DiaLLMs：用于临床检查推荐和诊断预测的EHR增强临床对话系统
DiaLLMs: EHR Enhanced Clinical Conversational System for Clinical Test Recommendation and Diagnosis Prediction
- College of Information Sciences and Technology, Pennsylvania State University（信息科学与技术学院，宾夕法尼亚州立大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出首个整合异构EHR数据的医疗LLM（DiaLLM），通过临床检查参考策略和强化学习框架实现临床检查推荐、结果解释与诊断预测，显著优于基线模型。
AI中文摘要：
大型语言模型（LLMs）的最新进展在医疗问诊方面取得了显著进展。然而，现有的医疗LLMs忽视了电子健康记录（EHR）的核心作用，主要侧重于诊断推荐，限制了其临床适用性。我们提出了DiaLLM，这是首个将异构EHR数据整合到具有临床依据的对话中的医疗LLM，能够进行临床检查推荐、结果解释和诊断预测，以更好地契合现实世界的医疗实践。为了从EHR构建具有临床依据的对话，我们设计了一种临床检查参考（CTR）策略，将每个临床代码映射到其对应的描述，并将检查结果分类为“正常”或“异常”。此外，DiaLLM采用强化学习框架进行证据获取和自动诊断。为了处理庞大的动作空间，我们引入了拒绝采样策略以减少冗余并提高探索效率。此外，还设计了确认奖励和类别敏感的诊断奖励来指导准确的诊断预测。大量实验结果表明，DiaLLM在临床检查推荐和诊断预测方面优于基线模型。
英文摘要：
Recent advances in Large Language Models (LLMs) have led to remarkable progresses in medical consultation. However, existing medical LLMs overlook the essential role of Electronic Health Records (EHR) and focus primarily on diagnosis recommendation, limiting their clinical applicability. We propose DiaLLM, the first medical LLM that integrates heterogeneous EHR data into clinically grounded dialogues, enabling clinical test recommendation, result interpretation, and diagnosis prediction to better align with real-world medical practice. To construct clinically grounded dialogues from EHR, we design a Clinical Test Reference (CTR) strategy that maps each clinical code to its corresponding description and classifies test results as "normal" or "abnormal". Additionally, DiaLLM employs a reinforcement learning framework for evidence acquisition and automated diagnosis. To handle the large action space, we introduce a reject sampling strategy to reduce redundancy and improve exploration efficiency. Furthermore, a confirmation reward and a class-sensitive diagnosis reward are designed to guide accurate diagnosis prediction. Extensive experimental results demonstrate that DiaLLM outperforms baselines in clinical test recommendation and diagnosis prediction.
