2025/10/17 by Huang, Shun, Zhang, Deyun, Fan, Sumei +5
#FOS: Electrical engineering #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · doi:10.48550/arxiv.2510.24750
Wolff-Parkinson-White (WPW) syndrome is a congenital cardiac condition associated with sudden cardiac death, with a prevalence of 0.1-0.3%. Conventional screening relies on electrophysiological testing or 12-lead electrocardiography interpreted by cardiologists, which limits large-scale and cost-effective screening. Building on our previous work developing a single-lead AI-ECG mobile system for atrial fibrillation screening, this study evaluates its efficiency and effectiveness for opportunistic detection of WPW syndrome in real-world settings. This retrospective analysis included 3,566,626 single-lead ECG recordings from 87,836 individuals in China, collected using the NMPA-approved portable ECG device WenXinWuYang. The AI system performance was validated using cardiologist annotations and random sampling. We quantified AI-assisted workload reduction and compared review efficiency across AI-positive and user-initiated workflows. The AI system achieved 45.5% sensitivity and 95.9% specificity. A positive AI result indicated about 210 times higher risk of confirmed WPW. Focusing on AI-selected positives reduced physician workload by 99.5%, requiring only 12 reviews to confirm one WPW case, compared with 909 and 875 in population-wide and user-driven approaches. In conclusion, this large-scale real-world study demonstrates that a single-lead AI-ECG system enables efficient and practical opportunistic screening for WPW syndrome, significantly reducing physician workload and supporting population-based cardiovascular prevention.