Efficacy of an Automated Algorithm for Screening Diabetic Retinopathy in Gradable and Ungradable Images in Real-Time Conditions.

Background: To examine the effectiveness of a computer-assisted device (CAD) for diabetic retinopathy (DR) screening from retinal photographs at a vitreoretinal outpatient department (VR OPD), telecamps, and diabetes outpatient clinic by an ophthalmologist. In particular, the effectiveness of CAD in gradable and ungradable retinal images was examined. Methods: A total of 848 eyes of 485 patients underwent 45° retinal photographs at the VR OPD of a tertiary care hospital in southern India. A total of 939 eyes of 472 patients with diabetes were examined in the telecamps conducted in remote villages in Tamil Nadu, a state in southern India. A total of 2,526 eyes of 1,263 patients were examined in a diabetes clinic using 45° field retinal photographs. The algorithm was validated under physiological dilatation (without pharmacological dilatation) in all three arms. Results: Seventy-one percent of 848 eyes in VR OPD, 13% of 939 eyes in telecamps, and 7% of 2,526 eyes in diabetes clinic were diagnosed to have DR. The algorithm showed 78.3% sensitivity and 55.1% specificity for all images and 78.9% sensitivity and 56.8% specificity for gradable images in the VR OPD; 80.1% sensitivity and 79.2% specificity for all images and 84.8% sensitivity and 80.0% sensitivity for gradable images in telecamps; 63.0% sensitivity and 79.6% specificity for all images and 63.2% sensitivity and 78.1% specificity for gradable images in the diabetes clinic. The algorithm had an overall accuracy of 76.4%. The ungradable rate was variable. Conclusion: The algorithm performs equally well in identifying DR from gradable and ungradable photographs and may be used for DR screening in a rural setting with limited or no access to eye care. [ABSTRACT FROM AUTHOR]