计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (10): 2219-2233.DOI: 10.3778/j.issn.1673-9418.2112118

• 综述·探索 • 上一篇    下一篇

中文医学知识图谱研究及应用进展

范媛媛, 李忠民+()   

  1. 中南大学 生命科学学院,长沙 410013
  • 收稿日期:2021-12-29 修回日期:2022-05-13 出版日期:2022-10-01 发布日期:2022-10-14
  • 通讯作者: + E-mail: tmbs300600@163.com
  • 作者简介:范媛媛(1997—),女,河南孟州人,硕士研究生,主要研究方向为信息组织、知识图谱。
    李忠民(1971—),女,湖南邵阳人,博士,副教授,硕士生导师,主要研究方向为医学信息学、医学信息组织。
  • 基金资助:
    中南大学中央高校基本科研业务费专项资金(2021zzts0558);湖南省研究生科研创新项目(CX20210122)

Research and Application Progress of Chinese Medical Knowledge Graph

FAN Yuanyuan, LI Zhongmin+()   

  1. College of Life Science, Central South University, Changsha 410013, China
  • Received:2021-12-29 Revised:2022-05-13 Online:2022-10-01 Published:2022-10-14
  • About author:FAN Yuanyuan, born in 1997, M.S. candidate. Her research interests include organization of information and knowledge graph.
    LI Zhongmin, born in 1971, Ph.D., associate professor, M.S. supervisor. Her research interests include medical informatics and medical information organization.
  • Supported by:
    Fundamental Research Funds for the Central Universities of Central South University(2021zzts0558);Postgraduate Scientific Research Innovation Project of Hunan Province(CX20210122)

摘要:

知识图谱是赋予机器背景知识的大规模语义网络。利用知识图谱对多源异构的医学信息进行有序化组织,能有效提升海量医学资源的利用价值,推动医学智能化发展。从知识图谱的关键技术、医学知识图谱构建以及医学知识图谱的应用三个维度刻画医学领域知识图谱研究、构建与应用现状,探索未来值得研究的课题。首先,系统梳理知识表示、知识抽取、知识融合以及知识推理四种知识图谱构建关键技术的发展脉络并探讨其研究进展,分析中文医学知识图谱构建的技术难点;其次,从医学本体、全科医学知识图谱和单病种医学知识图谱三个角度阐述中文医学知识图谱已有研究并分析了中文医学知识图谱的研究特点;最后,对中文医学知识图谱在语义搜索、决策支持以及智能问答等方面的应用研究进行分析并探讨新的应用场景。针对中文医学知识图谱研究面临的术语标准化程度不高、标注语料缺乏、技术研究不够深入以及应用场景有局限性等挑战,对其未来的研究方向做出了展望。

关键词: 医学知识图谱, 知识表示, 知识抽取, 决策支持, 智能问答

Abstract:

Knowledge graph is a large-scale semantic network that gives machine background knowledge. Using knowledge graph to organize heterogeneous medical information can effectively improve the utilization value of massive medical resources and promote the development of medical intelligence. This paper describes the research, construction and application status of knowledge graph in medical field from three dimensions: the key technology of knowledge graph, the construction of medical knowledge graph and the application of medical knowledge graph, and explores the topics worthy of research in the future. Firstly, the development of knowledge representation, knowledge extraction, knowledge fusion and knowledge inference are systematically summarized, their latest progress is discussed, and the technical difficulties in the construction of Chinese medical knowledge graph are analyzed. Secondly, the existing research on Chinese medical knowledge graph is illustrated from three perspectives of medical ontology, general practice knowledge graph and single disease medical knowledge graph. The research characteristics of Chinese medical knowledge graph are also analyzed. Finally, the application of medical know-ledge graph in semantic search, decision support and intelligent question answering are analyzed, and the new app-lication scenarios are discussed. In view of the challenges faced by Chinese medical knowledge graph, such as low standardization of terminology, lack of annotated corpus, insufficient technical research and limitations of applica-tion scenarios, the future research directions of Chinese medical knowledge graph are prospected.

Key words: medical knowledge graph, knowledge representation, knowledge extraction, decision support, intelli-gent question answering

中图分类号: