Diabetic retinopathy (DR) and diabetic macular edema (DME) remain major causes of vision loss among working-age adults. Artificial intelligence (AI), particularly deep learning, has gained attention in ophthalmic imaging, offering opportunities to improve both diagnostic accuracy and efficiency. This review examined applications of AI in DR and DME published between 2010 and 2025. A narrative search of PubMed and Google Scholar identified English-language, peer-reviewed studies, with additional screening of reference lists. Eligible articles evaluated AI algorithms for detection, classification, prognosis, or treatment monitoring, with study selection guided by PRISMA 2020. Of 300 records screened, 60 met the inclusion criteria. Most reported strong diagnostic performance, with sensitivities up to 96% and specificities up to 98% for detecting referable DR on fundus photographs. Algorithms trained on optical coherence tomography (OCT) data showed high accuracy for identifying DME, with area under the receiver operating characteristic curve (AUC) values frequently exceeding 0.90. Several models also predicted anti-vascular endothelial growth factor (anti-VEGF) treatment response and recurrence of fluid with encouraging results. Autonomous AI tools have gained regulatory approval and have been implemented in clinical practice, though performance can vary depending on image quality, device differences, and patient populations. Overall, AI demonstrates strong potential to improve screening, diagnostic consistency, and personalized care, but broader validation and system-level integration remain necessary.
Jukić et al. (2025) studied this question.