IBM uses deep learning AI for early eye disease detection

IBM Research developed deep learning and visual analytics technology to identify the severity of diabetic retinopathy, an eye disease that can cause blindness if left untreated in diabetic patients.

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

© Copyright ASC COMMUNICATIONS 2019. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Top 40 Articles from the Past 6 Months