研究人员开发了HEM-Med，一个旨在改进跨多家医院用药推荐的新框架。该系统解决了两个关键挑战：将可泛化的临床经验与医院特定实践区分开来，以及纳入药物相互作用和当地处方集依从性等关键安全约束。在eICU数据集上的实验表明，HEM-Med在准确性和安全性方面均优于现有的迁移学习、基于LLM的方法和其他推荐方法。 AI
影响 该框架有望提高医疗环境中AI驱动的临床决策支持系统的安全性和准确性。
排序理由 该集群描述了一篇详细介绍特定AI应用新颖框架的研究论文。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Medication recommendation (MR) is critical for clinical decision support. While existing MR methods are mostly designed for single-center learning, where only one independent hospital is involved, multi-center MR with hospitals of different scales has become increasingly demandin…
Medication recommendation (MR) is critical for clinical decision support. While existing MR methods are mostly designed for single-center learning, where only one independent hospital is involved, multi-center MR with hospitals of different scales has become increasingly demandin…