Ophthalmology Science

To evaluate the performance of artificial intelligence (AI) systems embedded in a mobile, handheld retinal camera, with a single retinal image protocol, in detecting both diabetic retinopathy (DR) and more-than- mild diabetic retinopathy (mtmDR).

Participants underwent fundus photographs using a portable retinal camera (Phelcom Eyer). The captured images were automatically analyzed by deep learning algorithms retinal alteration score (RAS) and diabetic retinopathy alteration score (DRAS), consisting of convolutional neural networks trained on EyePACS data sets and fine-tuned using data sets of portable device fundus images. The ground truth was the classification of DR corresponding to adjudicated expert reading, performed by 3 certified ophthalmologists.

Of 327 analyzed patients (mean age, 57.0 16.8 years; mean diabetes duration, 16.3 9.7 years), 307 completed the study protocol. Sensitivity and specificity of the AI system were high in detecting any DR with DRAS (sensitivity, 90.48% [95% confidence interval (CI), 84.99%e94.46%]; specificity, 90.65% [95% CI, 84.54%e94.93%]) and mtmDR with the combination of RAS and DRAS (sensitivity, 90.23% [95% CI, 83.87%e 94.69%]; specificity, 85.06% [95% CI, 78.88%e90.00%]). The area under the receiver operating characteristic curve was 0.95 for any DR and 0.89 for mtmDR.

This study showed a high accuracy for the detection of DR in different levels of severity with a single retinal photo per eye in an all-in-one solution, composed of a portable retinal camera powered by AI. Such a strategy holds great potential for increasing coverage rates of screening programs, contributing to prevention of avoidable blindness.