The algorithm (Kardiaband, AliveCor) for atrial fibrillation (AF) detection, when supported by physician review can accurately differentiate AF from sinus rhythm (SR). This technology can help screen patients prior to elective cardioversion and avoid unnecessary procedures.
One hundred patients were enrolled in the study from March 2017 until June 2017. Cardioversion was performed in 85% of study participants. Of the 15 patients who did not undergo cardioversion, eight were cancelled due to presentation in sinus rhythm. There were 169 simultaneous 12-lead electrocardiogram (ECG) and band recordings obtained from study participants, and 57 band recordings were determined as unclassified by the band algorithm. Of the 57 unclassified band tracings, 16 (28%) were due to baseline artefact and low amplitude of the recording, 12 (21%) were due to a recording of less than 30 seconds in duration, six (10%) were due to a heart rate of less than 50 bpm, five (9%) were due to a heart rate of greater than 100 bpm, and the remaining 18 (32%) were unclassified due to an unclear reason. Electrophysiologist interpreted 12-lead ECGs were all interpretable.
In order to test the ability of the algorithm to detect atrial fibrillation (AF), automated band rhythm interpretations and electrophysiologist interpreted 12-lead ECGs were compared. Among the 112 recordings where the band provided a diagnosis, it correctly diagnosed AF with 93% sensitivity, 84% specificity and a K coefficient of 0.77 (95% confidence interval 0.65-0.89) when compared to the electrophysiologist interpreted 12-lead ECG.
To determine whether the automated band recordings labelled as “unclassified” by the algorithm were still clinically useful, these tracings were interpreted by blinded electrophysiologists and compared to the electrophysiologist interpreted 12-lead ECGs. Of the 57 automated unclassified band recordings, the interpreting electrophysiologists were able to correctly diagnose AF with 100% sensitivity, 80% specificity and a K coefficient of 0.74.
To assess the fidelity and overall quality of the band tracings produced by the smartwatch, electrophysiologist interpreted band recordings were compared to corresponding 12-lead ECG tracings. Twenty-two recordings were determined to be non-interpretable by the reading electrophysiologist, and these were predominately due to baseline artifact. Of the remaining 147 simultaneous recordings, the electrophysiologist interpreted 12-lead ECGs and electrophysiologist interpreted band recordings, physician interpretation of the band tracings demonstrated 99% sensitivity, 83% specificity and a K coefficient of 0.83.
The bands automated algorithm interpretation was compared to physician interpretation of the same recordings. Of the cases where both methods were interpretable, the band automated algorithm was 93% sensitive and 97% specific in detecting AF with a K coefficient of 0.88.
The study concluded that KardiaBand smartwatch automated algorithm for AF detection, supported by physician review of these recordings, can reliably differentiate AF from sinus rhythm. Avoiding scheduling unnecessary electrical cardioversions is one example of a clinical application of the KardiaBand system. Many other potential applications warrant further investigation and might transform care of AF patients.