JMIR Publications

ABSTRACT

Background:

Atrial fibrillation (AF) and atrial flutter (AFL) are common arrhythmias associated with risk of ischemic stroke, which can be reduced with anticoagulation therapy. Thus, early diagnosis of AF and AFL is essential. However, diagnosis may be challenging due to the paroxysmal and asymptomatic nature of these arrhythmias.

Objective:

Current diagnostic workflows involve time-consuming and resource-intensive manual review of noisy signals and prolonged recordings. We evaluated a mobile system combining wireless wearable single-lead chest strap electrocardiogram (ECG) and novel deep neural network (DNN) based artificial intelligence (AI) method for detecting AF/AFL episodes, AF/AFL burden, and rhythm change and the detection delay in the change from AF/AFL to sinus rhythm (SR). Rhythm classification performance was also assessed.

Methods:

A total of 116 patients with recent-onset AF or AFL undergoing cardioversion were monitored using a mobile single-lead chest strap ECG system. Simultaneously, a three-lead Holter ECG served as the reference. The DNN-based AI analyzed single-lead chest strap ECG data to detect AF/AFL, non-AF/AFL rhythm, and non-interpretable segments, as well as to estimate AF/AFL burden and detect rhythm change. Performance metrics included sensitivity, specificity, PPV, NPV and the intraclass correlation coefficient (ICC) for AF and AFL burden estimation.

Results:

The sensitivity and specificity for detecting AF/AFL were 91.9% and 99.5%, respectively. The sensitivity for detecting AF was 96.2%, while for AFL it was 55.8%. The PPV and NPV for AF/AFL detection were 99.5% and 93.1%, respectively. The ICC between AF/AFL burden estimated by the DNN-based AI method and that derived from physician-interpreted reference ECG was 0.96 (95% CI: 0.94–0.97; P<.001). Rhythm change detection occurred within one minute in most cases.

Conclusions:

The mobile single-lead chest strap ECG system powered by a DNN-based AI algorithm demonstrated strong performance in detecting AF, estimating AF burden, and recognizing rhythm change to SR. This AI-driven approach enables automated and accurate rhythm analysis, supporting clinical decision-making. Further validation in real-world ambulatory settings is warranted. Clinical Trial: ClinicalTrials.gov database, NCT04917653, https://clinicaltrials.gov/study/NCT04917653