A recently published study revealed that routine eye examinations could accurately predict a person's risk of stroke, using a retinal "vascular fingerprint" comprised of 29 indicators of vascular health. The study, titled "Retinal vascular fingerprints predict incident stroke: findings from the UK Biobank cohort study," was published in the journal *Heart* on January 13, 2025, and was led by experts from The Hong Kong Polytechnic University and the University of Melbourne, according to SciTechDaily.
The researchers analyzed fundus images from 68,753 participants in the UK Biobank study, measuring 30 indicators across five categories of retinal vascular architecture, including diameter, density, branching, and complexity of the veins and arteries. They found that after adjusting for known stroke risk factors, 29 measurable "fingerprint" differences were related to the risk of having a stroke for the first time, as reported by Adevarul.
Over an average follow-up period of 12.5 years, 749 participants were found to have had a stroke. The researchers accounted for potentially influential risk factors, including demographic and socioeconomic factors, lifestyle, and health parameters such as blood pressure, cholesterol, blood glucose (HbA1c), and weight (BMI), according to Medical Dialogues.
The study revealed that changes in the density, complexity, and twistedness of the retina's blood vessels were significantly associated with an increased risk of stroke. Each change in vascular density indicators was associated with an increased stroke risk of 10–19%. Similarly, decreases in twistedness and complexity indicators were associated with an increased stroke risk of 10.5–19.5%.
Notably, the retinal "vascular fingerprint," even when combined with just age and sex, was as effective as traditional risk factors alone for predicting future stroke risk, including measures such as cholesterol, weight, and smoking status. "Importantly, when combined with age and sex, the newly identified retinal parameters had comparable predictive power for stroke risk when compared with established traditional risk factors," wrote Mingguang He, a researcher at The Hong Kong Polytechnic University, according to Inside Precision Medicine.
The researchers utilized a machine learning tool called the Retina-based Microvascular Health Assessment System (RMHAS) to analyze the fundus photographs, enabling them to develop an accurate tool for identifying biomarkers associated with stroke.
"The retinal vascular fingerprint presents a practical and easily implementable approach for incident stroke risk assessment, particularly for primary healthcare and low-resource settings," the authors wrote, as quoted by PTI.
This non-invasive screening approach can be easily implemented in primary healthcare settings, making it an ideal tool for stroke risk assessment without the need for invasive tests or expensive examinations. "Using fundus photography as a diagnostic tool is a step towards more accessible and non-invasive medicine," the researchers stated, according to Gazeta.ru.
Stroke affects approximately 100 million people worldwide each year, resulting in 6.7 million deaths, highlighting the urgency of effective risk assessment methods, as reported by Newsweek.
Most stroke cases are caused by modifiable risk factors, such as high blood pressure, high cholesterol, poor diet, and smoking. Although having a stroke can lead to significant health problems, such an event can often be prevented by early treatment of these risk factors, according to SciTechDaily.
The intricate network of blood vessels in the retina shares common anatomical and physiological characteristics with those in the brain, making it an ideal candidate for assessing damage from systemic health issues, including chronic conditions like diabetes.
However, the study is observational and mainly involved white British participants, so its findings may not apply to people of different ethnicities. The researchers acknowledge that this is a limitation and that further research is needed to validate the findings in more diverse populations.
Additionally, the researchers were unable to assess the risk associated with different types of stroke. Despite these limitations, the discovery offers hope for the future of stroke prevention, according to Scientias.
"Improved models for predicting strokes are needed, and new approaches to analyzing retinal vessels offer the possibility of improving prediction accuracy," the researchers stated.
The article was written with the assistance of a news analysis system.