KREL：基于大型语言模型对临床证据进行知识引导推理的自动医学编码方法
KREL: Automatic Medical Coding via Knowledge-Guided Reasoning over Clinical Evidence with LLMs
另 1 家 · 查看机构详情
- The University of New South Wales（新南威尔士大学）
- University of Göttingen（哥廷根大学）
- Macquarie University（麦考瑞大学）
- Beijing Intelligent Decision Medical Technology Co. Ltd（北京智决医疗科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究提出KREL框架，将LLM与ICD编码指南知识结合解决自动医学编码问题，在基准数据集上性能优于现有方法。
中文摘要 AI 辅助
自动医学编码（AMC）是指将标准化的国际疾病分类（ICD）代码分配给临床病历的任务，对医疗报销、质量报告和临床研究至关重要。现有的基于预训练语言模型（PLM）的方法通常将AMC表述为对预定义代码集的极端多标签分类问题，而近期基于大型语言模型（LLM）的方法则将其框架化为生成或多步推理任务。然而，仍存在关键挑战：临床病历的超长长度阻碍了有效解读、ICD标签空间极为庞大、以及LLM未明确捕捉到的复杂编码规则。本研究提出KREL框架，即基于大型语言模型对临床证据进行知识引导推理的方法，该框架利用LLM进行临床文本理解与推理，同时将外部ICD编码指南作为结构化知识进行整合。此设计实现了领域知识与LLM推理的紧密耦合，减少了幻觉并提升了编码标准的合规性。在基准数据集上的实验表明，KREL始终优于强大的基于PLM的基线方法和当前最优的基于LLM的基线方法。
英文摘要
Automatic Medical Coding (AMC), which assigns standardized International Classification of Diseases (ICD) codes to clinical notes, is essential for medical reimbursement, quality reporting, and clinical research. Existing pre-trained language model (PLM)-based methods typically formulate AMC as an extreme multi-label classification problem over a predefined code set, while recent large language model (LLM)-based approaches instead frame it as generation or multi-step reasoning. However, key challenges remain, including the extreme length of clinical notes that hinders effective interpretation, the vast ICD label space, and complex coding rules that are not explicitly captured by LLMs. In this work, we propose Knowledge-Guided Reasoning over Clinical Evidence with LLMs (KREL), a framework that leverages LLMs for clinical text understanding and reasoning while integrating external ICD coding guidelines as structured knowledge. This design enables tight coupling between domain knowledge and LLM reasoning, reducing hallucinations and improving compliance with coding standards. Experiments on benchmark datasets show that KREL consistently outperforms strong PLM-based and state-of-the-art LLM-based baselines.
