用检索增强生成技术提升临床对话结构化提取准确率
Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction
- 构建检索增强生成流水线，结合模式约束提示与后处理
- 最佳方案达80.36% F1，RAG显著提升性能
- 适合医疗信息提取、临床数据自动化系统开发者
对话式护患记录包含可操作的临床观察，但大规模转化为结构化数据仍具挑战。现有研究显示，临床工作者大量时间耗费在文书工作而非患者照护上。MEDIQA-SYNUR聚焦于从护患对话中提取观察信息，要求系统将叙述性内容归一化为预定义模式并满足值类型约束。本文提出模块化检索增强生成（RAG）流程：以训练集作为实例语料库，结合全模式与剪枝候选模式的约束提示、基于模式的确定性后处理及二次审计机制，采用Llama-4-Scout-17B-16E-Instruct和GPT-5.2两种LLM作为核心模型，并搭配对应嵌入模型实现RAG。最优配置使用GPT-5.2、全模式约束、RAG与二次审计，取得80.36% F1分数。整体结果表明，RAG持续提升性能，而最优模式约束程度依赖模型，二次审计通过修正残留模式偏差带来小幅增益。
原文摘要 · Abstract (English)
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.
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。