Designs for Randomized Phase II Clinical Trials with Two Arms: Agent A vs. Agents A Plus B

• Activity Number: 394
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Myron Chang*+ and Sin-Ho Jung and Meenakshi Devidas
• Companies: University of Florida and Duke University and University of Florida
• Keywords: single-stage design ; two-stage design ; testing procedure ; error rate and power

Abstract

Recently, there has been increasing interest in utilizing randomized design in phase II cancer clinical trials in which patients are randomized to two or more treatment regimens. In this article, we consider studies with two treatment regimens: agent A and the combination of agents A and B. In these studies, clinicians want to evaluate the efficacy of regimen A, and to evaluate the potential benefit by adding B to A. We propose single-stage and two-stage randomized phase II designs for these studies. The proposed test is conducted within each arm in the same fashion as in a typical single-arm phase II trial. If data show that both arms have certain efficacy, then the two arms are compared. We precisely define the error rates and powers for the proposed testing procedure. The proposed testing procedure controls error rates and powers at prefixed levels with minimum sample size. We apply our design to a randomized phase II clinical trial in patients with relapsed non-Hodgkin's disease.