Clinical validation of artificial intelligence-based cataract screening solution with smartphone images (Logy AI cataract screening module)

Abstract

Background: Purpose of the study was to clinically assess the accuracy of Logy AI cataract screening solution, an artificial intelligence-based module, which works through WhatsApp and also as a separate smart phone application, that can detect cataracts using images taken by a smartphone camera, by comparing with slit lamp based diagnoses made by ophthalmologists. Methods: A prospective clinical study was conducted in an eye clinic of a tertiary care hospital in the southern part of India with 437 patients. Smartphone images taken were sent to the Logy AI cataract screening solution which predicted if the patient had cataract or not. It graded cataracts as immature and mature. Patients were examined by ophthalmologists with slit-lamp and diagnosis was documented. Both were compared. Results: 794 eye images were included in the study. The overall accuracy of the AI screening solution for cataract detection was computed to be 90.08%. Further, the accuracy was 88.02% for immature cataract, 97.16% for mature cataract, and 90.08% normal category. The sensitivity was 90.38%, the specificity was 89.87%, and the F1 score was 87.98%. The positive predictive value was 85.71% and the negative predictive value was 93.29%. Logy AI cataract prediction module’s AUC (0.8946) falls under the good category. Conclusions: Logy AI cataract screening module could work as an effective cataract screening tool at the community level in remote areas where there is no expensive equipment and ophthalmic health care workers considering the accuracy and efficiency to work in low resource settings. It can also be a good home screening tool suitable for the post-COVID era.