DIA 2022 Global Annual Meeting

Component Type: Session
Level: Intermediate
CE: ACPE 1.00 Knowledge UAN: 0286-0000-22-621-L04-P ; CME 1.00; RN 1.00

In the drug development space, there is a growing expectation demanding pharmaceutical companies generate more evidence by conducting increased number of clinical trials due to increased regulatory requirements ensuring patient safety. One of the biggest speed limiting steps in clinical trials, is patient enrollment. Selecting the right sites would potentially accelerate the overall enrollment and ultimately the clinical development timeline. We can identify and prioritize sites for clinical trials by predicting key metrics that define a site’s overall performance, including, site start-up time and enrollment rate. The traditional way of identifying sites to participate in a study could be a combination of referral, working relationship or data-driven approach like identifying sites that have had prior experience conducting trials in similar indication and analyzing their historical average performance. While field knowledge is irreplaceable, we can better leverage the data using advanced analytical techniques like machine learning and feasibility studies influencing data-driven decision making.

Learning Objectives

Describe various solutions to identify high-performing countries and sites for clinical trials; Discuss various factors influencing site performance in clinical trials; Describe how to make data-driven decision in site selection for clinical trials.

Chair

Dinesh Kumar Subbarayalu, MS

Speaker

A Machine Learning-Based Approach to Identify Highly Efficient Sites to Prioritize for Clinical Trial
Dinesh Kumar Subbarayalu, MS

Streamlining the Feasibility Process to Enhance Site-Sponsor Collaboration and Accelerate Cycle Times
Kavitha Lokesh