Answers are grounded in this paper and cite their sources.
Objective: To compare the results obtained for the detection of diabetic retinopathy through artificial intelligence and fundus assessment by indirect ophthalmoscopy in patients with type 2 DM.Methods: Cross-sectional, descriptive, prospective, monocentric study, in which indirect ophthalmoscopy was assessed, and the results were compared by artificial intelligence for the detection of diabetic retinopathy.Results: Detection of diabetic retinopathy using artificial intelligence has a sensitivity of 100%, a specificity of 97%, a positive predictive value of 94% and a negative predictive value of 100%, taking the physical examination as a reference.Conclusions: No differences were found in the detection of diabetic retinopathy when comparing both methods, with clinical assessment being of notable importance owing to AI can exclude a certain number of patients.
No takes yet. Share an insight, caveat, or question.
Lugo-Sánchez et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: