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 di-agnosis in specific domains. The core innovation lies in our end-to-end knowledge graph generation methodology, incor-porating: (1) semantic-driven entity and relation extraction optimized for medical terminology, (2) multi-dimensional de-cision relationship reconstruction from unstructured medical texts, and (3) human-guided reasoning for knowledge ex-pansion. 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 devel-oping targeted medical diagnosis systems. We provide archi-tectural guidelines and protocols to facilitate adoption across medical contexts.
How to Cite
Zuo, K., Jiang, Y., & Mo, F. (2026). KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis. Asia Journal of Social Innovation and Development, 2(1), 10. Retrieved from https://www.ajsid.org/index.php/pub/article/view/30
📄Abdulla, K.; Mukherjee, S.; and Ranganathan, P. 2023. Inte-grating Multimodal Data for Enhancing Knowledge Graphs:Current Challenges and Opportunities. Journal of Big Data,10(1): 1–15.
📄Al Khatib, H. S.; Neupane, S.; Kumar Manchukonda, H.;Golilarz, N. A.; Mittal, S.; Amirlatifi, A.; and Rahimi, S.2024. Patient-centric Knowledge Graphs: A Survey of Cur-rent Methods, Challenges, and Applications. Frontiers in Artificial Intelligence, 7: 1388479.
📄Alam, F.; Giglou, H. B.; and Malik, K. M. 2023. Auto-mated Clinical Knowledge Graph Generation Framework for Evidence-based Medicine. Expert Systems with Appli-cations, 233: 120964.
📄Alsentzer, E.; Murphy, J.; Boag, W.; Weng, W.; Jin, D.; Nau-mann, T.; and McDermott, M. 2019. Publicly Available Clinical BERT Embeddings. arXiv:1901.08746.
📄Amos, L.; Anderson, D.; Brody, S.; Ripple, A.; and Humphreys, B. L. 2020. UMLS Users and Uses: A Current Overview. Journal of the American Medical Informatics As-sociation, 27(10): 1606–1611.
📄Avula, R.; et al. 2022. Data-Driven Decision-Making in Healthcare Through Advanced Data Mining Techniques: A Survey on Applications and Limitations. International Jour-nal of Applied Machine Learning and Computational Intel-ligence, 12(4): 64–85.
📄Bonner, S.; Barrett, I. P.; Ye, C.; Swiers, R.; Engkvist, O.; Bender, A.; Hoyt, C. T.; and Hamilton, W. L. 2022. A Re-view of Biomedical Datasets Relating to Drug Discovery: A Knowledge Graph Perspective. Briefings in Bioinformatics, 23(6): bbac404.
📄Bosselut, A.; Chen, Z.; Romanou, A.; Bonnet, A.;Hernandez-Cano, A.; Alkhamissi, B.; Matoba, K.; Salvi, F.; ´Pagliardini, M.; Fan, S.; et al. 2024. MEDITRON: Open Medical Foundation Models Adapted for Clinical Practice.
📄Brown, T.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.;Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; andAskell, A. 2020. Language Models Are Few-Shot Learners.arXiv:2005.14165.
📄Chang, E.; and Mostafa, J. 2021. The Use of SNOMED CT,2013-2020: A Literature Review. Journal of the American Medical Informatics Association, 28(9): 2017–2026.
📄Garc´ıa-Ferrero, I.; Agerri, R.; Salazar, A. A.; Cabrio, E.;de la Iglesia, I.; Lavelli, A.; Magnini, B.; Molinet, B.;Ramirez-Romero, J.; Rigau, G.; et al. 2024. Medical mT5:An Open-Source Multilingual Text-to-Text LLM for the Medical Domain. arXiv preprint arXiv:2404.07613.
📄Guo, T.; Chen, X.; Wang, Y.; Chang, R.; Pei, S.; Chawla,N. V.; Wiest, O.; and Zhang, X. 2024. Large Language Model Based Multi-Agents: A Survey of Progress and Chal-lenges. arXiv preprint arXiv:2402.01680.
📄Huang, L.; Yu, W.; Ma, W.; Zhong, W.; Feng, Z.; Wang, H.;Chen, Q.; Peng, W.; Feng, X.; Qin, B.; et al. 2023. A Sur-vey on Hallucination in Large Language Models: Principles,Taxonomy, Challenges, and Open Questions. ACM Transac-tions on Information Systems.
📄Tang, B.; Chang, T.-H.; Wang, S.; et al. 2020. Real-World Data Medical Knowledge Graph: Construction and Applica-tions. Artificial Intelligence in Medicine, 103: 101817.
📄Liu, Y.; Ott, M.; Goyal, N.; Du, J.; Joshi, M.; Chen, D.; Levy,O.; Lewis, M.; Zettlemoyer, L.; and Stoyanov, V. 2023. Med-HALT: Evaluating Hallucinations in Medical LLMs.arXiv:2410.15702.
📄Lu, Z.; Afridi, I.; Kang, H. J.; Ruchkin, I.; and Zheng, X.2024. Surveying Neuro-Symbolic Approaches for Reliable Artificial Intelligence of Things. Journal of Reliable Intelli-gent Environments, 10(3): 257–279.
📄Luo, R.; Sun, L.; Xia, Y.; Qin, T.; Zhang, S.; Poon, H.; and Liu, T.-Y. 2022. BioGPT: Generative Pre-Trained Trans-former for Biomedical Text Generation and Mining. Brief-ings in Bioinformatics, 23(6): bbac409.
📄Masoumi, S.; Amirkhani, H.; Sadeghian, N.; and Shahraz,S. 2024. Natural Language Processing (NLP) to Facilitate Abstract Review in Medical Research: The Application of BioBERT to Exploring the 20-Year Use of NLP in Medical Research. Systematic Reviews, 13(1): 107.
📄Mo, F.; Chaplin, J. C.; Sanderson, D.; Mart´ınez-Arellano,G.; and Ratchev, S. 2024. Semantic models and knowl-edge graphs as manufacturing system reconfiguration en-ablers. Robotics and Computer-Integrated Manufacturing,86: 102625.
📄Nori, H.; Lee, Y. T.; Zhang, S.; Carignan, D.; Edgar, R.;Fusi, N.; King, N.; Larson, J.; Li, Y.; Liu, W.; et al. 2023.Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine. arXiv preprint arXiv:2311.16452.
📄OpenAI. 2022. ChatGPT: Optimizing Language Models for Dialogue. OpenAI Technical Blog.
📄Pandey, H. G.; Amod, A.; and Kumar, S. 2024. Advanc-ing Healthcare Automation: Multi-Agent System for Medi-cal Necessity Justification. In Demner-Fushman, D.; Ana-niadou, S.; Miwa, M.; Roberts, K.; and Tsujii, J., eds., Pro-ceedings of the 23rd Workshop on Biomedical Natural Lan-guage Processing, 39–49. Bangkok, Thailand: Association for Computational Linguistics.
📄Peng, C.; Xia, F.; Naseriparsa, M.; and Osborne, F. 2023. Knowledge Graphs: Opportunities and Challenges. Artificial Intelligence Review, 56(11): 13071–13102.
📄Qian, J.; Jin, Z.; Zhang, Q.; Cai, G.; and Liu, B. 2024. A Liver Cancer Question-Answering System Based on Next-Generation Intelligence and the Large Model Med-PaLM 2. International Journal of Computer Science and Information Technology, 2(1): 28–35.
📄Rives, A.; Meier, J.; Sercu, T.; Goyal, S.; Lin, Z.; Liu, J.;Guo, D.; Ott, M.; Zitnick, C. L.; Ma, J.; et al. 2021. Bio-logical Structure and Function Emerge from Scaling Unsu-pervised Learning to 250 Million Protein Sequences. Pro-ceedings of the National Academy of Sciences, 118(15):e2016239118.
📄Shuifa, S.; Xiaolong, L.; Weisheng, L.; Dajiang, L.; Sihui,L.; Liu, Y.; and Yirong, W. 2023. Review of Graph Neural Networks Applied to Knowledge Graph Reasoning. Journal of Frontiers of Computer Science & Technology, 17(1): 27.
📄Singhal, K.; Tu, T.; Gottweis, J.; Sayres, R.; and Wulczyn, E.2023b. Towards Expert-Level Medical Question Answeringwith Large Language Models. Nature Medicine, 29(1): 50–58.
📄Tang, X.; Chi, G.; Cui, L.; Ip, A. W.; Yung, K. L.; and Xie,X. 2023. Exploring Research on the Construction and Ap-plication of Knowledge Graphs for Aircraft Fault Diagnosis.Sensors, 23(11): 5295.
📄Tonmoy, S.; Zaman, S.; Jain, V.; Rani, A.; Rawte, V.;Chadha, A.; and Das, A. 2024. A Comprehensive Surveyof Hallucination Mitigation Techniques in Large Language Models. arXiv preprint arXiv:2401.01313.
📄Touvron, H.; Lavril, T.; Izacard, G.; Martinet, X.; Lachaux,M.-A.; Lacroix, T.; Roziere, B.; Goyal, N.; Hambro, E.; `Azhar, F.; et al. 2023. LLaMA: Open and Efficient Foun-dation Language Models. arXiv preprint arXiv:2302.13971.
📄Wu, J.; Zhu, J.; Qi, Y.; Chen, J.; Xu, M.; Menolascina,F.; and Grau, V. 2024. Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation. arXiv preprint arXiv:2408.04187.
📄Wu, Z.; Zhang, Y.; and Lin, X. 2023. Scalability Challenges in Medical Knowledge Graph Construction. IEEE Transac-tions on Medical Informatics, 14(2): 120–132.
📄Zhang, J.; Zan, H.; Wu, S.; Zhang, K.; and Huo, J. 2024.Adaptive Graph Neural Network with Incremental Learning Mechanism for Knowledge Graph Reasoning. Electronics,13(14): 2778.
📄Zhang, Y. 2021. Knowledge Reasoning with Graph Neural Networks. Georgia Institute of Technology: Atlanta, GA,USA.
📄Zhang, Y.; Li, X.; and Wang, J. 2023. Knowledge Graph for Fraud Detection: Case of Fraudulent Related Party Transac-tions. In Advances in Knowledge Discovery and Data Min-ing, 182–194. Springer.
📄Zhou, J.; Cui, G.; Zhang, Z.; Yang, C.; Liu, Z.; Wang, L.; Li,C.; and Sun, M. 2022. Graph Neural Networks: A Reviewof Methods and Applications. AI Open, 1(1): 1–12.