Using Bayesian Proof-of-Concept (POC) Criteria to Design Randomized Phase II Oncology Trials Stratified by Biomarker Status

• Activity Number: 70
• Type: Contributed
• Date/Time: Sunday, July 31, 2011 : 4:00 PM to 5:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Kalyanee Appanna and Valentine Jehl and Yong Zhang*+ and Yun Wang and Amy Racine and Beat Neuenschwander and Emmanuel Zuber
• Companies: Novartis Oncology and Novartis Oncology and Novartis Oncology and Novartis Oncology and Novartis and Novartis Pharma AG and Novartis Oncology
• Keywords: Bayesian proof-of-concept ; Phase II oncology trials ; Targeted therapy

Abstract

In the early stage development of a targeted therapy, assumed to be more effective in a specific subpopulation, it is very challenging to decide whether clinical trials should be conducted in all patients or only in the specific subpopulation. We propose to use randomized Phase II study results to help make that decision in a subsequent Phase III study. Traditional frequentist designs often use Type I/II error rates only to determine sample sizes and make decisions based on p-values. However, critical values needed for statistical significance are often implicit and a significant p-value does not necessarily imply a clinically meaningful effect size. We propose some Bayesian PoC criteria with clearly defined effect size, which require a reasonably high probability that treatment is better than control, and the estimated hazard ratio reaches a clinically meaningful size. Frequentist probabilities of making the right decision for various scenarios are investigated. Simulations show that the proposed design has good frequentist operating characteristics. The new design has been applied in a new randomized Phase II trial.