Author(s)

Jinzhu Yang ¹

Affiliation(s)

¹ Dyania Health Inc, 525 Washington Blvd Suite 300, Jersey City, 07310, NJ, USA

Corresponding Author

Jinzhu Yang

ABSTRACT

This article proposes an innovative comprehensive framework that deeply integrates Large Language Models (LLM) with Knowledge Graphs (KG) to meet the urgent need for high-quality professional knowledge in medical question answering systems. We have fully utilized the triplet data structure of the knowledge graph, which effectively enhances the professional knowledge foundation of LLM in the medical field and significantly enhances its explanatory power. By accurately aligning the output of LLM with relevant information in KG, this method achieves dual verification and enhancement of model output accuracy and consistency, greatly improving the security and reliability of medical question answering systems. The experimental results show that the method proposed in this article exhibits significant advantages in accuracy and reliability compared to traditional knowledge base question answering (KBQA) systems and single LLM methods. This achievement provides a more efficient and accurate solution for the field of medical knowledge services, and this study also demonstrates the enormous potential and prospects of integrating LLM and KG in medical text mining and knowledge extraction.

KEYWORDS

LLM, Knowledge Base Q&A System, Professional Knowledge Background, Medical Knowledge Services, Triple Data Structures, Model Output Validation

CITE THIS PAPER

Jinzhu Yang, Integrated Application of LLM Model and Knowledge Graph in Medical Text Mining and Knowledge Extraction. Social Medicine and Health Management (2024) Vol. 5: 56-62. DOI: http://dx.doi.org/10.23977/socmhm.2024.050208.

REFERENCES

[1] Zhang Heyi, Wang Xin, Han Lifan, et al. Big language model applying knowledge map of question answering system research. Journal of computer science and exploration, 2023, 17 (10): 2377-2388. The DOI: 10.3778 / j.i SSN. 1673-9418.2308070.
[2] Huang Bo, Wu Shenao, Wang Wenguang, et al. Complementation of graph and model: a review on fusion of Knowledge graph and large model. Journal of Wuhan University (Science Edition), 2024.
[3] Xing Zhenchang, Wan Zhenyu, Wang Changjing, et al. A method and system for querying and clarifying knowledge-guided large language model for API recommendation: CN202310661769.7. CN116776895A [2024-07-06].
[4] Pan Yudai, Zhang Lingling, CAI Zhongmin, et al. Knowledge map based on large-scale language model differentiable rules extraction. Journal of computer science and exploration, 2023, 17 (10): 2403-2412. The DOI: 10.3778 / j.i SSN. 1673-9418.2306049.
[5] Anonymous." Construction method of Mold Professional Question and answer System based on LLM model", CN117909458A.2024.
[6] Cao Yi, Zhang Li, Guo Jing, et al. The development and application prospect of low-carbon electricity market based on large language model. Smart Power, 2024, 52 (2): 8-16.
[7] Ye Luchen, Fan Yuan, Wang Xin, et al. Research on content detection algorithm and bypass mechanism of large language model. Information Security Research, 2023, 9 (6): 524-532. (in Chinese)
[8] Varatharajah, Y., Chen, H., Trotter, A., & Iyer, R. K. (2020). A Dynamic Human-in-the-loop Recommender System for Evidence-based Clinical Staging of COVID-19. In HealthRecSys@ RecSys (pp. 21-22).
[9] Chen, H., Varatharajah, Y., de Ramirez, S. S., Arnold, P., Frankenberger, C., Hota, B., & Iyer, R. (2020). A retrospective longitudinal study of COVID-19 as seen by a large urban hospital in Chicago. medRxiv, 2020-11.
[10] Guo Pengrui, Wen Tingxiao. Big language model of information retrieval system and user behavioral impact study. Journal of agricultural information, 2023, 35 (11): 13-22. DOI: 10.13998 / j.carol carroll nki issn1002-1248.23-0573.
[11] Yan Debiao. Design and implementation of medical question answering system based on Knowledge graph. Information and Computer, 2023, 35 (13): 123-125. (in Chinese) 
[12] Bao Yong, Feng Yuanyuan, Xie Qing, et al. Discussion on hot spots and emerging fields of medical consortium research based on knowledge graph. Chinese Public Health Administration, 2022 (001): 038.

Sponsors, Associates, and Links

---

• Information Systems and Economics
  
  
• Accounting, Auditing and Finance
  
  
• Industrial Engineering and Innovation Management
  
  
• Tourism Management and Technology Economy
  
  
• Journal of Computational and Financial Econometrics
  
  
• Financial Engineering and Risk Management
  
  
• Accounting and Corporate Management
  
  
• Social Security and Administration Management
  
  
• Population, Resources & Environmental Economics
  
  
• Statistics & Quantitative Economics
  
  
• Agricultural & Forestry Economics and Management
  
  
• Land Resource Management
  
  
• Information, Library and Archival Science
  
  
• Journal of Human Resource Development
  
  
• Manufacturing and Service Operations Management
  
  
• Operational Research and Cybernetics