23 July 2025
University of Dundee scientists have developed a deep-learning artificial intelligence (AI) model that predicts cardiovascular risk among patients with type 2 diabetes from retinal images.
The research, which was published in Cardiovascular Diabetology, found that the model could predict an individual’s risk of a major cardiovascular event – such as a heart attack or stroke – over the next decade with 70% accuracy.
The authors highlighted that an AI retinal assessment might enable a “one-stop cardiovascular risk assessment at routine retinal screening.”
Dr Ify Mordi, British Heart Foundation research fellow at the University of Dundee, highlighted that the eyes can act as a window to the heart.
“If there is damage or narrowing of the blood vessels at the back of the eye, there is a good chance that will also be seen in the blood vessels further inside the body, supplying the heart, which could lead to a heart attack or stroke,” he said.
“This is a one-stop scan which is routinely performed and takes less than a minute. It could be an important part of the package, alongside blood pressure and cholesterol checks, in identifying people who could benefit from medication or lifestyle changes,” Mordi explained.
Chief scientific and medical officer at the British Heart Foundation, Professor Bryan Williams OBE, highlighted that the research could help to improve risk prediction.
He added that more research is needed to show that the prediction accuracy is robust and to explore the feasibility of incorporating retinal scans into clinical practice.
Comments (1)
You must be logged in to join the discussion. Log in
Don Williams29 July 2025
This is an exciting development that highlights the growing synergy between ophthalmology and cardiology through AI-enabled diagnostics. The ability of a deep-learning model to extract systemic insights, like cardiovascular risk from retinal images reinforces the eye's role as a window into whole-body health.
From an optometrist’s perspective, this research offers a compelling glimpse into the future of preventive care. Retinal screening is already routine for patients with diabetes and integrating AI could allow us to stratify cardiovascular risk non-invasively, quickly, and at scale. Such tools, once validated in larger and more diverse datasets, may well become part of a broader AI-assisted screening ecosystem.
However, as always, clinical utility hinges on robustness, transparency and equitable deployment. Continued interdisciplinary collaboration will be key to ensuring that these algorithms enhance but not replace human clinical judgment, while addressing bias and explainability.
As an AI postgraduate, I view this as a pivotal step toward augmented care that empowers patients and practitioners alike.
ReportLike0