基于EMR的乳腺肿瘤知识图谱构建研究

摘要

As a new method to describe entities and their relationships,knowledge graph has been paid more and more attention in the medical field.However,most of the knowledge of the medical knowledge graph is derived from the open medical literature,and less related to the EMR electronic medical records.EMR electronic medical records cover the whole process of patient diagnosis and treatment with a wealth of medical facts,which is an important source of knowledge of medical knowledge graph.Therefore,this paper takes the specific disease of breast tumor as an example.According to the basic principle of knowledge graph technology,we firstly gave the definition of knowledge of breast tumors.Combined with the actual EMR electronic medical records data set of Ruijin Hospital Affiliated to Shanghai Jiaotong University School of Medicine,the knowledge of breast cancer medical facts was extracted from EMR by means of knowledge extraction technology.On this basis,a method for constructing knowledge map of breast tumors is proposed.%知识图谱作为一种描述实体及其联系的新方法,在医学领域也逐渐得到关注,出现了多种医学知识图谱.但是这些医学知识图谱的知识大多来源于公开的医学文献,较少涉及到EMR电子病历.EMR电子病历涵盖了医院各科室各病种的患者诊疗全过程数据,具有丰富的医疗事实知识,是医学知识图谱的重要知识来源.为此,以乳腺肿瘤这一具体病种为应用实例,结合知识图谱技术的基本原理,给出了乳腺肿瘤知识图谱的定义;结合上海交通大学医学院附属瑞金医院的实际EMR电子病历数据集,通过知识抽取技术从EMR中提取乳腺肿瘤医疗事实知识.在此基础上提出乳腺肿瘤知识图谱的构建方法.