'Game changer': New AI tool can detect hidden heart attack risks

Supported by NHS England, a pilot project is underway at five hospital trusts

A team from Caristo Daignostics, an Oxford University spinout company, has developed an AI tech that has the ability to identifiy individuals at risk of a heart attack within the next decade.

Described as "game-changing" by scientists, this model detects heart inflammation that is not visible on CT scans, which use a combination of X-rays and computer technology.

Supported by NHS England, a pilot project is underway at five hospital trusts in Oxford, Milton Keynes, Leicester, Liverpool, and Wolverhampton. A decision on its implementation within the NHS is expected in the coming months.

The technology is also being adapted to prevent diabetes and strokes. Professor Keith Channon from the University of Oxford said: "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 precedes the development of narrowings and blockages [within the heart]."

In the pilot, patients with chest pain referred for a routine CT scan have their scans analysed by Caristo Diagnostics' CaRi-Heart AI platform. An algorithm that detects coronary inflammation and plaque is then verified by trained operators.

Research has linked increased inflammation to a higher risk of cardiovascular disease and fatal heart attacks.

According to the British Heart Foundation (BHF), approximately 7.6 million people in the UK live with heart disease, costing the NHS in England £7.4bn annually. About 350,000 cardiac CT scans are performed each year in the UK.

The Orfan study (Oxford Risk Factors and Non-invasive Imaging), involving 40,000 patients and published in the Lancet, revealed that 80% of people were sent back to primary care without a defined prevention or treatment plan.

Researchers found that patients with inflammation in their coronary arteries had a 20 to 30 times higher risk of dying from a cardiac event over the next 10 years. Using this AI technology, 45% of these patients were prescribed medication or encouraged to make lifestyle changes to prevent future heart attacks.

Source