Scientists have developed a predictive AI model for heart failure.
New AI model detects early heart failure risk
Researchers at the University of Oxford have created an artificial intelligence tool capable of identifying an individual’s risk of developing heart failure up to five years before clinical onset, marking a significant advance in early cardiovascular diagnostics.
The system analyses cardiac CT scans to detect subtle inflammatory changes in perivascular fat surrounding the heart - biological signals that are not visible to the human eye. These markers are associated with early pathological processes that precede the onset of heart failure, a condition affecting more than 60 million people globally.
Trained and validated on data from 72,000 patients across nine NHS trusts in England, the model demonstrated an accuracy rate of 86 per cent in predicting five-year risk. Patients identified as high risk were found to be up to 20 times more likely to develop heart failure, with approximately a 25 per cent probability of onset within five years.
Charalambos Antoniades, who led the research, told The Guardian: “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.”
The research team is now seeking regulatory approval to integrate the tool into clinical workflows, including routine imaging analysis within the NHS.
Dr Sonya Babu-Narayan, clinical director at the British Heart Foundation and lead initiator of the study, added: “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.”