Architecture-Specific Impact of Preprocessing on Machine Learning Models for ECG Classification
Studies in Health Technology and Informatics · 21.05.2026
DOI: 10.3233/shti260227 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Lucas Bickmann und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Medical Data Science, Otto-von-Guericke University Magdeburg. Hauptthemen laut MEDLINE: Electrocardiography, Signal Processing, Computer-Assisted, Deep Learning, Neural Networks, Computer. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Automated analysis of electrocardiograms relies increasingly on deep learning models. In these models, preprocessing steps may often be applied under the assumption that they inherently improve performance. This study investigates the effects of signal cleaning, trend removal, and normalization on six leading deep learning architectures for electrocardiogram classification, based on the well-established PTB-XL dataset, a widely used reference standard in electrocardiogram (ECG) data analysis. By exhaustively evaluating 24 combinations of preprocessing techniques with each model, and repeating each trial ten times for robustness, we find a surprising degree of architecture-dependent sensitivity. Notably, convolutional neural networks performed best when raw, unnormalized electrocardiograms are used, in direct contradiction to prevailing assumptions. In contrast, wavelet-based models benefited substantially from trend removal, while transformer-based models demonstrated robustness across a broad range of preprocessing options. These findings suggest that preprocessing pipelines should be designed with specific model architectures in mind, challenging the conventional wisdom of applying normalization in preprocessing for bounded signal data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Medical Data Science, Otto-von-Guericke University Magdeburg.
- Institute of Medical Informatics, University of Münster.
- Clinic for Cardiology II: Electrophysiology, University Hospital Münster.
Zitieren
APA
Bickmann, L., Plagwitz, L., Büscher, A., & Varghese, J. (2026). Architecture-Specific Impact of Preprocessing on Machine Learning Models for ECG Classification. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260227
Vancouver
Bickmann L, Plagwitz L, Büscher A, Varghese J. Architecture-Specific Impact of Preprocessing on Machine Learning Models for ECG Classification. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260227
BibTeX
@article{Bickmann2026,
author = {Bickmann, Lucas and Plagwitz, Lucas and Büscher, Antonius and Varghese, Julian},
title = {Architecture-Specific Impact of Preprocessing on Machine Learning Models for ECG Classification},
journal = {Studies in Health Technology and Informatics},
year = {2026},
doi = {10.3233/shti260227}
}
EUVIMED