NAIROBI, Kenya- Imagine discovering a hidden heart condition before it ever causes a problem.
That’s exactly what a new artificial intelligence tool is doing—scanning GP records for early warning signs of atrial fibrillation (AF), a condition that dramatically increases the risk of stroke.
Developed by scientists at the University of Leeds and Leeds Teaching Hospitals NHS Trust, this AI-powered system is part of a groundbreaking trial called Find-AF, funded by the British Heart Foundation (BHF) and Leeds Hospitals Charity.
The goal? Spot AF early, get patients on treatment, and prevent life-threatening strokes before they happen.
Instead of waiting for symptoms to appear—or worse, for a stroke to be the first sign of trouble—this algorithm analyzes GP records for red flags. It factors in Age, sex, ethnicity and Medical history.
Once a potential AF case is flagged, doctors can bring the patient in for further evaluation and, if necessary, start treatment right away.
For patients like John Pengelly, a 74-year-old former Army captain from Apperley Bridge, Bradford, this AI tool has been life-changing.
Despite having zero symptoms, he was diagnosed with AF through the trial and now takes daily medication to reduce his stroke risk.
“You never think these things will happen to you,” he said. “But now I take a few pills every day that will hopefully keep me going for a good few more years yet.”
“Too often, the first sign that someone has undiagnosed AF is a stroke. This can be devastating for patients and their families, changing their lives in an instant.”
By using AI to catch AF before symptoms develop, doctors hope to dramatically reduce the number of preventable strokes—and potentially save thousands of lives.
