Diabetic retinopathy (DR) is a highly prevalent cause of vision loss worldwide. Detection of DR requires substantial human resources and high medical costs. Therefore, the use of diagnostic software has been recently explored. The study aimed to assess the results of DR diagnoses by Cybersight, an artificial intelligence software. A total of 1,012 patients with type 2 diabetes mellitus (1,943 eyes) with a mean age of 74.61 ± 6.73 years were included. Comprehensive demographic and clinical data were gathered, and all patients underwent color fundus photography following Cybersight's standardized protocols. The study compared Cybersight's accuracy with that of ophthalmologists in identifying key DR lesions, including retinal microvascular changes, exudates, hemorrhages, the diagnosis and staging of DR, using sensitivity, specificity, and weighted Kappa metrics. The prevalence of DR was 16.2%. A high level of agreement was found between Cybersight and ophthalmologists in DR diagnosis, with a sensitivity of 85.0%, specificity of 95.8%, and a weighted Kappa of 0.78. The presence of cataracts and the degree of pupil dilation notably impacted on the accuracy of DR diagnosis. The results have important implications for the potential application of Cybersight as a low-cost and effective tool for diabetic eye screening.
Read full abstract7-days of FREE Audio papers, translation & more with Prime
7-days of FREE Prime access