人工智能辅助外周血细胞形态学检查的中国专家共识  

Chinese expert consensus on artificial intelligence assisted morphology examination of peripheral blood cells

作　　者：白求恩精神研究会检验医学分会 中华医学会检验医学分会血液体液学组 中国医学装备协会检验医学分会基础检验设备学组 刘贵建[2] 王建中[3] 关明[4] 续薇[5] 李永哲[6] Medical Laboratory Diagnostics Branch Society of Bethune Spiritual Research Association;Laboratory Medicine Committee of Chinese Association of Integrative Medicine;Hematology and Body Fluid Group;Liu Guijian;Wang Jianzhong;Guan Ming

机构地区：[1]不详 [2]中国中医科学院广安门医院 [3]北京大学第一医院 [4]复旦大学附属华山医院 [5]吉林大学医学院第一附属医院 [6]中国医学科学院北京协和医院

出　　处：《中华检验医学杂志》2023年第3期243-258,共16页Chinese Journal of Laboratory Medicine

摘　　要：血细胞形态学检查在引起白细胞、红细胞、血小板变化的相关临床疾病诊疗过程中起着非常重要的作用,也是目前临床实验室血细胞分析的重要复检手段。人工显微镜下血细胞形态学检查被认为是标准方法,但存在的不足明显限制了其广泛开展和深入应用。人工智能辅助血细胞形态学检查具有检验效率高、重复性好、便于结果审核和确认等性能特点,但该技术方法还存在诸多不完善的方面,在应用时需要制定科学、规范、有效的检验流程和操作程序。为此白求恩精神研究会检验医学分会等3家学术团体组织专家结合文献学习和来自全国多家医疗机构的专家临床工作总结制定了本专家共识。共识包括术语和定义、标本采集和血涂片制备、血涂片染色、临床应用范围、检测系统的性能评估、阅片方式和数据采集、结果分析和报告、数据保存共享和再利用、检验人员的能力要求、标准化共10个方面的内容,提出了28条专家建议。Morphology examination of blood cells plays a vital role in diagnosing and treating various diseases that cause the changes in white blood cells,red blood cells and platelets.A review of the morphology is also an important method for blood cell analysis in clinical laboratories at present.Morphology examination of blood cells under an artificial microscope is considered a standard method,but its shortcomings obviously limit its extensive development and in-depth application.Artificial intelligence-assisted blood cell morphology examination has the characteristics of high efficiency,good repeatability,and convenience for review and confirmation of the results.However,there are still many imperfections in this technical method.It is necessary to formulate a scientific,standardized and effective examination and operation procedure.For this reason,three academic groups,including theMedical Laboratory Diagnostics Branch Society of Bethune Spiritual Research Association,organized experts to formulate this consensus based on literature study and clinical work summary of experts from many medical institutions across the country.It consists of 10 aspects,including terms and definitions,specimen collection and blood smear preparation,blood smear staining,clinical application scope,performance evaluation of the test system,blood smear reading mode,data collection,analysis and report,data preservation,sharing and reuse,ability requirements of laboratory personnel,and standardization.A total of 28 suggestions are put forward in this consensus.

关 键 词：人工智能 血细胞 形态学检查 自动化 性能评价 结果报告 专家共识 

分 类 号：R446.11[医药卫生—诊断学]