Opportunistic Screening of Wolff-Parkinson-White Syndrome using Single-Lead AI-ECG Mobile System: A Real-World Study of over 3.5 million ECG Recordings in China

TL;DR

It is suggested that a risk-stratification-based human-AI collaborative system provides a promising paradigm for the early public health detection of low-prevalence, high-risk arrhythmias.

Abstract

Wolff-Parkinson-White (WPW) syndrome, a congenital cardiac conduction abnormality with low prevalence, carries a significant risk of sudden cardiac death. Early identification remains challenging due to screening costs and professional resource scarcity. This retrospective real-world study systematically evaluates an integrated Artificial Intelligence-enabled mobile screening system comprising portable single-lead devices, AI primary screening, and cardiologist review. Analyzing 3,566,626 ECG records from 87,836 individuals between 2019 and 2025, the AI model achieved an AUC of 0.6676 and a specificity of 95.92% in complex real-world signal environments. Despite predictive probability bias inherent in ultra-low prevalence contexts, the model demonstrated stable risk stratification, with high-confidence scores concentrated among true positive individuals. The risk of detecting WPW in AI-positive records was 86.2-fold higher than in AI-negative records. By implementing a human-AI collaborative workflow, the volume of ECGs requiring manual review was reduced by approximately 99.5% compared to universal screening. In an ideal collaborative scenario, an average of only 18 ECGs required review to confirm one WPW case, representing a more than 60-fold increase in screening efficiency. Compared to traditional 12-lead ECGs and electrophysiological studies, this system significantly reduced time and medical costs. Our findings suggest that a risk-stratification-based human-AI collaborative system provides a promising paradigm for the early public health detection of low-prevalence, high-risk arrhythmias.

Figures (6)

• Figure 1: Schematic overview of the AI-ECG mobile screening system workflow.
• Figure 2: Study flowchart and multi-layer data stratification strategy.
• Figure 3: Diagnostic performance and risk stratification capability of the AI model in real-world settings. (A) Receiver Operating Characteristic (ROC) curve illustrating the overall discriminative performance of the AI model for WPW detection. (B) Confusion matrix showing the distribution of True Positives, False Positives, False Negatives, and True Negatives. (C) Calibration curve assessing the agreement between predicted probabilities and observed frequencies, highlighting the global probability overestimation caused by the extremely low disease prevalence. (D) Score stability analysis for confirmed True Positive cases, demonstrating the concentration of predictive confidence scores within the high-risk stratum.
• Figure 4: Dynamics of user behavior and selection bias in the human-AI collaborative workflow. (A) Comparison of cardiologist review rates stratified by AI results, demonstrating that AI-positive alerts serve as a strong behavioral driver for seeking medical advice. (B) Comparison of the Positive Predictive Value (PPV) in the user-initiated AI-positive cohort and the confirmation rate in the randomly sampled non-reviewed cohort. (C) Composition of diagnoses within the AI-negative review cohort, revealing that the detection of "other cardiac conditions" is the primary motivator for user-initiated reviews. (D) Confirmation rate in the AI-negative cohort, validating the model's robust negative predictive capability and low risk of missed detection.
• Figure 5: Comparative analysis of screening efficiency and cumulative resource burdens. (A) Comparison of screening efficiency measured by Number Needed to Review (NNR) across different strategies. The human-AI collaborative workflow significantly lowered the NNR compared to universal manual screening. (B) Cumulative cost comparison between the AI-ECG mobile system and traditional hospital procedures over 10 sequential screening sessions, highlighting the widening cost-saving trend. (C) Cumulative time consumption comparison between the AI-ECG mobile system and traditional hospital procedures over 10 sequential screening sessions.