EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing ECG Classification Generalization Through Unified Multi-Dataset Training

Minchan Kim iD, Miyoung Shin

Sensors · 13.03.2026 · 26 (6) · 1830

DOI: 10.3390/s26061830 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.03.2026. Verfasst von Minchan Kim und 1 weiteren Autor:innen. Beteiligte Einrichtung: Bio-Intelligence & Data Mining Laboratory, School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Republic of K…. Hauptthemen laut MEDLINE: Electrocardiography, Atrial Fibrillation. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Atrial fibrillation (AF) is one of the most prevalent and clinically significant cardiac arrhythmias, and electrocardiography (ECG) is widely used for its detection. However, existing models often exhibit performance degradation when applied to unseen data due to dataset-specific biases and distributional shifts. This limited generalization remains a major obstacle to reliable clinical deployment. To address this, we propose a multi-dataset ECG classification framework designed to improve cross-dataset robustness. The model employs supervised contrastive learning and layer-wise normalization to stabilize training and mitigate the influence of domain-specific variations. The proposed approach was evaluated under a Leave-One-Dataset-Out setting, achieving an average accuracy of 97.5% and an F1-score of 89.3%. It consistently demonstrated superior performance compared with single-dataset training and naïve multi-dataset aggregation. These results indicate that the proposed framework can contribute to more stable automated AF detection across diverse clinical environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectrocardiographyAtrial FibrillationHumansClassification AlgorithmsAlgorithmsSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

artificial intelligenceatrial fibrillationcontrastive learningelectrocardiogrammulti-dataset trainingrepresentation learning

Autor:innen und Institutionen

  • Bio-Intelligence & Data Mining Laboratory, School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Republic of Korea.

ORCID-Profile: Minchan Kim

Förderung

  • National Research Foundation of Korea

Zitieren

APA

Kim, M., & Shin, M. (2026). Enhancing ECG Classification Generalization Through Unified Multi-Dataset Training. Sensors, 26(6), 1830. https://doi.org/10.3390/s26061830

Vancouver

Kim M, Shin M. Enhancing ECG Classification Generalization Through Unified Multi-Dataset Training. Sensors. 2026;26(6):1830. doi:10.3390/s26061830

BibTeX
@article{Kim2026,
  author = {Kim, Minchan and Shin, Miyoung},
  title = {Enhancing ECG Classification Generalization Through Unified Multi-Dataset Training},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {6},
  pages = {1830},
  doi = {10.3390/s26061830}
}
Kostenlos starten →