Zhang Wen-Fei, Li Dong-Hong, Wei Qi-Jie, Ding Da-Yong, Meng Li-Hui, Wang Yue-Lin, Zhao Xin-Yu, Chen You-Xin
Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, China.
Key Laboratory of Ocular Fundus Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
Front Med (Lausanne). 2022 May 16;9:839088. doi: 10.3389/fmed.2022.839088. eCollection 2022.
To evaluate the performance of a deep learning (DL)-based artificial intelligence (AI) hierarchical diagnosis software, EyeWisdom V1 for diabetic retinopathy (DR).
The prospective study was a multicenter, double-blind, and self-controlled clinical trial. Non-dilated posterior pole fundus images were evaluated by ophthalmologists and EyeWisdom V1, respectively. The diagnosis of manual grading was considered as the gold standard. Primary evaluation index (sensitivity and specificity) and secondary evaluation index like positive predictive values (PPV), negative predictive values (NPV), etc., were calculated to evaluate the performance of EyeWisdom V1.
A total of 1,089 fundus images from 630 patients were included, with a mean age of (56.52 ± 11.13) years. For any DR, the sensitivity, specificity, PPV, and NPV were 98.23% (95% CI 96.93-99.08%), 74.45% (95% CI 69.95-78.60%), 86.38% (95% CI 83.76-88.72%), and 96.23% (95% CI 93.50-98.04%), respectively; For sight-threatening DR (STDR, severe non-proliferative DR or worse), the above indicators were 80.47% (95% CI 75.07-85.14%), 97.96% (95% CI 96.75-98.81%), 92.38% (95% CI 88.07-95.50%), and 94.23% (95% CI 92.46-95.68%); For referral DR (moderate non-proliferative DR or worse), the sensitivity and specificity were 92.96% (95% CI 90.66-94.84%) and 93.32% (95% CI 90.65-95.42%), with the PPV of 94.93% (95% CI 92.89-96.53%) and the NPV of 90.78% (95% CI 87.81-93.22%). The kappa score of EyeWisdom V1 was 0.860 (0.827-0.890) with the AUC of 0.958 for referral DR.
The EyeWisdom V1 could provide reliable DR grading and referral recommendation based on the fundus images of diabetics.
评估基于深度学习（DL）的人工智能（AI）分级诊断软件EyeWisdom V1用于糖尿病视网膜病变（DR）的性能。
这项前瞻性研究是一项多中心、双盲、自身对照的临床试验。非散瞳后极部眼底图像分别由眼科医生和EyeWisdom V1进行评估。将人工分级诊断视为金标准。计算主要评估指标（敏感性和特异性）以及次要评估指标，如阳性预测值（PPV）、阴性预测值（NPV）等，以评估EyeWisdom V1的性能。
共纳入630例患者的1089张眼底图像，平均年龄为（56.52±11.13）岁。对于任何DR，敏感性、特异性、PPV和NPV分别为98.23%（95%CI 96.93 - 99.08%）、74.45%（95%CI 69.95 - 78.60%）、86.38%（95%CI 83.76 - 88.72%）和96.23%（95%CI 93.50 - 98.04%）；对于威胁视力的DR（STDR，重度非增殖性DR或更严重情况），上述指标分别为80.47%（95%CI 75.07 - 85.14%）、97.96%（95%CI 96.75 - 98.81%）、92.38%（95%CI 88.07 - 95.50%）和94.23%（95%CI 92.46 - 95.68%）；对于转诊DR（中度非增殖性DR或更严重情况），敏感性和特异性分别为92.96%（95%CI 90.66 - 94.84%）和93.32%（95%CI 90.65 - 95.42%），PPV为94.93%（95%CI 92.89 - 96.53%），NPV为90.78%（95%CI 87.81 - 93.22%）。EyeWisdom V1对于转诊DR的kappa评分为0.860（0.827 - 0.890），AUC为0.958。
EyeWisdom V1可根据糖尿病患者的眼底图像提供可靠的DR分级和转诊建议。
