AI trial to spot heart condition before symptoms

The tool scours medical records for potential risk factors

A new artificial intelligence tool is being used to identify people with a heart condition before they even have symptoms.

The tool scours GP records to look for "red flags" which could indicate whether a patient is at risk of developing atrial fibrillation (AF).

AF is a heart condition that causes an irregular and often abnormally fast heart rate. People with it have a significantly higher risk of having a stroke.

John Pengelly, from Apperley Bridge, Bradford, said he was "really grateful" his AF was detected in the trial.

The 74-year-old former Army captain said he now takes medication daily to reduce his heightened risk of a potentially deadly stroke.

About 1.6 million people across the UK have been diagnosed with AF, but heart charity the British Heart Foundation (BHF) said there were likely thousands more undiagnosed people unaware they were living with the condition.

When AF is identified and treated early it can be managed and the stroke risk reduced.

Developed by scientists and clinicians at the University of Leeds and Leeds Teaching Hospitals NHS Trust, the tool is being assessed in a trial, called Find-AF, which is being funded by the BHF and Leeds Hospitals Charity.

The algorithm has been trained to find warning signs that could indicate a person is at risk of developing AF and is currently being used to examine GP records at several surgeries in West Yorkshire.

Mr Pengelly, who spent 29 years in the Army Catering Corps before he retired, was diagnosed with AF after accepting an invitation to take part in the trial.

"You never think these things will happen to you," he said.

He said he never had any symptoms, but now takes "a few pills every day that will hopefully keep me going for a good few more years yet".

The technology has been developed by the University of Leeds and Leeds Teaching Hospitals NHS Trust

The algorithm works out someone's risk based on factors including age, sex, ethnicity and whether or not they have other medical conditions, including heart failure, high blood pressure, diabetes, ischaemic heart disease and chronic obstructive pulmonary disease.

Estimates suggest AF is a contributing factor in around 20,000 strokes every year in the UK.

"All too often the first sign that someone is living with undiagnosed AF is a stroke," said Chris Gale, a professor of cardiovascular medicine at the University of Leeds and honorary consultant cardiologist at Leeds Teaching Hospitals NHS Trust.

"This can be devastating for patients and their families, changing their lives in an instant.

Dr Ramesh Nadarajah, from Leeds Teaching Hospitals NHS Trust, said it was hoped the West Yorkshire study would pave the way for a UK-wide trial, which would hopefully prevent a number of avoidable strokes.

"Ultimately, we hope that this approach will lead to an increase in the number of people diagnosed with AF at an early stage who get the treatment they need to reduce their risk of stroke," he said.

Listen to highlights from West Yorkshire on BBC Sounds, catch up with the latest episode of Look North or tell us a story you think we should be covering here.