Retrieval-Augmented LLMs for Evidence Localization in Clinical Trial Recruitment from Longitudinal EHR Narratives

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Ziyi, Lyu, Mengxian, Peng, Cheng, Wu, Yonghui
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915965241917440
author Chen, Ziyi
Lyu, Mengxian
Peng, Cheng
Wu, Yonghui
author_facet Chen, Ziyi
Lyu, Mengxian
Peng, Cheng
Wu, Yonghui
contents Screening patients for enrollment is a well-known, labor-intensive bottleneck that leads to under-enrollment and, ultimately, trial failures. Recent breakthroughs in large language models (LLMs) offer a promising opportunity to use artificial intelligence to improve screening. This study systematically explored both encoder- and decoder-based generative LLMs for screening clinical narratives to facilitate clinical trial recruitment. We examined both general-purpose LLMs and medical-adapted LLMs and explored three strategies to alleviate the "Lost in the Middle" issue when handling long documents, including 1) Original long-context: using the default context windows of LLMs, 2) NER-based extractive summarization: converting the long document into summarizations using named entity recognition, 3) RAG: dynamic evidence retrieval based on eligibility criteria. The 2018 N2C2 Track 1 benchmark dataset is used for evaluation. Our experimental results show that the MedGemma model with the RAG strategy achieved the best micro-F1 score of 89.05%, outperforming other models. Generative LLMs have remarkably improved trial criteria that require long-term reasoning across long documents, whereas trial criteria that span a short piece of context (e.g., lab tests) show incremental improvements. The real-world adoption of LLMs for trial recruitment must consider specific criteria for selecting among rule-based queries, encoder-based LLMs, and generative LLMs to maximize efficiency within reasonable computing costs.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05190
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Retrieval-Augmented LLMs for Evidence Localization in Clinical Trial Recruitment from Longitudinal EHR Narratives
Chen, Ziyi
Lyu, Mengxian
Peng, Cheng
Wu, Yonghui
Computation and Language
Artificial Intelligence
Information Retrieval
Screening patients for enrollment is a well-known, labor-intensive bottleneck that leads to under-enrollment and, ultimately, trial failures. Recent breakthroughs in large language models (LLMs) offer a promising opportunity to use artificial intelligence to improve screening. This study systematically explored both encoder- and decoder-based generative LLMs for screening clinical narratives to facilitate clinical trial recruitment. We examined both general-purpose LLMs and medical-adapted LLMs and explored three strategies to alleviate the "Lost in the Middle" issue when handling long documents, including 1) Original long-context: using the default context windows of LLMs, 2) NER-based extractive summarization: converting the long document into summarizations using named entity recognition, 3) RAG: dynamic evidence retrieval based on eligibility criteria. The 2018 N2C2 Track 1 benchmark dataset is used for evaluation. Our experimental results show that the MedGemma model with the RAG strategy achieved the best micro-F1 score of 89.05%, outperforming other models. Generative LLMs have remarkably improved trial criteria that require long-term reasoning across long documents, whereas trial criteria that span a short piece of context (e.g., lab tests) show incremental improvements. The real-world adoption of LLMs for trial recruitment must consider specific criteria for selecting among rule-based queries, encoder-based LLMs, and generative LLMs to maximize efficiency within reasonable computing costs.
title Retrieval-Augmented LLMs for Evidence Localization in Clinical Trial Recruitment from Longitudinal EHR Narratives
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2604.05190