medIKAL: Integrating Knowledge Graphs as Assistants of LLMs for Enhanced Clinical Diagnosis on EMRs

2024-06-20

International Conference on Computational Linguistics

AI Summary

To address the challenges of high information redundancy and difficulty in clinical reasoning within electronic medical records (EMRs), which hinder diagnostic accuracy, this paper proposes a diagnostic framework integrating large language models (LLMs) with domain-specific medical knowledge graphs (KGs). Our method introduces three key innovations: (1) a novel residual LLM-KG collaboration mechanism that enables dynamic, complementary integration of semantic understanding and structured biomedical knowledge; (2) an entity-type-weighted localization strategy coupled with a multi-hop path re-ranking algorithm to enhance retrieval precision of critical clinical evidence; and (3) a cloze-style prompting template that explicitly guides stepwise diagnostic reasoning. Evaluated on a newly constructed, publicly available Chinese EMR dataset, our approach achieves a significant +8.7% improvement in diagnostic accuracy over strong baselines, demonstrating its effectiveness and practical utility in real-world clinical settings.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Large Multimodal Models (LMMs)

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: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Electronic Medical Records (EMRs), while integral to modern healthcare, present challenges for clinical reasoning and diagnosis due to their complexity and information redundancy. To address this, we proposed medIKAL (Integrating Knowledge Graphs as Assistants of LLMs), a framework that combines Large Language Models (LLMs) with knowledge graphs (KGs) to enhance diagnostic capabilities. medIKAL assigns weighted importance to entities in medical records based on their type, enabling precise localization of candidate diseases within KGs. It innovatively employs a residual network-like approach, allowing initial diagnosis by the LLM to be merged into KG search results. Through a path-based reranking algorithm and a fill-in-the-blank style prompt template, it further refined the diagnostic process. We validated medIKAL's effectiveness through extensive experiments on a newly introduced open-sourced Chinese EMR dataset, demonstrating its potential to improve clinical diagnosis in real-world settings.

Problem

• Electronic Health Records
• Diagnostic Difficulty
• Information Redundancy

Innovation

• Knowledge Graph
• Large Language Model
• Disease Diagnosis