adverse Events with\nIncidence ≥5% in Any Group, On-Therapy Period, Safety\nPopulation\\]{.smallcaps}\n:::\n\n*Children* *Adolescents* *Overall*\n\n______________________________________________________________________\n\n*Placebo (*n* = 42)* *Fluoxetine (*n* = 45)* *Desvenlafaxine (*n* = 43)* *Placebo (*n* = 70)* *Fluoxetine (*n* = 67)* *Desvenlafaxine (*n* = 72)* *Placebo (*n* = 112)* *Desvenlafaxine (*n* = 112)* *Desvenlafaxine (*n* = 115)*\nAny TEAE 27 (64.3) 29 (64.4) 22 (51.2) 52 (74.3) 43 (64.2) 47 (65.3) 79 (70.5) 72 (64.3) 69 (60.0)\nHeadache 8 (19.0) 3 (6.7) 5 (11.6) 13 (18.6) 13 (19.4) 14 (19.4) 21 (18.8) 16 (14.3) 19 (16.5)\nAbdominal pain upper 2 (4.8) 1 (2.2) 6 (14.0) 5 (7.1) 8 (11.9) 9 (12.5) 7 (6.3) 9 (8.0) 15 (13.0)\nNausea 3 (7.1) 4 (8.9) 2 (4.7) 7 (10.0) 9 (13.4) 6 (8.3) 10 (8.9) 13 (11.6) 8 (7.0)\nDizziness 3 (7.1) 1 (2.2) 2 (4.7) 3 (4.3) 2 (3.0) 5 (6.9) 6 (5.4) 3 (2.7) 7 (6.1)\nInfluenza 0 2 (4.4) 2 (4.7) 0 0 4 (5.6) 0 2 (1.8) 6 (5.2)\nNasopharyngitis 4 (9.5) 2 (4.4) 1 (2.3) 4 (5.7) 5 (7.5) 5 (6.9) 8 (7.1) 7 (6.3) 6 (5.2)\nUpper respiratory tract infection 2 (4.8) 3 (6.7) 1 (2.3) 4 (5.7) 1 (1.5) 5 (6.9) 6 (5.4) 4 (3.6) 6 (5.2)\nVomiting 1 (2.4) 5 (11.1) 1 (2.3) 3 (4.3) 2 (3.0) 4 (5.6) 4 (3.6) 7 (6.3) 5 (4.3)\nDiarrhea 1 (2.4) 0 4 (9.3) 2 (2.9) 3 (4.5) 1 (1.4) 3 (2.7) 3 (2.7) 5 (4.3)\nInsomnia 1 (2.4) 1 (2.2) 0 2 (2.9) 4 (6.0) 4 (5.6) 3 (2.7) 5 (4.5) 4 (3.5)\nFatigue 1 (2.4) 3 (6.7) 0 1 (1.4) 3 (4.5) 2 (2.8) 2 (1.8) 6 (5.4) 2 (1.7)\nPharyngitis 2 (4.8) 3 (6.7) 1 (2.3) 0 1 (1.5) 1 (1.4) 2 (1.8) 4 (3.6) 2 (1.7)\nRash 0 3 (6.7) 0 0 1 (1.5) 1 (1.4) 0 4 (3.6) 1 (0.9)\nArthralgia 3 (7.1) 1 (2.2) 1 (2.3) 1 (1.4) 2 (3.0) 0 4 (3.6) 3 (2.7) 1 (0.9)\nFall 2 (4.8) 4 (8.9) 0 0 1 (1.5) 0 2 (1.8) 5 (4.5) 0\nConstipation 3 (7.1) 0 0 1 (1.4) 0 0 4 (3.6) 0 0\n\nTEAE, treatment-emergent adverse event.:::: \n\n### Deaths and serious AEs There were no deaths during the study. Five randomized patients experienced serious AEs: two assigned to fluoxetine (suicidal ideation [acute suicidality; discontinued] and suicide attempt [occurred poststudy], one patient each), three assigned to desvenlafaxine (suicidal ideation [discontinued due to lack of confidence in caregiver reliability to report patient status], disinhibition [discontinued], and postpartum hemorrhage with anemia and endometritis [occurred poststudy], one patient each), and no placebo-treated patients. The desvenlafaxine-treated patient with postpartum hemorrhage had been withdrawn from the study following a positive pregnancy test at the final treatment phase visit and delivered a healthy full-term infant. \n\n### Suicidality A summary of C-SSRS results for treatment-emergent suicidal ideation or behavior is presented for the safety population in [Table 4](#) (full C-SSRS results are presented in [Supplementary Table S3](#)). Treatment-emergent suicidal ideation or suicidal behavior, which included both new-onset and worsening suicidal ideation or behavior, was reported for 29 (8.6%) of 337 patients who had a C-SSRS assessment at baseline and at 1 or more postbaseline time points. A total of 29/337 (8.6%) patients had treatment-emergent suicidal ideation, and 1 patient (0.3%) also had treatment-emergent suicidal behavior. The suicidal behavior event was categorized as a preparatory act toward imminent suicidal behavior (preparatory acts or behavior; interrupted attempt) and was reported in a fluoxetine-treated adolescent ([Supplementary Table S3](#)). The patient was discontinued due to a serious AE of acute suicidality (described in \"Deaths and Serious AEs\" section). ::::table-wrap\n::: caption\n\\[Summary of Treatment-Emergent Suicidal Ideation and Behavior Reported\non the Columbia-Suicide Severity Rating Scale at Any Postbaseline\nAssessment, Safety Population\\]{.smallcaps}\n:::\n\n*Placebo (*N* = 112)* *Fluoxetine (*N* = 110)* *Desvenlafaxine (*N* = 115)* *Total (*N* = 337)*\n\n______________________________________________________________________\n\nTreatment-emergent SIB^[a](#)^ 8/112 (7.1) 12/110 (10.9) 9/115 (7.8) 29/337 (8.6)\nNew-onset SIB^[b](#)^ 7/104 (6.7) 10/97 (10.3) 8/102 (7.8) 25/303 (8.3)\nWorsening SIB^[c](#)^ 1/8 (12.5) 2/13 (15.4) 1/13 (7.7) 4/34 (11.8)\nTreatment-emergent SI^[d](#)^ 8/112 (7.1) 12/110 (10.9) 9/115 (7.8) 29/337 (8.6)\nNew-onset SI^[e](#)^ 7/104 (6.7) 10/97 (10.3) 8/102 (7.8) 25/303 (8.3)\nWish to be dead 5 4 3 12\nNonspecific active suicidal thoughts 1 1 1 3\nActive SI with any methods (no plan) without intent to act 1 5 4 10\nWorsening SI^[f](#)^ 1/8 (12.5) 2/13 (15.4) 1/13 (7.7) 4/34 (11.8)\nShift to nonspecific active suicidal thoughts 1 0 0 1\nShift to active SI with any methods (no plan) without intent to act 0 1 1 2\nShift to active SI with specific plan and intent 0 1 0 1\nTreatment-emergent SB^[g](#)^ 0/112 (0.0) 1/110 (0.9) 0/115 (0.0) 1/337 (0.3)\nNew-onset SB^[h](#)^ 0/112 (0.0) 1/110 (0.9) 0/115 (0.0) 1/337 (0.3)\nInterrupted attempt 0 1 0 1\nWorsening SB^[i](#)^ 0 0 0 0\n\nThere was one poststudy suicide attempt reported as a serious adverse\nevent that was not captured on the C-SSRS; C-SSRS was not performed\nfollowing that event. *N* represents the number of patients in this\nanalysis, that is, patients who had a baseline and a postbaseline C-SSRS\nassessment.\n\nTreatment-emergent SIB is defined as (1) new-onset SI or SB, (2)\nworsening SI or SB, or (3) postbaseline SB on patients reporting SI at\nbaseline.\n\nNew-onset SIB is defined as any SI or SB reported postbaseline on\npatients who reported no SI and no SB at baseline.\n\nWorsening SIB is defined as (1) shift from SI at baseline to a more\nsevere SI postbaseline, (2) shift from SI at baseline (and no SB at\nbaseline) to any SB postbaseline, or (3) shift from SB at baseline to a\nmore severe SB postbaseline.\n\nTreatment-emergent SI is defined as new-onset SI or worsening SI.\n\nNew-onset SI is defined as any SI reported postbaseline on patients who\nreported no SI at baseline.\n\nWorsening SI is defined as shift to a more severe SI postbaseline on\npatients reporting SI at baseline.\n\nTreatment-emergent SB is defined as new-onset SB or worsening SB.\n\nNew-onset SB is defined as any SB reported postbaseline on patients who\nreported no SB at baseline.\n\nWorsening SB is defined as shift to a more severe SB postbaseline on\npatients reporting SB at baseline.\n\nC-SSRS, Columbia-Suicide Severity Rating Scale; SB, suicidal behavior;\nSI, suicidal ideation; SIB, suicidal ideation or behavior.:::: New-onset self-injurious behavior without suicidal intent was reported in two (1.8%) fluoxetine-treated adolescents and one (0.9%) desvenlafaxine-treated adolescent. The suicide attempt reported as a serious AE in the \"Deaths and Serious AEs\" section was not captured on the C-SSRS because it occurred poststudy. \n\n### Other safety measures The frequencies of patients with on-therapy potentially clinically important (PCI) vital sign values can be found in [Supplementary Table S4](#). Upon review of patient data by the medical monitor, eight patients (all adolescents) were deemed to have clinically important vital sign results: postural hypotension in three desvenlafaxine-treated patients (35-, 35-, and 50-mg/d doses) and in four fluoxetine-treated patients, and increased supine systolic blood pressure in one desvenlafaxine-treated patient (122--126 mm Hg at weeks 3--6; baseline, 117 mm Hg). No patients assigned to placebo had clinically important vital sign findings, and the observed changes from baseline in body mass index (BMI) were negligible. Mean changes from baseline in BMI, blood pressure, and pulse measurements are reported by age group in [Supplementary Table S5](#). Expected shifts associated with development assessed by Tanner staging were observed during the study. Clinically important ECG findings were reported for one patient assigned to fluoxetine who had Wolff--Parkinson--White syndrome at study entry, with no change over the course of the study. The frequencies of on-therapy PCI laboratory findings are presented in [Supplementary Table S6](#). Findings in nine patients (four desvenlafaxine, five fluoxetine) were determined to be clinically important: three had elevated triglycerides (two desvenlafaxine, one fluoxetine), one high prolactin (desvenlafaxine), one low hematocrit and low hemoglobin (desvenlafaxine), three positive urine protein (fluoxetine), and one abnormal liver function test (fluoxetine). No clinically important laboratory values were observed in the placebo group. Mean changes from baseline for selected laboratory values are reported by age group and treatment in [Supplementary Table S7](#).\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** desvenlafaxine\n**Comparator:** placebo\n**Outcome:** Treatment-emergent adverse events (TEAEs)\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: 69\n group_size: 115\ncomparator:\n events: 79.0\n group_size: 112"
}
] |
intervention:
events: 69
group_size: 115
comparator:
events: 79.0
group_size: 112
|
263
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in extracting data from randomized controlled trials. Your task is to produce a 2x2 contingency table in YAML format based on the provided article context.\n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Results sections of a randomized controlled trial. Pay close attention to the details in the article to accurately classify the outcome type.\n\nYou will also be provided with an ICO (Intervention, Comparator, and Outcome) triplet, which includes the intervention, comparator, and outcome of interest. Your task is to extract the number of events and group sizes for both the intervention and comparator groups.\n\n**Article:** \n\n# Abstract\n\n # Abstract\n\n ***Objectives:*** To evaluate the short-term efficacy and safety of desvenlafaxine (25--50 mg/d) compared with placebo in children and adolescents with major depressive disorder (MDD). ***Methods:*** Outpatient children (7--11 years) and adolescents (12--17 years) who met DSM-IV-TR criteria for MDD and had screening and baseline Children's Depression Rating Scale--Revised (CDRS-R) total scores >40 were randomly assigned to 8-week treatment with placebo, desvenlafaxine (25, 35, or 50 mg/d based on baseline weight), or fluoxetine (20 mg/d). The primary efficacy endpoint was change from baseline in CDRS-R total score at week 8, analyzed using a mixed-effects model for repeated measures. Secondary efficacy endpoints included week 8 Clinical Global Impressions--Severity, Clinical Global Impressions--Improvement (CGI-I), and response (CGI-I ≤ 2). Safety assessments included adverse events, physical and vital sign measurements, laboratory evaluations, electrocardiogram, and the Columbia-Suicide Severity Rating Scale. ***Results:*** The safety population included 339 patients (children, *n* = 130; adolescents, *n* = 209). The primary endpoint, change from baseline in CDRS-R total score at week 8, did not statistically separate from placebo, for either desvenlafaxine (adjusted mean [standard error] change, −22.6 [1.17]) or fluoxetine (−24.8 [1.17]; placebo, −23.1 [1.18]). Week 8 CGI-I response rates were significantly greater for fluoxetine (78.2%; *p* = 0.017) than for placebo (62.6%); desvenlafaxine (68.7%) did not differ from placebo. Other secondary outcomes were consistent with those obtained with CDRS-R. Rates of treatment-emergent adverse events were comparable among treatment groups (desvenlafaxine, 60.0%; placebo, 70.5%; and fluoxetine, 64.3%). ***Conclusion:*** Desvenlafaxine did not demonstrate efficacy for treating MDD in children and adolescents in this trial. Because neither desvenlafaxine nor the reference medication, fluoxetine, demonstrated a statistically significant difference from placebo on the primary endpoint, this was considered a failed trial and no efficacy conclusions can be drawn. Desvenlafaxine 25--50 mg/d was generally safe and well tolerated in children and adolescents in this study. # Results \n\n## Study population A total of 340 patients were randomly assigned to treatment; 339 patients (children, *n* = 130; adolescents, *n* = 209) were included in the safety population (desvenlafaxine, *n* = 115; fluoxetine, *n* = 112; placebo, *n* = 112). The ITT population included 130 children and 207 adolescents. A total of 42 (12%) patients discontinued early (desvenlafaxine, 16 [14%]; fluoxetine, 13 [12%]; and placebo, 13 [12%]). Lost to follow-up was the most common reason for discontinuation from the desvenlafaxine and placebo groups; in the fluoxetine group, the most common reason for discontinuation was \"no longer willing to participate\" ([Fig. 1](#)). <figure> <p><img src=\"\" /></p> <figcaption>Study flow. <sup>a</sup>One patient was screened and, although not randomized, received a total of eight blinded placebo doses. The patient was discontinued after the week 1 visit once the error was identified and listed as a protocol violation.</figcaption> </figure> Demographic and baseline characteristics were comparable among treatment groups for both children and adolescents ([Table 1](#)). Mean (SD) CDRS-R Total Score at baseline was 56.5 (8.9), mean (SD) CGI-S score was 4.5 (0.6), and the duration of the most recent depressive episode ranged from 1 to 96 months (median, 7; mean [SD], 13.4 [15.1]). Overall, 30.4% (103) of patients in the safety population had a prior or active psychiatric condition other than MDD in their medical history (desvenlafaxine, 31.3%; fluoxetine, 25.9%; and placebo, 33.9%). The most common psychiatric conditions (reported by ≥2% of patients) included attention-deficit/hyperactivity disorder (desvenlafaxine, 12.2%; fluoxetine, 13.4%; and placebo, 5.4%), nonsuicidal self-injurious behavior (desvenlafaxine, 7.0%; fluoxetine, 8.0%; and placebo, 12.5%), insomnia (desvenlafaxine, 7.0%; fluoxetine, 6.3%; and placebo, 8.0%), generalized anxiety disorder (desvenlafaxine, 0.9%; fluoxetine, 6.3%; and placebo, 0), and oppositional defiant disorder (desvenlafaxine, 3.5%; fluoxetine, 3.6%; and placebo, 0). ::::table-wrap\n\n::: caption\n\\[Demographic and Baseline Characteristics, Safety\nPopulation\\]{.smallcaps}\n:::\n\n*Children* *Adolescents*\n\n______________________________________________________________________\n\n*Placebo (*n* = 42)* *Fluoxetine (*n* = 45)* *Desvenlafaxine (*n* = 43)* *Total (*n* = 130)* *Placebo (*n* = 70)* *Fluoxetine (*n* = 67)* *Desvenlafaxine (*n* = 72)* *Total (*n* = 209)*\nAge, mean (SD), years 9.4 (1.3) 9.6 (1.3) 9.3 (1.4) 9.4 (1.3) 14.6 (1.5) 14.7 (1.6) 15.0 (1.5) 14.8 (1.5)\nSex, *n* (%)\\\nFemale 23 (55) 14 (31) 20 (47) 57 (44) 41 (59) 43 (64) 43 (60) 127 (61)\nMale 19 (45) 31 (69) 23 (53) 73 (56) 29 (41) 24 (36) 29 (40) 82 (39)\nRace, *n* (%)\\\nAsian 1 (2) 0 1 (2) 2 (2) 0 2 (3) 0 2 (1)\nBlack 15 (36) 15 (33) 14 (33) 44 (34) 10 (14) 19 (28) 18 (25) 47 (22)\nWhite 25 (60) 26 (58) 23 (53) 74 (57) 56 (80) 41 (61) 49 (68) 146 (70)\nOther 1 (2) 4 (9) 5 (12) 10 (8) 4 (6) 5 (7) 5 (7) 14 (7)\nHeight, mean (SD), cm 140.5 (10.6) 141.3 (11.2) 144.3 (11.5) 142.0 (11.1) 164.5 (9.8) 165.8 (8.4) 167.3 (9.1) 165.9 (9.2)\nWeight, mean (SD), kg 39.4 (14.0) 44.0 (18.9) 46.0 (15.2) 43.2 (16.3) 68.0 (19.1) 73.3 (21.8) 71.7 (19.0) 71.0 (20.0)\nBMI, mean (SD), kg/m^2^ 19.5 (4.7) 21.3 (6.4) 21.6 (5.0) 20.8 (5.5) 25.0 (6.0) 26.5 (6.9) 25.5 (5.8) 25.6 (6.3)\nDuration of most recent episode, median (range), months 11 (1--57) 6 (1--42) 8 (1--71) 7 (1--71) 8 (1--69) 7 (1--96) 7 (1--61) 7 (1--96)\nCDRS-R total score, mean (SD) 57.0 (8.6) 55.0 (8.7) 56.4 (10.9) 56.1 (9.4) 57.1 (9.1) 57.0 (8.1) 56.3 (8.8) 56.8 (8.7)\n\nBMI, body mass index; CDRS-R, Children's Depression Rating\nScale--Revised; SD, standard deviation.:::: \n\n## Efficacy Statistical separation from placebo was not observed on the primary efficacy endpoint for either desvenlafaxine or for the fluoxetine reference group. Adjusted mean (standard error) change from baseline in CDRS-R total score at week 8 was −22.6 (1.17) and −23.1 (1.18) for the desvenlafaxine and placebo groups, respectively, and for fluoxetine was −24.8 (1.17) ([Fig. 2](#)). The change from baseline in CDRS-R over the 8-week treatment phase was similar for the three arms. Point differences were statistically significant between desvenlafaxine and placebo at week 2 and between fluoxetine and placebo at weeks 1 and 2; no significant differences were observed at any other time points. Results were similar for the child and adolescent groups in an exploratory analysis of change from baseline in CDRS-R total score ([Supplementary Fig. S1](#)). <figure> <p><img src=\"\" /></p> <figcaption>Adjusted mean (SE) change from baseline in CDRS-R total score in children and adolescents; MMRM analysis, ITT population. \\*<em>p</em> \\< 0.01, fluoxetine versus placebo. <sup>†</sup><em>p</em> \\< 0.05, fluoxetine versus placebo and desvenlafaxine versus placebo. CDRS-R, Children's Depression Rating Scale–Revised; CI, confidence interval; ITT, intent-to-treat; MMRM, mixed-effects model for repeated measures; SE, standard error.</figcaption> </figure> At week 8, the CGI-I response rate for fluoxetine (78.2%) was significantly greater compared with placebo (62.6%; *p* = 0.017). Week 8 CGI-I response rate for desvenlafaxine (68.7%) was also greater than placebo, although this comparison did not reach statistical significance (*p* = 0.343). Results for CGI-S and CGI-I scores were otherwise consistent with those for CDRS-R total score, with no statistically significant difference from placebo for either desvenlafaxine or fluoxetine at week 8 ([Table 2](#)). ::::table-wrap\n::: caption\n[Summary of Secondary Efficacy Outcomes at Week 8]{.smallcaps}\n:::\n\n*CGI-S* n *Adjusted mean change (SE) from baseline*^[a](#)^ *Difference in adjusted means (placebo-active)* *95% CI* p\n\n______________________________________________________________________\n\nPlacebo 99 −1.71 (0.12) --- --- ---\nFluoxetine 101 −1.88 (0.12) 0.18 −0.11 to 0.46 0.224\nDesvenlafaxine 99 −1.70 (0.11) −0.01 −0.29 to 0.27 0.944\n\n*CGI-I*^[b](#)^ n *Very much improved (%)* *Much improved (%)* *Minimally improved (%)* *No change (%)* *CMH test*^[c](#)^ p\\*-value\\*\n\n______________________________________________________________________\n\nPlacebo 99 27.3 35.4 32.3 4.0 ---\nFluoxetine 101 30.7 47.5 16.8 4.0 0.095\nDesvenlafaxine 99 23.2 45.5 21.2 9.1 0.852\n\n*CGI-I response*^[d](#)^ *Proportion responders* *%* *Adjusted odds ratio*^[e](#)^ *Wald 95% CI* p\n\n______________________________________________________________________\n\nPlacebo 62/99 62.6 --- --- ---\nFluoxetine 79/101 78.2 0.465 0.249 to 0.871 0.017\nDesvenlafaxine 68/99 68.7 0.751 0.415 to 1.357 0.343\n\nEstimates of adjusted mean, SE, difference in means, 95% CI, and\n*p*-values were based on a mixed-effects model for repeated measures for\nthe change from baseline in CGI-S with terms for treatment, week,\ninteraction of treatment and week, age group, country, gender, and\nbaseline CGI-S total score.\n\nCGI-I scored as 1, very much improved; 2, much improved; 3, minimally\nimproved; 4, no change; 5, minimally worse; 6, much worse; 7, very much\nworse. No patients scored 5--7 at week 8.\n\nCMH test was controlled for age group and country.\n\nCGI-I response was defined as CGI-I score of 1 (very much improved) or 2\n(much improved).\n\nEstimates of odds ratios, 95% CI, and *p*-values were based on a\nlogistic regression model of the response rate, with terms for treatment\ngroup, age group, and country.\n\nCGI-I, Clinical Global Impressions--Improvement; CGI-S, Clinical Global\nImpressions--Severity; CI, confidence interval; CMH,\nCochran--Mantel--Haenszel; SE, standard error.:::: \n\n## Safety \n\n### Adverse events A total of 220/339 (64.9%) patients experienced AEs during the on-therapy period (desvenlafaxine, 69/115 [60.0%]; fluoxetine, 72/112 [64.3%]; and placebo, 79/112 [70.5%]). Most AEs were mild or moderate in severity. AEs considered by the investigator to be related to study medication were reported by 31.9% of patients (desvenlafaxine, 28.7%; fluoxetine, 32.1%; and placebo, 34.8%). Severe AEs (those that interfered significantly with patients' usual function) considered by the investigator to be unrelated to study medication were reported by 3.5% of patients (desvenlafaxine, 1.7%; fluoxetine, 5.4%; and placebo, 3.6%). In three patients, severe AEs were considered related to study medication: One desvenlafaxine-treated patient reported severe pruritus and severe macular rash and discontinued treatment. One placebo-treated patient reported severe agitation and severe anger, and a second reported severe insomnia; neither was discontinued due to those AEs. Five adolescents (0 children) discontinued due to AEs, two each from the desvenlafaxine (disinhibition; macular rash and pruritus) and placebo (vomiting; headache) groups and one from the fluoxetine group (suicidal ideation). \n\n### Treatment-emergent adverse events Treatment-emergent adverse events (TEAEs) reported by more than 10% of patients in any group were headache, upper abdominal pain, and nausea. [Table 3](#) shows the most frequent (≥5% in any group) TEAEs by age group, and overall. There were no statistically significant differences between desvenlafaxine or fluoxetine and placebo in the incidence of any prespecified TEAEs of clinical interest for desvenlafaxine (tier-1 TEAEs) ([Supplementary Table S2](#)). ::::table-wrap\n::: caption\n\\[Number (%) of Patients Reporting Treatment-Emergent Adverse Events with\nIncidence ≥5% in Any Group, On-Therapy Period, Safety\nPopulation\\]{.smallcaps}\n:::\n\n*Children* *Adolescents* *Overall*\n\n______________________________________________________________________\n\n*Placebo (*n* = 42)* *Fluoxetine (*n* = 45)* *Desvenlafaxine (*n* = 43)* *Placebo (*n* = 70)* *Fluoxetine (*n* = 67)* *Desvenlafaxine (*n* = 72)* *Placebo (*n* = 112)* *Desvenlafaxine (*n* = 112)* *Desvenlafaxine (*n* = 115)*\nAny TEAE 27 (64.3) 29 (64.4) 22 (51.2) 52 (74.3) 43 (64.2) 47 (65.3) 79 (70.5) 72 (64.3) 69 (60.0)\nHeadache 8 (19.0) 3 (6.7) 5 (11.6) 13 (18.6) 13 (19.4) 14 (19.4) 21 (18.8) 16 (14.3) 19 (16.5)\nAbdominal pain upper 2 (4.8) 1 (2.2) 6 (14.0) 5 (7.1) 8 (11.9) 9 (12.5) 7 (6.3) 9 (8.0) 15 (13.0)\nNausea 3 (7.1) 4 (8.9) 2 (4.7) 7 (10.0) 9 (13.4) 6 (8.3) 10 (8.9) 13 (11.6) 8 (7.0)\nDizziness 3 (7.1) 1 (2.2) 2 (4.7) 3 (4.3) 2 (3.0) 5 (6.9) 6 (5.4) 3 (2.7) 7 (6.1)\nInfluenza 0 2 (4.4) 2 (4.7) 0 0 4 (5.6) 0 2 (1.8) 6 (5.2)\nNasopharyngitis 4 (9.5) 2 (4.4) 1 (2.3) 4 (5.7) 5 (7.5) 5 (6.9) 8 (7.1) 7 (6.3) 6 (5.2)\nUpper respiratory tract infection 2 (4.8) 3 (6.7) 1 (2.3) 4 (5.7) 1 (1.5) 5 (6.9) 6 (5.4) 4 (3.6) 6 (5.2)\nVomiting 1 (2.4) 5 (11.1) 1 (2.3) 3 (4.3) 2 (3.0) 4 (5.6) 4 (3.6) 7 (6.3) 5 (4.3)\nDiarrhea 1 (2.4) 0 4 (9.3) 2 (2.9) 3 (4.5) 1 (1.4) 3 (2.7) 3 (2.7) 5 (4.3)\nInsomnia 1 (2.4) 1 (2.2) 0 2 (2.9) 4 (6.0) 4 (5.6) 3 (2.7) 5 (4.5) 4 (3.5)\nFatigue 1 (2.4) 3 (6.7) 0 1 (1.4) 3 (4.5) 2 (2.8) 2 (1.8) 6 (5.4) 2 (1.7)\nPharyngitis 2 (4.8) 3 (6.7) 1 (2.3) 0 1 (1.5) 1 (1.4) 2 (1.8) 4 (3.6) 2 (1.7)\nRash 0 3 (6.7) 0 0 1 (1.5) 1 (1.4) 0 4 (3.6) 1 (0.9)\nArthralgia 3 (7.1) 1 (2.2) 1 (2.3) 1 (1.4) 2 (3.0) 0 4 (3.6) 3 (2.7) 1 (0.9)\nFall 2 (4.8) 4 (8.9) 0 0 1 (1.5) 0 2 (1.8) 5 (4.5) 0\nConstipation 3 (7.1) 0 0 1 (1.4) 0 0 4 (3.6) 0 0\n\nTEAE, treatment-emergent adverse event.:::: \n\n### Deaths and serious AEs There were no deaths during the study. Five randomized patients experienced serious AEs: two assigned to fluoxetine (suicidal ideation [acute suicidality; discontinued] and suicide attempt [occurred poststudy], one patient each), three assigned to desvenlafaxine (suicidal ideation [discontinued due to lack of confidence in caregiver reliability to report patient status], disinhibition [discontinued], and postpartum hemorrhage with anemia and endometritis [occurred poststudy], one patient each), and no placebo-treated patients. The desvenlafaxine-treated patient with postpartum hemorrhage had been withdrawn from the study following a positive pregnancy test at the final treatment phase visit and delivered a healthy full-term infant. \n\n### Suicidality A summary of C-SSRS results for treatment-emergent suicidal ideation or behavior is presented for the safety population in [Table 4](#) (full C-SSRS results are presented in [Supplementary Table S3](#)). Treatment-emergent suicidal ideation or suicidal behavior, which included both new-onset and worsening suicidal ideation or behavior, was reported for 29 (8.6%) of 337 patients who had a C-SSRS assessment at baseline and at 1 or more postbaseline time points. A total of 29/337 (8.6%) patients had treatment-emergent suicidal ideation, and 1 patient (0.3%) also had treatment-emergent suicidal behavior. The suicidal behavior event was categorized as a preparatory act toward imminent suicidal behavior (preparatory acts or behavior; interrupted attempt) and was reported in a fluoxetine-treated adolescent ([Supplementary Table S3](#)). The patient was discontinued due to a serious AE of acute suicidality (described in \"Deaths and Serious AEs\" section). ::::table-wrap\n::: caption\n\\[Summary of Treatment-Emergent Suicidal Ideation and Behavior Reported\non the Columbia-Suicide Severity Rating Scale at Any Postbaseline\nAssessment, Safety Population\\]{.smallcaps}\n:::\n\n*Placebo (*N* = 112)* *Fluoxetine (*N* = 110)* *Desvenlafaxine (*N* = 115)* *Total (*N* = 337)*\n\n______________________________________________________________________\n\nTreatment-emergent SIB^[a](#)^ 8/112 (7.1) 12/110 (10.9) 9/115 (7.8) 29/337 (8.6)\nNew-onset SIB^[b](#)^ 7/104 (6.7) 10/97 (10.3) 8/102 (7.8) 25/303 (8.3)\nWorsening SIB^[c](#)^ 1/8 (12.5) 2/13 (15.4) 1/13 (7.7) 4/34 (11.8)\nTreatment-emergent SI^[d](#)^ 8/112 (7.1) 12/110 (10.9) 9/115 (7.8) 29/337 (8.6)\nNew-onset SI^[e](#)^ 7/104 (6.7) 10/97 (10.3) 8/102 (7.8) 25/303 (8.3)\nWish to be dead 5 4 3 12\nNonspecific active suicidal thoughts 1 1 1 3\nActive SI with any methods (no plan) without intent to act 1 5 4 10\nWorsening SI^[f](#)^ 1/8 (12.5) 2/13 (15.4) 1/13 (7.7) 4/34 (11.8)\nShift to nonspecific active suicidal thoughts 1 0 0 1\nShift to active SI with any methods (no plan) without intent to act 0 1 1 2\nShift to active SI with specific plan and intent 0 1 0 1\nTreatment-emergent SB^[g](#)^ 0/112 (0.0) 1/110 (0.9) 0/115 (0.0) 1/337 (0.3)\nNew-onset SB^[h](#)^ 0/112 (0.0) 1/110 (0.9) 0/115 (0.0) 1/337 (0.3)\nInterrupted attempt 0 1 0 1\nWorsening SB^[i](#)^ 0 0 0 0\n\nThere was one poststudy suicide attempt reported as a serious adverse\nevent that was not captured on the C-SSRS; C-SSRS was not performed\nfollowing that event. *N* represents the number of patients in this\nanalysis, that is, patients who had a baseline and a postbaseline C-SSRS\nassessment.\n\nTreatment-emergent SIB is defined as (1) new-onset SI or SB, (2)\nworsening SI or SB, or (3) postbaseline SB on patients reporting SI at\nbaseline.\n\nNew-onset SIB is defined as any SI or SB reported postbaseline on\npatients who reported no SI and no SB at baseline.\n\nWorsening SIB is defined as (1) shift from SI at baseline to a more\nsevere SI postbaseline, (2) shift from SI at baseline (and no SB at\nbaseline) to any SB postbaseline, or (3) shift from SB at baseline to a\nmore severe SB postbaseline.\n\nTreatment-emergent SI is defined as new-onset SI or worsening SI.\n\nNew-onset SI is defined as any SI reported postbaseline on patients who\nreported no SI at baseline.\n\nWorsening SI is defined as shift to a more severe SI postbaseline on\npatients reporting SI at baseline.\n\nTreatment-emergent SB is defined as new-onset SB or worsening SB.\n\nNew-onset SB is defined as any SB reported postbaseline on patients who\nreported no SB at baseline.\n\nWorsening SB is defined as shift to a more severe SB postbaseline on\npatients reporting SB at baseline.\n\nC-SSRS, Columbia-Suicide Severity Rating Scale; SB, suicidal behavior;\nSI, suicidal ideation; SIB, suicidal ideation or behavior.:::: New-onset self-injurious behavior without suicidal intent was reported in two (1.8%) fluoxetine-treated adolescents and one (0.9%) desvenlafaxine-treated adolescent. The suicide attempt reported as a serious AE in the \"Deaths and Serious AEs\" section was not captured on the C-SSRS because it occurred poststudy. \n\n### Other safety measures The frequencies of patients with on-therapy potentially clinically important (PCI) vital sign values can be found in [Supplementary Table S4](#). Upon review of patient data by the medical monitor, eight patients (all adolescents) were deemed to have clinically important vital sign results: postural hypotension in three desvenlafaxine-treated patients (35-, 35-, and 50-mg/d doses) and in four fluoxetine-treated patients, and increased supine systolic blood pressure in one desvenlafaxine-treated patient (122--126 mm Hg at weeks 3--6; baseline, 117 mm Hg). No patients assigned to placebo had clinically important vital sign findings, and the observed changes from baseline in body mass index (BMI) were negligible. Mean changes from baseline in BMI, blood pressure, and pulse measurements are reported by age group in [Supplementary Table S5](#). Expected shifts associated with development assessed by Tanner staging were observed during the study. Clinically important ECG findings were reported for one patient assigned to fluoxetine who had Wolff--Parkinson--White syndrome at study entry, with no change over the course of the study. The frequencies of on-therapy PCI laboratory findings are presented in [Supplementary Table S6](#). Findings in nine patients (four desvenlafaxine, five fluoxetine) were determined to be clinically important: three had elevated triglycerides (two desvenlafaxine, one fluoxetine), one high prolactin (desvenlafaxine), one low hematocrit and low hemoglobin (desvenlafaxine), three positive urine protein (fluoxetine), and one abnormal liver function test (fluoxetine). No clinically important laboratory values were observed in the placebo group. Mean changes from baseline for selected laboratory values are reported by age group and treatment in [Supplementary Table S7](#).\n\n\nBased on the given trial article, produce a 2x2 contingency table in YAML format for the following ICO (Intervention, Comparator, and Outcome) triplet: \n\n**Intervention:** fluoxetine\n**Comparator:** placebo\n**Outcome:** Treatment-emergent adverse events (TEAEs)\n\nThe YAML format should include the fields \"events\" and \"group_size\" for \"intervention\" and \"comparator\", but not for \"outcome\". \n\n**Example:**\nintervention:\n events: NUMBER\n group_size: NUMBER\ncomparator:\n events: NUMBER\n group_size: NUMBER\n\nOnly produce the YAML response. Do not provide any additional explanation. If any of the numerical information is unavailable, not extractable or not possible to calculate, replace it with \"x\".\n\nIf there is numerical data for pre and post-intervention, choose the post-intervention data. If there are multiple timeframes for the outcome, choose the one closest to the outcome timepoint of interest, or alternatively the last one. Be as accurate as possible.\n\nYAML:\n"
}
] |
[
{
"role": "assistant",
"content": "intervention:\n events: 72\n group_size: 112\ncomparator:\n events: 79.0\n group_size: 112"
}
] |
intervention:
events: 72
group_size: 112
comparator:
events: 79.0
group_size: 112
|
| Links | |
|---|---|
| Homepage: | Github |
| Repository: | Github |
| Paper: | arXiv |
| Leaderboard: | PapersWithCode |
| Contact (Original Authors): | Hye Sun Yun ([email protected]) |
| Contact (Curator): | Artur Guimarães ([email protected]) |
The human-annotated data is available in the data folder as both csv and json formats. The dev set has 10 RCTs with 43 number of total ICO triplets. The test set has 110 RCTs with 656 number of total ICO triplets. Additional dataset statistics can be found in evaluation/data/analyze_data.ipynb file.
{
"id":6,
"evidence_inference_prompt_id":11451,
"pmcid":1574360,
"outcome":"The amount of saturated fat in the foods purchased",
"intervention":"fully automated advice that recommended specific switches from selected products higher in saturated fat to alternate similar products lower in saturated fat",
"comparator":"control received general non-specific advice about how to eat a diet lower in saturated fat","outcome_type":"continuous",
"intervention_events":null,
"intervention_group_size":"251",
"comparator_events":null,
"comparator_group_size":"246",
"intervention_mean":"0.77",
"intervention_standard_deviation":1.37,
"comparator_mean":0.04,
"comparator_standard_deviation":0.32,
"notes":"Have to use CI to calculate the SDs",
"is_data_in_figure_graphics":false,
"is_relevant_data_in_table":false,
"is_table_in_graphic_format":true,
"is_data_complete":true,
"tiktoken_with_attributes_xml_token_num":1959,
"tiktoken_without_attributes_xml_token_num":1620,
"tiktoken_without_attributes_markdown_token_num":1376,
"split":"test",
"abstract":"# Abstract\n\n \n\n## Objectives: The supermarket industry now services many customers through online food shopping over the Internet. The Internet shopping process offers a novel opportunity for the modification of dietary patterns. The aim of this study was to evaluate the effects on consumers' purchases of saturated fat of a fully automated computerised system that provided real-time advice tailored to the consumers' specific purchases recommending foods lower in saturated fat. \n\n## Design: This study was a blinded, randomised controlled trial. \n\n## Setting: The study was conducted in Sydney, New South Wales, Australia. \n\n## Participants: The participants were consumers using a commercial online Internet shopping site between February and June 2004. \n\n## Interventions: Individuals assigned to intervention received fully automated advice that recommended specific switches from selected products higher in saturated fat to alternate similar products lower in saturated fat. Participants assigned to control received general non-specific advice about how to eat a diet lower in saturated fat. \n\n## Outcome Measures: The outcome measure was the difference in saturated fat (grams per 100 g of food) in shopping baskets between the intervention and control groups. \n\n## Results: There were 497 randomised participants, mean age 40 y, each shopping for an average of about three people. The amount of saturated fat in the foods purchased by the intervention group was 0.66% lower (95% confidence interval 0.48--0.84, *p* < 0.001) than in the control group. The effects of the intervention were sustained over consecutive shopping episodes, and there was no difference in the average cost of the food bought by each group. \n\n## Conclusions: Fully automated, purchase-specific dietary advice offered to customers during Internet shopping can bring about changes in food purchasing habits that are likely to have significant public health implications. Because implementation is simple to initiate and maintain, this strategy would likely be highly cost-effective. # RESULTS \n\n## Participants A total of 4,548 individuals were offered participation, and 497 were randomised (251 intervention and 246 control) ([Figure 1](#)). Of these, 456 (224 intervention and 232 control) completed at least one episode of shopping that included one or more of the 524 foods studied. Median follow-up time completed by the end of the study in June 2004 was 35 d, and the median number of shopping episodes done by participants was three (range 1--20). The baseline characteristics documented on the questionnaire were balanced between randomised groups, with a mean participant age of 40 y and a proportion female of 88% ([Table 1](#)). <figure> <p><img src=\"\" \/><\/p> <figcaption>Flow Chart of Study<\/figcaption> <\/figure> ::::table-wrap\n\n::: caption\nBaseline Characteristics\n:::\n\n:::: \n\n## Outcomes and Estimation For the first occasion on which advice was offered, the amount of saturated fat in the food purchased by the intervention group after advice was a mean of 0.66% (0.48--0.84, *p \\<* 0.001) lower than in the corresponding foods purchased by the control group ([Table 2](#)), which is equivalent to an approximate 10% reduction in saturated fat content of foods purchased ([Figure 2](#)). This difference resulted from a decrease in the mean saturated fat content in the foods purchased following the advice offered to the intervention group of 0.77% (0.60--0.94, *p \\<* 0.001), with no corresponding decrease in the control group 0.04% (0.00--0.08, *p =* 0.07). The effect estimate for the primary outcome was 0.62% (0.46--0.79, *p \\<* 0.001) if analysis was restricted to only the 456 individuals that selected one of the 524 foods studied and was 0.58 (0.39--0.77, *p \\<* 0.001) if the change in saturated fat was set to zero for those individuals that did not select one of the foods. The subgroup analyses provided some evidence that the intervention had greater effects among individuals with higher body mass index and among people above 40 y of age (for both, homogeneity *p* < 0.03) ([Table 3](#)). There was no baseline variable that substantively altered the main result as a consequence of its inclusion or exclusion as a covariate. ::::table-wrap\n::: caption\nEffects of Intervention on Primary Outcome\n:::\n\n:::: <figure> <p><img src=\"\" \/><\/p> <figcaption>Effects of Repeated Advice in the Intervention (<em>n =<\/em> 115) and Control Group (<em>n =<\/em> 121)<br \/> Squares are placed at the point estimate of the effect observed in the intervention (A) and control (B) groups, and the vertical lines extend to the 95% confidence intervals around the estimate. The <em>p<\/em>-value for trend in the intervention group indicates a progressive decrease in effect size with repeated shopping episodes. There was no significant decrease in saturated fat at any time point in the control group, nor any trend over time (all <em>p<\/em> > 0.09).<\/figcaption> <\/figure> ::::table-wrap\n::: caption\nEffects of Intervention on Primary Outcome in Main Participant Subgroups\n:::\n\n:::: A secondary outcome of the study was to assess the impact of the intervention on the cost of foods purchased online. The mean cost per 100 g of the foods purchased by the intervention group was not different from that in the control group (intervention AUD$0.63 [0.58--0.68]\/100 g versus control AUD$0.62 [0.58--0.67]\/100 g, *p =* 0.19). The foods higher in saturated fat that were most commonly present in the shopping basket prior to advice being offered but absent after the advice had been offered were higher-fat dairy products. Lower-fat dairy products were the items most frequently added to the shopping basket after advice was provided. \n\n## Ancillary Analyses The effects of the intervention over repeated episodes of shopping were explored amongst the 115 participants that completed six shopping episodes during the study. These analyses demonstrated that for the intervention group the magnitude of the reduction in saturated fat achieved was greater in earlier compared to later shopping episodes (for trend, *p* = 0.01) ([Figure 2](#)) and showed that there was no effect of the control condition on saturated fat during any shopping episode (*p* > 0.09 for all six shopping episodes in the control group).\n"
}
TO:DO
TO:DO
@article{yun2024automatically,
title={Automatically extracting numerical results from randomized controlled trials with large language models},
author={Yun, Hye Sun and Pogrebitskiy, David and Marshall, Iain J and Wallace, Byron C},
journal={arXiv preprint arXiv:2405.01686},
year={2024}
}
Thanks to araag2 for adding this dataset.