Early stopping of randomized clinical trials for overt efficacy is problematic

Dirk Bassler, Victor Manuel Montori, Matthias Briel, Paul Glasziou, Gordon Guyatt

Research output: Contribution to journalArticle

81 Citations (Scopus)

Abstract

Objective: To illustrate controversial issues associated with stopping randomized controlled trials (RCTs) early for apparent benefit. Study Design and Setting: The article presents our review of prior relevant work and our research group's reflections on early stopping. Results: Compelling evidence suggests that trials stopped early for benefit systematically overestimate treatment effects, sometimes by a large amount. Unresolved controversies in trials stopped early for benefit include ethical and statistical problems in the interpretation of results. Conclusions: The best strategy to minimize the problems associated with early stopping of RCTs for benefit is not to stop early. As an alternative, we suggest a threefold approach: a low P-value as the threshold for stopping at the time of interim analyses, not to look before a sufficiently large number of events has accrued and continuation of enrollment and follow-up for a further period.

Original languageEnglish (US)
Pages (from-to)241-246
Number of pages6
JournalJournal of Clinical Epidemiology
Volume61
Issue number3
DOIs
StatePublished - Mar 2008

Fingerprint

Randomized Controlled Trials
Research

Keywords

  • Data-monitoring committee
  • Interim analysis
  • Randomized controlled trial
  • STOPIT-2
  • Stopping for benefit
  • Stopping rule

ASJC Scopus subject areas

  • Medicine(all)
  • Public Health, Environmental and Occupational Health
  • Epidemiology

Cite this

Early stopping of randomized clinical trials for overt efficacy is problematic. / Bassler, Dirk; Montori, Victor Manuel; Briel, Matthias; Glasziou, Paul; Guyatt, Gordon.

In: Journal of Clinical Epidemiology, Vol. 61, No. 3, 03.2008, p. 241-246.

Research output: Contribution to journalArticle

Bassler, Dirk ; Montori, Victor Manuel ; Briel, Matthias ; Glasziou, Paul ; Guyatt, Gordon. / Early stopping of randomized clinical trials for overt efficacy is problematic. In: Journal of Clinical Epidemiology. 2008 ; Vol. 61, No. 3. pp. 241-246.
@article{24e6cc1cdf3a4f9da31cacc792911463,
title = "Early stopping of randomized clinical trials for overt efficacy is problematic",
abstract = "Objective: To illustrate controversial issues associated with stopping randomized controlled trials (RCTs) early for apparent benefit. Study Design and Setting: The article presents our review of prior relevant work and our research group's reflections on early stopping. Results: Compelling evidence suggests that trials stopped early for benefit systematically overestimate treatment effects, sometimes by a large amount. Unresolved controversies in trials stopped early for benefit include ethical and statistical problems in the interpretation of results. Conclusions: The best strategy to minimize the problems associated with early stopping of RCTs for benefit is not to stop early. As an alternative, we suggest a threefold approach: a low P-value as the threshold for stopping at the time of interim analyses, not to look before a sufficiently large number of events has accrued and continuation of enrollment and follow-up for a further period.",
keywords = "Data-monitoring committee, Interim analysis, Randomized controlled trial, STOPIT-2, Stopping for benefit, Stopping rule",
author = "Dirk Bassler and Montori, {Victor Manuel} and Matthias Briel and Paul Glasziou and Gordon Guyatt",
year = "2008",
month = "3",
doi = "10.1016/j.jclinepi.2007.07.016",
language = "English (US)",
volume = "61",
pages = "241--246",
journal = "Journal of Clinical Epidemiology",
issn = "0895-4356",
publisher = "Elsevier USA",
number = "3",

}

TY - JOUR

T1 - Early stopping of randomized clinical trials for overt efficacy is problematic

AU - Bassler, Dirk

AU - Montori, Victor Manuel

AU - Briel, Matthias

AU - Glasziou, Paul

AU - Guyatt, Gordon

PY - 2008/3

Y1 - 2008/3

N2 - Objective: To illustrate controversial issues associated with stopping randomized controlled trials (RCTs) early for apparent benefit. Study Design and Setting: The article presents our review of prior relevant work and our research group's reflections on early stopping. Results: Compelling evidence suggests that trials stopped early for benefit systematically overestimate treatment effects, sometimes by a large amount. Unresolved controversies in trials stopped early for benefit include ethical and statistical problems in the interpretation of results. Conclusions: The best strategy to minimize the problems associated with early stopping of RCTs for benefit is not to stop early. As an alternative, we suggest a threefold approach: a low P-value as the threshold for stopping at the time of interim analyses, not to look before a sufficiently large number of events has accrued and continuation of enrollment and follow-up for a further period.

AB - Objective: To illustrate controversial issues associated with stopping randomized controlled trials (RCTs) early for apparent benefit. Study Design and Setting: The article presents our review of prior relevant work and our research group's reflections on early stopping. Results: Compelling evidence suggests that trials stopped early for benefit systematically overestimate treatment effects, sometimes by a large amount. Unresolved controversies in trials stopped early for benefit include ethical and statistical problems in the interpretation of results. Conclusions: The best strategy to minimize the problems associated with early stopping of RCTs for benefit is not to stop early. As an alternative, we suggest a threefold approach: a low P-value as the threshold for stopping at the time of interim analyses, not to look before a sufficiently large number of events has accrued and continuation of enrollment and follow-up for a further period.

KW - Data-monitoring committee

KW - Interim analysis

KW - Randomized controlled trial

KW - STOPIT-2

KW - Stopping for benefit

KW - Stopping rule

UR - http://www.scopus.com/inward/record.url?scp=38349177944&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38349177944&partnerID=8YFLogxK

U2 - 10.1016/j.jclinepi.2007.07.016

DO - 10.1016/j.jclinepi.2007.07.016

M3 - Article

C2 - 18226746

AN - SCOPUS:38349177944

VL - 61

SP - 241

EP - 246

JO - Journal of Clinical Epidemiology

JF - Journal of Clinical Epidemiology

SN - 0895-4356

IS - 3

ER -