Artificial Intelligence for Screening of Multiple Retinal and Optic Nerve Diseases

作者：Li Dong, Wanji He, Ruiheng Zhang, Zongyuan Ge, Ya Xing Wang, Jinqiong Zhou, Jie Xu, Lei Shao, Qian Wang, Yanni Yan, Ying Xie, Li-Jian Fang, Haiwei Wang, Yenan Wang, Xiaobo Zhu, Jinyuan Wang, Chuan Zhang, Heng Wang, Yining Wang, Rongtian Chen, Qianqian Wan, Jing Yang, Wen‐Da Zhou, Heyan Li, Xuan Yao, Zhiwen Yang, Jianhao Xiong, Xin Wang, Yelin Huang, Yuzhong Chen, Zhaohui Wang, Ce Rong, Jianxiong Gao, Huiliang Zhang, Shouling Wu, Jost B. Jonas, Wen Bin Wei · 发表于：JAMA Network Open · 年份：2022 · DOI：10.1001/jamanetworkopen.2022.9960 · 被引用次数：154 · 研究领域：Retinal Imaging and Analysis、Retinal and Optic Conditions、Ocular Diseases and Behçet’s Syndrome

Importance: The lack of experienced ophthalmologists limits the early diagnosis of retinal diseases. Artificial intelligence can be an efficient real-time way for screening retinal diseases. Objective: To develop and prospectively validate a deep learning (DL) algorithm that, based on ocular fundus images, recognizes numerous retinal diseases simultaneously in clinical practice. Design, Setting, and Participants: This multicenter, diagnostic study at 65 public medical screening centers and hospitals in 19 Chinese provinces included individuals attending annual routine medical examinations and participants of population-based and community-based studies. Exposures: Based on 120 002 ocular fundus photographs, the Retinal Artificial Intelligence Diagnosis System (RAIDS) was developed to identify 10 retinal diseases. RAIDS was validated in a prospective collected data set, and the performance between RAIDS and ophthalmologists was compared in the data sets of the population-based Beijing Eye Study and the community-based Kailuan Eye Study. Main Outcomes and Measures: The performance of each classifier included sensitivity, specificity, accuracy, F1 score, and Cohen κ score. Results: In the prospective validation data set of 208 758 images collected from 110 784 individuals (median [range] age, 42 [8-87] years; 115 443 [55.3%] female), RAIDS achieved a sensitivity of 89.8% (95% CI, 89.5%-90.1%) to detect any of 10 retinal diseases. RAIDS differentiated 10 retinal diseases with acc...