Can AI Prevent Vision Loss From Glaucoma?

Reviewed by  Preeti Subramanian, PhD, BrightFocus Foundation 

Glaucoma is a group of eye conditions that can cause vision loss and blindness. As the use of artificial intelligence (AI) becomes more prevalent, eye doctors are looking for ways to harness this technology toward better glaucoma detection and tracking of disease progression.  

“AI is when a computer is mimicking human-level intelligence,” said Dr. Atalie C. Thompson, MD, MPH, in an episode of BrightFocus Foundation’s Glaucoma Chats, free monthly audio conversations with vision experts. “In AI, computers are trained to analyze data so that they can perform complex tasks that would ordinarily require human intelligence, like learning or problem solving or language acquisition.” 

Dr. Thompson broke down the current opportunities and challenges surrounding the use of AI for glaucoma. Check out her answers below.  

How might AI improve the detection of glaucoma and other age-related eye diseases?  

Dr. Thompson: There has been a lot of interest in developing AI algorithms that can be useful to clinicians because they could either detect disease earlier or maybe predict who is going to progress or respond to treatment better than a person could by just looking at a scan.  

Glaucoma is complicated because patients don’t realize they have glaucoma until the disease is really advanced. Also, a lot of patients aren’t motivated to take their medication because they can’t feel their glaucoma, so they can’t tell if it’s getting worse, and that’s because glaucoma progresses really slowly. It makes it hard for us as physicians to predict who’s going to get worse or how quickly people are getting worse.  

The hope here is that AI algorithms could help us develop technology for detecting who has glaucoma earlier, maybe years before they lose their vision so that they could get treatment earlier. That could be maybe applied at a telehealth setting where they get a picture remotely and then it tells them, “Here’s a color photo of your optic nerve. You look suspicious for glaucoma, and so you should see an eye provider within 3 months,” and get them set up for a referral.  

On the flip side of that, once you have glaucoma and you’re starting to see your clinician, there are a lot of pieces of data that go into helping to figure out how quickly somebody is progressing and how likely they are to get worse. AI could potentially be less subjective and help the provider have a tool to incorporate the multiple pieces of data and decide if think this person is at a really high risk of progressing.   

Can AI prevent or reverse vision loss from glaucoma?  

Dr. Thompson: I think if these algorithms are successfully developed and implemented, and if we’re able to detect glaucoma earlier in people who didn’t know they had glaucoma (years before they have vision loss), then by referring them for treatment and getting treatment sooner, that would prevent blindness.  

Similarly, if we had good risk-prediction tools to use in clinic with our patients, and if that motivated people to better understand the potential risk of eye disease progression if they’re not taking their drops and then they were more compliant, then I think that will decrease their risk of blindness.  

I haven’t seen anything about new technology that’s going to reverse blindness that you’ve already had or reverse vision loss that’s already happened from glaucoma. And that’s because retinal ganglion cells, which are the cells that die in glaucoma, are not something that we can resurrect from the dead. They are connected from your retina all the way through your brain, so we’d have to regenerate parts of the brain as well. That’s very complicated because of all the ways nerves connect to each other and connect to other parts of the brain. That’s why we’re so adamantly concerned about detecting glaucoma early and treating it appropriately.   

What are the limitations of using AI in glaucoma?   

Dr. Thompson: Like any new technology, there’s a lot of work to be done. One challenge is that we don’t always understand or know how an AI algorithm makes its decisions or predictions, and that can lead to difficulties when we’re trying to interpret the prediction or the output. This is commonly called the “black box” phenomenon. Sometimes AI algorithms use labeled data, where a doctor has looked at pictures of the optic nerve and said, “This looks like glaucoma,” so they labeled it as glaucoma, and “This one doesn’t look like glaucoma,” and they labeled it as not having glaucoma. In those kinds of algorithms, the AI algorithm learns from data that’s been supervised by a human being, so it’s called supervised learning.  

But there’s also the potential for algorithms to look at data without any labels on it at all and pick up patterns in the data that, many times, even humans have not been able to pick up, and then make predictions. And that’s called unsupervised learning, and it’s working with data that’s not labeled. Often, we don’t really understand or know how it’s making those predictions, and that can lead to some concern among physicians or scientists just to make sure that the predictions are being made on something that’s biologically plausible.  

That’s a big thing about AI that sometimes gives people pause.   

Want to learn more? Listen to the full Glaucoma Chats episode, “Exploring Artificial Intelligence and Glaucoma: Challenges, Opportunities, and Hope,” with Dr. Thompson and register for upcoming episodes.  

Responses have been edited for length and clarity.

About BrightFocus Foundation

BrightFocus Foundation is a premier global nonprofit funder of research to defeat Alzheimer’s, macular degeneration, and glaucoma. Through its flagship research programs — Alzheimer’s Disease Research, National Glaucoma Research, and Macular Degeneration Research — the Foundation has awarded nearly $300 million in groundbreaking research funding over the past 51 years and shares the latest research findings, expert information, and resources to empower the millions impacted by these devastating diseases. Learn more at brightfocus.org.  

The information provided in this section is a public service of BrightFocus Foundation, should not in any way substitute for the advice of a qualified healthcare professional, and is not intended to constitute medical advice. Although we make efforts to keep the medical information on our website updated, we cannot guarantee that the information on our website reflects the most up-to-date research.        

Please consult your physician for personalized medical advice; all medications and supplements should only be taken under medical supervision. BrightFocus Foundation does not endorse any medical product or therapy.