通过病因感知注意力监督增强大型语言模型在临床诊断决策中的可信性
Enhancing Trustworthy Clinical Diagnosis Decision-Making in Large Language Models via Etiology-Aware Attention Supervision
AI总结：
该研究提出病因感知注意力监督框架，通过引入临床病因模式对大型语言模型进行参数高效微调，在两类诊断队列上提升了诊断准确率与注意力聚焦性，增强了模型临床诊断的可信性。
摘要：
目标：大型语言模型（LLMs）在医学文本理解与生成方面展现出强大能力，但面向诊断的医学任务中，其可信性受限于模型学习过程中缺乏对临床相关诊断证据如何被内部关注和利用的结构化指导。方法：我们提出一种病因感知注意力监督（Etiology-Aware Attention Supervision）框架，引入结构化病因信息作为外部监督信号用于训练大型语言模型。具体而言，我们基于权威临床指南构建了针对三种急性腹部病症（急性阑尾炎、急性胰腺炎、急性胆囊炎）的临床病因模式（Clinical Etiology Schema, CES）。基于CES标注，我们开发了病因感知头部识别策略，以识别与病因证据一致的注意力头。基于该分析，我们设计了结构引导的参数高效微调方法，通过额外的监督损失引导注意力分布聚焦于临床相关证据，且不修改基础模型架构。结果：在一致性诊断队列上开展的实验表明，与基线模型相比，所提框架将平均诊断准确率提升了15.65%；推理聚焦分数、推理注意力频率等基于注意力的指标显示，模型对病因相关证据的关注更为集中。在不一致诊断队列上开展的外部评估进一步证实，该框架在真实世界临床不一致场景下诊断性能提升的稳健性。
英文摘要：
Objective: Large Language Models (LLMs) have demonstrated strong capabilities in medical text understanding and generation. However, their trustworthiness in diagnosis-oriented medical tasks remains constrained by the lack of structured guidance on how clinically relevant diagnostic evidence is internally attended to and utilized during model learning. Method: We propose an Etiology-Aware Attention Supervision framework that introduces structured etiological information as an external supervisory signal for training large language models. Specifically, we construct Clinical Etiology Schema (CES) derived from authoritative clinical guidelines for three acute abdominal conditions: acute appendicitis, acute pancreatitis, and acute cholecystitis. Based on CES annotations, we develop an Etiology-Aware Head Identification strategy to identify attention heads that consistently align with etiological evidence. Building on this analysis, we design a structure-guided parameter-efficient fine-tuning approach that steers attention distributions toward clinically relevant evidence through an additional supervision loss, without modifying the base model architecture. Result: Experiments conducted on a Consistent Diagnosis Cohort demonstrate that the proposed framework improves average diagnostic accuracy by 15.65% compared with baseline models. Attention-based metrics, including Inference Focus Score and Inference Attention Frequency, show more concentrated attention on etiologically relevant evidence. External evaluation on a Discrepant Diagnosis Cohort further confirms the robustness of diagnostic performance improvements under real-world clinical inconsistencies.
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。
