LLM-Match：基于大型语言模型与检索增强生成的开源患者匹配模型
LLM-Match: An Open-Sourced Patient Matching Model Based on Large Language Models and Retrieval-Augmented Generation
AI总结：
提出LLM-Match框架，利用微调的开源大语言模型和检索增强生成进行患者匹配，在四个公开数据集上优于TrialGPT等基线。
摘要：
患者匹配是将患者与合适的临床试验联系起来的过程，通过准确识别和匹配患者的医疗记录与试验入选标准来实现。我们提出了LLM-Match，一种利用微调的开源大型语言模型进行患者匹配的新框架。我们的方法包含四个关键组件。首先，检索增强生成（RAG）模块从海量电子健康记录（EHRs）中提取相关的患者上下文。其次，提示生成模块通过整合试验入选标准（包括纳入和排除标准）、患者上下文和系统指令来构建输入提示。第三，带有分类头的微调模块使用结构化提示和真实标签优化模型参数。第四，评估模块评估微调模型在测试数据集上的性能。我们在四个开放数据集——n2c2、SIGIR、TREC 2021和TREC 2022上，使用开源模型评估了LLM-Match，并将其与TrialGPT、Zero-Shot和基于GPT-4的闭源模型进行比较。LLM-Match在所有基线中表现最优。
英文摘要：
Patient matching is the process of linking patients to appropriate clinical trials by accurately identifying and matching their medical records with trial eligibility criteria. We propose LLM-Match, a novel framework for patient matching leveraging fine-tuned open-source large language models. Our approach consists of four key components. First, a retrieval-augmented generation (RAG) module extracts relevant patient context from a vast pool of electronic health records (EHRs). Second, a prompt generation module constructs input prompts by integrating trial eligibility criteria (both inclusion and exclusion criteria), patient context, and system instructions. Third, a fine-tuning module with a classification head optimizes the model parameters using structured prompts and ground-truth labels. Fourth, an evaluation module assesses the fine-tuned model's performance on the testing datasets. We evaluated LLM-Match on four open datasets - n2c2, SIGIR, TREC 2021, and TREC 2022 - using open-source models, comparing it against TrialGPT, Zero-Shot, and GPT-4-based closed models. LLM-Match outperformed all baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
