A Melbourne-designed rapid screening test is set to advance the detection and treatment of one of the leading causes of irreversible blindness in older Australians.
Some 80 million people worldwide have glaucoma, with more than 110 million expected to be living with the disease by 2040.
About one in 50 Australians will develop the condition in their lifetimes. The resulting loss of sight is usually gradual, with half the people who suffer from glaucoma not realising they have it.
Diagnosis is currently via a 30-minute eye pressure test delivered by an ophthalmologist.
However a new AI-powered test, developed by a team of engineers and ophthalmology specialists at RMIT University, takes just 10 seconds.
The procedure uses infra-red sensors to monitor eye movement and can accurately predict the risk of glaucoma, making it ideal for use in a national screening program.
Lead researcher Professor Dinesh Kumar says the breakthrough is critical, given early detection, diagnosis and treatment can help prevent blindness.
"This research will allow a non-contact, easy-to-use and low-cost test that can be performed routinely at general clinics," he said.
"It could also promote a community-wide screening program, reaching people who might not otherwise seek treatment until it's too late."
The pioneering technology differentiates between glaucoma and healthy eyes by analysing changes in pupil size.
The research, the results of which have been published in scientific journal IEEE Access, involved measuring pupils 60 times per second using a low-cost commercial eye tracker.
Under ambient light, patients looked at a computer screen while software measured and analysed specific changes in pupil size.
The results were then compared with existing samples of glaucoma and healthy eyes to determine risk.
RMIT's Dr Quoc Cuong Ngo says the technology is faster and better than any similar AI-based approach.
"Our software can measure how the pupil adjusts to ambient light and capture minuscule changes in the shape and size of the pupil," he said.
"Existing AI glaucoma tests require the patient to be perfectly still for up to 10 minutes. Our tech does the job in 10 seconds, without compromising on accuracy."
Researchers are now looking to adapt the technology to work with smartphone cameras instead of the eye tracker used in the study.
They are also seeking a commercial partner ahead of a clinical trial planned for 2022.