Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     

Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     
Tech

AI spots form of child blindness more accurately than doctors

04/06/2018
The inventors of an artificial intelligence algorithm claim it can automatically diagnose a leading form of childhood blindness more accurately than most eye specialists.

Researchers from the Oregon Health and Science University (OHSU) and Massachusetts General Hospital (MGH) found the algorithm accurately diagnosed retinopathy of prematurity (ROP) from pictures of infants’ eyes 91% of the time. In comparison, a team of eight doctors with ROP expertise were only able to diagnose the same set of images with 82% accuracy.

“There’s a huge shortage of ophthalmologists who are trained and willing to diagnose ROP. This creates enormous gaps in care, even in the United States, and sadly leads too many children around the world to go undiagnosed,” study co-lead Dr Michael Chiang said.

The algorithm was initially trained on more than 5,000 images taken from infants during visits to ophthalmologists. It was then trained to differentiate between diseased and healthy vessels, after which the researchers compared the algorithm’s accuracy with those of the group of experts.

“This algorithm distills the knowledge of ophthalmologists who are skilled at identifying ROP and puts it into a mathematical model so clinicians who may not have that same wealth of experience can still help babies receive a timely, accurate diagnosis,” MGH Associate Professor Jayashree Kalpathy-Cramer said.

The research team is currently collaborating with a team in India to test the algorithm for ROP among Indian babies and see if its success correlates with the group of primarily Caucasian babies from the initial study.

They are also exploring whether the algorithm can diagnose the condition in images of other parts of the retina besides vessels, with an ultimate goal of enabling physicians to incorporate the technology into their clinical practices.

largeleaderboard_pen
advertisement


skyscraper_article
advertisement
Editor's Suggestion
Hot Stories

AND/OR
 

Subscribe for Insight in your Inbox

Get Insight with the latest in industry news, trends, new products, services and equipment!