EUVIMEDEUVIMED entdecken
Crossref

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

Hagai Hamami, Yosef Solewicz, Daniel Zur, Yonatan Kleerekoper, Joachim A Behar

IEEE Transactions on Biomedical Engineering · 2026-10 · 73 (10) · 3567-3575

DOI: 10.1109/tbme.2026.3655531 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2026-10. Verfasst von Hagai Hamami und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Ventricular Premature Complexes, Deep Learning, Electrocardiography, Signal Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: Israel PBC-VATAT.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Ventricular Premature ComplexesDeep LearningElectrocardiographySignal Processing, Computer-AssistedHumansAlgorithmsDatabases, Factual

Förderung

  • Israel PBC-VATAT

Zitieren

APA

Hamami, H., Solewicz, Y., Zur, D., Kleerekoper, Y., & Behar, J. A. (2026). uPVC-Net: A Universal Premature Ventricular Contraction Detection Deep Learning Algorithm. IEEE Transactions on Biomedical Engineering, 73(10), 3567-3575. https://doi.org/10.1109/tbme.2026.3655531

Vancouver

Hamami H, Solewicz Y, Zur D, Kleerekoper Y, Behar JA. uPVC-Net: A Universal Premature Ventricular Contraction Detection Deep Learning Algorithm. IEEE Transactions on Biomedical Engineering. 2026;73(10):3567-3575. doi:10.1109/tbme.2026.3655531

BibTeX
@article{Hamami2026,
  author = {Hamami, Hagai and Solewicz, Yosef and Zur, Daniel and Kleerekoper, Yonatan and Behar, Joachim A},
  title = {uPVC-Net: A Universal Premature Ventricular Contraction Detection Deep Learning Algorithm},
  journal = {IEEE Transactions on Biomedical Engineering},
  year = {2026},
  volume = {73},
  number = {10},
  pages = {3567--3575},
  doi = {10.1109/tbme.2026.3655531}
}
Kostenlos starten →