Artificial intelligence can detect those most at risk of a heart attack up to ten years in advance, a major study has found.
With trials of the technology finding it can spot warning signs that conventional scans miss, there is potential to save thousands of lives a year.
The study, which was led by Oxford University, showed that up to a fifth of heart attacks could be prevented. Meanwhile, the findings also indicated 8 per cent fewer deaths.
Researchers analysed the data of more than 40,000 patients undergoing routine cardiac CT scans at eight UK hospitals.
They found those whose results showed ‘significant’ narrowing of the arteries were more likely to have a serious heart attack. Yet twice as many patients with no significant narrowing also went on to have heart attacks.
The study, which was led by Oxford University, showed that up to a fifth of heart attacks could be prevented
The team then used a new AI tool, trained using information on changes in the fat around inflamed arteries, which can indicate the risk of events such as heart attacks.
Further testing on an additional 3,393 patients over several years revealed it could accurately predict the risk of cardiac events.
Among those with no obstructions to their arteries, those with the highest levels of inflammation in their blood vessels had a more than 10-fold higher risk of cardiac death compared to those with lower levels of inflammation.
In a world-first pilot presented at the American Heart Association’s Scientific Sessions in Philadelphia, they provided AI-generated risk scores to clinicians for 744 patients and found that in up to 45 per cent of cases, clinicians altered patients’ treatment plans.
Professor Charalambos Antoniades, of the University of Oxford, said: ‘Our study found that some patients presenting in hospital with chest pain – who are often reassured and sent back home – are at high risk of having a heart attack in the next decade, even in the absence of any sign of disease in their heart arteries.
Researchers analysed the data of more than 40,000 patients undergoing routine cardiac CT scans at eight UK hospitals
‘Here we demonstrated that providing an accurate picture of risk to clinicians can alter, and potentially improve, the course of treatment for many heart patients.’
Professor Sir Nilesh Samani, medical director at the British Heart Foundation, said it shows the ‘valuable role AI-based technology can play’ in identifying those most at risk of future heart attacks.
He said: ‘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.’
It comes as the NHS revealed a series of pilot schemes using AI to try and prevent hospital admissions this winter.
They include an initiative in Buckinghamshire to track frail people’s eating and drinking habits in their homes in a bid to prevent them being admitted to hospital.
The new AI tool is trained using information on changes in the fat around inflamed arteries, which can indicate the risk of events such as heart attacks
Electronic sensors will be placed on kettles and fridges to track changes in patterns of consumption, which are then flagged with a care team.
Meanwhile, NHS teams in Birmingham are piloting an algorithm to prevent thousands of hospital or GP visits.
It predicts the top 5 per cent of patients at risk of attending or being admitted to hospital so staff can check in to offer social care measures.
Over the next two years, the scheme is aiming to prevent 4,500 unnecessary trips to A&E, as well as 17,000 overnight hospital stays and 23,000 GP appointments.
Amanda Pritchard, head of NHS England, said it will help to identify the ‘most at-risk or vulnerable patients’ and reduce the number of avoidable A&E attendances.