An AI tool predicted heart failure risk up to five years before onset with 86 per cent accuracy in 72,000 patients in England, researchers said.
The AI tool, developed by a team at the University of Oxford, looks for signs in fat around the heart that show whether it is inflamed and unhealthy.
Those signs are not visible to the human eye.
Charalambos Antoniades, professor of cardiovascular medicine at Oxford, who led the research, said: “We have used developments in bioscience and computing to take a big step forward in treating heart failure.
“Our new AI tool is able to take cardiac CT scan data and produce an absolute risk score for each patient without any need for human input.
“Although this study used cardiac CT scans, we are now working towards applying this method to any CT scan of the chest, performed for any reason.
“This will allow doctors to make more informed decisions about the best way to treat patients, giving the most intensive treatment to those at the highest risk.”
Until now, there had not been a way to accurately predict heart failure using routine cardiac CT scans, the researchers said.
The tool gives doctors a patient’s risk score, which could help them make decisions about care, including how closely patients should be monitored.
Those in the highest risk group were 20 times more likely to develop heart failure than those in the lowest risk group and had about a one in four chance of developing the condition within five years.
The AI tool was trained and validated in 72,000 patients from nine NHS trusts in England, who were followed up for a decade after their CT scans. It predicted their risk of developing heart failure in the next five years with 86 per cent accuracy.
The Oxford team is seeking regulatory approval to roll out the tool in healthcare systems including the NHS.
They hope to add it to routine cardiac CT scan analysis carried out in hospital radiology departments.
Sonya Babu-Narayan, clinical director at the British Heart Foundation, which funded the study, said: “Heart failure is consistently diagnosed too late, sometimes only when a patient is admitted to hospital. Late diagnosis may mean patients already have severe damage to their heart muscle which might have been avoided.
“This tool could help doctors spot heart failure earlier, by monitoring more closely those at highest risk.
“Early heart failure diagnosis is crucial – it means doctors can better manage someone’s condition which gives them a fighting chance of living longer in better health.
“This study demonstrates the power of harnessing technology to unlock improvements in cardiovascular care.”
Experts said the best ways to support heart health include eating plenty of fruit and vegetables, staying physically active, keeping to a healthy weight, quitting smoking, reducing alcohol intake and keeping blood pressure under control.
