用大模型和检索增强实现精准患者匹配，提升临床试验招募效率。
LLM-Match: An Open-Sourced Patient Matching Model Based on Large Language Models and Retrieval-Augmented Generation
- 结合检索增强生成与微调，从电子病历中提取关键信息
- 在四个公开数据集上超越GPT-4等基线模型，准确率更高
- 开源框架适合医疗AI研究者快速搭建患者匹配系统
患者匹配是通过精准识别和匹配患者病历与临床试验入组标准，将患者链接至合适临床试验的过程。本文提出一种名为LLM-Match的新框架，利用微调的开源大语言模型实现患者匹配。该框架包含四个核心组件：第一，检索增强生成（RAG）模块从大量电子健康记录（EHRs）中提取相关患者上下文；第二，提示生成模块整合入组/排除标准、患者上下文及系统指令构建输入提示；第三，带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，评估模块在测试数据集上检验模型性能。我们在n2c2、SIGIR、TREC 2021和TREC 2022四个公开数据集上，采用开源模型评估了LLM-Match，并与TrialGPT、零样本方法及基于GPT-4的封闭模型对比，结果表明其性能全面优于所有基线。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。