A Scalable AI Approach for Clinical Trial Cohort Optimization

TL;DR

This paper introduces an AI-based method using transformer NLP to optimize clinical trial eligibility criteria, improving scalability and generalizability by analyzing real-world data and aiding trial design for diverse populations.

Contribution

It presents a novel AI approach that automates and scales the process of optimizing clinical trial eligibility criteria using transformer models and real-world data analysis.

Findings

Successfully extracted eligibility variables from large trial datasets

Enhanced trial design generalizability for breast cancer

Enabled rapid simulation of eligibility criteria

Abstract

FDA has been promoting enrollment practices that could enhance the diversity of clinical trial populations, through broadening eligibility criteria. However, how to broaden eligibility remains a significant challenge. We propose an AI approach to Cohort Optimization (AICO) through transformer-based natural language processing of the eligibility criteria and evaluation of the criteria using real-world data. The method can extract common eligibility criteria variables from a large set of relevant trials and measure the generalizability of trial designs to real-world patients. It overcomes the scalability limits of existing manual methods and enables rapid simulation of eligibility criteria design for a disease of interest. A case study on breast cancer trial design demonstrates the utility of the method in improving trial generalizability.