Artificial intelligence could predict if a person is at risk of having a heart attack up to 10 years in the future, a study revealed on Monday.
Researchers at Oxford University found that AI could help improve the accuracy of cardiac CT scans, which are carried out on 350,000 patients in the UK each year.
The scans regularly fail to detect small blockages or narrowing in the arteries that can lead to a future heart attack.
Nearly 100,000 hospital admissions each year are due to heart attacks, according to the British Heart Foundation.
Scientists analysed data from more than 40,000 patients undergoing routine cardiac CT scans at eight UK hospitals, with a median follow-up time of 2.7 years.
They found those whose results showed “significant” narrowing of the arteries were more likely to have a serious heart attack, but twice as many patients with no significant narrowings also went on to have heart attacks, which were sometimes fatal.
The AI was trained using information on changes in the fat around inflamed arteries, which can signify the risk of a heart attack.
It was then tested on a further 3,393 patients over almost eight years, with results showing that the tool could accurately predict the risk of a heart attack.
AI-generated risk scores were then presented to doctors for 744 patients, with nearly half (45 per cent) having their treatment plans altered by medics as a result.
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.
“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 comes months after London scientists and doctors unveiled an AI model that can accurately identify cancer.
A study found that the tool, designed by experts at the Royal Marsden NHS Trust and the Institute of Cancer Research, is more efficient than current methods at identifying whether abnormal growths found on CT scans are cancerous.
