EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Detection of Normal, Atrial, and Ventricular Premature Beats from Single-Lead ECG Using Convolutional Neural Networks

Dimitri Kraft iD, Peter Rumm

Sensors · 2026

DOI: 10.3390/s26020513 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Dimitri Kraft und 1 weiteren Autor:innen. Beteiligte Einrichtung: MedTec & Science GmbH, Maria-Merian-Straße 6, 85521 Ottobrunn, Germany. Hauptthemen laut MEDLINE: Electrocardiography, Ventricular Premature Complexes, Atrial Premature Complexes. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: custo med GmbH.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate detection of premature atrial contractions (PACs) and premature ventricular contractions (PVCs) in single-lead electrocardiograms (ECGs) is crucial for early identification of patients at risk for atrial fibrillation, cardiomyopathy, and other adverse outcomes. In this work, we present a fully convolutional one-dimensional U-Net that reframes beat classification as a segmentation task and directly detects normal beats, PACs, and PVCs from raw ECG signals. The architecture employs a ConvNeXt V2 encoder with simple decoder blocks and does not rely on explicit R-peak detection, handcrafted features, or fixed-length input windows. The model is trained on the Icentia11k database and an in-house single-lead ECG dataset that emphasizes challenging, noisy recordings, and is validated on the CPSC2020 database. Generalization is assessed across several benchmark and clinical datasets, including MIT-BIH Arrhythmia (ADB), MIT 11, AHA, NST, SVDB, CST STRIPS, and CPSC2020. The proposed method achieves near-perfect QRS detection (sensitivity and precision up to 0.999) and competitive PVC performance, with sensitivity ranging from 0.820 (AHA) to 0.986 (MIT 11) and precision up to 0.993 (MIT 11). PAC detection is more variable, with sensitivities between 0.539 and 0.797 and precisions between 0.751 and 0.910, yet the resulting F1-score of 0.72 on SVDB exceeds that of previously published approaches. Model interpretability is addressed using Layer-wise Gradient-weighted Class Activation Mapping (LayerGradCAM), which confirms physiologically plausible attention to QRS complexes for PVCs and to P-waves for PACs. Overall, the proposed framework provides a robust, interpretable, and hardware-efficient solution for joint PAC and PVC detection in noisy, single-lead ECG recordings, suitable for integration into Holter and wearable monitoring systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectrocardiographyVentricular Premature ComplexesAtrial Premature ComplexesHumansConvolutional Neural NetworksSignal Processing, Computer-AssistedAlgorithms

Stichwörter der Autor:innen

1D U-Net neural networkHolter monitoringPremature Atrial Contraction (PAC) detectionPremature Ventricular Contraction (PVC) detection

Autor:innen und Institutionen

  • MedTec & Science GmbH, Maria-Merian-Straße 6, 85521 Ottobrunn, Germany.
  • custo med, GmbH, Maria-Merian-Straße 6, 85521 Ottobrunn, Germany.

ORCID-Profile: Dimitri Kraft

Förderung

  • custo med GmbH

Zitieren

APA

Kraft, D., & Rumm, P. (2026). Automated Detection of Normal, Atrial, and Ventricular Premature Beats from Single-Lead ECG Using Convolutional Neural Networks. Sensors. https://doi.org/10.3390/s26020513

Vancouver

Kraft D, Rumm P. Automated Detection of Normal, Atrial, and Ventricular Premature Beats from Single-Lead ECG Using Convolutional Neural Networks. Sensors. 2026. doi:10.3390/s26020513

BibTeX
@article{Kraft2026,
  author = {Kraft, Dimitri and Rumm, Peter},
  title = {Automated Detection of Normal, Atrial, and Ventricular Premature Beats from Single-Lead ECG Using Convolutional Neural Networks},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26020513}
}
Kostenlos starten →