AI analysis of retinal images could be used to predict cardiac risk

UK researchers highlight the potential of eye scans as an alternative to blood sampling or blood pressure checks when assessing heart health

heart attack
Getty/boonchai wedmakawand

UK researchers have put forward analysis of retinal images as a low-cost, non-invasive, fully automated alternative to traditional measures for assessing heart health.

Writing in the British Journal of Ophthalmology, Professor Alicja Rudnicka and colleagues examined the performance of artificial intelligence-enabled retinal vasculometry in predicting different forms of cardiac risk in individuals.

They concluded that the approach provides an alternative predictive biomarker to traditional risk-scores for vascular health, without the need for blood sampling or blood pressure measurement.

The AI-enabled tool, Quartz, was used to assess images from 88,052 UK Biobank participants between the ages of 40 and 69.

The authors noted that as optometrists are based on the High Street, the technology could help achieve greater screening coverage.

“In the general population it could be used as a non-contact form of systemic vascular health check, to triage those at medium-high risk of circulatory mortality for further clinical risk assessment and appropriate intervention,” they shared.

University of Dundee scientists, Dr Ify Mordi and Professor Emanuele Trucco, who were not involved in the study, commented on the work in a linked editorial.

They noted that the retina has the potential to provide a “rich source of prognostic information” relating to cardiovascular disease risk.

Mordi and Trucco highlighted that cardiovascular disease (CVD) accounts for one in four deaths in the UK.

“Given the morbidity associated with CVD, identification of individuals at high risk is particularly important,” they emphasised.