As the role of artificial intelligence (AI) in ophthalmology rapidly grows, we are launching the “AI in Ophthalmology” column to keep readers apprised of developments in the field that could streamline practices and enhance patient outcomes.
An old adage says that the eyes are the windows to the soul. As ophthalmologists can attest, they are also windows to the body. An eye exam can reveal signs of autoimmune disorders, brain tumors, cancer, diabetes, heart and vascular diseases, high cholesterol, Lyme disease, multiple sclerosis, and sexually transmitted diseases, among others.1
Healthcare from the Eye
With this in mind, last year Topcon Healthcare Inc. announced it had partnered with Microsoft on a prescreening initiative2 to facilitate earlier detection and better management of disease. Donned “Healthcare from the Eye,” the initiative uses noninvasive, robotic retinal imaging to capture data from any DICOM-compliant device, at any location—whether it be an ophthalmology practice, an endocrinology practice, a primary care office, or even a pharmacy kiosk. That data are then securely uploaded to Harmony, Topcon’s cloud-based clinical image and data management platform. From there, physicians can use integrated, third-party AI tools to analyze their patients’ images for signs of systemic health issues. If a referral is needed, it can be made directly through Harmony’s clinical dashboard.
“We are committed to making healthcare accessible and affordable through prescreening using oculomics—leveraging the eye for insights into systemic and neurological health,” Ali Tafreshi, CEO and president of Topcon Healthcare Inc., stated in a press release. “A key element of this effort is Harmony.”
Topcon vice president of marketing Leslie Amodei noted that teaming up with Microsoft strengthens Harmony’s security and scalability. “This partnership ensures that patient data can be accessed securely across various healthcare settings, improving patient care and reducing healthcare costs,” she said.
Beyond Imaging, Grading, and Reporting
Global healthcare company Eyenuk, Inc. also recognizes the value of AI in retinal imaging, proclaiming itself to be “on a mission to screen every eye in the world to ensure timely diagnosis of life- and vision-threatening diseases” such as stroke, cardiovascular disease, Alzheimer’s disease, glaucoma, age-related macular degeneration (AMD), and diabetic retinopathy (DR).3
The company’s EyeArt AI system employs predictive biomarkers (such microaneurysm turnover), deep learning, and image-analysis algorithms to detect the presence and extent of DR lesions; assess risk and level of disease; and track disease progression.3,4 It is the first technology to be FDA-approved for autonomous detection of both more-than-mild and vision-threatening DR, as well as for use with multiple fundus cameras from different manufacturers.3-5
As of press time, Eyenuk is actively developing its EyeMark6 change detection engine, which, the company says, “takes fully automated DR analysis one step beyond imaging, grading and reporting.” It is designed to track disease progression from visit to visit to determine if, or how, a patient’s disease has changed.
Eliminating Barriers to Retinal Screening
AI Optics Inc. announced earlier this year that it is developing AI-based retinal screening software for integration with its portable handheld Sentinel camera, which received FDA 510(k) clearance in late January.7
“Our vision with the Sentinel camera is to eliminate barriers to retinal screening and ensure that every patient who needs screening has access,” said Luke Moretti, cofounder and CEO of AI Optics.
Moretti cited specialist shortages, cost, and inconvenience as obstacles to patients who need the testing, saying that the Sentinel camera helps tackle these challenges by allowing for non-dilated imaging at locations other than ophthalmology offices—such as primary care providers, optometry practices, retail health clinics, and home health settings.7
The Sentinel camera supports DICOM-compliant image formats, enabling integration with electronic health record systems to streamline care coordination. The planned AI software could further improve that care by breaking down barriers and enabling early detection of sight-threatening disease. 7 OM
REFERENCES
Mukamal, R. 20 Surprising health problems an eye exam can catch. American Academy of Ophthalmology. April 24, 2024. Accessed January 31, 2025. www.aao.org/eye-health/tips-prevention/surprising-health-conditions-eye-exam-detects.
Topcon Healthcare Inc. partners with Microsoft to deliver AI-powered ‘Healthcare from the Eye’ through a connected healthcare platform. News release. Topcon Healthcare Inc. May 8, 2024. Accessed February 2, 2025. https://topconhealthcare.com/article/topcon-healthcare-inc-partners-with-microsoft-to-deliver-ai-powered-healthcare-from-the-eye-through-a-connected-healthcare-platform
Eyenuk. About Us. Accessed February 2, 2025. www.eyenuk.com/us-en/company/
Eyenuk. EyeArt® AI Eye Screening System. Accessed February 2, 2025. www.eyenuk.com/us-en/products/eyeart/
Lim JI, Regillo CD, Sadda SR, et al. Artificial intelligence detection of diabetic retinopathy: subgroup comparison of the EyeArt system with ophthalmologists’ dilated examinations. Ophthalmol Sci. 2022;3(1):100228. doi: 10.1016/j.xops.2022.100228.
Eyenuk. Products Under Development. Accessed February 2, 2025. www.eyenuk.com/us-en/products-under-development/
AI Optics receives FDA clearance, increasing patient access to retinal screening. News release. AI Optics, Inc. January 28, 2025. Accessed February 2, 2025. https://www.prnewswire.com/news-releases/ai-optics-receives-fda-clearance-increasing-patient-access-to-retinal-screening-302361438.html