LONDON: A new artificial intelligence (AI) tool in the UK is finding people with a heart condition before they even have symptoms, reported German news agency (dpa).
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).
One former army captain who took part in the trial said he is "really grateful" that his AF was detected.
John Pengelly said he now just takes a "couple of pills a day" to reduce his heightened risk of a potentially deadly stroke.
AF is a heart condition that 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 effected person is completely unaware that their heart rate is irregular.
Around 1.6 million people across the UK have been diagnosed with AF.
But leading heart charity the British Heart Foundation (BHF) said there are likely many thousands of undiagnosed people in the UK who are unaware they're living with the condition.
When AF is identified and treated early, it can be managed and the stroke risk reduced.
The new AI tool is being assessed in a trial, called Find-AF, which is being funded by BHF and Leeds Hospitals Charity.
The algorithm was developed by scientists and clinicians at the University of Leeds and Leeds Teaching Hospitals NHS Trust, with funding from the BHF.
They created the tool using anonymised electronic health records of over 2.1 million people, training the algorithm to find warning signs that could indicate a person is at risk of developing AF.
The tool was validated with medical records from a further 10 million people.
Experts are assessing how effective it is at finding people who are at risk of developing AF in the next six months, with those identified then offered further testing.
The algorithm is examining GP records at several surgeries in West Yorkshire.
The algorithm works out someone's risk based on a number of 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.
If people involved in the study are identified as high risk, they will be 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.
Experts hope that the West Yorkshire study will pave the way for a UK-wide trial, which would hopefully prevent a number of avoidable strokes.
Estimates suggest that AF is a contributing factor in around 20,000 strokes every year in the UK.
Chris Gale, professor of cardiovascular medicine at the University of Leeds and honorary consultant cardiologist at Leeds Teaching Hospitals NHS Trust, said: "All too often the first sign that someone is living with undiagnosed atrial fibrillation is a stroke.
"This can be devastating for patients and their families, changing their lives in an instant. It also has major cost implications for health and social care services – costs which could have been avoided if the condition was spotted and treated earlier."
Sonya Babu-Narayan, associate medical director at the British Heart Foundation and consultant cardiologist at Royal Brompton Hospital, 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."
Ramesh Nadarajah, from Leeds Teaching Hospitals NHS Trust, said: "Data are collected about patients in every interaction they have with the NHS.
"These data have huge potential to make early identification of and testing for conditions like AF easier and more efficient.
"If it's successful, this study will be the launchpad for a larger nationwide trial to determine whether our algorithm could become part of everyday clinical practice.
"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."
