An artificial intelligence system that can identify people who are likely to suffer heart attacks up to 10 years in the future could soon be in operation across Britain. The technology, which could save thousands of lives a year, is being assessed by the National Institute for Health and Care Excellence (Nice) and a decision on its use in the NHS is expected by the end of the year. The project’s scientists have also revealed they are working on similar AI systems to predict whether someone is in danger of suffering a stroke and to spot those at risk of conditions such as diabetes. “This technology has now been tested at several hospitals across the UK and results have been tremendously encouraging,” said Prof Charalambos Antoniades, leader of the Orfan (Oxford Risk Factors And Non Invasive Imaging) study. “If installed nationally, it would help save thousands of people from suffering early heart attacks or deaths from heart disease.” More than 300,000 people in Britain each year suffered severe chest pains and were given CT scans to discover if they were suffering from cardiac abnormalities such as arterial blockages, said Antoniades. Fewer than 20% of those scanned were found to have obstructions or dangerous narrowing of their coronary arteries, however. “The remaining 80%-plus show no abnormalities. They are reassured and sent home,very often without any medication,” said Antoniades, chair of cardiovascular medicine at the University of Oxford. “However, these reassurances are often misplaced.” In fact, about two-thirds of this “safe” group go on to suffer major – sometimes fatal – cardiac events, including heart attacks. “Clearly we have been missing signals from our scans that could tell us about those who are in real danger,” he added. “It is a massive healthcare problem, and we believe AI is the perfect technology to deal with it.” The research, led by a team at Oxford University’s Radcliffe Department of Medicine and published in the Lancet last week, has been designed to spot the abnormalities that are being missed from standard CT (computed tomography) scans. This knowledge would allow doctors to give the patients preventative treatments such as anti-inflammatory drugs. Much of the problem was that damage to an artery caused by inflammation was not picked up by a CT scan, Antoniades said. “Our discovery was to find a way to bring up hidden information by using AI to enhance our CT scan images in order to show what damage has been done. In the past, we were not able to picture this but now we can.” The technique uses data on the characteristics of coronary plaques, as well as changes in the fat around inflamed arteries, to provide key information about the health status of our heart arteries. “Essentially, these readings tell us what is the absolute risk of a patient having a fatal cardiac event over the next 10 years,” he said. These risk factors were originally worked out using US case studies but the data has since been evaluated using 40,000 patients at UK hospitals. “What we found was clear-cut. Patients who were shown to have high inflammation in their coronary arteries were also found to be at extremely high risk of suffering severe cardiac illness, such as heart attacks. We have found a way to pinpoint the hidden factors that lead to heart attacks. The study, funded by the British Heart Foundation, revealed that in 45% of cases, clinicians decided to change a patient’s treatment in view of data that was provided by AI analysis. These treatments include giving high doses of statins or drugs such as colchicine, which are known to reduce risks of cardiovascular illness. Antoniades added: “We are also planning to expand delivery of this UK-made technology in the US, where it is also under evaluation by the Food and Drug Administration, and in Europe where it is already approved for clinical use.”