Artificial intelligence may help physicians make glaucoma screening more widely accessible, according to new research.
A trained AI program correctly identified glaucoma patients 88% to 90% of the time, outperforming human graders who achieved accuracy rates of 79% to 81%, researchers reported Saturday at a meeting of the American Academy of Ophthalmology (AAO) in Orlando, Florida.
Lead researcher Dr. Anthony Khawaja, a professor at the University College London Institute of Ophthalmology, stated: “Glaucoma remains one of the most common causes of vision loss that can’t be repaired globally.”
Khawaja added in a news release: “To date, screening is too expensive for glaucoma, but I hope that artificial intelligence solutions, in combination with other approaches such as targeting by genetic risk, will be the solution.”
Study Design
Researchers had both an AI program and human experts evaluate more than 6,300 participants, of whom nearly 700 had glaucoma in at least one eye.
Understanding Glaucoma
Glaucoma develops when fluid pressure accumulates in the eye. This pressure damages the optic nerve, creating blind spots in a person’s vision and potentially leading to complete blindness.
The AI and human experts assessed glaucoma risk based on a crucial eye disorder measure called the vertical cup-disc ratio, which monitors structural changes in the eye caused by fluid pressure buildup.
Study Significance
Researchers described their results as encouraging because only 11% of the eyes examined were suspected of having glaucoma—a proportion that reflects what would typically be found during routine screening.
They suggested accuracy could be further enhanced by incorporating other glaucoma risk indicators, such as intraocular pressure measurements.
Current Treatment Options
Glaucoma is typically managed using eyedrops to reduce eye pressure. In some cases, surgical intervention may be necessary, according to the AAO.
Findings presented at medical meetings should be considered preliminary until published in a peer-reviewed journal.
This research demonstrates AI’s potential to improve glaucoma detection and make screening more cost-effective and accessible, potentially helping prevent irreversible vision loss in more patients worldwide.