Scaling Clinical Trial Matching Using Large Language Models: A Case Study in Oncology

TL;DR

This study explores using large language models like GPT-4 to improve clinical trial matching in oncology by structuring eligibility criteria and extracting matching logic, showing promising results and identifying key challenges.

Contribution

It demonstrates the potential of LLMs to enhance clinical trial matching processes and highlights areas for further improvement in accuracy and context handling.

Findings

LLMs can structure complex eligibility criteria effectively.

LLMs outperform previous baselines in matching tasks.

Challenges remain in context understanding and data accuracy.

Abstract

Clinical trial matching is a key process in health delivery and discovery. In practice, it is plagued by overwhelming unstructured data and unscalable manual processing. In this paper, we conduct a systematic study on scaling clinical trial matching using large language models (LLMs), with oncology as the focus area. Our study is grounded in a clinical trial matching system currently in test deployment at a large U.S. health network. Initial findings are promising: out of box, cutting-edge LLMs, such as GPT-4, can already structure elaborate eligibility criteria of clinical trials and extract complex matching logic (e.g., nested AND/OR/NOT). While still far from perfect, LLMs substantially outperform prior strong baselines and may serve as a preliminary solution to help triage patient-trial candidates with humans in the loop. Our study also reveals a few significant growth areas for applying LLMs to end-to-end clinical trial matching, such as context limitation and accuracy, especially in structuring patient information from longitudinal medical records.