Mayo Clinic researchers developed the device to detect the electrocardiogram signature of atrial fibrillation present during normal sinus rhythm (using standard 10-second, 12-lead ECGs) and analyzed data from nearly 650,000 sinus rhythm electrocardiograms in more than 180,000 adults between December 1993 and July 2017. They divided participants into three groups: training (70%), internal validation (10%), and testing (20%).
The testing group used the artificial intelligence-enabled ECG. The artificial intelligence model identified the presence of artificial intelligence with 79% accuracy for a single scan and 83% accuracy when analyzing multiple ECGs for the same patient.
Atrial fibrillation presents as an irregular and often rapid heart rate and is among the most common arrhythmias seen in seniors. The condition can increase the risk of stroke, heart failure and other cardiac-related complications.
The study was published August 1 in The Lancet online.