Artificial intelligence can predict a person's risk of having a heart attack up to ten years in advance, according to a study released on Monday. Researchers at Oxford University found that AI can enhance the accuracy of cardiac CT scans, which are performed on 350,000 patients in the UK each year.
Standard scans often miss small blockages or narrowing in arteries that can lead to future heart attacks. The British Heart Foundation reports that nearly 100,000 hospital admissions annually are due to heart attacks. Scientists analysed data from over 40,000 patients undergoing routine cardiac CT scans at eight UK hospitals, with a median follow-up of 2.7 years.
They discovered that patients with 'significant' narrowing of arteries were more likely to have a serious heart attack, but twice as many patients without significant narrowing also went on to have heart attacks, sometimes fatal. The AI was trained to detect changes in fat around inflamed arteries, which can indicate heart attack risk. Tested on 3,393 patients over nearly eight years, the tool accurately predicted risk.
When AI-generated risk scores were presented to doctors for 744 patients, nearly half (45 per cent) had their treatment plans altered. Professor Sir Nilesh Samani, medical director at the British Heart Foundation, said: 'Too many people are needlessly dying from heart attacks each year. It is vital we harness the potential of AI to guide patient treatment, as well as ensuring that the NHS is equipped to support its use.'
He added: 'We hope that this technology will ultimately be rolled out across the NHS, and help to save the lives of thousands each year who may otherwise be left untreated.' The breakthrough follows a separate AI model developed by London scientists that can accurately identify cancer from CT scans.
