Scientists have developed an artificial intelligence (AI) model that can identify people at risk of a heart attack within the next 10 years by detecting hidden inflammation in the heart — something that traditional CT scans cannot reveal. This innovative technology, currently being piloted in five NHS hospital trusts across England, could soon be implemented nationwide.
Developed by Oxford University spinout Caristo Diagnostics, the AI platform, known as CaRi-Heart, analyzes routine CT scans for coronary inflammation and plaque. Research has shown that increased inflammation is linked to a significantly higher risk of cardiovascular disease and fatal heart attacks.
A study involving 40,000 patients, published in The Lancet, found that those with inflammation in their coronary arteries had a 20 to 30 times higher risk of dying from a cardiac event over the next decade. The AI technology enabled doctors to prescribe medication or recommend lifestyle changes to 45% of these high-risk patients, potentially preventing future heart attacks.
The British Heart Foundation estimates that 7.6 million people in the UK live with heart disease, costing the NHS in England £7.4 billion annually. About 350,000 cardiac CT scans are performed each year in the UK, and this AI technology could significantly improve outcomes by identifying high-risk individuals who might otherwise be overlooked.
The National Institute for Health and Care Excellence (NICE) is currently evaluating the AI model for broader NHS use, with decisions expected soon. The technology is also under review in the U.S. and has already been approved for use in Europe and Australia.
“This technology is transformative and game changing because for the first time we can detect the biological processes that are invisible to the human eye, which precede the development of narrowings and blockages [within the heart],” said Prof Keith Channon, from the University of Oxford, in an interview with the BBC.
