MedKGI: Iterative Differential Diagnosis with Medical Knowledge Graphs and Information-Guided Inquiring

TL;DR

MedKGI addresses the gap between LLM-based clinical reasoning and real differential diagnosis by grounding hypothesis generation in a medical knowledge graph, guiding inquiries with information gain, and tracking evidence with OSCE-aligned records. The method achieves higher diagnostic accuracy and reduces dialogue rounds across three benchmarks compared to strong baselines. Its key contributions are KG grounding, information-theoretic inquiry, and structured state management, validated by extensive ablation studies. The work demonstrates practical potential for efficient, grounded AI-assisted differential diagnosis, while acknowledging the need for real-world validation and richer symptom-likelihood modeling.

Abstract

Recent advancements in Large Language Models (LLMs) have demonstrated significant promise in clinical diagnosis. However, current models struggle to emulate the iterative, diagnostic hypothesis-driven reasoning of real clinical scenarios. Specifically, current LLMs suffer from three critical limitations: (1) generating hallucinated medical content due to weak grounding in verified knowledge, (2) asking redundant or inefficient questions rather than discriminative ones that hinder diagnostic progress, and (3) losing coherence over multi-turn dialogues, leading to contradictory or inconsistent conclusions. To address these challenges, we propose MedKGI, a diagnostic framework grounded in clinical practices. MedKGI integrates a medical knowledge graph (KG) to constrain reasoning to validated medical ontologies, selects questions based on information gain to maximize diagnostic efficiency, and adopts an OSCE-format structured state to maintain consistent evidence tracking across turns. Experiments on clinical benchmarks show that MedKGI outperforms strong LLM baselines in both diagnostic accuracy and inquiry efficiency, improving dialogue efficiency by 30% on average while maintaining state-of-the-art accuracy.

Figures (14)

• Figure 1: Comparison of diagnostic dialogues and the MedKGI workflow. Left: The dialogues from the baseline LLMs. Right: The dialogues from the proposed MedKGI framework. Bottom: The MedKGI workflow.
• Figure 2: An illustration of the iterative hypothesis refinement process and its corresponding clinical differential diagnosis example.
• Figure 3: An illustration of the iterative hypothesis refinement process and its corresponding clinical differential diagnosis example.
• Figure 4: An overview of MedKGI framework. Given a patient's chief complaint, MedKGI iteratively refines differential diagnosis through (1) medical knowledge graph alignment, (2) information gain–driven symptom inquiry to minimize diagnosis uncertainty, and (3) OSCE-aligned diagnostic records for coherent evidence tracking. A hypothesis-driven termination policy ensures diagnostic efficiency.
• Figure 5: (a) Impact of candidate disease settings on accuracy. (b) Effect of $k$ on Accuracy where $k$ is defined as the ratio of the number of candidate diseases to the number of related symptoms from the KG.