Researchers Build an Online Simulator for Glaucoma

Researchers at the University of Toronto have developed an online simulator that offers an enhanced visual representation of the effects of glaucoma. This simulator, created by Professor Willy Wong and Ph.D. candidate Yan Li from the Faculty of Applied Science & Engineering in collaboration with others, provides a perspective on the disease from the patient's point of view.

According to Wong, almost all other representations of glaucoma found on the internet are inaccurate.

He explains, "If you do an internet search for what glaucoma looks like, the images returned are tunnel vision with the periphery blacked out. There's very little truth to this," says Wong of the Edward S. Rogers Sr. department of electrical and computer engineering. "What's really happening is patches of your visual field are losing their spatial integrity—more what you might see when you just wake up, when you're not really focused in."

Wong and Li's online simulator is based on a data-driven model they developed to quantify glaucoma measurements. This model accounts for the physiological processes of the eye and was recently published in the journal Translational Vision Science & Technology.

Li explains their collaborative approach, saying, "We closely collaborated with glaucoma specialists, two of whom are co-authors on the paper. They provided us with valuable insights into the eye's pathophysiology, allowing us to gain firsthand experience in understanding clinicians' technological needs."

While glaucoma is a leading cause of blindness, its progression can be significantly slowed through medication and other interventions. Doctors regularly perform proactive monitoring, which includes various qualitative tests such as examining the optic nerve and retinal layer, employing numerical measurements to ensure precision.

"But even with these measurements, the doctors don't always know if it's trending upwards or downwards or staying the same," says Wong.

This is attributed to the inherent noise present in numerous physiological measurements. Take visual field tests, for instance, which hinge on measuring visual thresholds—the minimal energy required for sight. However, these thresholds often prove to be unreliable. Furthermore, the noise in these measurements is exacerbated by the extended duration of the tests and the inevitable gaps resulting from missed appointments.

Li emphasizes the uniqueness of their model, highlighting its integration of data from these tests with knowledge about the biology of the eye. He elaborates, "You have to be mindful of how the nerves go from the eye itself—from the visual field into the optic disc. If you know the relationship between the two and add that causality to the clinical data, you have a much better prediction tool."

Wong and Li's online simulator offers users the ability to set the patient's age range and control progression rates, starting from mild, moderate, or severe. It then simulates the yearly progression of the disease through photos depicting people, landscapes, and city scenes.

"I showed an ophthalmologist our simulator, and he said, 'This is exactly what I need,'" Wong reports. "Glaucoma is so slow in developing that it's apparently hard to convince patients to take the medication because they don't see or understand the difference."

Li's next objective in this project is to integrate various testing methodologies for glaucoma, leveraging machine learning (ML) techniques to expedite the reliable detection of its onset. Faster detection will enable earlier intervention and a greater likelihood of halting irreversible vision loss, he asserts.

"The development of medicine heavily relies on doctors sharing their expertise with one another, and ML facilitates rapid and efficient knowledge transfer from domain experts," Li notes. "This is a significant advantage of the era of big data in healthcare."

Professor Deepa Kundur, chair of the electrical and computer engineering department, commends the combination of computational power with in-depth biological knowledge, as demonstrated by Wong and Li. She remarks, "The results speak for themselves, and I wouldn't be surprised to see this hybrid model make a difference in other applications."

Reference

Yan Li et al, A Data-Driven Model for Simulating Longitudinal Visual Field Tests in Glaucoma, Translational Vision Science & Technology (2023). DOI: 10.1167/tvst.12.6.27