Sample Size Reassessment in Fixed-Duration Survival Trials

• Activity Number: 130
• Type: Contributed
• Date/Time: Monday, August 1, 2011 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Alison Pedley*+ and Ralph B. D'Agostino Sr. and Michael Pencina and Joseph Massaro
• Companies: Boston University and Boston University and Boston University and Boston University
• Keywords: Conditional Power ; Interim Analysis ; Sample Size Re-estimation ; Survival Trials

Abstract

The log-rank test is often performed in randomized clinical trials designed to assess the superiority of an experimental treatment over a control with respect to a time to event endpoint. Due to uncertainties in the design stage and the desire to accelerate drug development while reducing costs, adaptive designs allowing for sample size adjustment at the time of interim analysis based on the conditional power of observing a significant result by the end of the trial are becoming increasingly popular. In this presentation, methodology for a 2-stage adaptive design based on the log-rank test is developed in the setting of fixed duration trials by adapting methodology originally proposed by Li et al (2002, 2005) for maximum information trials. Simulations were performed to evaluate the performance of the new methodology. By redefining the relationship between the observed number of events and the final critical value and removing the restriction on the maximum value of the interim efficacy boundary, the methodology developed achieved the desired interim conditional power while still maintaining control of the type I error rate.