Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 280 - Application of Machine Learning in Clinical Development
Type: Topic-Contributed
Date/Time: Wednesday, August 11, 2021 : 1:30 PM to 3:20 PM
Sponsor: Biopharmaceutical Section
Abstract #317174
Title: Predicting Patient Adherence in a Changing World
Author(s): Dooti Roy*
Companies: Boehringer Ingelheim Pharmaceuticals, Inc.
Keywords: Adherence; Behavior Modeling; Machine Learning; Pill counts; Compliance; Prediction
Abstract:

Patient adherence to clinical trial protocol is critical to the success of any trial. Patient adherence is a known challenge in clinical trials, initially identified in CNS studies, and increasingly recognized as a factor more broadly in clinical research. Such trials are often designed with 20-30% dropouts. Reducing proportion of patients who drop-out can increase statistical power of the trial, enhance study decision-making, as well as shorten development timelines. So far our understanding of patient adherence to their medication have been limited by pill counts and self-reported diaries. With the advent of new, innovative, digital technologies, our capabilities in monitoring patient adherence has dramatically improved. It brought us an unique opportunity of looking deeply into such app-based data and extract meaningful, actionable quantitative insights which can improve data quality, reduce missingness and dropouts from trials. In this talk, this unique journey will be recounted along with the deeper dive into the data, the methodological details, the knowledge gained and the business impact of such an exploration.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program