Beyond burden metrics: Wearable photoplethysmography-derived spatiotemporal progression of atrial fibrillation linked to clinical outcomes

<h2>ABSTRACT</h2><h3>Background</h3> Traditional atrial fibrillation (AF) classification lacks dynamic quantification. Current AF burden assessment is constrained by intermittent monitoring and simplistic metrics. <h3>Objective</h3> To establish a continuous, multidimensional AF progression model using wearable photoplethysmography (PPG) for real-world, dynamic burden quantification. <h3>Methods</h3> In this prospective cohort, 110 patients with paroxysmal AF underwent synchronized PPG (Huawei Watch GT3) and 24-hour Holter monitoring. We developed a multi-scale fusion AF algorithm and a five-dimensional (5D) spatiotemporal progression model quantifying episode frequency, duration, clustering, circadian rhythm, and tachycardia burden. <h3>Results</h3> The fusion algorithm achieved an accuracy of 0.97. The 5D model showed strong concordance with Holter monitoring, with near-perfect correlation for episode duration (r=0.97) and high interchangeability (ICC>0.75). It demonstrated excellent diagnostic performance for burden trajectories (AUC=0.98). A composite AF burden score ≥ 0.59 identified patients at high risk for AF-related symptoms or heart rate issues. Clinically, AF burden increased with worsening EHRA symptoms (p=0.04), varied by risk profile (p=0.03), and differed between ablation and drug-treated patients (episode duration: p<0.001). <h3>Conclusion</h3> Continuous PPG-based spatiotemporal modeling robustly quantified dynamic AF progression, enabled precise phenotyping, and may support early intervention in high-risk patients.