Chiang M, Guth D, Pardeshi AA, et al. - In this retrospective cross-sectional study, researchers sought to compare the performance of a novel convolutional neural network (CNN) classifier and human graders in detecting angle closure in EyeCam goniophotographs. Participants from the Chinese American Eye Study (CHES) underwent EyeCam goniophotography in four angle quadrants. Using 29,706 open and 2,929 closed angle images, the CNN classifier was developed. A CNN classifier can efficiently identify angle closure in goniophotographs with performance similar to that of an experienced glaucoma specialist. This offers an automated approach for promoting remote detection of patients at risk for primary angle closure glaucoma (PACG).