Scaling Clinical Trial Matching Using Large Language Models: A Case Study in Oncology
This addresses the challenge of unscalable manual processing in clinical trial matching for healthcare providers and researchers, though it is incremental as it builds on existing LLM capabilities.
The paper tackled the problem of scaling clinical trial matching in oncology by using large language models (LLMs) like GPT-4 to structure eligibility criteria and extract matching logic, resulting in LLMs substantially outperforming prior baselines and serving as a preliminary solution for triaging patient-trial candidates with human oversight.
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.