Some 2,000 people have taken part in a ground-breaking trial to test an algorithm that can help doctors identify people at risk of developing atrial fibrillation (AF).
The trial is evaluating an algorithm called ‘FIND-AF’ – which was developed using machine learning – that looks for red flags in people’s GP records that suggest they’re at risk of developing AF in the next six months.
The trial is being funded by the charity the British Heart Foundation and means people identified by the algorithm are then offered further testing to confirm a diagnosis of AF.
The research team from the University of Leeds hope the West Yorkshire pilot will lay the groundwork for a UK-wide trial that could one day improve early diagnosis of AF and prevent more avoidable strokes.
Atrial fibrillation
Number of strokes will rise 51% by 2035, warns charity
Atrial fibrillation: blood thinners preventing thousands of strokes
Stroke risk fears as 1.5 million now have atrial fibrillation
More than 1.6 million people in the UK have been diagnosed with AF. But there are likely to be many thousands more people in the UK who remain undiagnosed and unaware they’re living with the condition. It’s estimated AF is a contributing factor in around 20,000 strokes each year in the UK.
In the study, led by Professor Chris Gale, professor of cardiovascular medicine at the University of Leeds, the algorithm has been integrated into medical records at several GP surgeries in West Yorkshire. People identified as at risk of AF are then offered at-home testing.
Those who agree are sent a handheld ECG machine and asked to take two readings a day for four weeks, as well as any time they feel palpitations. This can all be done with no need for people to visit their GP surgery.
If the ECG readings reveal that they have AF, their GP is informed, and they can then discuss treatment options.
Dr Sonya Babu-Narayan, BHF clinical director, said: “We have effective treatments for people with atrial fibrillation who are at high risk of having a stroke. But right now, some people are missing out because they don’t know that they may be living with this hidden threat to their health.
“By harnessing the power of routinely collected health care data and prediction algorithms, this research offers a real opportunity to identify more people who are at risk of atrial fibrillation, and who may benefit from treatment to reduce their risk of a devastating stroke.”
The FIND-AF algorithm was developed by scientists and clinicians at the University of Leeds and Leeds Teaching Hospitals NHS Trust, with funding from the charity.
Using the anonymised electronic health records of more than 2.1 million people, the team trained the algorithm to find warning signs that suggest that they’re at high risk of developing AF in the next six months.
The algorithm was then validated using data from over 10 million people in countries outside the UK. The trial is also being funded by Leeds Hospital Charity.
Sign up to our weekly round-up of HR news and guidance
Receive the Personnel Today Direct e-newsletter every Wednesday
