The AI model has been hailed as a “game changer” for being able to analyze CT scan images to identify patients at risk of heart attack in the next 10 years.

The artificial intelligence (AI) model detects inflammation in the heart that doesn’t show up on CT scans, using a combination of X-rays and computer technology.
This is mA pilot project supported by NHS England is being carried out at five hospitals in Oxford, Milton Keynes, Leicester, Liverpool and Wolverhampton. A decision on the use of the technology in the NHS is expected to be made within months. The technology’s developer, Oxford University subsidiary Caristo Diagnostics, said it has been working to adapt the technology to prevent strokes and diabetes.
Professor Keith Channon, from the University of Oxford, said: “This technology is transformational and game-changing because for the first time we can detect biological processes invisible to the human eye, before when developing narrowing and blockages in the heart”.
As part of the pilot project, patients with chest pain referred for a CT scan will typically have their scans analyzed using Caristo Diagnostics’ CaRi-Heart AI platform. An algorithm for detecting coronary artery inflammation and plaque was then evaluated by qualified operators to verify its accuracy.
Research has shown that increased inflammation is associated with a higher risk of cardiovascular disease and fatal heart attacks. According to government figures, the British Heart Foundation (BHF) estimates that around 7.6 million people are living with heart disease in the UK and the annual cost to the NHS in England is £7.4 billion. The BHF says around 350,000 patients are referred for cardiac CT scans each year in the UK. The Orfan study (Oxford risk factors and non-invasive imaging) involving 40,000 patients and published in the journal Lancet, found that 80% of people were readmitted to primary care without Have a defined prevention or treatment plan.
Focusing on this population, researchers say they found that if patients had coronary artery inflammation, they were 20 to 30 times more likely to die from a cardiovascular event over the next 10 years. . Research funded by the BHF found that using AI technology, 45% of those patients were prescribed medication or encouraged to make lifestyle changes to prevent the risk of future heart attacks.
Word of warning
Mr. Ian Pickard, 58 years old, lives in Barwell, Leicestershire, is one of 40,000 patients participating in the study. Mr Pickard was referred for a CT scan in November 2023 after experiencing persistent chest pain. He was enrolled in the Orfan study at Leicester University Hospitals NHS Trust.
After using AI analysis technology, test results showed that he was at risk of having a heart attack. At that time, he was prescribed statin medication and asked to quit smoking and increase regular exercise combined with a healthy diet.
“This was a ‘big wake-up call’ for me and when you see the test results on paper you realize how serious it really is. It’s something you can look at every day and think you have to do something about this,” he said.
The AI model measures heart inflammation based on the fat around the arteries
Professor Charalambos Antoniades, who led Orfan’s research, said the tools available so far were still rudimentary because the computers could only assess general risk factors, such as whether a patient had diabetes, smoking or obesity.
He said: “Now, with this type of AI technology, we can know exactly which patients have disease activity in their arteries before the disease develops. This means we can act Act early to stop the disease process and treat this patient to prevent the disease from developing and then prevent heart attacks from occurring.”
The National Institute for Health and Care Excellence is currently evaluating the technology to determine whether it should be rolled out across the NHS. The technology is also under review in the United States and has been approved for use in Europe and Australia.
Information translated from BBC
Join the Club
Like this story? You’ll love our monthly newsletter.
Thank you for subscribing to the newsletter.
Oops. Something went wrong. Please try again later.
