Atrial fibrillation detection in outpatient electrocardiogram monitoring: An algorithmic crowdsourcing approach

Diagnostic validation of smart wearable device embedded with single-lead electrocardiogram for arrhythmia detection

Objective

To validate a single-lead electrocardiogram algorithm for identifying atrial fibrillation, atrial premature beats, ventricular premature beats, and sinus rhythm.

Methods

A total of 656 subjects aged 19 to 94 years were enrolled. Participants were simultaneously tested with a wristwatch (Huawei Watch GT2 Pro, Huawei Technologies Co., Ltd, Shenzhen, China) and a 12-lead electrocardiogram for 3 minutes. A total of 1926 electrocardiogram signals from 628 subjects (282 men and 346 women) aged 19 to 94 years (median 64 years) were analyzed using an algorithm.

Results

The numbers of subjects with atrial fibrillation, atrial premature beats, ventricular premature beats, and sinus rhythm were 129, 141, 107, and 251, respectively, and together they had a total of 1926 electrocardiogram signals. For the three-class classification system, the recall, precision, and F1 score were 97.6%, 96.5%, 97.0% for sinus rhythm; 96.7%, 96.9%, 96.8% for atrial fibrillation; and 92.8%, 94.2%, 93.5% for ectopic beats, respectively. The macro-F1 score of the three-class classification system was 95.8%. For the four-class classification system, the recall, precision, and F1 score were 97.6%, 96.5%, 97.0% for sinus rhythm; 96.7%, 96.9%, 96.8% for atrial fibrillation; 90.5%, 89.4%, 89.9% for atrial premature beats; and 86.1%, 89.6%, 87.8% for ventricular premature beats, respectively. The macro-F1 score of the four-class classification system was 92.9%.

Conclusions

The single-lead electrocardiogram algorithm embedded into smart wearables demonstrated good performance in detecting atrial fibrillation, atrial/ventricular premature beats, and sinus rhythm, and thus would facilitate atrial fibrillation screening and management.

Artificial intelligence for the detection, prediction, and management of atrial fibrillation

The present article reviews the state of the art of machine learning algorithms for the detection, prediction, and management of atrial fibrillation (AF), as well as of the development and evaluation of artificial intelligence (AI) in cardiology and beyond. Today, AI detects AF with a high accuracy using 12-lead or single-lead electrocardiograms or photoplethysmography. The prediction of paroxysmal or future AF currently operates at a level of precision that is too low for clinical use. Further studies are needed to determine whether patient selection for interventions may be possible with machine learning.

Smartwatch Electrocardiograms for Automated and Manual Diagnosis of Atrial Fibrillation: A Comparative Analysis of Three Models

Aims

The diagnostic accuracy of proprietary smartwatch algorithms and the interpretability of smartwatch ECG tracings may differ between available models. We compared the diagnostic potential for detecting atrial fibrillation (AF) of three commercially available smartwatches.

Methods

We performed a prospective, non-randomized, and adjudicator-blinded clinical study of 100 patients in AF and 100 patients in sinus rhythm, patients with atrial flutter were excluded. All patients underwent 4 ECG recordings: a conventional 12-lead ECG, Apple Watch Series 5®, Samsung Galaxy Watch Active 3®, and Withings Move ECG® in random order. All smartwatch ECGs were analyzed using their respective automated proprietary software and by clinical experts who also graded the quality of the tracings.

Results

The accuracy of automated AF diagnoses by Apple and Samsung outperformed that of Withings, which was attributable to a higher proportion of inconclusive ECGs with the latter (sensitivity/specificity: 87%/86% and 88%/81% vs. 78%/80%, respectively, p < 0.05). Expert interpretation was more accurate for Withings and Apple than for Samsung (sensitivity/specificity: 96%/86% and 94%/84% vs. 86%/76%, p < 0.05), driven by the high proportion of uninterpretable tracings with the latter (2 and 4% vs. 15%, p < 0.05).

Conclusion

Diagnosing AF is possible using various smartwatch models. However, the diagnostic accuracy of their automated interpretations varies between models as does the quality of ECG tracings recorded for manual interpretation.