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

arXiv: https://arxiv.org/abs/2512.24181 · HTML: https://mlsanity.com/paper/2512.24181/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [CMB: A Comprehensive Medical Benchmark in Chinese](https://mlsanity.com/paper/2308.08833/) (2023)
- [Diagnostic Reasoning Prompts Reveal the Potential for Large Language Model Interpretability in Medicine](https://mlsanity.com/paper/2308.06834/) (2023)
- [Sequential Diagnosis with Language Models](https://mlsanity.com/paper/2506.22405/) (2025)
- [CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis](https://mlsanity.com/paper/2407.13301/) (2024)
- [Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoning](https://mlsanity.com/paper/2502.04381/) (2025)
- [Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2505.19630/) (2025)
- [KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis](https://mlsanity.com/paper/2412.16833/) (2024)
- [ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning](https://mlsanity.com/paper/2502.14860/) (2025)
- [MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis](https://mlsanity.com/paper/2502.19175/) (2025)
- [Adaptive Retrieval-Augmented Generation for Conversational Systems](https://mlsanity.com/paper/2407.21712/) (2024)
- [Reasoning Like a Doctor: Improving Medical Dialogue Systems via Diagnostic Reasoning Process Alignment](https://mlsanity.com/paper/2406.13934/) (2024)
- [medIKAL: Integrating Knowledge Graphs as Assistants of LLMs for Enhanced Clinical Diagnosis on EMRs](https://mlsanity.com/paper/2406.14326/) (2024)
- [ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs](https://mlsanity.com/paper/2508.13514/) (2025)
- [The Multi-Round Diagnostic RAG Framework for Emulating Clinical Reasoning](https://mlsanity.com/paper/2504.07724/) (2025)

## Built on by (most cited first, 7 of 7)

- [MeDxAgent: Multi-Agent Consultation for Interactive Medical Diagnosis](https://mlsanity.com/paper/2606.03416/) (2026)
- [RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical Diagnosis](https://mlsanity.com/paper/2602.01297/) (2026)
- [MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision Support](https://mlsanity.com/paper/2604.20022/) (2026)
- [Within the MDT Room: Situated in Multidisciplinary Team-Grounded Agent Debate for Clinical Diagnosis](https://mlsanity.com/paper/2603.28393/) (2026)
- [VeriLLMed: Interactive Visual Debugging of Medical Large Language Models with Knowledge Graphs](https://mlsanity.com/paper/2604.23356/) (2026)
- [NSIDDx: A Design Framework for Neuro-Symbolic, Practitioner-First Differential Diagnosis in Low-Resource Settings](https://mlsanity.com/paper/2609.00256/) (2026)
- [HPOQuest: A Rare-Disease Diagnostic Agent Using Active Phenotype Acquisition](https://mlsanity.com/paper/2609.18431/) (2026)

## Abstract (arXiv)

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.