Credibility of claims of subgroup effects in randomised controlled trials: systematic review

被引：245

作者：

Sun, Xin ^{[1
,2
]}

Briel, Matthias ^{[1
,3
]}

Busse, Jason W. ^{[1
,4
]}

You, John J. ^{[1
,5
]}

Akl, Elie A. ^{[1
,6
,7
]}

Mejza, Filip ^{[8
]}

Bala, Malgorzata M. ^{[9
]}

Bassler, Dirk ^{[10
,11
]}

Mertz, Dominik ^{[1
,5
,12
]}

Diaz-Granados, Natalia ^{[1
]}

Vandvik, Per Olav ^{[13
,14
]}

Malaga, German ^{[15
]}

Srinathan, Sadeesh K. ^{[16
]}

Dahm, Philipp ^{[17
]}

Johnston, Bradley C. ^{[1
,18
]}

Alonso-Coello, Pablo ^{[19
]}

Hassouneh, Basil ^{[1
]}

Walter, Stephen D. ^{[1
]}

Heels-Ansdell, Diane ^{[1
]}

Bhatnagar, Neera ^{[20
]}

Altman, Douglas G. ^{[21
]}

Guyatt, Gordon H. ^{[1
]}

机构：

[1] McMaster Univ, Dept Clin Epidemiol & Biostat, Hamilton, ON L8S 4K1, Canada

[2] Kaiser Permanente NW, Ctr Hlth Res, Portland, OR USA

[3] Univ Basel Hosp, Basel Inst Clin Epidemiol & Biostat, CH-4031 Basel, Switzerland

[4] Inst Work & Hlth, Toronto, ON, Canada

[5] McMaster Univ, Dept Med, Hamilton, ON, Canada

[6] SUNY Buffalo, Dept Med, Buffalo, NY 14260 USA

[7] SUNY Buffalo, Dept Family Med, Buffalo, NY 14260 USA

[8] Jagiellonian Univ, Sch Med, Dept Pulm Dis, Krakow, Poland

[9] Jagiellonian Univ, Sch Med, Dept Internal Med 2, Krakow, Poland

[10] Univ Childrens Hosp Tuebingen, Dept Neonatol, Tubingen, Germany

[11] Univ Childrens Hosp Tuebingen, Ctr Pediat Clin Studies, Tubingen, Germany

[12] McMaster Univ, Michael G DeGroote Inst Infect Dis Res, Hamilton, ON, Canada

[13] Norwegian Knowledge Ctr Hlth Serv, Oslo, Norway

[14] Innlandet Hosp Trust, Dept Med, Gjovik, Norway

[15] Univ Peruana Cayetano Heredia, Dept Med, Lima, Peru

[16] Univ Manitoba, Dept Surg, Winnipeg, MB R3T 2N2, Canada

[17] Univ Florida, Coll Med, Dept Urol, Gainesville, FL USA

[18] Hosp Sick Children, Dept Anaesthesiol & Pain Med, Toronto, ON M5G 1X8, Canada

[19] Biomed Res Inst CIBER Epidemiol & Publ Hlth, IberoAmer Cochrane Ctr, Barcelona, Spain

[20] McMaster Univ, Hlth Sci Lib, Hamilton, ON, Canada

[21] Univ Oxford, Ctr Stat Med, Oxford, England

来源：

BMJ-BRITISH MEDICAL JOURNAL | 2012年 / 344卷

基金：

加拿大健康研究院; 瑞士国家科学基金会; 中国国家自然科学基金;

关键词：

CLINICAL-TRIALS; CANCER;

D O I：

10.1136/bmj.e1553

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

Objective To investigate the credibility of authors' claims of subgroup effects using a representative sample of recently published randomised controlled trials. Design Systematic review. Data source Core clinical journals, as defined by the National Library of Medicine, in Medline. Study selection Randomised controlled trials published in 2007. Using prespecified criteria, teams of trained reviewers independently judged whether authors claimed subgroup effects and the strength of their claims. Reviewers assessed each of these claims against 10 predefined criteria, developed through a search of existing criteria and a consensus process. Results Of 207 randomised controlled trials reporting subgroup analyses, 64 (31%) made claims for the primary outcome. Of those, 20 were strong claims and 28 claims of a likely effect. Authors included subgroup variables measured at baseline in 60 (94%) trials, used subgroup variable as a stratification factor at randomisation in 13 (20%), clearly prespecified their hypotheses in 26 (41%), correctly prespecified direction in 4 (6%), tested a small number of hypotheses in 28 (44%), carried out a test of interaction that proved statistically significant in 6 (9%), documented replication of a subgroup effect with previous related studies in 21 (33%), identified consistency of a subgroup effect across related outcomes in 19 (30%), and provided a compelling indirect evidence for the effect in 14 (22%). In the 19 trials making more than one claim, only one (5%) checked the independence of the interaction. Of the 64 claims, 54 (84%) met four or fewer of the 10 criteria. For strong claims, more than 50% failed each of the individual criteria, and only three (15%) met more than five criteria. Conclusion Authors often claim subgroup effects in their trial report. However, the credibility of subgroup effects, even when claims are strong, is usually low. Users of the information should treat claims that fail to meet most criteria with scepticism. Trial researchers should report the conduct of subgroup analyses and provide sufficient evidence when claiming a subgroup effect or suggesting a possible effect.

引用

页数：9

共 27 条

[1] Statistics Notes - Interaction revisited: the difference between two estimates [J].