Closed Tests for Multi-Arm Phase II Oncology Trials

• Activity Number: 513
• Type: Contributed
• Date/Time: Wednesday, August 1, 2012 : 10:30 AM to 12:20 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Karen Messer*+ and Hongying Li and Minya Pu
• Companies: University of California at San Diego and University of California at San Diego and University of California at San Diego
• Keywords: closed tests ; simon design ; phase II trial ; interim analysis

Abstract

Interim analyses which allow early stopping for futility are standard in Phase II oncology trials, in order to minimize patient exposure to potentially toxic treatments. The family-wise Type I error rate for the multiple comparisons of a multi-arm trial can be strongly controlled using a closed testing strategy, and this is often an efficient approach. Efficient strategies to combine closed test procedures with interim stopping boundaries have been proposed in the literature; however these are difficult to apply to the standard two-stage Phase II oncology trial because of the small sample sizes and discrete nature of the test statistics. We discuss some of the issues involved in multi-arm trials in which each arm uses a Simon two-stage design, and compare some of the approaches in the literature.