The current state of Bayesian methods in medical product development: survey results and recommendations from the DIA Bayesian Scientific Working Group

Abstract

Bayesian applications in medical product development have recently gained popularity. Despite many advances in Bayesian methodology and computations, increase in application across the various areas of medical product development has been modest. The DIA Bayesian Scientific Working Group (BSWG), which includes representatives from industry, regulatory agencies, and academia, has adopted the vision to ensure Bayesian methods are well understood, accepted more broadly, and appropriately utilized to improve decision making and enhance patient outcomes. As Bayesian applications in medical product development are wide ranging, several sub-teams were formed to focus on various topics such as patient safety, non-inferiority, prior specification, comparative effectiveness, joint modeling, program-wide decision making, analytical tools, and education. The focus of this paper is on the recent effort of the BSWG Education sub-team to administer a Bayesian survey to statisticians across 17 organizations involved in medical product development. We summarize results of this survey, from which we provide recommendations on how to accelerate progress in Bayesian applications throughout medical product development. The survey results support findings from the literature and provide additional insight on regulatory acceptance of Bayesian methods and information on the need for a Bayesian infrastructure within an organization. The survey findings support the claim that only modest progress in areas of education and implementation has been made recently, despite substantial progress in Bayesian statistical research and software availability.

Minimizing Patient Burden Through the Use of Historical Subject-Level Data in Innovative Confirmatory Clinical Trials: Review of Methods and Opportunities

“…A survey carried out by the Drug Information Association (DIA) Bayesian Scientific Working Group of industry statisticians in 2012 identified "a lack of clarity of the regulatory position and/or lack of guidance" as one of the 4 main barriers to the implementation of Bayesian methodology. 7 Guideline expresses a major concern about only using historical controls (ie, the inability to control bias), but also describes the usefulness of such controls under certain scenarios. Guideline describes situations where appropriately and carefully chosen historical controls are more persuasive and potentially less biased.…”

“…A survey carried out by the Drug Information Association (DIA) Bayesian Scientific Working Group of industry statisticians in 2012 identified “a lack of clarity of the regulatory position and/or lack of guidance” as one of the 4 main barriers to the implementation of Bayesian methodology. 7 In 2016, representatives from FDA’s Centers for Drug Evaluation and Research (CDER), Biologic Evaluation and Research (CBER), and Devices and Radiological Health (CDRH) participated in a workshop “Substantial Evidence in 21st Century Regulatory Science: Borrowing Strength from Accumulating Data” that focused on methods to incorporate historical information. 8 This indicates a growing acceptance by regulators of using historical controls for late-stage drug development.…”

CBER’s Experience With Adaptive Design Clinical Trials

“…This result supports findings of the DIA Bayesian Scientific Working Group (BSWG), which reported that there are more opportunities for statisticians to implement Bayesian adaptive design approaches in early phase than in late phase clinical development. 27 In very general terms, the chief advantages of Bayesian approaches are the ability to easily incorporate external information into an analysis and mathematical flexibility in fitting certain complicated models that may be intractable in a classical framework. The fact that CBER primarily receives Bayesian proposals for dose-finding models in early-phase trials suggests that it is the latter rather than the former factor spurring Bayesian applications in regulatory submissions to CBER.…”

Bayesian applications in pharmaceutical statistics

“…A special issue on Bayesian Statistics was published in 2014 with coverage of a variety of areas, including network meta‐analysis in drug safety . The issue also contained a paper by the DIA Bayesian Scientific Working Group reporting a survey showing that “having access to fully worked case examples was considered the most helpful factor to start applying Bayesian approaches.” In recent years, we have encouraged Andy Grieve to share his knowledge and experience with case studies which are easy to follow and can hopefully cast light on a variety of areas of work which can be improved by a Bayesian approach …”