可解释人工智能在疾病诊疗中的应用  

Explainable artificial intelligence in disease diagnosis and treatment

作　　者：井杰 王蓓蕾 刘善荣 JING Jie;WANG Beilei;LIUShanrong(Department of Clinical Laboratory,the First Affiliated Hospital of Naval Medical University,Shanghai 200433,China)

机构地区：[1]海军军医大学第一附属医院实验诊断科,上海200433

出　　处：《检验医学》2021年第9期976-980,共5页Laboratory Medicine

基　　金：上海市优秀学科带头人基金项目(18XD1405300)。

摘　　要：可解释人工智能(XAI)是基于人工智能(AI)原则构建的可被用户理解和信任的AI系统,在检验医学领域具有广阔的应用前景。文章立足于检验医学的研究现状,结合XAI的基本概念、重要性和实现方法,重点阐述基于知识图谱的XAI技术在检验医学领域的研究思路,并展望检验XAI在疾病诊疗中的应用前景,及其研发面临的挑战和应用局限性。Explainable artificial intelligence(XAI)refers to an artificial intelligence(AI)system based on some AI principles that can be understood and trusted by users,and has broad application prospects in the field of laboratory medicine.This review is based on the research status of clinical laboratory medicine,combined with the basic concepts,importance and implementation methods of XAI,focuses on the research ideas of XAI technology based on knowledge graphs in the field of clinical laboratory medicine,and looks forward to the application prospects of XAI in disease diagnosis and treatment,research challenges and application limitations.

关 键 词：可解释人工智能 检验医学 知识图谱 

分 类 号：R446[医药卫生—诊断学]