Share Tweet Share Email Print

Tech that detects cause of preemie blindness gets federal nod

Artificial intelligence algorithm receives FDA breakthrough device status
close up image of a father, holding his infant son's hand, and kissing it
Jonathan Brown of Keizer, Oregon kisses his son's hand as they wait for an eye appointment in 2017. Every year up to 16,000 prematurely born U.S. infants like Nathan, are affected by retinopathy of prematurity, a leading cause of childhood blindness in the U.S. and worldwide. (OHSU/Kristyna Wentz-Graff)

An artificial intelligence algorithm that can detect a potentially devastating cause of childhood blindness better than most human experts has been granted breakthrough status by the FDA.

The FDA Breakthrough Device Program aims to accelerate development - and potentially approval - of medical devices for “more effective treatment or diagnosis of life-threatening or irreversibly debilitating diseases.”

The algorithm, called the i-ROP DL system, diagnoses retinopathy of prematurity, or ROP. Every year up to 16,000 prematurely born U.S. infants are affected by the disorder, which causes abnormal blood vessel growth near the retina, the light-sensitive portion in the back of an eye. About 600 U.S. babies go blind from ROP annually, making it a leading cause of childhood blindness in the U.S. and worldwide. Musician Stevie Wonder is blind as a result of ROP.

The algorithm diagnoses the condition in images of infant eyes with comparable or better accuracy than today’s standard method, which involves an examination by expertly trained ophthalmologists.

A 2018 study in JAMA Ophthalmology showed the technology diagnoses the condition 91% of the time, compared with 82% for trained ophthalmologists. Subsequent studies in 2019 described how the algorithm can be used to quantitatively measure the condition’s severity and help physicians evaluate how well treatment is working against the disease.

Oregon Health & Science University and Massachusetts General Hospital led the technology’s development, with support from Northeastern University and the University of Illinois at Chicago as well as the Imaging & Informatics in ROP (i-ROP) consortium.

OHSU and MGH are developing a commercialization plan for the technology, in the hope that it will be used by ophthalmologists and neonatologists worldwide to better diagnose and treat retinopathy of prematurity.

Research related to the technology was funded by the National Eye Institute, the National Science Foundation, Research to Prevent Blindness, the Oregon State Elks, the OCTRI Biomedical Innovation Program and OHSU Foundation’s University Venture Development Fund.

Previous Story OHSU, Ionis Pharmaceuticals to develop drugs for ‘undruggable’ cancer targets Next Story Oregonian gets life-saving heart valve repair without open-heart surgery