Bayesian Adaptive Commensurate Prior Methods for Rare Disease and Pediatric Clinical Trials

• Activity Number: 16
• Type: Topic Contributed
• Date/Time: Sunday, August 9, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Bradley P. Carlin* and Cynthia Basu and Brian Hobbs
• Companies: University of Minnesota and University of Minnesota and MD Anderson Cancer Center
• Keywords: adaptive clinical trial ; Bayesian methods ; commensurate prior ; rare disease

Abstract

Rare diseases are difficult to study, since the numbers of persons who can be enrolled in a traditional clinical trial is typically insufficient to demonstrate a statistically significant treatment effect. Pediatric disease researchers face similar challenges. Here, drugs successfully tested on adults are sometimes available, but we still lack information on dosing, safety, and efficacy of these drugs in children. Full or partial extrapolation of existing adult data to the pediatric case is sometimes justified, but current methods are often ad hoc and depend crucially on knowing the appropriate amount of information to borrow from the adult data. This talk considers a collection of novel Bayesian statistical methods and software tools for more efficient and effective orphan and pediatric drug trials. Bayesian methods offer a formal statistical framework for incorporating all sources of knowledge (structural constraints, expert opinion, and both historical and experimental data), thus offering the possibility of substantially reduced trial sizes, thanks to their more efficient use of information. This in turn typically leads to increases in statistical power and reductions in cost