大语言模型构建鼻炎医案知识图谱的应用研究

doi:10.3778/j.issn.1002-8331.2403-0379

摘要/Abstract

摘要： 将大语言模型用于医案的自动化知识抽取，构建国医大师干祖望治疗鼻炎知识图谱，为中医药领域的智能化发展提供新思路和方法。采用干祖望教授的临床医案数据作为基础样本，使用OWL（Web ontology language）构建本体模型，确定抽取对象与关系，再采用示范案例与关系列表结合的提示模板，引导大语言模型对医案数据进行自动化抽取实验，并使用Nebula Graph进行知识图谱的存储和可视化展示。与传统的知识抽取模型Bert-BiLSTM-CRF相比，ChatGPT4模型在综合指标上表现最佳，F1值达到82.75%，为快速处理非结构化医案数据提供了有效的解决方案，并实现了半自动化构建中医药领域知识图谱。利用大语言模型进行知识图谱构建，不仅为中医药领域的智能化提供了切实可行的方案，也为名老中医的诊疗经验传承和中医药知识图谱的快速构建贡献了新的研究思路，推动了中医药事业的发展。

关键词: 国医大师, 干祖望, 大语言模型, Nebula Graph

Abstract: An automated knowledge extraction method based on large language model is explored, aiming to construct a knowledge graph on the treatment of rhinitis by national medical master Gan Zuwang, and to provide innovative ideas and methods for the intelligent advancement in the field of traditional Chinese medicine. The clinical medical case data of professor Gan Zuwang are used as the base sample, and the ontology model is constructed using OWL (Web ontology language) to determine the extraction objects and relations, and then the prompt template combining the demonstration case and the relation list is used to guide the automated extraction experiments of the medical case data with the large language model, and the Nebula Graph is used for the storage and the visual display of the knowledge graph. Compared with the traditional knowledge extraction model Bert-BiLSTM-CRF, the ChatGPT4 model performs the best in terms of comprehensive indexes, with an F1 value of 82.75%, which provides an effective solution for the rapid processing of unstructured medical case data and achieves semi-automatic construction of knowledge graph in the field of Chinese medicine. The use of large language models for knowledge graph construction not only provides a practical solution for the intelligence in the field of Chinese medicine, but also contributes new research ideas for the inheritance of diagnostic and treatment experience of famous and veteran Chinese medicine practitioners and the rapid construction of the knowledge graph of Chinese medicine, which promotes the development of Chinese medicine.

Key words: national medical master, Gan Zuwang, large language model, Nebula Graph

李玥, 洪海蓝, 李文林, 杨涛. 大语言模型构建鼻炎医案知识图谱的应用研究[J]. 计算机工程与应用, 2025, 61(4): 167-175.

LI Yue, HONG Hailan, LI Wenlin, YANG Tao. Study on Application of Large Language Model in Constructing Knowledge Graph of Medical Cases of Rhinitis[J]. Computer Engineering and Applications, 2025, 61(4): 167-175.

参考文献

[1] GREINER A N, HELLINGS P W, ROTIROTI G, et al. Allergic rhinitis[J]. Lancet, 2011, 378(9809): 2112-2122.
[2] EIFAN A O, DURHAM S R. Pathogenesis of rhinitis[J]. Clinical & Experimental Allergy, 2016, 46(9): 1139-1151.
[3] CHENG L, CHEN J, FU Q, et al. Chinese society of allergy guidelines for diagnosis and treatment of allergic rhinitis[J]. Allergy, Asthma & Immunology Research, 2018, 10(4): 300-353.
[4] LU W. Advances on the treatment of allergic rhinitis by traditional Chinese medicine and western medicine[J]. Journal of Biosciences and Medicines, 2023, 11(4): 137-152.
[5] WANG C, YU H, WAN F. Information retrieval technology based on knowledge graph[C]//Proceedings of the 2018 3rd International Conference on Advances in Materials, Mechatronics and Civil Engineering, 2018: 291-296.
[6] YE Q, HSIEH C Y, YANG Z, et al. A unified drug-target interaction prediction framework based on knowledge graph and recommendation system[J]. Nature Communications, 2021, 12(1): 6775.
[7] YANG Z, WANG Y, GAN J, et al. Design and research of intelligent question-answering (Q&A) system based on high school course knowledge graph[J]. Mobile Networks and Applications, 2021, 26(5): 1884-1890.
[8] 杨涛, 王欣宇, 朱垚, 等. 大语言模型驱动的中医智能诊疗研究思路与方法[J]. 南京中医药大学学报, 2023, 39(10): 967-971.
YANG T, WANG X Y, ZHU Y, et al. Research ideas and methods of intelligent diagnosis and treatment of traditional Chinese medicine driven by large language model[J]. Journal of Nanjing University of Traditional Chinese Medicine, 2023, 39(10): 967-971.
[9] WANG L, MA C, FENG X, et al. A survey on large language model based autonomous agents[J]. Frontiers of Computer Science, 2024, 18(6): 186345.
[10] HOFFMANN J, BORGEAUD S, MENSCH A, et al. Training compute-optimal large language models[J]. arXiv:2203.15556, 2022.
[11] SHANAHAN M. Talking about large language models[J]. Communications of the ACM, 2024, 67(2): 68-79.
[12] TAYLOR R, KARDAS M, CUCURULL G, et al. Galactica: a large language model for science[J]. arXiv:2211.09085, 2022.
[13] WU M, YI X, YU H, et al. Nebula graph: an open source distributed graph database[J]. arXiv:2206.07278, 2022.
[14] 文森, 钱力, 胡懋地, 等. 基于大语言模型的问答技术研究进展综述[J]. 数据分析与知识发现, 2024, 8(6): 16-29.
WEN S, QIAN L, HU M D, et al. Review of research progress on question-answering techniques based on large language models[J]. Data Analysis and Knowledge Discovery, 2024, 8(6): 16-29.
[15] ORRù G, PIARULLI A, CONVERSANO C, et al. Human-like problem-solving abilities in large language models using ChatGPT[J]. Frontiers in Artificial Intelligence, 2023, 6: 1199350.
[16] KASNECI E, SESSLER K, STEFAN K, et al. ChatGPT for good? On opportunities and challenges of large language models for education[J]. Learning and Individual Differences, 2023, 103: 102274.
[17] FLORIDI L, CHIRIATTI M. GPT-3: its nature, scope, limits, and consequences[J]. Minds and Machines, 2020, 30(4): 681-694.
[18] WU T, HE S, LIU J, et al. A brief overview of ChatGPT: the history, status quo and potential future development[J]. IEEE/CAA Journal of Automatica Sinica, 2023, 10(5): 1122-1136.
[19] SHEN Y, SONG K, TAN X, et al. HuggingGPT: solving AI tasks with ChatGPT and its friends in hugging face[C]//Advances in Neural Information Processing Systems 36, 2023.
[20] 裴炳森, 李欣, 吴越. 基于ChatGPT的电信诈骗案件类型影响力评估[J]. 计算机科学与探索, 2023, 17(10): 2413-2425.
PEI B S, LI X, WU Y. Influence evaluation of telecom fraud case types based on ChatGPT[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(10): 2413-2425.
[21] YAO B W, JIANG M, YANG D Y, et al. Empowering LLM-based machine translation with cultural awareness[J]. arXiv:2305.14328, 2023.
[22] HERBOLD S, HAUTLI-JANISZ A, HEUER U, et al. A large-scale comparison of human-written versus ChatGPT-generated essays[J]. Scientific Reports, 2023, 13(1): 18617.
[23] HU Z Q, LI X Y, PAN X Y, et al. A question answering system for assembly process of wind turbines based on multi-modal knowledge graph and large language model[J]. Journal of Engineering Design, 2023. DOI:10.1080/09544828.2023.2272555.
[24] 张鹤译, 王鑫, 韩立帆, 等. 大语言模型融合知识图谱的问答系统研究[J]. 计算机科学与探索, 2023, 17(10): 2377-2388.
ZHANG H Y, WANG X, HAN L F, et al. Research on question answering system on joint of knowledge graph and large language models[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(10): 2377-2388.
[25] TANG R, HAN X, JIANG X, et al. Does synthetic data generation of LLMs help clinical text mining?[J]. arXiv:2303.04360, 2023.
[26] NOV O, SINGH N, MANN D. Putting ChatGPT’s medical advice to the (turing) test: survey study[J]. JMIR Medical Education, 2023, 9: e46939.
[27] CHEN S, KANN B, FOOTE M, et al. The utility of ChatGPT for cancer treatment information[J]. medRxiv, 2023. DOI:10.1101/2023.03.16.23287316.
[28] JEBLICK K, SCHACHTNER B, DEXL J, et al. ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports[J]. European Radiology, 2024, 34(5): 2817-2825.
[29] 王松, 李正钧, 杨涛, 等. 国医大师周仲瑛辨治肺癌的中医药本体构建研究[J]. 世界科学技术-中医药现代化, 2022, 24(2): 495-501.
WANG S, LI Z J, YANG T, et al. Study on construction of ontology for diagnosis and treatment of lung cancer by professor Zhou Zhongying in traditional Chinese medicine[J]. World Science and Technology-Modernization of Traditional Chinese Medicine, 2022, 24(2): 495-501.
[30] 黄贺瑄, 王晓燕, 顾正位, 等. 医学知识图谱构建技术及发展现状研究[J]. 计算机工程与应用, 2023, 59(13): 33-48.
HUANG H X, WANG X Y, GU Z W, et al. Research on construction technology and development status of medical knowledge graph[J]. Computer Engineering and Applications, 2023, 59(13): 33-48.
[31] MONTEIRO J, Sá F, BERNARDINO J. Experimental evaluation of graph databases: JanusGraph, Nebula Graph, Neo4j, and TigerGraph[J]. Applied Sciences, 2023, 13(9): 5770.