Predicting 1, 2 and 3 year emergent referable diabetic retinopathy and maculopathy using deep learning

Abstract

Predicting diabetic retinopathy (DR) progression could enable individualised screening with prompt referral for high-risk individuals for sight-saving treatment, whilst reducing screening burden for low-risk individuals. We developed and validated deep learning systems (DLS) that predict 1, 2 and 3 year emergent referable DR and maculopathy using risk factor characteristics (tabular DLS), colour fundal photographs (image DLS) or both (multimodal DLS). From 162,339 development-set eyes from south-east London (UK) diabetic eye screening programme (DESP), 110,837 had eligible longitudinal data, with the remaining 51,502 used for pretraining. Internal and external (Birmingham DESP, UK) test datasets included 27,996, and 6928 eyes respectively. Internal multimodal DLS emergent referable DR, maculopathy or either area-under-the receiver operating characteristic (AUROC) were 0.95 (95% CI: 0.92–0.98), 0.84 (0.82–0.86), 0.85 (0.83–0.87) for 1 year, 0.92 (0.87–0.96), 0.84 (0.82–0.87), 0.85 (0.82–0.87) for 2 years, and 0.85 (0.80–0.90), 0.79 (0.76–0.82), 0.79 (0.76–0.82) for 3 years. External multimodal DLS emergent referable DR, maculopathy or either AUROC were 0.93 (0.88–0.97), 0.85 (0.80–0.89), 0.85 (0.76–0.85) for 1 year, 0.93 (0.89–0.97), 0.79 (0.74–0.84), 0.80 (0.76–0.85) for 2 years, and 0.91 (0.84–0.98), 0.79 (0.74–0.83), 0.79 (0.74–0.84) for 3 years. Multimodal and image DLS performance is significantly better than tabular DLS at all intervals. DLS accurately predict 1, 2 and 3 year emergent referable DR and referable maculopathy using colour fundal photographs, with additional risk factor characteristics conferring improvements in prognostic performance. Proposed DLS are a step towards individualised risk-based screening, whereby AI-assistance allows high-risk individuals to be closely monitored while reducing screening burden for low-risk individuals. Diabetic retinopathy (DR) is a disease where the light-sensing layer at the back of the eye (retina) becomes damaged by raised blood sugar levels. It affects around one in three of the 463 million people with diabetes worldwide and is a leading cause of acquired vision loss in working-age adults. In this study, we developed computer-based models to predict when DR would reach a stage where vision could be threatened up to 3-years in the future. Our study shows that this system can accurately predict sight-threatening DR in patients with diabetes. This could mean fewer unnecessary visits for individuals at low-risk of DR progression, but closer monitoring and potentially earlier treatment for individuals at high-risk of DR progression, which could reduce the risk of vision loss. Nderitu et al. present deep learning systems developed to predict emergent referable diabetic retinopathy and maculopathy over 1, 2 and 3 years. Using validated tabular, image and multimodal systems they aim to individualise risk-based screening.