A Transparent and Efficient Approach in Proof-of-Concept Study Design and Subsequent Decisionmaking

• Activity Number: 414
• Type: Contributed
• Date/Time: Tuesday, August 2, 2011 : 2:00 PM to 3:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Gang Jia*+ and Paul Delucca and Bruce Binkowitz and Daniel Bloomfield
• Companies: Merck & Co., Inc. and Merck & Co., Inc. and Merck & Co., Inc. and Merck & Co., Inc.
• Keywords: Clinical trial ; proof of concept ; Sample size ; Bayesian analysis ; Decision analysis ; Study design

Abstract

Consider designing a two-arm parallel POC (proof of concept) clinical study in which the primary endpoint is a continuous and normally distributed variable. The goal of the POC study is to obtain information on the efficacy and safety of the experiment drug and to make reasonable decision in the next step of development. Generally resources are limited at this stage of the development process, which poses the question of how to decide on the size of the POC study to adequately serve the purpose of the study. The usual approach of sample size calculation based on Type I error rate and study power is confusing and doesn't provide the relevant information for the purpose of the study. Here we provide a framework of the study design and analysis based on a transparent decision making process. We also propose to incorporate Bayesian analysis approaches to have the flexibility to apply all the relevant information in the decision making.