Tree-based RAG-Agent Recommendation System: A Case Study in Medical Test Data
This work addresses medical test recommendations for healthcare professionals, representing a significant advance by integrating medical reasoning into tree-based structures, though it is incremental as it builds on existing RAG and tree-based methods.
The paper tackled the problem of medical test recommendation by developing a tree-structured system that uses Retrieval-Augmented Generation for step-wise medical reasoning, achieving superior performance in coverage rate, accuracy, and miss rate compared to conventional methods.
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.