Researchers at the University of Oxford have created an AI tool that can identify the risk of heart failure up to five years before it happens.
This is important because more than 60 million people worldwide currently suffer from heart failure, a condition where the heart cannot pump blood effectively.
Oxford Scientists Develop AI Tool to Predict Heart Failure Years in Advance
Early detection could allow doctors to manage or even prevent the condition before it becomes severe.
The tool works by analyzing fat around the heart to detect signs of inflammation and poor health that are not visible to the human eye.
Until now, doctors could not reliably predict heart failure using standard cardiac CT scans, making this development significant.
Additionally, the system provides a risk score for each patient, helping doctors decide how closely someone should be monitored or treated.
Notably, people in the highest risk group were 20 times more likely to develop heart failure than those in the lowest group.
In fact, these high-risk individuals had about a 25% chance of developing the condition within five years.
The tool was tested on 72,000 patients across nine NHS trusts in England and tracked over ten years.
It achieved an accuracy rate of 86% in predicting heart failure within five years.
These findings were published in the Journal of the American College of Cardiology.
Professor Charalambos Antoniades explained, “We have used developments in bioscience and computing to take a big step forward in treating heart failure.”
He added that the tool can generate a patient’s risk score automatically from CT scan data without human input.
Oxford AI Tool Could Expand to All CT Scans as Researchers Seek NHS Approval
Furthermore, the team aims to apply this method to all chest CT scans, not just heart-specific ones.
This could help doctors make better treatment decisions and focus care on high-risk patients.
The researchers are now seeking approval to introduce the tool into healthcare systems like the NHS.
They plan to integrate it into routine hospital scan analysis in radiology departments.
Dr. Sonya Babu-Narayan stated, “Heart failure is consistently diagnosed too late… which might have been avoided.”
She emphasized that earlier detection would allow better care and improve patients’ chances of living longer.
Experts still recommend healthy habits like eating well, exercising, avoiding smoking, limiting alcohol, and controlling blood pressure to reduce heart risk.
