A brief, non-invasive test using artificial intelligence has been found to identify patients with abnormal heart rhythm even when their rhythm seems normal.
The study, which involved almost 181,000 patients, is the first to use deep learning to find signals in heart scans that might be invisible to the human eye.
Writing in The Lancet, researchers from the Mayo Clinic describe how they trained an AI model to detect the signature of atrial fibrillation in 10-second electrocardiograms (ECGs), with 83% accuracy.
Atrial fibrillation is estimated to affect as many as six million people in the US alone, and is associated with increased risk of stroke, heart failure and mortality.
It is difficult to detect on a single ECG because patients’ hearts can go in and out of this abnormal rhythm, so atrial fibrillation often goes undiagnosed.
“Applying an AI model to the ECG permits detection of atrial fibrillation even if not present at the time the ECG is recorded,” says co-author Paul Friedman. “It is like looking at the ocean now and being able to tell that there were big waves yesterday.”
The researchers trained a neural network to recognise subtle differences in nearly 650,000 ECGs from the 181,000 patients.
Testing on the first cardiac ECG output from each patient, the accuracy was 79% for a single scan; when using multiple ECGs for the same patient the accuracy improved to 83%.
Friedman notes that as the AI was trained using ECGs from people who needed clinical investigations, it is not yet clear how it would perform diagnosing people with unexplained stroke, or the general population.
“However, the ability to test quickly and inexpensively with a non-invasive and widely available test might one day help identify undiagnosed atrial fibrillation and guide important treatment, preventing stroke and other serious illness,” he adds.
Further research is needed before clinical application is possible, but nevertheless the researchers speculate that it may one day be possible to use this technology as a point-of-care diagnostic test in a doctor’s surgery to screen high-risk groups.