Dr Sonya Babu-Narayan
Clinical Director at the British Heart Foundation and consultant cardiologist
A routine heart test has hit the headlines after it was given a makeover for the 21st century.
Artificial intelligence is increasingly part of everyday life, and its role in healthcare continues to grow. Thanks to the generosity of the public, the BHF has been able to fund research that is harnessing the power of cutting-edge science and emerging technology, including AI.
Around a billion ECGs are performed worldwide each year
Recently, at the world’s biggest heart conference, a team of researchers led by Professor Fu Siong Ng presented their study applying AI to electrocardiograms (ECGs).
The ECG is one of the most common tests in medicine, which records the rhythm, rate and electrical activity of your heart. It is routinely used to diagnose conditions such as heart attacks and abnormal heart rhythms. But an ECG contains far more information than the human eye can typically see — which AI can now detect in less than two seconds.
Technology like this has the potential to identify high-risk patients early,
AI detects heart disease from ECGs
The researchers from Imperial College London trained the technology on ECGs from millions of patients, then tested it on a further 65,000 ECGs. It identified around 80% of patients who had heart failure and 90% of patients with heart valve disease.
The technology cannot be used on its own to definitively diagnose or rule out heart failure or heart valve disease. However, it could give a strong indication that someone may have these conditions.
AI can speed up ECG interpretation
Technology like this has the potential to identify high-risk patients early, even though – like any test – we can’t rely on it to detect everyone with a heart condition. However, it could be a solution to help fast-track the patients most likely to have a heart abnormality for the tests and the treatment they need.
ECGs are cheap and common tests used around the world. Applying AI to an ECG trace for further diagnosis and triage has the potential to save or improve the lives of millions.
