基于SOAP流程的两阶段系统，让AI更像医生一样制定个性化诊疗方案。
MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generation
- 分两步走：先评估症状与客观数据，再生成带历史信息的治疗计划。
- 在评估准确性和治疗方案质量上均显著优于现有方法。
- 适合需要精准、可解释医疗决策支持的临床场景。
尽管大型语言模型（LLMs）在电子健康记录（EHR）应用中取得进展，但多数系统仍侧重于诊断评估而非治疗规划。现有方法存在三大局限：治疗计划生成为单步过程，不符合临床的逐步推理习惯；缺乏患者特定的历史背景信息；难以有效区分主观与客观临床信息。受SOAP（主观、客观、评估、计划）方法论启发，我们提出 exttt{MedPlan}，一种新型框架，使LLM推理过程与真实临床工作流对齐。该方法采用两阶段架构：第一阶段基于患者症状和客观数据生成临床评估；第二阶段在此评估基础上，结合检索增强生成（RAG）引入患者历史信息，形成结构化治疗计划。全面评估表明，该方法在评估准确性和治疗方案质量上均显著优于基线模型。
原文摘要 · Abstract (English)
Despite recent success in applying large language models (LLMs) to electronic health records (EHR), most systems focus primarily on assessment rather than treatment planning. We identify three critical limitations in current approaches: they generate treatment plans in a single pass rather than following the sequential reasoning process used by clinicians; they rarely incorporate patient-specific historical context; and they fail to effectively distinguish between subjective and objective clinical information. Motivated by the SOAP methodology (Subjective, Objective, Assessment, Plan), we introduce \ours{}, a novel framework that structures LLM reasoning to align with real-life clinician workflows. Our approach employs a two-stage architecture that first generates a clinical assessment based on patient symptoms and objective data, then formulates a structured treatment plan informed by this assessment and enriched with patient-specific information through retrieval-augmented generation. Comprehensive evaluation demonstrates that our method significantly outperforms baseline approaches in both assessment accuracy and treatment plan quality.
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。