CMStatistics 2018: Start Registration
View Submission - CMStatistics
Title: A Bayesian non-parametric causal inference model for synthesizing randomized clinical trials and real-world evidence Authors:  Gary Rosner - Johns Hopkins University (United States) [presenting]
Chenguang Wang - Johns Hopkins University (United States)
Abstract: With the wide availability of various real-world data (RWD), there is an increasing interest in synthesizing information from both randomized clinical trials and RWD for health-care decision making. The task of addressing study-specific heterogeneities is one of the most difficult challenges in synthesizing data from disparate sources. Bayesian hierarchical models with non-parametric extensions provide a powerful and convenient platform that formalizes the information borrowing strength across the sources. We propose a propensity score-based Bayesian non-parametric Dirichlet process mixture model that summarizes subject-level information from randomized and registry studies to draw inference on the causal treatment effect. Simulation studies are conducted to evaluate the model performance under different scenarios. We demonstrate the proposed method using data from a clinical study.