New research shows that popular wearable devices can detect atrial fibrillation (AF), a common type of irregular heart rate.
The peer-reviewed study by researchers at the University of California, San Francisco (UCSF), used an app designed for the Apple Watch to find out whether a commercially available smartwatch coupled with a machine-learning algorithm could lead to earlier detection of AF — one of the leading causes of stroke.
Sometimes, AF doesn’t cause any symptoms and it can remain undetected until a stroke actually occurs. Earlier diagnosis would allow patients to be given treatment to mitigate the risk of stroke and other complications.
The study involved 9,750 participants in the UCSF Health eHeart Study (including 347 people with known AF), who wore smartwatches to collect heart rate and step count data in order to train the app’s deep neural network. Some participants also used a smartphone device equipped with electrodes to obtain a single electrocardiogram (ECG) to help train the AI algorithm.
Validation was performed against 51 patients with AF undergoing a cardioversion procedure, which electrically shocks the heart back into normal rhythm, and against a second validation group of 1,617 Health eHeart participants (64 with AF) using the Apple Watch.
When compared to the cardioversion cohort, the researchers found the algorithm was 97% accurate, while the two standard statistical methods for AF detection were 91% and 86% accurate. It was also significantly more accurate than the two standard methods in predicting AF in the second validation group, which only used the Apple Watch, at 72% versus 48% and 45%.
“By identifying candidates for appropriate anticoagulation treatment, we might ultimately leverage common wearable devices to reduce major thromboembolic complications, even death,” said senior author Dr Gregory Marcus, a UCSF Health cardiologist and director of clinical research in the UCSF Division of Cardiology.