uPVC-Net: A Universal Premature Ventricular Contraction Detection Deep Learning Algorithm

TL;DR

uPVC-Net is a deep learning model capable of accurately detecting Premature Ventricular Contractions from single-lead ECGs across diverse datasets, demonstrating high generalization and robustness for clinical use.

Contribution

We introduce uPVC-Net, a universal deep learning architecture trained on multiple datasets for reliable PVC detection across various ECG recording conditions.

Findings

Achieved AUC of 97.8% to 99.1% on held-out datasets

Performed with 99.1% AUC on wearable ECG data

Demonstrated strong cross-dataset generalization

Abstract

Introduction: Premature Ventricular Contractions (PVCs) are common cardiac arrhythmias originating from the ventricles. Accurate detection remains challenging due to variability in electrocardiogram (ECG) waveforms caused by differences in lead placement, recording conditions, and population demographics. Methods: We developed uPVC-Net, a universal deep learning model to detect PVCs from any single-lead ECG recordings. The model is developed on four independent ECG datasets comprising a total of 8.3 million beats collected from Holter monitors and a modern wearable ECG patch. uPVC-Net employs a custom architecture and a multi-source, multi-lead training strategy. For each experiment, one dataset is held out to evaluate out-of-distribution (OOD) generalization. Results: uPVC-Net achieved an AUC between 97.8% and 99.1% on the held-out datasets. Notably, performance on wearable single-lead ECG data reached an AUC of 99.1%. Conclusion: uPVC-Net exhibits strong generalization across diverse lead configurations and populations, highlighting its potential for robust, real-world clinical deployment.