Automated Construction of Medical Indicator Knowledge Graphs Using Retrieval Augmented Large Language Models

TL;DR

Medical knowledge is dispersed across guidelines and literature, hindering automated clinical decision support. The authors propose a retrieval-augmented generation framework that grounds LLM reasoning with guideline retrieval, an ontology-driven schema, and expert-in-the-loop validation to automatically construct medical indicator knowledge graphs. The approach comprises data acquisition, ontology design, information extraction, and knowledge fusion, producing over 120 standardized indicators from 38 guidelines across eight systems, with GraphRAG-enabled QA and CDSS applications, and an initial precision of 88% on 240 extracted triples. This framework enables scalable, reliable, and interpretable medical knowledge graphs to accelerate AI-powered diagnosis, decision support, and biomedical research.

Abstract

Artificial intelligence (AI) is reshaping modern healthcare by advancing disease diagnosis, treatment decision-making, and biomedical research. Among AI technologies, large language models (LLMs) have become especially impactful, enabling deep knowledge extraction and semantic reasoning from complex medical texts. However, effective clinical decision support requires knowledge in structured, interoperable formats. Knowledge graphs serve this role by integrating heterogeneous medical information into semantically consistent networks. Yet, current clinical knowledge graphs still depend heavily on manual curation and rule-based extraction, which is limited by the complexity and contextual ambiguity of medical guidelines and literature. To overcome these challenges, we propose an automated framework that combines retrieval-augmented generation (RAG) with LLMs to construct medical indicator knowledge graphs. The framework incorporates guideline-driven data acquisition, ontology-based schema design, and expert-in-the-loop validation to ensure scalability, accuracy, and clinical reliability. The resulting knowledge graphs can be integrated into intelligent diagnosis and question-answering systems, accelerating the development of AI-driven healthcare solutions.

Figures (1)

• Figure 1: Workflow of the proposed knowledge graph construction framework.