This JAMA Guide to Statistics and Methods discusses how to interpret the results of clinical trials that are stopped early based on formal, prespecified stopping rules.
Clinical trials require significant resources to complete in terms of patients, investigators, and time and should be carefully designed and conducted so that they use the minimum amount of resources necessary to answer the motivating clinical question. The size of a clinical trial is typically based on the minimum number of patients required to have high probability of detecting the anticipated treatment effect. However, it is possible that strong evidence could emerge earlier in the trial either in favor of or against the benefit of the novel treatment. If early trial results are compelling, stopping the trial before the maximum planned sample size is reached presents ethical advantages for patients inside and outside the trial and can save resources that can be redirected to other clinical questions. This advantage must be balanced against the potential for overestimation of the treatment effect and other limitations of smaller trials (eg, limited safety data, less information about treatment effects in subgroups).
Many methods have been proposed to allow formal incorporation of early stopping into a clinical trial.1,2 All of these methods allow a trial to stop at a prespecified interim analysis while maintaining good statistical properties. Data monitoring committees or other similar governing bodies may also monitor the progress of a trial and recommend stopping the trial early in the absence of a prespecified formal rule. An overwhelmingly positive treatment effect might lead to a recommendation for unplanned early stopping but, more commonly, unplanned early stopping results from concerns for participant safety, lack of observed benefit, or concerns about the feasibility of continuing the trial due to slow patient accrual or new external information. Trials stopped for success in an ad hoc manner are challenging to interpret rigorously. In this chapter, we focus on early stopping for success or futility based on formal, prespecified stopping rules.
In 2015, Stupp et al3 reported the results of a trial assessing electric tumor-treating fields plus temozolomide vs temozolomide alone in patients with glioblastoma. The trial design included a preplanned interim analysis defined according to an early stopping procedure. The trial was stopped for success at the interim analysis, reporting a hazard ratio of 0.62 for the primary end point of progression-free survival.
Why Is Early Stopping Used?
When 2 treatments are compared in a randomized clinical trial, the treatment effects observed both during the trial and when the trial ends are subject to random highs and lows that depart from the true treatment effect. Sample sizes for trials are selected to reliably detect an anticipated treatment effect even if a modest, random low observed treatment effect occurs at the final analysis. If such a random low ...