Early Stopping of Trials

Reviewed and revised 26 August 2015

OVERVIEW

Clinical trials are planned to stop when one of the following is reached

• sample size 
• event count
• length of follow up goal
• scheduled date of closure

Unplanned early stopping of trials may occur for a number of reasons (e.g. lack of funding, failure to recruit participants), which may affect the internal validity of the study

INTERIM ANALYSIS

• should be planned a priori
• ideally involve an independent data monitoring committee
  
• multiple statistical examinations of accumulating data without appropriate correction can lead to erroneous results and interpretations, this must be corrected for (e.g. if five interim analyses that use a P value of 0.05 are performed, the overall false positive rate is nearer to 19% than to the nominal 5%)

REASONS FOR EARLY STOPPING

• interim analysis showing larger than expected benefit or harm from an intervention
• futility (evidence of no important difference between experimental and control interventions)
• trial becomes non-viable (e.g. funding vanishes, researchers cannot access eligible patients or study interventions, or other studies make the research question irrelevant)
  

CONSEQUENCES

• Full reporting of why a trial ended is important for evidence based decision making
• Trials that stop early for reasons apparently independent of trial findings, and trials that reach their planned termination, are unlikely to introduce bias by stopping

References and Links

LITFL

• CCC — How to conduct a clinical trial
• CCC — Early stopping of clinical trial
• CCC — How to analyse a clinical trial

FOAM and web resources

• CONSORT Statement — Early Stopping and Reason for stopped trial