Clinical Ophthalmology (Aug 2022)
Towards a Device Agnostic AI for Diabetic Retinopathy Screening: An External Validation Study
Abstract
Divya Parthasarathy Rao,1 Manavi D Sindal,2 Sabyasachi Sengupta,3 Prabu Baskaran,4 Rengaraj Venkatesh,2 Anand Sivaraman,5 Florian M Savoy6 1Artificial Intelligence R&D, Remidio Innovative Solutions Inc, Glen Allen, VA, USA; 2Vitreoretinal Services, Aravind Eye Hospitals and Postgraduate Institute of Ophthalmology, Pondicherry, India; 3Department of Retina, Future Vision Eye Care and Research Center, Mumbai, India; 4Vitreoretinal Services, Aravind Eye Hospitals and Postgraduate Institute of Ophthalmology, Chennai, India; 5Artificial Intelligence R&D, Remidio Innovative Solutions Pvt Ltd, Bangalore, India; 6Artificial Intelligence R&D, Medios Technologies, SingaporeCorrespondence: Divya Parthasarathy Rao, Artificial Intelligence R&D, Remidio Innovative Solutions Inc, 11357 Nuckols Road, #102, Glen Allen, VA, 23059, USA, Tel +1 855 513-3335, Email [email protected]: To evaluate the performance of a validated Artificial Intelligence (AI) algorithm developed for a smartphone-based camera on images captured using a standard desktop fundus camera to screen for diabetic retinopathy (DR).Participants: Subjects with established diabetes mellitus.Methods: Images captured on a desktop fundus camera (Topcon TRC-50DX, Japan) for a previous study with 135 consecutive patients (233 eyes) with established diabetes mellitus, with or without DR were analysed by the AI algorithm. The performance of the AI algorithm to detect any DR, referable DR (RDR Ie, worse than mild non proliferative diabetic retinopathy (NPDR) and/or diabetic macular edema (DME)) and sight-threatening DR (STDR Ie, severe NPDR or worse and/or DME) were assessed based on comparisons against both image-based consensus grades by two fellowship trained vitreo-retina specialists and clinical examination.Results: The sensitivity was 98.3% (95% CI 96%, 100%) and the specificity 83.7% (95% CI 73%, 94%) for RDR against image grading. The specificity for RDR decreased to 65.2% (95% CI 53.7%, 76.6%) and the sensitivity marginally increased to 100% (95% CI 100%, 100%) when compared against clinical examination. The sensitivity for detection of any DR when compared against image-based consensus grading and clinical exam were both 97.6% (95% CI 95%, 100%). The specificity for any DR detection was 90.9% (95% CI 82.3%, 99.4%) as compared against image grading and 88.9% (95% CI 79.7%, 98.1%) on clinical exam. The sensitivity for STDR was 99.0% (95% CI 96%, 100%) against image grading and 100% (95% CI 100%, 100%) as compared against clinical exam.Conclusion: The AI algorithm could screen for RDR and any DR with robust performance on images captured on a desktop fundus camera when compared to image grading, despite being previously optimized for a smartphone-based camera.Keywords: smartphone, Deep Learning, retina, imaging, screening
