Nearly 2,000 people have taken part in the trial that aims to help doctors identify more people at risk of developing atrial fibrillation (AF), a common abnormal heart rhythm, which makes them five times more likely to have a potentially fatal or life-changing stroke.

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.

The West Yorkshire trial is investigating an algorithm called FIND-AF, developed using machine learning, which looks for red flags in people's GP records that suggest they're at risk of developing AF in the next six months. People identified as at risk of AF are offered at-home testing and those who agree are sent a handheld ECG machine – a device that can measure their heart rhythm – 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.

Professor Chris P Gale, honorary consultant cardiologist at Leeds Teaching Hospitals NHS Trust, said: ‘Our FIND-AF digital diagnostic and treatment care pathway supports government's ambition of moving from treating illness to preventing it.

‘We're now looking to partner with the NHS and other providers to accelerate its use more widely.'

The study is being funding by the British Heart Foundation and Leeds Hospitals Charity.