An artificial intelligence system that can identify people who are likely to have a heart attack within the next 10 years could soon be operational across the UK.
The technology, which has the potential to save thousands of lives a year, is being assessed by the UK’s National Institute for Health and Care Excellence (Nice), with a decision on its use in the NHS expected to be made by the end of the year.
Scientists on the project also said they were working on developing similar AI systems that could predict whether someone is at risk of having a stroke, or identify people at risk of diseases like diabetes.
“The technology is currently being tested in several hospitals across the UK and the results are very promising,” said Professor Charalambos Antoniades, leader of the ORPHAN (Oxford Risk Factor and Non-Invasive Imaging) study. “If rolled out nationwide, it could save thousands of people from premature heart attacks and death from heart disease.”
More than 300,000 people in the UK suffer from severe chest pain each year and have a CT scan to check for blocked arteries and other heart problems, Antoniades said. But of those who have a scan, fewer than 20% are found to have blocked or dangerously narrowed coronary arteries. “For the remaining 80% or more, nothing is found and they are sent home with reassurance, and often no medication,” said Antoniades, director of cardiovascular medicine at the University of Oxford. “But these reassurances are often misplaced.”
In fact, about two-thirds of this “safe” group will suffer a serious, sometimes fatal, heart attack, including a heart attack. “We’ve clearly been missing signals from the scans that could tell us about people who are really at risk,” he added. “This is a huge medical problem, and we believe AI is the perfect technology to address it.”
The study was led by a team from the Radcliffe School of Medicine at the University of Oxford. Lancet The study, published last week, aims to spot abnormalities that would be missed on standard CT scans — information that could allow doctors to prescribe preventative treatments, such as anti-inflammatory drugs, to patients.
Much of the problem was that CT scans didn’t pick up the damage to arteries caused by inflammation, Antoniades said. “Our discovery was to find a way to unlock that hidden information by using AI to enhance the CT scan images and show us what damage has occurred. We couldn’t image this before, but now we can.”
The technology uses data on the characteristics of coronary plaque and changes in the fat around inflamed arteries to provide important information about the health of the heart’s arteries. “Essentially, these measurements tell us what the absolute risk of a patient having a fatal heart attack is over the next 10 years,” he said.
These risk factors were originally calculated using US case studies, but the data was then evaluated using 40,000 patients from UK hospitals.
After newsletter promotion
“What we found is clear: patients with high levels of inflammation in their coronary arteries are also at significantly higher risk of suffering serious heart problems, including heart attacks. We have discovered a way to pinpoint the hidden factors that lead to heart attacks.”
The study, funded by the British Heart Foundation, found that in 45% of cases, clinicians decided to change patients’ treatment after taking into account the data provided by AI analysis. These treatments include higher doses of drugs such as statins and colchicine, which are known to reduce the risk of cardiovascular disease.
Antoniades added: “We plan to expand availability of this UK-made technology to the US, where it is undergoing evaluation by the Food and Drug Administration, and in Europe, where it has already been approved for clinical use.”
