BackgroundDiabetic retinopathy (DR) is a leading cause of vision impairment worldwide. With the increasing prevalence of diabetes, especially in low- and middle-income countries like India, early detection and intervention are critical to preventing blindness. This study evaluates the diagnostic accuracy of a portable, non-contact, handheld retinal camera compared to conventional tabletop fundus cameras for DR screening.ObjectiveTo assess the diagnostic accuracy, sensitivity, and specificity of a portable, non-contact handheld retinal camera in detecting diabetic retinopathy and to evaluate its practical utility for DR screening in resource-limited settings.MethodsA cross-sectional diagnostic evaluation was conducted at the Indian Institute of Diabetes, Thiruvananthapuram. 101 diabetic patients aged 18 years and above were enrolled, and retinal images were obtained using both a commercial tabletop TRC-NW8F fundus camera and a Bosch non-mydriatic handheld camera. Diagnostic performance metrics, including sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were calculated. ROC curve analysis was used to evaluate the overall performance of the handheld camera.ResultsOf the 191 eyes analyzed, the handheld retinal camera correctly identified 34 of the 46 newly diagnosed DR cases. The sensitivity was 73.9%, and specificity was 99.3%. The ROC curve demonstrated an area under the curve (AUC) of 0.976, indicating excellent discriminatory power. Subgroup analysis showed lower sensitivity for detecting mild non-proliferative diabetic retinopathy (NPDR) but achieved 100% sensitivity for detecting proliferative diabetic retinopathy (PDR).ConclusionsThe portable, non-contact handheld retinal camera demonstrated high specificity and overall diagnostic accuracy, making it a reliable and cost-effective tool for diabetic retinopathy screening, particularly in resource-limited settings.