AI has Perfect Detection Rate for Severe Cases of Condition that Causes Blindness in Preemies

Key Takeaways

  • An artificial intelligence technology can accurately and independently detect 100% of severe cases of a blindness-causing condition that affects prematurely born babies.
  • The technology has the potential to expand worldwide screening—and ultimately sight-saving treatment—for retinopathy of prematurity, or ROP.

ROP causes abnormal blood vessel growth near the retina. About 2 million babies annually are born early enough to develop ROP, although in most cases, the disease is mild and resolves without treatment. Severe cases cause about 500 babies in the United States and about 50,000 babies globally to go blind every year. More cases go untreated in low- and middle-income countries, where there are fewer ophthalmologists to examine and treat preemies. “ROP is the leading cause of blindness in children in the U.S. and around the world, and perhaps the most solvable problem among many in global efforts to reduce preventable blindness,” said Peter Campbell, M.D., M.P.H., corresponding author of a new study published in JAMA Ophthalmology. “Although we cannot fully prevent ROP, we can almost always prevent blindness from ROP.

Currently, specially trained ophthalmologists must manually review retinal images for blood vessel anomalies to diagnose ROP. However, there are not enough doctors to screen all the babies who are at risk. Therefore, researchers at the Oregon Health & Science University developed the i-ROP Deep Learning system, which uses an artificial intelligence (AI) algorithm to identify blood vessel anomalies in retinal images. The team’s earlier research showed that their AI technology could accurately diagnose ROP and can also be effectively used remotely through telemedicine appointments instead of traditional, in-person eye exams.

This new study, which showed a 100% success rate in identifying severe cases of ROP, marks the first time that autonomous AI screening for ROP has been shown to work in a real-world population—meaning the technology correctly flags the condition on its own, without ophthalmologist support and without preselecting images to improve data quality. While many AI algorithms work in controlled experiments, they often fail to work in the real world due to differences between training data and real-world use. “This paper demonstrates that AI can effectively replace the physician for bedside screening and refer the most urgent cases to a physician for treatment,” says Campbell.

Edited by Miriam Kaplan, PhD

Source: Franny White, Oregon Health & Science University, Medical Xpress, March 7, 2024; see source article