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

arXiv: https://arxiv.org/abs/2406.14326 · HTML: https://mlsanity.com/paper/2406.14326/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 43 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation](https://mlsanity.com/paper/2107.02137/) (2021)
- [Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs](https://mlsanity.com/paper/2404.07103/) (2024)
- [CMB: A Comprehensive Medical Benchmark in Chinese](https://mlsanity.com/paper/2308.08833/) (2023)
- [CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark](https://mlsanity.com/paper/2106.08087/) (2021)
- [Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning](https://mlsanity.com/paper/2105.03654/) (2021)
- [StageNet: Stage-Aware Neural Networks for Health Risk Prediction](https://mlsanity.com/paper/2001.10054/) (2020)
- [KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques](https://mlsanity.com/paper/2403.05881/) (2024)
- [ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World](https://mlsanity.com/paper/2406.13890/) (2024)
- [REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models](https://mlsanity.com/paper/2402.07016/) (2024)
- [Guiding Clinical Reasoning with Large Language Models via Knowledge Seeds](https://mlsanity.com/paper/2403.06609/) (2024)
- [keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLM](https://mlsanity.com/paper/2401.00426/) (2023)
- [TREA: Tree-Structure Reasoning Schema for Conversational Recommendation](https://mlsanity.com/paper/2307.10543/) (2023)
- [Joint Multi-Facts Reasoning Network For Complex Temporal Question Answering Over Knowledge Graph](https://mlsanity.com/paper/2401.02212/) (2024)

## Built on by (most cited first, 16 of 16)

- [KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs](https://mlsanity.com/paper/2507.02773/) (2025)
- [MedKGI: Iterative Differential Diagnosis with Medical Knowledge Graphs and Information-Guided Inquiring](https://mlsanity.com/paper/2512.24181/) (2025)
- [Brittleness and Promise: Knowledge Graph Based Reward Modeling for Diagnostic Reasoning](https://mlsanity.com/paper/2509.18316/) (2025)
- [RUIE: Retrieval-based Unified Information Extraction using Large Language Model](https://mlsanity.com/paper/2409.11673/) (2024)
- [DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaboration](https://mlsanity.com/paper/2505.18630/) (2025)
- [EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs](https://mlsanity.com/paper/2605.30637/) (2026)
- [HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways](https://mlsanity.com/paper/2508.07308/) (2025)
- [MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation](https://mlsanity.com/paper/2603.03677/) (2026)
- [From Triage to Discharge: A Survey of NLP Tasks, Methods, and Open Challenges in the Emergency Department](https://mlsanity.com/paper/2608.23627/) (2026)
- [ICA-RAG: Information Completeness Guided Adaptive Retrieval-Augmented Generation for Disease Diagnosis](https://mlsanity.com/paper/2502.14614/) (2025)
- [MIMIC-SR-ICD11: A Dataset for Narrative-Based Diagnosis](https://mlsanity.com/paper/2511.05485/) (2025)
- [LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval](https://mlsanity.com/paper/2604.18913/) (2026)
- [VeriLLMed: Interactive Visual Debugging of Medical Large Language Models with Knowledge Graphs](https://mlsanity.com/paper/2604.23356/) (2026)
- [WPG-MoE: Weak-Prior-Guided Dense Mixture-of-Experts for User-Level Social Media Depression Detection](https://mlsanity.com/paper/2607.04350/) (2026)
- [Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models](https://mlsanity.com/paper/2608.26587/) (2026)
- [MedVA: An End-to-End Neuro-Symbolic Agentic System for Medical Volume Visualization](https://mlsanity.com/paper/2609.14874/) (2026)

## Abstract (arXiv)

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.