Scientists are hailing a new artificial intelligence (AI) technology as “game changing” for its ability to identify individuals at risk of heart attacks up to a decade before they occur. This groundbreaking technology, developed by Caristo Diagnostics, an Oxford University spinout, detects inflammation in the heart that traditional CT scans often miss.
The AI model, known as CaRi-Heart, analyzes routine CT scans using an advanced algorithm to identify coronary inflammation and plaque. Unlike conventional CT scans, which rely on X-rays and computer technology, CaRi-Heart can detect subtle biological processes that are invisible to the human eye but crucial for predicting cardiovascular risk.
The technology is currently being tested in a pilot project supported by NHS England, running at five hospital trusts across Oxford, Milton Keynes, Leicester, Liverpool, and Wolverhampton. A decision on whether the technology will be adopted widely within the NHS is expected within the coming months.
Prof. Keith Channon from the University of Oxford praised the technology for its transformative potential. “For the first time, we can detect biological processes that precede the development of blockages and narrowings in the heart,” he said.
During the pilot, patients experiencing chest pain who are referred for a routine CT scan have their results analyzed by the CaRi-Heart platform. The algorithm’s findings are then reviewed by trained operators to ensure accuracy. Research has linked increased inflammation to a higher risk of cardiovascular disease and fatal heart attacks.
The British Heart Foundation (BHF) reports that around 7.6 million people in the UK live with heart disease, with the annual NHS cost estimated at £7.4 billion. Each year, approximately 350,000 patients in the UK undergo cardiac CT scans. The Orfan study (Oxford Risk Factors and Non-invasive Imaging), involving 40,000 patients and published in The Lancet, found that 80% of patients returned to primary care without a defined prevention or treatment plan. However, the study also indicated that patients with coronary inflammation had a 20 to 30 times higher risk of dying from a cardiac event within the next decade.
Using the new AI technology, 45% of these high-risk patients were prescribed medication or advised to make lifestyle changes to mitigate future heart attack risks.
Ian Pickford, 58, from Barwell in Leicestershire, was referred for a CT scan in November 2023 due to persistent chest pain and enrolled in the Orfan study. The AI analysis indicated he was at high risk for a heart attack, leading to a prescription for statins and lifestyle recommendations. “It’s a huge wake-up call,” Pickford said, reflecting on the impact of the findings.
Prof. Charalambos Antoniades, lead researcher for the Orfan study, emphasized the advanced capabilities of this AI technology compared to traditional risk calculators. “Now, with this technology, we can identify disease activity in arteries before the disease develops, allowing us to intervene early and prevent heart attacks,” he said.
The National Institute for Health and Care Excellence is currently reviewing the AI technology to determine its potential for broader NHS use. It is also under evaluation in the US and has already received approval for use in Europe and Australia.
