Innovative AI heart attack scanners could soon be rolled out across the UK | Science

An artificial intelligence system that can identify people most likely to suffer heart attacks within 10 years could soon be operational across Britain.

The technology, which could save thousands of lives a year, is being evaluated by the National Institute for Health and Care Excellence (Nice) and a decision on its use in the National Health Service is expected by the end of the year. .

Scientists on the project have also revealed that they are working on similar artificial intelligence systems to predict whether someone is in danger of having a stroke and detect those at risk of diseases such as diabetes.

“This technology has already been trialled in a number of hospitals across the UK and the results have been tremendously encouraging,” said Professor Charalambos Antoniades, leader of the Orfan (Oxford Risk Factors And Non Invasive Imaging) study. “If installed nationwide, it would help save thousands of people from premature heart attacks or deaths from heart disease.”

More than 300,000 people in Britain suffered severe chest pain each year and underwent CT scans to find out if they had heart abnormalities such as arterial blockages, Antoniades said. However, less than 20% of those examined were found to have blockages or dangerous narrowing of their coronary arteries. “The remaining 80% do not show anomalies. They are calmed down and sent home, very often without any medication,” said Antoniades, professor of cardiovascular medicine at the University of Oxford. “However, these assurances are often misplaced.”

Professor Charalambos Antoniades led the study. Photography: Brochure

In fact, about two-thirds of this “safe” group suffer major, sometimes fatal cardiac events, including heart attacks. “We have clearly been missing signals from our scanners that could tell us about those who are in real danger,” he added. “It’s a huge health problem and we believe AI is the perfect technology to address it.”

The research, led by a team from the Radcliffe Department of Medicine at the University of Oxford and published in the Lancet last week, has been designed to detect abnormalities that are not detected in standard CT (computed tomography) scans. This knowledge would allow doctors to give patients preventive treatments, such as anti-inflammatory medications.

Much of the problem was that damage to an artery caused by inflammation was not detected by a CT scan, Antoniades said. “Our discovery was to find a way to reveal hidden information by using AI to enhance our CT scan images and show what damage has been caused. In the past we were not able to imagine this, but now we can.”

The technique uses data on the characteristics of coronary plaques, as well as changes in fat around inflamed arteries, to provide key information about the health of our heart’s arteries. “Basically, these readings tell us what the absolute risk is of a patient suffering a fatal cardiac event in the next 10 years,” she said.

These risk factors were originally determined using US case studies, but the data has since been evaluated with 40,000 patients in UK hospitals.

skip past newsletter promotion

“What we found was clear. Patients who had high inflammation in their coronary arteries were also found to have an extremely high risk of serious heart disease, such as heart attacks. We have found a way to identify the hidden factors that lead to heart attacks.

The study, funded by the British Heart Foundation, revealed that in 45% of cases, doctors decided to change a patient’s treatment in light of the data provided by the AI ​​analysis. These treatments include administering high doses of statins or medications such as colchicine, which are known to reduce the risk of cardiovascular disease.

Antoniades added: “We are also planning to expand the delivery of this UK-made technology in the US, where it is also being evaluated by the Food and Drug Administration, and in Europe, where it is already approved for clinical use.” .

Leave a Comment