The IBM Research team trained the deep learning model to identify lesions on more than 35,000 eye images. The method currently achieves an accuracy score of 86 percent when classifying the severity of the disease, however, the team plans to continue to advance the system’s capabilities.
IBM hopes this tool will help physicians screen patients more quickly, particularly in remote areas that lack access to specialty clinicians.
“Automated and highly accurate [diabetic retinopathy] screening methods have the potential to help doctors screen far more patients than currently possible,” said Joanna Batstone, PhD, vice president and lab director of IBM Research Australia.
More articles on health IT:
CardioNet agrees to $2.5M HIPAA settlement
Which EMR vendor is most focused on sepsis technology? Clinicians weigh in
American Well live on Samsung Health app
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.
