Diagnostic Accuracy of Automated Diabetic Retinopathy Image Assessment Softwares: IDx-DR and Medios Artificial Intelligence

Abstract Introduction: Numerous studies have demonstrated the use of artificial intelligence (AI) for early detection of referable diabetic retinopathy (RDR). A direct comparison of these multiple automated diabetic retinopathy (DR) image assessment softwares (ARIAs) is, however, challenging. We retrospectively compared the performance of two modern ARIAs, IDx-DR and Medios AI. Methods: In this retrospective-comparative study, retinal images with sufficient image quality were run on both ARIAs. They were captured in 811 consecutive patients with diabetes visiting diabetic clinics in Poland. For each patient, four non-mydriatic images, 45° field of view, i.e., two sets of one optic disc and one macula-centered image using Topcon NW400 were captured. Images were manually graded for severity of DR as no DR, any DR (mild non-proliferative diabetic retinopathy [NPDR] or more severe disease), RDR (moderate NPDR or more severe disease and/or clinically significant diabetic macular edema [CSDME]), or sight-threatening DR (severe NPDR or more severe disease and/or CSDME) by certified graders. The ARIA output was compared to manual consensus image grading (reference standard). Results: On 807 patients, based on consensus grading, there was no evidence of DR in 543 patients (67%). Any DR was seen in 264 (33%) patients, of which 174 (22%) were RDR and 41 (5%) were sight-threatening DR. The sensitivity of detecting RDR against reference standard grading was 95% (95% CI: 91, 98%) and the specificity was 80% (95% CI: 77, 83%) for Medios AI. They were 99% (95% CI: 96, 100%) and 68% (95% CI: 64, 72%) for IDx-DR, respectively. Conclusion: Both the ARIAs achieved satisfactory accuracy, with few false negatives. Although false-positive results generate additional costs and workload, missed cases raise the most concern whenever automated screening is debated.