眼底病专业医师、非眼底病专业医师和AI软件在眼底阅片诊断中的敏感性和特异性  

The sensitivity and sepecificity of fundus disease specialist doctors non-fundus disease specialist doctors,and AI software in fundus image interpretation

作　　者：薛文文 方晓玲 陈霞 索燕 陶津华 王于蓝[1] XUE Wenwent;FANG Xiaoling;CHEN Xia;SUO Yan;TAO Jinhua;WANG Yulans(Department of Ophthalmology,Shanghai Eye Disease Prevention and Treatment Center/Shanghai Ophthalmology Hospital,Shanghai 200040,CHN)

机构地区：[1]上海市眼病防治中心/上海市眼科医院眼科,上海200040

出　　处：《河南大学学报（医学版）》2024年第6期434-439,共6页Journal of Henan University:Medical Science

基　　金：上海市眼病防治中心院级临床课题(21LC01003)。

摘　　要：目的:分析比较眼底病专业医师与非眼底病专业医师及人工智能辅助诊断软件,三者眼底读片的一致性。方法:收集523例眼底病患者共750张眼底图像,由眼底病专业医师、非眼底病专业医师和AI辅助软件对其进行阅片诊断,另设专家组诊断结果为金标准,分析比较其的敏感性和特异性。结果:眼底图像中左眼、右眼构成为51.54%和48.46%;经金标准阅片,其中有糖尿病性视网膜病变75例、黄斑水肿14例、老年性黄斑变性56例,视网膜静脉阻塞71例,黄斑前膜12例,病理性近视317例,其他147例。评判指标阴性定义为未检出需转诊或诊断的眼底疾病,阳性定义为检出需转诊或其他疾病。多种眼底病的诊断性能结果:眼底病专业医生组的诊断敏感性Se=93.80%(91.62%,95.55%),特异性S_(p)=55.26%(45.66%,64.58%);非眼底病专业医生组的诊断敏感性Se=86.33%(83.39%,88.92%),特异性S_(p)=85.96%(78.21%,91.76%);AI组的诊断敏感性Se=83.31%(80.17%,86.13%),特异性S_(p)=79.24%(70.28%,86.51%)。眼底病专业医生组的诊断敏感性高于非眼底病专业医生组和AI组,非眼底病专业组的诊断特异性高于眼底专业组和AI组。AI辅助软件在眼科多病种的总体诊断应用的灵敏度较高、在单组目标值和非眼底医师对照时满足设计要求,但特异度在各指标设计中均未达到设计标准。结论:研究中的眼底病专业医生和非眼底病专业医生的工作年限和门诊量基本相同,参加的临床研究也基本相同,而眼底病专业组医生曾经接受过快速大量的眼底图片读片专门训练,这一点很可能是诊断敏感性高的主要原因。AI软件在多种眼底病总体诊断中特异性和敏感性较好,可以辅助训练眼底病专业医生的眼底病阅片能力,为培养年轻医生提供新思路。Objective:This study aims to analyze and compare the consistency of fundus image interpretation among professional fundus disease doctors,non-professional fundus disease doctors,and artificial intelligence-assisted diagnostic software.Methods:A total of 750 fundus images from 523 patients with fundus diseases were collected.These images were diagnosed by a professional group of fundus disease doctors,a non-professional group of fundus disease doctors,and Al-assisted software.The expert group's diagnosis results were used as the gold standard.The sensitivity and specificity of the different diagnostic groups were analyzed and compared.Results:Among the images,the left and right eye compositions were 51.54%and 48.46%,respectively.According to the gold standard,there were 75 cases of diabetie retinopathy,14 cases of macular edema,56 cases of age-related macular degeneration.71 cases of retinal vein occlusion,12 cases of macular epiretinal membrane,317 cases of pathological myopia,and 147 other cases.Negative evaluation criteria were defined as no detection of fundus diseases requiring referral or diagnosis,and positive criteria were defined as the detection of fundus diseases requiring referral or other diseases.The diagnostic performance results for various fundus diseases are as follows:The diagnostic sensitivity(S_(p))of the fundus disease specialist group was 93.80%(91.62%,95.55%),and the specificity(S_(p))was 55.26%(45.66%,64.58%).The diagnostic sensitivity(S_(p))of the non-ophthalmologists group was 86.33%(83.39%,88.92%),and the specificity(S_(p))was 85.96%(78.21%,91.76%).The diagnostic sensitivity(S_(p))of the AI group was 83.31%(80.17%,86.13%),and the specificity(S_(p))was 79.24%(70.28%,86.51%).The diagnostic sensitivity of the professional group of fundus disease doctors was higher than that of the non-fundus disease professional group and the AI group,while the diagnostic specificity of the non-fundus disease professional group was higher than that of the fundus disease professional group and the Al group.

关 键 词：人工智能 眼底病 眼底阅片 眼科医师 

分 类 号：R774[医药卫生—眼科]