EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SHAP-Based Feature Augmentation and Stacking Ensemble Learning for ECG-Based Serum Potassium Abnormality Prediction

Yi-Hsin Ko iD, Chuan-Sheng Hung iD, Chun-Hung Richard Lin iD, Yi-Fong Ciou iD, Chiang-Chi Huang iD, Pin-Chen Lin, Jui-Hsiu Tsai iD

Bioengineering · 16.07.2026 · 13 (7) · 816

DOI: 10.3390/bioengineering13070816 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 16.07.2026. Verfasst von Yi-Hsin Ko und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, National Sun Yat-sen University, Kaohsiung 804, Taiwan. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electrocardiogram (ECG) signals contain important clinical information associated with serum potassium abnormalities. However, in Taiwan, raw patient data and original medical signals generally cannot be taken outside the hospital environment, thereby limiting their subsequent reuse and cross-institutional applications. The objective of this study is to transform classification-related information contained in raw ECG signals into high-level SHAP features and to evaluate their feasibility as auxiliary or alternative features to the original wave-segment model outputs. To this end, this study proposes a time-series classification framework that integrates ECG wave-segment submodels, SHAP-based feature augmentation, and stacking ensemble learning for serum potassium abnormality prediction. Submodels are first trained separately using different ECG wave segments and their combinations. SHAP is then applied to transform the contributions of the wave-segment submodel outputs to the prediction results into high-level features. In addition, PCA features are included as a comparison baseline to analyze the effects of different feature transformation methods on classification performance. The experimental results show that incorporating SHAP-based augmented features improves ECG-based serum potassium abnormality prediction performance under most settings. Even when only SHAP-based augmented features are used for training, some models still maintain performance comparable to or better than the Baseline. Although PCA provides more stable classification balance for some patients, SHAP-based augmented features can still represent classification-related model contribution information under most settings while achieving better or comparable classification performance. Overall, even without directly using the original ECG signals in the final classification stage, these features retain a certain degree of discriminative information and demonstrate the potential to serve as alternative features to the original wave-segment model outputs. Therefore, the findings of this study provide a preliminary reference for future medical data reuse, cross-institutional collaboration, and privacy risk assessment.

Schlagwörter

Stichwörter der Autor:innen

electrocardiogramexplainable artificial intelligencefeature augmentationmachine learningtime-series classification

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, National Sun Yat-sen University, Kaohsiung 804, Taiwan.
  • Autonomous UAV & AI Robotics Research Center, National Sun Yat-sen University, Kaohsiung 804, Taiwan.
  • Artificial Intelligence Research and Promotion Center, National Sun Yat-sen University, Kaohsiung 804, Taiwan.
  • Center of Teaching and Research, Kaohsiung Municipal Siaogang Hospital, Kaohsiung 812, Taiwan.
  • Division of Nephrology, Department of Internal Medicine, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung 833, Taiwan.
  • School of Medicine, Tzu Chi University, Hualien 970, Taiwan.

ORCID-Profile: Yi-Hsin Ko, Chuan-Sheng Hung, Chun-Hung Richard Lin, Yi-Fong Ciou, Chiang-Chi Huang, Jui-Hsiu Tsai

Förderung

  • Dalin Tzu Chi Hospital
  • Buddhist Tzu Chi Medical Foundation

Zitieren

APA

Ko, Y. H., Hung, C. S., Lin, C. R., Ciou, Y. F., Huang, C. C., Lin, P. C., & Tsai, J. H. (2026). SHAP-Based Feature Augmentation and Stacking Ensemble Learning for ECG-Based Serum Potassium Abnormality Prediction. Bioengineering, 13(7), 816. https://doi.org/10.3390/bioengineering13070816

Vancouver

Ko YH, Hung CS, Lin CR, Ciou YF, Huang CC, Lin PC, et al. SHAP-Based Feature Augmentation and Stacking Ensemble Learning for ECG-Based Serum Potassium Abnormality Prediction. Bioengineering. 2026;13(7):816. doi:10.3390/bioengineering13070816

BibTeX
@article{Ko2026,
  author = {Ko, Yi-Hsin and Hung, Chuan-Sheng and Lin, Chun-Hung Richard and Ciou, Yi-Fong and Huang, Chiang-Chi and Lin, Pin-Chen and Tsai, Jui-Hsiu},
  title = {SHAP-Based Feature Augmentation and Stacking Ensemble Learning for ECG-Based Serum Potassium Abnormality Prediction},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {7},
  pages = {816},
  doi = {10.3390/bioengineering13070816}
}
Kostenlos starten →