Tree-based RAG-Agent Recommendation System: A Case Study in Medical Test Data
Yahe Yang, Chengyue Huang
TL;DR
Medical test recommendation faces challenges from contextual dependence and diagnostic uncertainty. The paper proposes HiRMed, a hierarchical RAG-enhanced framework with dual-layer knowledge bases and memory-augmented reasoning to perform stepwise diagnostic reasoning from symptoms to tests. Empirical results show superior coverage, accuracy, and lower miss rates compared with traditional approaches, with favorable clinical validation. The work demonstrates a practical pathway for integrating structured medical reasoning with LLM-driven retrieval for decision support in healthcare.
Abstract
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.