Bayesian Approach for Similarity Assessment of Treatment Effects in Bridging Studies

• Activity Number: 307
• Type: Contributed
• Date/Time: Tuesday, August 6, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Sinae Kim*+ and Weichung Joe Shih
• Companies: University of Medicine and Dentistry of New Jersey and University of Medicine and Dentistry of New Jersey
• Keywords: bridging study ; similarity ; population difference ratio ; Bayesian random effect model

Abstract

For a registration of a new drug which has been approved in original studies, bridging studies have been conducted in regional countries to examine its efficacy. We employ a Bayesian hierarchical random effect model to obtain a distribution of overall efficacy of a drug, and also to accommodate the variability among the multiple results from the original studies. We utilize a posterior predictive distribution to replicate the original studies from updated distributions of their treatment effects and also to generate new data set for a bridging study from population distribution of its treatment effect with updated overall efficacy. To assess the similarity in efficacy between the original study and a bridging study, the estimated population difference ratio (pPDR) a posterior, replicates vs. new study is calculated, and compared to the pre-fixed cutoff. We also provide the calculation of sample size based on PDR. We show a simulation study in difference scenarios and a clinical trial example to illustrate the application of the method.