arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.02727cs.IRcs.AI
收藏

基于树的RAG智能体推荐系统:医学检验数据案例研究

Tree-based RAG-Agent Recommendation System: A Case Study in Medical Test Data

George Washington University(乔治·华盛顿大学);University of Iowa(爱荷华大学)

Yahe Yang, Chengyue Huang

AI总结:

本文提出树状结构的 HiRMed 系统,在各节点利用RAG进行分层医学推理并动态推荐检验,实验显示其覆盖率、准确率和漏检率优于传统检索方法。

摘要:

我们提出 HiRMed(Hierarchical RAG-enhanced Medical Test Recommendation,分层RAG增强医学检验推荐),这是一种新颖的树状结构推荐系统,利用检索增强生成(RAG)进行智能医学检验推荐。与传统基于向量相似度的方法不同,我们的系统通过专门的RAG流程在每个树节点执行医学推理。系统从包含初始症状的根节点开始,逐步开展医学分析,以识别潜在的基础疾病及其相应诊断需求。在每一层级,RAG增强节点并非进行简单匹配,而是分析检索到的医学知识,以理解症状—疾病关系,并确定最合适的诊断路径。系统会根据医学推理结果动态调整推荐策略,同时考虑紧急程度和诊断不确定性等因素。实验结果表明,与传统基于检索的方法相比,我们的方法在覆盖率、准确率和漏检率方面均取得更优性能。本工作通过将医学推理能力引入传统的基于树的检索结构,代表了医学检验推荐领域的一项重要进展。

英文摘要:

We present HiRMed (Hierarchical RAG-enhanced Medical Test Recommendation), a novel tree-structured recommendation system that leverages Retrieval-Augmented Generation (RAG) for intelligent medical test recommendations. Unlike traditional vector similarity-based approaches, our system performs medical reasoning at each tree node through a specialized RAG process. Starting from the root node with initial symptoms, the system conducts step-wise medical analysis to identify potential underlying conditions and their corresponding diagnostic requirements. At each level, instead of simple matching, our RAG-enhanced nodes analyze retrieved medical knowledge to understand symptom-disease relationships and determine the most appropriate diagnostic path. The system dynamically adjusts its recommendation strategy based on medical reasoning results, considering factors such as urgency levels and diagnostic uncertainty. Experimental results demonstrate that our approach achieves superior performance in terms of coverage rate, accuracy, and miss rate compared to conventional retrieval-based methods. This work represents a significant advance in medical test recommendation by introducing medical reasoning capabilities into the traditional tree-based retrieval structure.

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。

↑