Oxford AI tool predicts heart failure risk five years early by detecting invisible heart fat

AI Predicts Heart Failure Risk From 'Invisible' Heart Fat

An artificial intelligence (AI) tool can identify hidden changes in fat around the heart and predict a patient's risk of heart failure up to 5 years in advance, a new study suggests. Researchers at the University of Oxford developed the tool to analyse routine cardiac CT scans, detecting subtle textural changes in pericardial fat linked to inflammation and underlying heart muscle disease. These changes are not visible to clinicians using standard imaging techniques, the British Heart Foundation (BHF), which funded the study, said. The AI model was trained and validated using data from 72,000 patients across nine NHS trusts in England who underwent cardiac CT scans between 2007 and 2022. AI analysis of these scans can warn doctors when a patient is at high risk of heart failure, which means the heart is unable to pump blood around the body properly. Patients classified as highest risk were 20 times more likely to develop heart failure than those at lowest risk. One in four high-risk patients developed the condition within 5 years. High-Risk Patients Identified Years Before Symptoms Overall, the algorithm predicted 5-year heart failure risk with 86% accuracy, the researchers reported in the Journal of the American College of Cardiology. The BHF said that until now, there has been no way to accurately predict who may develop heart failure this way. The charity said that the algorithm was found to predict the risk that a person developed heart failure in the next 5 years with 86% accuracy. It said that researchers are now looking to roll the tool out across the NHS. With around 350,000 patients are referred for a cardiac CT scan each year in the UK, the tool has the potential to have a big impact. Dr Sonya Babu-Narayan, clinical director at the British Heart Foundation, 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." Professor Charalambos Antoniades, British Heart Foundation professor of cardiovascular medicine at the University of 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. "We hope that, if this programme is rolled out nationwide, it could reduce hospital pressures by helping patients live well for longer."

Scientists develop AI tool to spot heart failure risk five years before it strikes

Oxford team's technology picked up danger signs with 86% accuracy in study of 72,000 patients in England Oxford scientists have developed a simple AI tool that can predict the risk of heart failure five years before it develops. More than 60 million people worldwide have the condition in which the heart cannot pump blood around the body as well as it should. Spotting cases before they develop into heart failure would be a big step forward, experts say. Doctors could prepare better for and manage the condition at an earlier stage or even prevent it entirely. The AI tool, developed by a team at the University of Oxford, looks for signs in fat around the heart that indicate whether it is inflamed and unhealthy. The signs are not visible to the human eye. Until now, there had not been a way to accurately predict heart failure using routine cardiac CT scans, the researchers said. The tool provides doctors with a patient's risk score that could help them make decisions about care such as 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 they 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% accuracy. The results were published on Wednesday in the Journal of the American College of Cardiology. Charalambos Antoniades, a 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." The Oxford team is seeking regulatory approval to roll out the tool in healthcare systems including in the NHS. They hope to add it to routine cardiac CT scan analysis performed in hospital radiology departments. Dr Sonya Babu-Narayan, the 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 say the best way to boost heart health is to eat plenty of fruit and vegetables, stay physically active, stick to a healthy weight, quit smoking, reduce alcohol consumption and keep blood pressure under control.