Two-stage adaptive design for clinical trials with survival data

In long-term clinical trials we often need to monitor the patients' enrollment, compliance, and treatment effect during the study. In this paper we take the conditional power approach and consider a two-stage design based on the ideas of Li et al. (2002) for trials with survival endpoints. We make projections and decisions regarding the future course of the trial from the interim data. The decision includes possible early termination of the trial for convincing evidence of futility or efficacy, and projection includes how many additional patients are needed to enroll and how long the enrollment and follow-up may be when continuing the trial. The flexibility of the adaptive design is demonstrated by an example, the Coumadin Aspirin Reinfarction Study.