Natarajan S, et al. - In this prospective, cross-sectional, population-based study, researchers assessed the performance of Medios artificial intelligence (AI) (Remidio), a proprietary, offline, smartphone-based, automated system of analysis of retinal images, to identify referable diabetic retinopathy (RDR; defined as any retinopathy more severe than mild diabetic retinopathy, with or without diabetic macular edema) in images taken by a minimally trained healthcare worker with Remidio Non-Mydriatic Fundus on Phone, a smartphone-based, nonmydriatic retinal camera. Of the 255 patients seen in the dispensaries, 231 patients consented to screen for diabetic retinopathy. Investigators found that the sensitivity and specificity of the study for diagnosing RDR were 100.0% and 88.4%, respectively, and the sensitivity and specificity for any diabetic retinopathy were 85.2% and 92.0%, respectively. Unwillingness to wait for screening and the blurring of vision that would occur after dilation were the major reasons for not partaking. This investigation proposes that the use of offline AI and a smartphone-based, nonmydriatic retinal imaging system could be used to monitor for RDR.