A new AI tool can identify people who have a heart condition before symptoms arise, reducing the risk of potentially deadly strokes.
The ground-breaking tool scours GP records to look for “red flags” which could indicate whether a patient is at risk of developing atrial fibrillation (AF).
The algorithm was created using anonymised electronic health records of more than 2.1 million people and was validated with medical records from a further 10 million people.
AF causes an irregular and often abnormally fast heart rate, and people with it have a significantly higher risk of having a stroke.
For some, AF can lead to heart palpitations, dizziness, shortness of breath and tiredness. But others have no symptoms of the condition, and the affected person is completely unaware that their heart rate is irregular.
When identified and treated early it can be managed and the stroke risk reduced.
Around 1.6 million people across the UK have been diagnosed with AF, but the British Heart Foundation (BHF) says there are likely many thousands of undiagnosed people in the UK who are unaware they’re living with the condition.
Six-month trial
Developed by scientists and clinicians at the University of Leeds and Leeds Teaching Hospitals NHS Trust, the tool is being assessed in a six-month trial in some surgeries in West Yorkshire.
It works out 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.
Those identified as being at high risk are offered a handheld electrocardiography (ECG) machine to measure their heart rhythm twice a day for four weeks, as well as any time they feel heart palpitations.
If the ECG machine readings indicate that a patient has AF, their GP is informed, and they can discuss treatment options. If successful, a UK-wide trial could follow.
A milestone in stroke prevention
Estimates suggest that AF is a contributing factor in around 20,000 strokes every year in the UK.
Dr Sonya Babu-Narayan, associate medical director at the BHF and consultant cardiologist at Royal Brompton Hospital, said: “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.”
It comes as NHS officials said the service has hit a milestone in stroke prevention, by increasing the number of patients with AF on potentially life-saving blood clot-preventing medicine by 8% in the last five years.
As a result, it estimates that thousands of strokes have been prevented in the last five years.