EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Post Hoc Sample Size Estimation for Deep Learning Architectures for ECG-Classification

Lucas Bickmann, Lucas Plagwitz, Julian Varghese

Studies in Health Technology and Informatics · 2023

DOI: 10.3233/shti230099 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2023. Verfasst von Lucas Bickmann und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Medical Informatics, University of Münster, Münster, Germany. Hauptthemen laut MEDLINE: Neural Networks, Computer, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep Learning architectures for time series require a large number of training samples, however traditional sample size estimation for sufficient model performance is not applicable for machine learning, especially in the field of electrocardiograms (ECGs). This paper outlines a sample size estimation strategy for binary classification problems on ECGs using different deep learning architectures and the large publicly available PTB-XL dataset, which includes 21801 ECG samples. This work evaluates binary classification tasks for Myocardial Infarction (MI), Conduction Disturbance (CD), ST/T Change (STTC), and Sex. All estimations are benchmarked across different architectures, including XResNet, Inception-, XceptionTime and a fully convolutional network (FCN). The results indicate trends for required sample sizes for given tasks and architectures, which can be used as orientation for future ECG studies or feasibility aspects.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerDeep LearningSample SizeMachine LearningElectrocardiography

Stichwörter der Autor:innen

deep learningecgestimationmachine learningsample size

Autor:innen und Institutionen

  • Institute of Medical Informatics, University of Münster, Münster, Germany.

Zitieren

APA

Bickmann, L., Plagwitz, L., & Varghese, J. (2023). Post Hoc Sample Size Estimation for Deep Learning Architectures for ECG-Classification. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti230099

Vancouver

Bickmann L, Plagwitz L, Varghese J. Post Hoc Sample Size Estimation for Deep Learning Architectures for ECG-Classification. Studies in Health Technology and Informatics. 2023. doi:10.3233/shti230099

BibTeX
@article{Bickmann2023,
  author = {Bickmann, Lucas and Plagwitz, Lucas and Varghese, Julian},
  title = {Post Hoc Sample Size Estimation for Deep Learning Architectures for ECG-Classification},
  journal = {Studies in Health Technology and Informatics},
  year = {2023},
  doi = {10.3233/shti230099}
}
Kostenlos starten →