KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis

2024-12-22

AI Summary

To address low reasoning reliability for complex cases, outdated medical knowledge, and insufficient cross-specialty collaboration in clinical diagnosis, this paper proposes a hierarchical multi-agent large language model (LLM) framework for diagnostic support. Methodologically, it introduces an end-to-end semantic-driven paradigm for medical knowledge graph (KG) construction—incorporating joint extraction of terms, entities, and relations; reconstruction of multidimensional diagnostic decision relationships; and human-in-the-loop KG expansion—covering 362 common diseases. It further designs a two-tier agent coordination mechanism: general-practice triage followed by specialty-level refinement, integrating LLMs, KGs, semantic parsing, and hybrid reinforcement learning. Key contributions include: (1) the first dynamically extensible KG construction method tailored for clinical diagnostics, significantly improving diagnostic interpretability and accuracy on complex cases; and (2) a modular architecture with standardized protocols enabling rapid deployment across multiple specialties.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Other Foundations of Multi Agent Systems

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Integrating Large Language Models (LLMs) in healthcare diagnosis demands systematic frameworks that can handle complex medical scenarios while maintaining specialized expertise. We present KG4Diagnosis, a novel hierarchical multi-agent framework that combines LLMs with automated knowledge graph construction, encompassing 362 common diseases across medical specialties. Our framework mirrors real-world medical systems through a two-tier architecture: a general practitioner (GP) agent for initial assessment and triage, coordinating with specialized agents for in-depth diagnosis in specific domains. The core innovation lies in our end-to-end knowledge graph generation methodology, incorporating: (1) semantic-driven entity and relation extraction optimized for medical terminology, (2) multi-dimensional decision relationship reconstruction from unstructured medical texts, and (3) human-guided reasoning for knowledge expansion. KG4Diagnosis serves as an extensible foundation for specialized medical diagnosis systems, with capabilities to incorporate new diseases and medical knowledge. The framework's modular design enables seamless integration of domain-specific enhancements, making it valuable for developing targeted medical diagnosis systems. We provide architectural guidelines and protocols to facilitate adoption across medical contexts.

Problem

• Disease Diagnosis
• Complex Medical Issues
• Continuous System Update

Innovation

• Knowledge Graph
• Large Language Model
• Dynamic Updating