Statistical Innovation: Transforming Pharmaceutical Research and Development

Music City Center 

Room: CC-104C 

Breakthroughs in statistical innovation have played paramount roles in enhancing quality, integrity, speed and efficiency in pharmaceutical research and development. In this session, we will provide an overview of innovative techniques that have had considerable impacts in changing the landscape of the pharmaceutical industry and in transforming the drug development paradigm accelerating the discovery, development, approval and manufacturing of new medicines for patients with unmet medical needs. We highlight how flexible and adaptive designs have helped accelerate drug development timelines and reduce cost, and we provide examples of how this has impacted the advancement of public health in the recent past, including the remarkable development of the COVID-19 messenger RNA vaccine. Advances in modeling and simulation, as well as Bayesian Statistics, have enabled integration of quantitative decision making in drug development in all phases and at all levels - from study design to portfolio prioritization. Novel statistical approaches have also helped with validation of surrogate endpoints and handling of multiplicity issues that support decision making by regulators and other stakeholders, while safeguarding the safety and well-being of patients. Among the emerging innovations, special attention is paid to such novel technologies and methodologies as causal inference and modern analytics. New approaches for causal inference have proved promising in the use of data beyond randomized controlled trials to generate reliable evidence concerning the relative risks and benefits of alternative treatment options. Lastly, thanks to the unfolding digital revolution, there is a growing adoption of artificial intelligence and machine learning tools at every stage of drug development, from discovery through loss of exclusivity.

Adaptive design

Efficient drug development

Multiplicity adjustment

Surrogate endpoints

Causal inference

Big data analytics 

Yes

Section for Statistical Programmers and Analysts

Biopharmaceutical Section

Health Policy Statistics Section