EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive wavelet base selection for deep learning-based ECG diagnosis: A reinforcement learning approach

Qiao Xiao, Chaofeng Wang iD

PLOS ONE · 03.02.2025 · 20 (2) · e0318070

DOI: 10.1371/journal.pone.0318070 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 03.02.2025. Verfasst von Qiao Xiao und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, University of South China, Hengyang, Hunan, China. Hauptthemen laut MEDLINE: Electrocardiography, Deep Learning, Wavelet Analysis, Cardiovascular Diseases. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Education Department of Hunan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electrocardiogram (ECG) signals are crucial in diagnosing cardiovascular diseases (CVDs). While wavelet-based feature extraction has demonstrated effectiveness in deep learning (DL)-based ECG diagnosis, selecting the optimal wavelet base poses a significant challenge, as it directly influences feature quality and diagnostic accuracy. Traditional methods typically rely on fixed wavelet bases chosen heuristically or through trial-and-error, which can fail to cover the distinct characteristics of individual ECG signals, leading to suboptimal performance. To address this limitation, we propose a reinforcement learning-based wavelet base selection (RLWBS) framework that dynamically customizes the wavelet base for each ECG signal. In this framework, a reinforcement learning (RL) agent iteratively optimizes its wavelet base selection (WBS) strategy based on successive feedback of classification performance, aiming to achieve progressively optimized feature extraction. Experiments conducted on the clinically collected PTB-XL dataset for ECG abnormality classification show that the proposed RLWBS framework could obtain more detailed time-frequency representation of ECG signals, yielding enhanced diagnostic performance compared to traditional WBS approaches.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectrocardiographyDeep LearningWavelet AnalysisCardiovascular DiseasesHumansAlgorithmsSignal Processing, Computer-Assisted

Autor:innen und Institutionen

  • School of Computer Science, University of South China, Hengyang, Hunan, China.
  • Department of Community Health, Faculty of Medicine and Health Sciences, Universiti Putra Malaysia, Serdang, Selangor, Malaysia.

ORCID-Profile: Chaofeng Wang

Förderung

  • Education Department of Hunan Province

Zitieren

APA

Xiao, Q., & Wang, C. (2025). Adaptive wavelet base selection for deep learning-based ECG diagnosis: A reinforcement learning approach. PLOS ONE, 20(2), e0318070. https://doi.org/10.1371/journal.pone.0318070

Vancouver

Xiao Q, Wang C. Adaptive wavelet base selection for deep learning-based ECG diagnosis: A reinforcement learning approach. PLOS ONE. 2025;20(2):e0318070. doi:10.1371/journal.pone.0318070

BibTeX
@article{Xiao2025,
  author = {Xiao, Qiao and Wang, Chaofeng},
  title = {Adaptive wavelet base selection for deep learning-based ECG diagnosis: A reinforcement learning approach},
  journal = {PLOS ONE},
  year = {2025},
  volume = {20},
  number = {2},
  pages = {e0318070},
  doi = {10.1371/journal.pone.0318070}
}
Kostenlos starten →