Loading...
Atrial fibrillation (AF) is associated with increased risks for stroke and other thromboembolic complications. By identifying asymptomatic AF, clinicians might be able to improve outcomes by instituting earlier use of anticoagulation. The rapid adoption of smartwatches in the general population may serve as an opportunity for population-based AF detection. To develop and train a neural network machine-learning model to detect AF, researchers used heart rate and step count data from 9750 participants enrolled in the Health eHeart Study, who were each fitted with a commercially available smartwatch. Data were obtained via a publicly accessible mobile phone app; its manufacturer provided some funding.
The model was validated in 51 patients undergoing cardioversion, with excellent sensitivity (98%) and specificity (90%). The model performed less well in 1617 ambulatory patients (64 with self-reported persistent AF), with sensitivity and specificity of 68%.
Tison GH et al. Passive detection of atrial fibrillation using a commercially available smartwatch. JAMA Cardiol 2018 Mar 21; [e-pub]. (https://doi.org/10.1001/jamacardio.2018.0136)
Comment
These findings show the potential of smartwatches to passively detect AF. However, challenges remain in generalizing from study results to ambulatory populations who are constantly moving and so providing countless data points for interpretation. Machine-learning algorithms will need to differentiate noise from clinically relevant signals. Although clinical applications of rhythm detection algorithms using data from wearable devices are in their infancy, direct-to-consumer technologies can eventually increase the reach of AF detection and the earlier use of prevention strategies.