All Times EDT
Keywords: Bayesian, clinical trials, master protocols, basket trials
Progress in the areas of genomics, disease pathways, and drug discovery have advanced into several clinical research paradigms of biomedicine. Precision medicine has emerged from the awareness that many human diseases are intrinsically heterogeneous by pathogenesis and response to emerging therapies, especially in oncology. Innovations in methodology have followed with statistical models and basket trial designs devised to measure the extent to which a treatment strategy offers benefit to various patient subpopulations. Consequently, characterization of subpopulation heterogeneity has become central to the formulation and selection of a study design. Yet, trial design formulation predominately continues to rely on convention, with hypothesis tests of “average benefit” for the “average patient.” Trials actually enroll mixtures of various patient subpopulations for which treatment effectiveness may be determined by a multitude of factors. This presentation will discuss recently developed Bayesian multi-source exchangeability models (MEMs), and their applications to master protocol designs.