Head to head comparison of diagnostic performance of three non-mydriatic cameras for Diabetic Retinopathy Screening with Artificial Intelligence

Abstract

Abstract Background Diabetic Retinopathy (DR) is a leading cause of blindness worldwide, affecting people with diabetes. The timely diagnosis and treatment of DR are essential in preventing vision loss. Non-mydriatic fundus cameras and artificial intelligence (AI) software have been shown to improve DR screening efficiency. However, few studies have compared the diagnostic performance of different non-mydriatic cameras and AI software. Methods This clinical study was conducted at the Endocrinology clinic of Akdeniz University with 900 diabetes patients who had not been diagnosed with DR but had diabetes already diagnosed. Fundus images of each patient were taken using three non-mydriatic fundus cameras without dilation, and EyeCheckup AI software was used to diagnose mtmDR, vtDR, and CSDME. The patients underwent dilation and 4-wide field fundus photography, and three retina specialists graded the images according to the Diabetic Retinopathy Treatment Preferred Practice Patterns of the American Academy of Ophthalmology. The study was pre-registered on clinicaltrials.gov with the ClinicalTrials.gov Identifier: NCT04805541. Results The Canon CR2 camera had an mtmDR diagnosis sensitivity and Specificity of 95.65% / 95.92%, the Topcon NW400 had 95.19% / 96.46%, and the Optomed Aurora had 90.48% / 97.21%. For vtDR, the Canon CR2 had a sensitivity and Specificity of 96.00% / 96.34%, the Topcon NW400 had 98.52% / 95.93%, and the Optomed Aurora had 95.12% / 98.82%. For CSDME, the Canon CR2 had a sensitivity and Specificity of 95.83% / 96.83%, the Topcon NW400 had 98.50% / 96.52%, and the Optomed Aurora had 94.93% / 98.95%. Conclusion These results demonstrate the potential of non-mydriatic fundus cameras and EyeCheckup software for diagnosing diabetic retinopathy. Each camera brand had varying degrees of sensitivity and Specificity. The Canon CR2 had the highest sensitivity and Specificity for mtmDR and vtDR, whereas the Topcon NW400 had the highest sensitivity and Specificity for CSDME. These findings suggest that clinicians should consider camera brand when selecting a screening tool for DR. Further studies are needed to confirm these results and investigate other factors affecting DR screening efficiency.