In recent years, an influx of articles in medicine and ophthalmology on artificial intelligence (AI) has appeared.

Deep learning, a recently described AI machine learning technique, when applied to image analysis, allows the algorithm to analyze data using multiple processing layers to extract different image features, with the lower processing layers recognizing basic features (e.g., the number and arrangement of edges of an image) and the higher layers identifying items more meaningful to human observers (e.g., nose, faces, disease lesions).

In ophthalmology, many groups have reported exceptional diagnostic performance using deep learning algorithms to detect various ocular conditions based on anterior segment topography (e.g., keratoconus), surgical videos (e.g., identification of phases in cataract surgeries), fundus photographs (e.g., diabetic retinopathy glaucoma, age-related macular degeneration, and retinopathy of prematurity), and anterior and posterior segment OCT (e.g., glaucoma and multiple retinal diseases).