The objective of this study is to apply an artificial intelligence algorithm to diagnose multi-retinal diseases in real-world settings. The effectiveness and accuracy of this algorithm are evaluated by sensitivity, specificity, positive predictive value, negative predictive value, and area under curve.

The objective of this study is to apply an artificial intelligence algorithm to diagnose referral diabetes retinopathy, referral age-related macular degeneration, referral possible glaucoma, pathological myopia, retinal vein occlusion, macular hole, macular epiretinal membrane, hypertensive retinopathy, myelinated fibers, retinitis pigmentosa and other retinal lesions from fundus photography. tic 45-degree fundus cameras, trained operators took binocular fundus photography on participants. Operators were then asked to identify gradable images and unload for algorithm diagnosis. The effectiveness and accuracy of this algorithm are evaluated by sensitivity, specificity, positive predictive value, negative predictive value, area under curve, and F1 score.

Inclusion Criteria:

• fundus photography around 45° field which covers optic disc and macula
• complete identification information

Exclusion Criteria:

• insufficient information for diagnosis

The study population is derived from an anonymous database that contains health examination results of the general population.