Controlled LLM-based Reasoning for Clinical Trial Retrieval
This addresses the challenge of scaling expert-level interpretation for clinical trial retrieval, though it is incremental as it extends existing LLM capabilities.
The paper tackled the problem of matching patients to clinical trials by systematizing reasoning over medical eligibility criteria using LLMs, achieving superior results with NDCG@10 of 0.693 and Precision@10 of 0.73 on the TREC 2022 benchmark.
Matching patients to clinical trials demands a systematic and reasoned interpretation of documents which require significant expert-level background knowledge, over a complex set of well-defined eligibility criteria. Moreover, this interpretation process needs to operate at scale, over vast knowledge bases of trials. In this paper, we propose a scalable method that extends the capabilities of LLMs in the direction of systematizing the reasoning over sets of medical eligibility criteria, evaluating it in the context of real-world cases. The proposed method overlays a Set-guided reasoning method for LLMs. The proposed framework is evaluated on TREC 2022 Clinical Trials, achieving results superior to the state-of-the-art: NDCG@10 of 0.693 and Precision@10 of 0.73.