Medical images of the retina can accurately predict an individual’s risk of cardiovascular disease and death, scientists report today.
Professor Alicja Rudnicka of St George’s University of London, UK, and colleagues examined the value of artificial intelligence (AI) enabled retinal vasculometry, for heart risks.
They analysed information from images of 88,052 UK Biobank participants, as well as 7,411 participants in the European Prospective Investigation into Cancer Norfolk, aged 40 to 92 years and followed for an average of seven to nine years.
Details included retinal arteriolar and venular width, tortuosity (curvature of the vessels) and retinal area.
A mathematical model to predict risk was developed, and its usefulness was compared to a normal risk prediction calculation involving age, smoking status and medical history.
They found that adding retinal vasculature to Framingham Risk Scores only led to slight improvements in the prediction of stroke or heart attack. But a simpler risk score including age, sex, smoking, medical history and retinal vasculature performed as well as the Framingham Risk Scores – with the advantage of being non-invasive.
In *British Journal of Ophthalmology* today they write: "Retinal vasculometry offers an alternative predictive biomarker to traditional risk-scores for vascular health, without the need for blood sampling or blood pressure measurement."
It "potentially has greater community reach to identify individuals at medium-high risk requiring further clinical assessment," they add.
However, they point out that further work is needed to discover whether retinal vasculometry is effective in population-level screening to identify people at high risk.
Rudnicka, A. R. et al. Artificial intelligence-enabled retinal vasculometry for prediction of circulatory mortality, myocardial infarction and stroke. *British Journal of Ophthalmology* 5 October 2022 doi: 10.1136/bjophthalmol-2022-321842
Leave a Reply