用多智能体框架实现可解释、安全的精准用药推荐。
SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation
- 构建知识增强的多智能体系统，结合临床上下文与安全验证
- 在MIMIC-III/IV上提升四层ATC代码预测准确率并控制药物风险
- 适合医疗AI研究者与临床决策支持系统开发者
药物推荐需为患者就诊提供用药建议，但现有方法仍面临两大挑战：模型层面，传统方法仅预测结构化药名代码，缺乏证据支撑；大模型智能体虽能利用丰富临床信息，却可能缺乏安全性验证与可追溯性。任务层面，现有基准常使用宽泛药物类别，忽略亚组级安全差异，导致风险误判。本文首次提出基于第四层ATC代码生成的细粒度药物推荐设定。提出SafeRx-Agent——一种基于知识的多智能体框架，通过整合患者上下文、外部临床知识及安全验证，生成可追溯的用药方案。在MIMIC-III和MIMIC-IV数据集上的实验表明，该框架在提升细粒度药物预测准确率的同时，有效控制了药物相互作用、禁忌症及用药组合规模。
原文摘要 · Abstract (English)
Medication recommendation predicts medications for patient visits, but existing methods still face two key challenges. At the model level, traditional drug recommendation methods only predict structured drug codes with limited evidence grounding, while LLM agents can use richer clinical context but may lack safety verification and traceability. At the task level, existing benchmarks often use broad medication categories, which ignore subgroup-level safety differences and can lead to risk overestimation. We introduce the first fine-grained medication recommendation setting based on fourth-level ATC code generation. We propose Safe Prescription Agent (SafeRx-Agent), a knowledge-grounded multi-agent framework that uses patient context, external clinical knowledge, and safety verification to recommend traceable medication sets. Experimental results on MIMIC-III and MIMIC-IV datasets show that SafeRx-Agent improves fine-grained medication prediction accuracy while controlling drug interactions, contraindications, and medication set size.
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。