AI predicts heart attack risk

Artificial intelligence (AI) developed by an international team of researchers has estimated the risk of someone having a heart attack over the next year on the basis of retinal scans.

A study describing the research, which was published in Nature machine intelligence, highlighted that the AI system had an accuracy of between 70% and 80%.

Professor Alex Frangi, from the University of Leeds and the Alan Turing Institute, shared that the technology opens up the possibility of “revolutionising” the screening of cardiac disease.

“Retinal scans are comparatively cheap and routinely used in many optician practices. As a result of automated screening, patients who are at high risk of becoming ill could be referred to specialist cardiac services,” he said.

To train the AI system, the technology analysed the retinal and cardiac scans of 5000 people.

The system identified associations between pathology in the retina and changes in the patient’s heart.

Sven Plein, from the University of Leeds, shared that the AI system can be used to unravel complex patterns that exist in nature.

“That is what we have found here – the intricate pattern of changes in the retina linked to changes in the heart," he said.