Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (6): 1193-1213.DOI: 10.3778/j.issn.1673-9418.2111031

• Surveys and Frontiers • Previous Articles     Next Articles

Research and Development of Medical Knowledge Graph Reasoning

DONG Wenbo1, SUN Shiliang1,+(), YIN Minzhi2   

  1. 1. School of Computer Science and Technology, East China Normal University, Shanghai 200062, China
    2. Department of Pathology, Shanghai Children’s Medical Center, Shanghai Jiao Tong University School of Medicine, Shanghai 200127, China
  • Received:2021-11-04 Revised:2022-01-20 Online:2022-06-01 Published:2022-06-20
  • About author:DONG Wenbo, born in 1992, Ph.D. candidate. His research interests include pattern recognition and machine learning, knowledge graph reasoning, etc.
    SUN Shiliang, born in 1979, Ph.D., professor, Ph.D. supervisor, member of CCF. His research interests include multi-view learning, pattern recognition and machine learning.
    YIN Minzhi, born in 1970, chief physician. Her research interests include the pathological diagnosis of children’s tumors and the application of AI in pathological diagnosis.
  • Supported by:
    National Natural Science Foundation of China(62076096);Project of Shanghai Knowledge Service Platform(ZF1213)

医学知识推理研究现状与发展

董文波1, 孙仕亮1,+(), 殷敏智2   

  1. 1. 华东师范大学 计算机科学与技术学院,上海 200062
    2. 上海交通大学医学院 附属上海儿童医学中心病理科,上海 200127
  • 通讯作者: + E-mail: slsun@cs.ecnu.edu.cn
  • 作者简介:董文波(1992—),男,河南新乡人,博士研究生,主要研究方向为模式识别与机器学习、知识图谱推理等。
    孙仕亮(1979—),男,博士,教授,博士生导师,CCF会员,主要研究方向为多视图学习、模式识别、机器学习。
    殷敏智(1970—),女,浙江宁波人,主任医师,主要研究方向为儿童肿瘤的病理诊断、AI在病理诊断中的应用。
  • 基金资助:
    国家自然科学基金(62076096);上海知识服务平台项目(ZF1213)

Abstract:

Knowledge graphs can effectively organize and represent knowledge, which have been applied to many advanced applications, for example, intelligent medicine. However, the medical knowledge graphs constructed manually or automatically are usually incomplete, which seriously limits their performance. Medical knowledge reasoning can complete medical knowledge graph and assist doctors in medical diagnosis. This paper first gives the basic concept and definition of medical knowledge reasoning, and then summarizes the key technologies of constructing medical knowledge graphs and the auxiliary diagnosis methods based on medical knowledge reasoning. Subsequently, this paper reviews the research development of medical knowledge reasoning, and classifies its reasoning methods into rule-based medical reasoning, representation learning-based medical reasoning and deep learning-based medical reasoning. For each category, representative algorithms and newly proposed algorithms are presented. The main feature of this survey is that it provides a comprehensive introduction for the recent development of knowledge graph reasoning on the basis of coherence with early methods. Finally, this paper prospects the development of medical knowledge reasoning based on the major challenges and key problems faced by medical knowledge reasoning, hoping to promote further research in this rapidly developing field.

Key words: knowledge graph, intelligent medicine, knowledge reasoning, medical assistant diagnosis, medical knowledge completion

摘要:

知识图谱可以有效地组织和表示知识,被应用于很多高级应用中,比如智能医疗。然而,无论是人工还是自动化构建的医学知识图谱通常是不完整的,这严重限制了它们的使用性能。医学知识推理可以补全医学知识图谱,并可辅助医生进行医学诊断。首先给出了医学知识推理的基本概念和定义,然后对构建医学知识图谱的关键技术和基于医学知识推理的辅助诊断进行了总结与归纳,并重点回顾了医学知识推理研究现状,将其推理方法划分为基于逻辑规则的医学推理、基于表示学习的医学推理以及基于深度学习的医学推理。对于每一类别,分别介绍了代表性算法和最新研究进展。特点是在现有方法的基础上对基于医学知识图谱的推理技术进行了综合的介绍。最后总结了医学知识推理目前面对的一些挑战和重要问题,并展望了其发展前景和研究趋势,希望能促进这一快速发展领域的进一步研究。

关键词: 知识图谱, 智能医疗, 知识推理, 医学辅助诊断, 医学知识补全

CLC Number: