基于检索增强的大型语言模型用于受模式约束的临床信息提取
Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction
AI总结：
本文提出一种模块化检索增强生成框架，通过schema约束提示、确定性后处理和二次审核，提升护士-患者对话中观察提取的F1分数达80.36%。
摘要：
对话护士-患者记录包含可操作的观察，但将这些记录转化为结构化表示仍具挑战性。MEDIQA-SYNUR专注于从对话记录中提取观察，要求系统将这些叙述规范化为预定义模式，并满足值-类型约束。我们提出了一种模块化检索增强生成（RAG）流程，利用训练集作为示例语料库，结合模式约束提示（完整模式与剪枝候选模式）、确定性模式后处理和二次审核，并采用两个LLM骨干：Llama-4-Scout-17B-16E-Instruct和GPT-5.2，配以相应的嵌入模型。我们的最佳配置使用GPT-5.2、完整模式、RAG和二次审核，达到80.36%的F1分数。整体结果表明，RAG consistently improves performance，而最佳模式约束程度取决于模型，二次审核通过纠正残余模式一致性错误带来小幅增益。
英文摘要：
Conversational nurse-patient transcripts contain actionable observations, but converting these transcripts into structured representations at scale remains challenging. Documentation burden is substantial, with prior studies showing clinicians spend large portions of their workday on documentation and related desk work rather than direct patient care. MEDIQA-SYNUR focuses on observation extraction from conversational nurse-patient transcripts, requiring systems to normalize these narratives into a predefined schema with value-type constraints. We propose a modular retrieval-augmented generation (RAG) pipeline that uses the training set as an exemplar corpus, combines schema-constrained prompting (full schema vs. pruned candidate schema), deterministic schema-based postprocessing, and a second-pass audit, with two LLM backbones: Llama-4-Scout-17B-16E-Instruct and GPT-5.2 with corresponding embedding models for RAG. Our best configuration uses GPT-5.2 with full schema, RAG, and a second-pass auditing, achieving 80.36% F1 score. Overall, our results show that RAG consistently improves performance, while the optimal degree of schema constraint depends on the model, and second-pass auditing yields modest additional gains by correcting residual schema-adherence errors.
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。
