Confirmatory Group Sequential Adaptive Designs for Time-To-Event Endpoints Using a Short-Term Endpoint for Treatment Arm or Population Selection

• Activity Number: 218 - Efficient Designs and Better Decision-Making Strategies in Complex Clinical Trials: Multiple Arms, Multiple Endpoints, and Multiple Stages
• Type: Topic Contributed
• Date/Time: Monday, July 31, 2017 : 2:00 PM to 3:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Gernot Wassmer* and Martin Posch and Franz Koenig and Silke Joergens
• Companies: Medical University of Vienna, Austria and Center for Medical Statistics, Informatics, and Intelligent Systems, Medical University o and Center for Medical Statistics, Informatics, and Intelligent Systems, Medical University o and ICON Clinical Research Inc, Cologne Germany
• Keywords: Adaptive Designs ; Multiarmed trials ; Surrogate ; enrichment designs

Abstract

Adaptive trial methodology for multi-armed and enrichment trial designs has been proposed that controls the familywise type I error rate in the strong sense. This is achieved by applying the closed testing principle to adaptive combination tests or to conditional error rate based tests (see, e.g., Bretz et al., Statistics in Medicine, 2009, 28, 1181 - 1217). However, the case of time-to-event endpoints is not fully covered by standard theory if information from secondary endpoints is used in the adaptation decision. Therefore, tailored approaches to guarantee type I error control for time-to-event endpoints have been proposed (Jenkins et al., Pharmaceutical Statistics 2011, 10, 347-356, Mehta, Cyrus, et al., Statistics in Medicine 2014, 33, 4515-4531). A limitation of these approaches is, however, that they do not allow for early rejection of the null hypothesis at interim. We derive an extension of the test proposed by Jenkins that allows for interim testing of the null hypotheses under consideration while controling the familywise error rate. The operating characteristic of the procedure is investigated by simulation