Glaucoma: Digital Momentum
Summer 2026
by Liz Hillman
Editorial Co-Director
While glaucoma as a subspecialty is not as far along as retina, for example, when it comes to development and utilization of big data and AI for diagnostic and patient care decisions, Barbara Wirostko, MD, FARVO, said there is a lot of work being done in this area to advance glaucoma care to being more proactive rather than reactive.
“For instance, we are interested in learning about IOP, medication, systemic risk factors, family history, OCT/OCT-A, and visual fields. How does it all fit together and shape our decisions as well as patient outcomes? It’s the totality of all this information that we’re hoping AI will be able to incorporate and help us make a diagnosis or inform on the best next steps for a patient,” Dr. Wirostko said. “It comes down to personalized medicine.”
Sophia Y. Wang, MD, who describes herself as a glaucoma specialist, clinician scientist, and clinician informaticist, said she has been working with many different big data sources to evaluate various aspects of glaucoma, such as its epidemiology, its risk factors, and to train AI models to predict glaucoma outcomes.
Source: Barbara Wirostko, MD, FARVO
The datasets and sources that are available now “dwarf some of the datasets that we had access to before in terms of size, number of patients, and different types of data,” Dr. Wang said. In recent years, information like IOP and visual acuity metrics have become more available in big datasets, and with this type of information, Dr. Wang said analysis can better evaluate outcomes of glaucoma medical and procedural treatments.
“Now we also have the ability to use this huge scale data to train AI models to predict those outcomes,” Dr. Wang said.
In terms of current applications of such information, Dr. Wang said she sees patients in clinic who might have rare outcomes and/or rare diseases. Prior to the availability of big datasets and analytic systems for them, scientists weren’t able to study such rarities on a large scale. “Now we can because of the aggregation of multicenter data,” she said.
“For example, if your center only does a few hundred of some procedure a year, there’s only so much you can do to study that with your own data. But on a large scale, now we can investigate more answers and really see how different people respond to different surgeries,” Dr. Wang explained.
Dr. Wang discussed one of her studies that used multicenter data to look at the outcomes of different kinds of glaucoma procedures like trabeculectomies, tube shunts, and MIGS. The study looked at multiple outcomes including postoperative IOP, how efficacy of the procedure lasted, and the need for additional surgery. “We can now train models to predict how a patient will do after a trabeculectomy or how they will do after a tube shunt,” she said, noting that in the future, as accuracy of these predictions improves, it could aid in selecting the right treatment for the right patient.
Dr. Wirostko has been heavily involved in analyzing data that’s been coming in with the iCare HOME2 tonometry system (Icare USA). She said there are about 4,000 patients who have used or are currently using iCare HOME2. With this data, she and colleagues are beginning to see patterns in IOP fluctuations, determine data-driven care recommendations for patients, and better understand things like the impact of sleep habits, exercise, and medication use. Data is also refining use of the iCare HOME2 system itself, informing things like how often a patient should take measurements, at which hours of the day/night, and for how long.
“We still don’t know what is contributing to the variation in presentation and the pathophysiology of glaucoma,” Dr. Wirostko said. “We know genetics plays a role, as well as IOP and risk factors like myopia, age, and lamina cribrosa stiffness, but I think all of these things still need to be incorporated into better predictive models.”
What’s being applied clinically due to learnings from the data from technology like iCare HOME2, Dr. Wirostko said, is a greater appreciation of the IOP elevations, patterns, and fluctuations that are occurring (and that previously went unidentified) that are contributing to disease pathology. “All of this is helping us determine who needs treatment sooner. I think it helps us identify who’s being overtreated or may not need treatment. It’s also helping us rule out IOP and perhaps glaucoma as a causative disease for a visual field defect,” she said.
Dr. Wirostko said Wilmer Eye Institute and Moran Eye Institute have been working on data coming from iCare HOME2 that is showing that certain therapies have a better effect on early morning pressure spikes, which go unnoticed without home tonometry monitoring. “We’re finding that if you want to completely eliminate those early morning spikes and reduce any variability in IOP, you need to bypass the whole outflow system, either with a trabeculectomy, tube, or shunt like PRESERFLO [Glaukos]. Even with some angle-based surgeries, you’re still getting some early morning elevations of IOP, probably higher than what we would want for those patients with advanced disease,” she said.
Dr. Wang said right now in glaucoma, treatment options are often applied in a stepwise and escalating approach for patients, taking time to find the most effective treatments. With clinical decisions supported by big data prediction tools, ophthalmologists might be able to go straight to selecting the most effective treatments for a given patient, bypassing potentially less effective treatments altogether.
In addition to using data amassed from EHRs, large-scale surveys, and other data sources, the availability of multimodal data is a game changer, Dr. Wang said. With imaging from OCT, visual fields, and more, incorporating these different types of modalities into data models can help pick up patterns and help establish if a patient may be progressing or if they’re stable. “That would be enormously helpful. That’s certainly an area of research that I’m interested in. It’ll take some work, though, to get there because of the complexity both of developing those multimodal models and deploying them into real clinical environments and IT infrastructures,” Dr. Wang said.
One thing that Dr. Wirostko is excited about is the availability of polygenic risk scores for glaucoma. “Right now, if we have a patient who has a family history and their pressures are borderline, but they don’t have any noticeable damage yet, how do we know the best way to follow that patient? … I think for these patients, when you start to incorporate big data and consider genetic risk scores, that’s going to be very exciting to help us determine who we should be following more closely and perhaps intervening on sooner.”
In the future, Dr. Wang is excited for AI to assist in glaucoma screening, identifying glaucoma suspects correctly, and not missing patients with real glaucoma and progressive disease. As previously mentioned, she looks forward to it helping clinicians decide what treatment or procedure would most benefit a patient.
“These things excite me, and I hope that we can make those applications a reality in a way that is responsible, fair for everyone, and improves healthcare access,” Dr. Wang said.
Dr. Wirostko said she’s excited for big data to provide answers to questions like why some patients experience elevated IOP in early waking hours. She’s also looking forward to more development in virtual reality visual field testing. She thinks the Humphrey for visual field testing is still more reliable than virtual visual fields, but it is also what we know, she said. She envisions being able to ship a virtual reality headset to a patient’s home and collect visual fields monthly, which will enable physicians to identify patients with progression earlier.
While clinician informaticists like Dr. Wang and Dr. Wirostko are excited about the questions they hope to answer in the future thanks to digital tools and big data, there are still hurdles to overcome. One of the main hurdles is that right now much of the information is stored in different systems.
“Dr. Wirostko has her mountain of home tonometry data, and we’ve got our EHR. Being able to combine those different kinds of data and come up with insights across multiple modalities is a challenge,” Dr. Wang said. “If we’re looking at imaging, too, there are different kinds of imaging, different vendors, different systems for storing the imaging. How we pull all of that together in a standardized way to really enable reproducible studies I think is a challenge in our field.”
A word of caution from Dr. Wang regarding the advances that big data and AI might bring to the glaucoma field: If you’re going to consider deploying an algorithm into your practice, keep in mind the generalizability of that algorithm. How was the algorithm created? What datasets was it tested in? Will it work in your patient population? “You don’t want to accidentally deploy a tool that is going to amplify health disparities in some way,” she said. “Keep these things in mind as we enter this brave new world of AI in clinical care. We should be cautious and do our due diligence, asking for these details on any clinical AI algorithm we are considering.”
When it comes to adopting newer digital technologies for glaucoma—now or in the future—Dr. Wirostko said there will be a learning curve, and she sees glaucoma specialists as paving the way for such technologies’ use on a broader scale.
“We are always looking at new and better ways to diagnose and prevent disease. There’s nothing worse than seeing a patient you’ve been following and managing for 10 years continue to lose vision, especially with relatively good IOPs,” Dr. Wirostko said. “This is where I would love to see big data help determine other risk factors that we may not be considering.”
Article sidebar
A patient story in digital, data-driven glaucoma care
Dr. Wirostko offered a specific patient example that highlighted how new data-driven tools are altering patient care for glaucoma and highlighting areas of new research.
She had a patient from Cabo San Lucas, Mexico, with pigmentary glaucoma. This patient had the iCare HOME2 and a virtual reality visual field headset. The monthly visual field data suggested he was progressing. Dr. Wirostko said she had him getting up earlier and earlier in the morning to check his IOP, and this revealed that, despite having PRESERFLO and pressures that were generally between 10–11 mm Hg in waking hours, in the early morning hours he was spiking to 17–18 mm Hg.
“For his advanced damage, this was too high for his nerve,” she said.
At this point, the patient flew up to see Dr. Wirostko and her colleagues in person. They advised he would likely need a tube shunt or trabeculectomy, which the patient preferred to have performed in Atlanta, Georgia, where he had an apartment to stay in during postop care. Between flying back to Cabo and awaiting his surgery in Atlanta, the patient learned he had sleep apnea from another physician.
“He stopped breathing about 44 times an hour,” Dr. Wirostko said, noting he didn’t have typical physical risk factors for sleep apnea. With CPAP treatment for sleep apnea, Dr. Wirostko said his early morning IOP fluctuations completely flattened.
“We always thought that sleep apnea had an association with glaucoma and that the association was due to low oxygen levels or hypoxia to the optic nerve,” Dr. Wirostko said. “But now we’re wondering, what if sleep apnea is actually responsible for some of these pressure spikes? That’s still unknown, and more research has to be done, but as we continue to collect data and think outside the box, I think we are going to answer more of these questions. … But again, these are just hypotheses based on individual cases, which is why we need big data.”
About the physicians
Sophia Y. Wang, MD
Assistant Professor of Ophthalmology
Stanford University School of Medicine
Stanford, California
Barbara Wirostko, MD, FARVO
Adjunct Professor of Ophthalmology and Biomedical Engineering
John A. Moran Eye Center
University of Utah
Salt Lake City, Utah
Relevant disclosures
Wang: None
Wirostko: Icare USA, Injectsense, MyEyes, Qlaris Bio
Contact
Wang: sywang@stanford.edu
Wirostko: barbara.wirostko@hsc.utah.edu
