Detecting visually significant cataract using retinal photograph-based deep learning
Yih Chung Tham, Jocelyn Hui Lin Goh, Ayesha Anees, Xiaofeng Lei, Tyler Hyungtaek Rim, Miao-Li Chee, Ya Xing Wang, Jost B. Jonas, Sahil Thakur, Zhen Ling Teo, Ning Cheung, Haslina Hamzah, Gavin Tan, Rahat Husain, Charumathi Sabanayagam, Jie Jin Wang, Qingyu Chen, Zhiyong Lu, Tiarnán D L Keenan, Emily Y. Chew, Ava Grace Tan, Paul Mitchell, Rick Siow Mong Goh, Xinxing Xu, Yong Liu, Tien Yin Wong, Ching‐Yu Cheng
Abstract
Age-related cataracts are the leading cause of visual impairment among older adults. Many significant cases remain undiagnosed or neglected in communities, due to limited availability or accessibility to cataract screening. In the present study, we report the development and validation of a retinal photograph-based, deep-learning algorithm for automated detection of visually significant cataracts, using more than 25,000 images from population-based studies. In the internal test set, the area under the receiver operating characteristic curve (AUROC) was 96.6%. External testing performed across three studies showed AUROCs of 91.6-96.5%. In a separate test set of 186 eyes, we further compared the algorithm's performance with 4 ophthalmologists' evaluations. The algorithm performed comparably, if not being slightly more superior (sensitivity of 93.3% versus 51.7-96.6% by ophthalmologists and specificity of 99.0% versus 90.7-97.9% by ophthalmologists). Our findings show the potential of a retinal photograph-based screening tool for visually significant cataracts among older adults, providing more appropriate referrals to tertiary eye centers.