Researchers have discovered a vascular ‘fingerprint’ on the retina that can predict a person’s risk of stroke as accurately as traditional risk factors alone, but without the need for multiple invasive lab tests.

The fingerprint, 29 indicators of vascular health, is a practical and readily implementable approach that is particularly well suited for primary healthcare and low-resource settings, the researchers observed.

The research is published online in the journal Heart.1

Stroke is one of the most common cardiovascular diseases and globally results in approximately 6.7 million deaths annually, the authors noted. They said nearly 90% of strokes are attributable to modifiable risk factors like hypertension, high cholesterol, diet, and smoking.

“Therefore, early identification of individuals at risk could empower earlier intervention, thereby reducing stroke-related disability and mortality.”

The researchers said the retina’s intricate vascular network is known to share common anatomical and physiological features with the vasculature of the brain, making it an ideal candidate for assessing damage from systemic health issues, such as diabetes.

They said the potential of fundus photography for stroke risk prediction hasn’t been fully explored, due to “inconsistent” study findings. However, machine learning, such as the retina-based microvascular health assessment system (RMHAS), has opened possibilities to identify biological markers that can accurately predict stroke risk without the need for invasive lab tests.

To explore this further, the study authors measured 30 indicators across five categories of retinal vascular architecture in fundus images from 68,753 UK Biobank study participants. The five categories included calibre (length, diameter, ratio) density, twistedness, branching angle, and complexity of the veins and arteries.

“After adjusting for traditional risk factors and multiple testing, we identified 29 indicators of increased stroke risk.

“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,” the authors said.

“Given that age and sex are readily available, and retinal parameters can be obtained through routine fundus photography, this model presents a practical and easily implementable approach for incident stroke risk assessment, particularly for primary healthcare and low-resource settings.

“Further investigation of identified parameters, especially density parameters, may provide valuable insights into the intricate pathophysiological processes associated with stroke.

“The non-invasive nature of retinal analysis paves the way for easier, more accessible stroke risk screening, especially in primary care settings. This approach could inform future policy regarding stroke prevention strategies, potentially leading to earlier intervention and improved patient outcomes.”

Reference
1. Yusufu M, Friedman DS, Kang M, et al. Retinal vascular fingerprints predict incident stroke: Findings from the UK Biobank cohort study, Heart, published Online First:13 Jan 2025. doi: 10.1136/heartjnl-2024-324705.