EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Deep Learning-Based Arrhythmia Detection Using Smartwatch ECG Electrocardiograms

Herwin Alayn Huillcen Baca iD, Flor de Luz Palomino Valdivia iD

Sensors · 2025

DOI: 10.3390/s25175244 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Herwin Alayn Huillcen Baca und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Engineering, Academic Department of Engineering and Information Technology, Jose Maria Arguedas National University, Andahuaylas 03701, Pe…. Hauptthemen laut MEDLINE: Deep Learning, Arrhythmias, Cardiac, Electrocardiography. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jose Maria Arguedas National University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

According to the World Health Organization, cardiovascular diseases, including cardiac arrhythmias, are the leading cause of death worldwide due to their silent, asymptomatic nature. To address this problem, early and accurate diagnosis is crucial. Although this task is typically performed by a cardiologist, diagnosing arrhythmias can be imprecise due to the subjectivity of reading and interpreting electrocardiograms (ECGs), and electrocardiograms are often subject to noise and interference. Deep learning-based approaches present methods for automatically detecting arrhythmias and are positioned as an alternative to support cardiologists’ diagnoses. However, these methods are trained and tested only on open datasets of electrocardiograms from Holter devices, whose results aim to improve the accuracy of the state of the art, neglecting the efficiency of the model and its application in a practical clinical context. In this work, we propose an efficient model based on a 1D CNN architecture to detect arrhythmias from smartwatch ECGs, for subsequent deployment in a practical scenario for the monitoring and early detection of arrhythmias. Two datasets were used: UMass Medical School Simband for a binary arrhythmia detection model to evaluate its efficiency and effectiveness, and the MIT-BIH arrhythmia database to validate the multiclass model and compare it with state-of-the-art models. The results of the binary model achieved an accuracy of 64.81%, a sensitivity of 89.47%, and a specificity of 6.25%, demonstrating the model’s reliability, especially in specificity. Furthermore, the computational complexity was 1.2 million parameters and 68.48 MFlops, demonstrating the efficiency of the model. Finally, the results of the multiclass model achieved an accuracy of 99.57%, a sensitivity of 99.57%, and a specificity of 99.47%, making it one of the best state-of-the-art proposals and also reconfirming the reliability of the model.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningArrhythmias, CardiacElectrocardiographyHumansNeural Networks, ComputerSignal Processing, Computer-AssistedAlgorithms

Stichwörter der Autor:innen

CNNECGPPGarrhythmia detectioncardiovascular diseasesdeep learningelectrocardiogramheart ratesmartwatch

Autor:innen und Institutionen

  • Faculty of Engineering, Academic Department of Engineering and Information Technology, Jose Maria Arguedas National University, Andahuaylas 03701, Peru.

ORCID-Profile: Herwin Alayn Huillcen Baca, Flor de Luz Palomino Valdivia

Förderung

  • Jose Maria Arguedas National University

Zitieren

APA

Baca, H. A. H., & Valdivia, F. L. P. (2025). Efficient Deep Learning-Based Arrhythmia Detection Using Smartwatch ECG Electrocardiograms. Sensors. https://doi.org/10.3390/s25175244

Vancouver

Baca HAH, Valdivia FLP. Efficient Deep Learning-Based Arrhythmia Detection Using Smartwatch ECG Electrocardiograms. Sensors. 2025. doi:10.3390/s25175244

BibTeX
@article{Baca2025,
  author = {Baca, Herwin Alayn Huillcen and Valdivia, Flor de Luz Palomino},
  title = {Efficient Deep Learning-Based Arrhythmia Detection Using Smartwatch ECG Electrocardiograms},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25175244}
}
Kostenlos starten →