The researchers used two validation sets of 9,963 images and 1,748 images to compare the performance of the automated deep learning algorithm with the performance of manual grading by ophthalmologists when identifying diabetic retinopathy from retinal fundus photographs.
When detecting referable diabetic retinopathy, the algorithm had high sensitivities (97.5 percent and 96 percent) and high specificities (93 percent and 94 percent) in both validation sets. The researchers concluded that “in this evaluation of retinal fundus photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy.”
More articles on health IT:
Innovaccer unveils MIPS calculator to help providers estimate payments
Survey: 86% of patients use online portals, 91% use mobile apps when providers offer
IBM Watson offers new tools for physician support, personalized medicine: 3 highlights
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.