Advances in Integrating Knowledge Graphs and Large Language Models for Health Management of Diabetes

Corresponding author: YI Faling, flyi@gdpu.edu.cn

DOI: 10.12201/bmr.202508.00035

•  

  Abstract: Purpose/Significance Diabetes, as a typical chronic disease, necessitates comprehensive health management spanning diagnosis, treatment, monitoring, and follow-up. The complexity of data types and diversity of management tasks pose significant challenges for traditional methods in providing effective intelligent support. To address these limitations, the fusion technology of Knowledge Graphs (KG) and Large Language Models (LLM) has garnered considerable attention. This paper aims to systematically explore the application potential and effectiveness of KG-LLM integration in intelligent diabetes health management. Method/Process We conducted a systematic analysis of the technical synergies between KG and LLM. Furthermore, we examined domestic and international case studies to demonstrate the practical efficacy of this integrated approach in key areas of diabetes management, including intelligent question answering, personalized interventions, and complication prediction. Result/Conclusion The deep integration of KG and LLM significantly enhances the accuracy and efficiency of diabetes health management. Future developments should focus on refining dynamic knowledge updating mechanisms, strengthening privacy protection measures, and fostering interdisciplinary collaboration. These advancements will be crucial for evolving diabetes management towards a comprehensive prevention-intervention-rehabilitation lifecycle model and establishing a robust technical paradigm for the widespread adoption of precision medicine in chronic disease care.

  Key words: diabetes; knowledge graph; large language model; health management; artificial intelligence

  Submit time: 15 August 2025

  Copyright: The copyright holder for this preprint is the author/funder, who has granted biomedRxiv a license to display the preprint in perpetuity.
• html

• 图表

• rui chen, chen yueqi, li jinbin, zhang shengfa. Progress and Trend of the Application of Artificial Intelligence in the Basic Health Management of Type 2 Diabetes. 2025. doi: 10.12201/bmr.202506.00072

  Shi Chenghao, Tu Xinyi, Shi Jiawei, Chen Hongshuang, Wang Qinlu, Zou Haiou. A Scoping Review of the Application of Large Language Models in Clinical Practice. 2024. doi: 10.12201/bmr.202406.00001

  WU Meng, LI Jiao. Construction of multimodal perinatal health care knowledge graph towards continuing medical education. 2024. doi: 10.12201/bmr.202402.00008

  GE Xiaoling. Application of Artificial Intelligence Large Models in Healthcare:a Survey. 2024. doi: 10.12201/bmr.202408.00039

  ZhengYanli, Han Fuhai, LI Shuyu, SU Wenxing. Application Status and Prospect of Artificial Intelligence Large Models in Medicine. 2023. doi: 10.12201/bmr.202312.00027

  XIANG AININGKUN, TIAN JINGXUE, HU DEHUA, LIU HAIXIA. Comparative Study on Response Efficacy of Generative Artificial Intelligence for Elderly Diabetes Mellitus. 2025. doi: 10.12201/bmr.202503.00019

  LvTingyu, LiXiaoying, LiuYuyang, DuJinhua, LiXinyi, LuoYan, Tangxiaoli, RenHuiling, LiuHui, YinHao. Research on the Construction of a Question-Answer Corpus Dataset for Chinese Medical Knowledge Large Language Models. 2024. doi: 10.12201/bmr.202404.00002

  fan chun, ma jie, xu anqi, xu yihan, shi jinlong. Data Model Design and Intelligent Applications of Health Profiling. 2024. doi: 10.12201/bmr.202402.00011

  Fang Pan, Cao Yu-Ting, Ding Zi-Xiao, Zhang Shun, Li Zhao-Rong, Zeng Zhen-Yu, Zhu Rui. Preliminary Study on the Construction and Application of Proactive Healthcare Knowledge Graph for the Elderly Population in Community Setting. 2023. doi: 10.12201/bmr.202303.00038

  niuyuxiang, geshanshan, wanglihua. Exploration and research of electronic medical record generation technology from traditional NLP to large language model. 2024. doi: 10.12201/bmr.202412.00080

• ID	Submit time	Number	Download
  1	2025-04-08	bmr.202508.00035V1	Download

• Public  Anonymous  To author only Submit Comments