EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RhythmX™: An Interpretable Self-Supervised Contrastive Learning Framework for Heartbeat Classification

Abdullah, Zulaikha Fatima, Haris Ali Safder, Mubasher Manzoor, Carlos Guzmán Sánchez-Mejorada, Miguel Jesús Torres Ruiz, Rolando Quintero Téllez

Technologies · 01.03.2026 · 14 (3) · 148

DOI: 10.3390/technologies14030148 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technologies, online erschienen am 01.03.2026. Verfasst von Abdullah und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated electrocardiogram (ECG) arrhythmia classification remains challenging due to signal noise, inter-patient variability, and limited annotated data, which constrain the generalization of supervised learning approaches. This study presents a self-supervised ECG representation learning framework that combines contrastive pretraining with ensemble-based supervised classification. A signal-to-noise ratio criterion is applied during self-supervised pretraining to stabilize contrastive optimization, while all extracted ECG beats, including noisy segments, are retained during downstream evaluation. The learned representations are classified using a hybrid ensemble composed of convolutional encoders and tree-based models. Model evaluation follows strict patient-level partitioning with stratified 10-fold cross-validation and bootstrap-based uncertainty estimation on a held-out test set. Under this evaluation protocol, the framework achieved high beat-level performance on curated datasets (internal and external). Class-wise performance shows precision and recall values between 0.99 and 0.999 across normal, supraventricular, ventricular, fusion, and paced beat categories. External validation is conducted on independent ECG cohorts, including PTB-XL, Chapman–Shaoxing, and INCART 12-lead datasets. On these datasets, the hybrid model attains macro-F1 scores ranging from 0.91 to 0.94, compared with standalone convolutional and handcrafted feature-based Random Forest classifiers evaluated under identical conditions. These results characterize the behavior of the proposed representation learning framework across heterogeneous patient populations and recording configurations.

Zitieren

APA

Abdullah, Fatima, Z., Safder, H. A., Manzoor, M., Sánchez-Mejorada, C. G., Ruiz, M. J. T., & Téllez, R. Q. (2026). RhythmX™: An Interpretable Self-Supervised Contrastive Learning Framework for Heartbeat Classification. Technologies, 14(3), 148. https://doi.org/10.3390/technologies14030148

Vancouver

Abdullah, Fatima Z, Safder HA, Manzoor M, Sánchez-Mejorada CG, Ruiz MJT, et al. RhythmX™: An Interpretable Self-Supervised Contrastive Learning Framework for Heartbeat Classification. Technologies. 2026;14(3):148. doi:10.3390/technologies14030148

BibTeX
@article{Abdullah2026,
  author = {Abdullah and Fatima, Zulaikha and Safder, Haris Ali and Manzoor, Mubasher and Sánchez-Mejorada, Carlos Guzmán and Ruiz, Miguel Jesús Torres and Téllez, Rolando Quintero},
  title = {RhythmX™: An Interpretable Self-Supervised Contrastive Learning Framework for Heartbeat Classification},
  journal = {Technologies},
  year = {2026},
  volume = {14},
  number = {3},
  pages = {148},
  doi = {10.3390/technologies14030148}
}
Kostenlos starten →