人工智能辅助诊断系统在宫颈细胞病理检查中的诊断性能评价  

Diagnostic performance evaluation of artificial intelligence-assisted diagnostic systems in cervical cytopathological examination

作　　者：叶子晨 杨怡晖 徐炼[3] 韦荣干[4] 阮细玲 薛鹏 江宇[1,6] 乔友林[1] Ye Zichen;Yang Yihui;Xu Lian;Wei Ronggan;Ruan Xiling;Xue Peng;Jiang Yu;Qiao Youlin(School of Population Medicine and Public Health,Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100730,China;Department of Pathology,Shenzhen Maternity and Child Healthcare Hospital,Southern Medical University,Shenzhen 518028,China;Department of Pathology,West China Second University Hospital,Sichuan University,Chengdu 610041,China;Department of Pathology,the People's Hospital of Guangxi Zhuang Autonomous Region,Nanning 530021,China;Department of Pathology,the First Affiliated Hospital of Hainan Medical University,Haikou 570102,China;School of Health Policy and Management,Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100730,China)

机构地区：[1]中国医学科学院北京协和医学院群医学及公共卫生学院,北京100730 [2]南方医科大学附属深圳市妇幼保健院病理科,深圳518028 [3]四川大学华西第二医院病理科,成都610041 [4]广西壮族自治区人民医院病理科,南宁530021 [5]海南医科大学第一附属医院病理科,海口570102 [6]中国医学科学院北京协和医学院卫生健康管理政策学院,北京100730

出　　处：《中华流行病学杂志》2025年第3期499-505,共7页Chinese Journal of Epidemiology

基　　金：博士后研究人员计划(GZB20230076);中国博士后科学基金(2024T170072);中国医学科学院医学与健康科技创新工程(2021-I2M-1-004)。

摘　　要：目的评价人工智能辅助诊断系统在宫颈细胞病理检查中的诊断性能。方法回顾性收集4家医院的宫颈细胞病理切片数据,对人工智能辅助诊断系统进行外部验证,然后利用前瞻性数据进行人机辅助研究。结果在回顾性研究中,共收集了3162名有效病例作为外部验证数据集,人工智能辅助诊断系统的曲线下面积(AUC)为0.890(95%CI:0.878~0.902),准确性为0.885(95%CI:0.873~0.896),灵敏度为0.928(95%CI:0.914~0.941),特异度为0.852(95%CI:0.834~0.867)。在前瞻性研究中,共收集了212名有效病例,5名低年资医生参与了人机辅助研究。医生独立诊断的AUC为0.686(95%CI:0.650~0.722),准确性为0.699(95%CI:0.671~0.727),灵敏度为0.653(95%CI:0.599~0.703),特异度为0.719(95%CI:0.685~0.750),Fleissκ值为0.510,阅片时间为223 s。在人工智能辅助诊断系统辅助下,医生的AUC、准确性、灵敏度和特异度分别提高了0.166、0.143、0.225和0.107,Fleissκ值为0.730,阅片时间减少了188 s,差异有统计学意义(均P<0.001)。结论人工智能辅助诊断系统的诊断性能优异,具有良好的泛化能力,且能显著提高低年资医生的诊断准确性、一致性和工作效率,可作为低年资医生在临床实践中的辅助工具。Objective To evaluate the diagnostic performance of artificial intelligence-assisted diagnostic systems in cervical cytopathological examination.Methods Cervical cytology slide data were retrospectively collected from four hospitals for the external validation of the developed artificial intelligence-assisted diagnostic system.Subsequently,prospective data collection was conducted for human-machine assisted studies.Results In the retrospective study,a total of 3162 valid samples were collected as external validation data.The system showed an area under the curve(AUC)of 0.890(95%CI:0.878-0.902),accuracy of 0.885(95%CI:0.873-0.896),sensitivity of 0.928(95%CI:0.914-0.941),and specificity of 0.852(95%CI:0.834-0.867).In the prospective study,212 valid samples were collected,and five junior cytologists participated in the human-machine assisted study.Without artificial intelligence assistance,the average AUC for the five cytologists was 0.686(95%CI:0.650-0.722),the accuracy was 0.699(95%CI:0.671-0.727),the sensitivity was 0.653(95%CI:0.599-0.703),the specificity was 0.719(95%CI:0.685-0.750),the Fleissκvalue was 0.510,and the reading time was 223 seconds.With artificial intelligence assistance,the AUC,accuracy,sensitivity,and specificity increased by 0.166,0.143,0.225,and 0.107,respectively.Additionally,Fleissκwas 0.730 and the reading time decreased by 188 seconds.All differences were statistically significant(all P<0.001).Conclusions Artificial intelligence-assisted diagnosis system shows excellent performance and good generalizability,significantly improving the diagnostic accuracy,consistency,and efficiency of junior cytologists.It can be an effective auxiliary tool for junior cytologists in clinical practice.

关 键 词：人工智能 宫颈癌 细胞病理学 外部验证 人机辅助 

分 类 号：R73[医药卫生—肿瘤]