 This study developed an artificial intelligence, AI, machine learning model to predict the development of diabetic retinopathy, DR, from fundus imagery of otherwise healthy eyes. The model achieved an area under receiver operating curve, AUC, of 0.81 when averaging scores from multiple images, and 0.76 when using a single image. These results suggest that the model could potentially be used to identify individuals at risk for developing referable DR. This article was authored by Tsuncho Ayancholev, Rochelle Aviv, Yovle Rom, and others.