Title: Bayesian detection of potential safety signal from blinded clinical trial data
Presenters: Saurabh Mukhopadhyay and Brian Waterhouse
Ensuring patients' safety in clinical trials is extremely important and is a major responsibility of the sponsors of the clinical trials. Regulatory authorities also encourage aggregate review of safety from ongoing clinical trials, specifically to identify potential risks of adverse events of special interest. Sponsors may decide that a blinded review of safety data can meet these needs while also ensuring clinical trial integrity. A Bayesian methodological framework has been developed that leverages historical data of the background rates of events of interest to monitor and detect potential safety signals using blinded data from ongoing clinical trials. This new method is a two‐step Bayesian evaluation of potential safety signals composed of a screening analysis followed by a sensitivity analysis. The blinded safety teams can use these steps to make an informed decision if any events of interest should be escalated for unblinded review.
To ease implementation and operationalization of the method, an R package called BDRIBS (Bayesian Detection of potential Risk using Inference on Blinded Safety data) and an associated R-Shiny application have been developed. The R-package and the R-Shiny tool are both publicly available.
The first part of the presentation will focus on the methodological development and the second part will feature the BDRIBS R-Shiny application to illustrate visualization and assessment of the events of interest to help in exploration of various scenarios and sensitivity analyses in real‐time.
Saurabh Mukhopadhyay, Ph.D.
Research Fellow, Statistical Innovation
Data and Statistical Sciences
Saurabh has over 25 years of experience in statistical consultancy and research in drug development and other fields of statistics. He joined AbbVie in 2015 as a Research Fellow in the Statistical Innovation group within Data and Statistical Sciences function. Through strategic leadership and cross-functional collaborations he has been promoting Bayesian and other novel statistical methodologies in AbbVie to make clinical trials more adaptive and efficient.
He started his career with academic research and teaching at Duke University and University of Connecticut. Then he joined Merck and during his 10 years of tenure there he supported all phases of clinical development in various therapeutic areas. He then went to India where he provided statistical consultancy in healthcare and finance sectors for about ten years before returning to US to join at AbbVie. He has published several manuscripts on novel statistical methodologies and their applications in peer-reviewed journals, presented at conferences and workshops as invited speaker, organized and chaired biostatistical sessions in US and international statistical conferences. Saurabh received his master’s degree in statistics from Indian Statistical Institute, Kolkata, and Ph.D. in Statistics from Purdue University. His current areas of research interests include Bayesian methods, adaptive designs and related decision making to optimize clinical trials, assessment on benefit-risk, detection of safety signals, and leveraging external data.
Brian Waterhouse, MSc.
Sr. Principal Scientist, Biostatistics
Clinical Safety Statistics
Biostatistics and Research Decision Sciences
Merck & Co., Inc.
Brian has over 20 years of experience in the pharmaceutical industry – designing and reporting clinical trial data in HIV, diabetes, osteoporosis, pulmonary arterial hypertension, heart failure, unstable angina, chronic kidney disease, psoriasis, and most recently, atopic dermatitis.
He started his career at DuPont Pharmaceuticals after receiving dual master’s degrees in mathematics and applied statistics from Syracuse University. He has held positions with increasing responsibility and scope at GlaxoSmithKline and AbbVie and has recently joined Merck’s safety statistics department where he will be supporting oncology and vaccines. Brian is active in the ASA Safety Working Group where he has recently been named the co-lead for the Benefit-Risk Assessment Tool Suite taskforce and is on the editorial board for Contemporary Clinical Trials.
Slides will be stored in http://www.bayesianscientific.org/kol-lecture-series/
Join Zoom Meeting
Meeting ID: 220 359 9026
One tap mobile
+16468769923,,2203599026# US (New York)
+16699006833,,2203599026# US (San Jose)
Dial by your location
+1 646 876 9923 US (New York)
+1 669 900 6833 US (San Jose)
+1 253 215 8782 US (Tacoma)
+1 301 715 8592 US (Germantown)
+1 312 626 6799 US (Chicago)
+1 346 248 7799 US (Houston)
855 880 1246 US Toll-free
877 853 5257 US Toll-free
Meeting ID: 220 359 9026
Find your local number: https://diaglobal.zoom.us/u/tdzNsDvQ
Join by Skype for Business