Oxford scientists have developed a simple AI tool that can predict the risk of heart failure five years before it develops, according to a study published in the Journal of the American College of Cardiology. The technology, trained and validated on 72,000 patients from nine NHS trusts in England, identified danger signs with 86% accuracy.
The AI examines fat around the heart for signs of inflammation and unhealthiness that are invisible to the human eye. It provides doctors with a risk score, helping them decide on care intensity. Patients in the highest risk group were 20 times more likely to develop heart failure than those in the lowest, with about a one in four chance within five years.
Professor Charalambos Antoniades, who led the research at the University of Oxford, said the tool uses cardiac CT scan data to produce an absolute risk score without human input. The team is now working to apply the method to any chest CT scan, aiming for regulatory approval to roll it out in healthcare systems including the NHS.
Dr Sonya Babu-Narayan of the British Heart Foundation, which funded the study, noted that heart failure is often diagnosed too late. She said the tool could help doctors spot it earlier, enabling better management and potentially preventing severe heart muscle damage.
