Artificial intelligence detects hidden risk of heart attack

Artificial intelligence (AI) can detect heart inflammation that doesn’t show up on CT scans, thus preventing the risk of a heart attack.

The new AI model, which identifies people at risk of heart attack, is based on a combination of X-rays and computer technology and scientists say it is a “groundbreaking innovation”. .

It is a pilot project, supported by NHS England, running in hospitals in Oxford, Milton Keynes, Leicester, Liverpool and Wolverhampton.

A decision on its use in the NHS is expected within months.

The developer of this model, the Oxford University company Caristo Diagnostics, said that they are already working to adapt the technology to prevent strokes and strokes. diabetes.

“This technology is transformative and game-changing because for the first time we can detect biological processes that are invisible to the human eye that are too narrow and obstructed (within the heart),” said Professor Keith Channon from the University of Oxford, quoted by the BBC.

As part of the study, patients suffering from chest pain undergo a routine CT scan, which is analyzed by the Caristo Diagnostics CaRi-Heart AI platform.

An algorithm, which detects coronary inflammation and atheroma plaque, is then evaluated by trained operators to verify their accuracy.

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

British Heart Foundation (BHF) estimates that around 7.6 million people in the UK suffer from heart disease and the annual costs are staggering, according to government data.

Each year in the UK, around 350,000 patients are referred for a cardiac CT scan, the BHF says.

The Orfan study (Oxford Risk Factors and non-invasive imaging), which included 40,000 patients and was published in The Lancet, found that 80% of them were sent back to primary care without a specific prevention or treatment plan.

The researchers focused on this group. And they found that if they had inflammation in their coronary arteries, they were 20 to 30 times more likely to die from a heart event in the next 10 years.

The study, funded by the BHF, found that by using AI technology, 45% of these patients were given medication or encouraged to make lifestyle changes to prevent risk of future heart attacks.

Professor Charalambos Antoniades, coordinator of the study, said that the tools available until now were primitive because they could only assess general risk factors: diabetes, smoking , obesity has problems in their arteries before the disease progresses. “This means that we can intervene to stop the onset of the disease and treat this patient, to prevent the development of the disease and then to prevent seizures – heart,” said the coordinator of the study.

The National Institute for Health and Care Excellence is currently evaluating the technology to determine whether it should be implemented in the NHS.

It is also under investigation in the US and has been approved for use in Europe and Australia.