Controlled LLM-based Reasoning for Clinical Trial Retrieval

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jullien, Mael, Bogatu, Alex, Unsworth, Harriet, Freitas, Andre
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916413549051904
author Jullien, Mael
Bogatu, Alex
Unsworth, Harriet
Freitas, Andre
author_facet Jullien, Mael
Bogatu, Alex
Unsworth, Harriet
Freitas, Andre
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_18998
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Controlled LLM-based Reasoning for Clinical Trial Retrieval
Jullien, Mael
Bogatu, Alex
Unsworth, Harriet
Freitas, Andre
Computation and Language
Artificial Intelligence
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.
title Controlled LLM-based Reasoning for Clinical Trial Retrieval
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2409.18998