EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

XGBoost Classification of Epileptic EEG Using Nonlinear Dynamical Features and SHAP

Xiaojie Lu, Hui Lou, Xiaoyang Jin, Bianmei Zhang

Entropy · 17.08.2026 · 28 (8) · 920

DOI: 10.3390/e28080920 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 17.08.2026. Verfasst von Xiaojie Lu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Medical Information, Wannan Medical University, Wuhu 241002, China. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Anhui Provincial Department of Education, University Natural Science Research Project of Anhui Province, Anhui Province New Era Talent Cultivation Quality Engineering Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To evaluate whether nonlinear descriptors of electroencephalogram (EEG) signals support interpretable XGBoost classification and to determine how analysis window duration affects performance. A secondary analysis of the public Bonn EEG dataset was performed. Nine nonlinear features were extracted from non-overlapping 1, 5, 10, and 20 s windows after an original-recording-level train/validation/test split, and a multiclass XGBoost model was interpreted with class-specific SHAP values. The model achieved 93.3% overall accuracy; the class-specific AUC values were 0.978 for Z/O, 0.978 for N/F, and 0.984 for S. Across the four fixed-split duration conditions, the 1 s condition had the lowest descriptive performance, whereas the 5, 10, and 20 s conditions were broadly comparable; no uniquely optimal duration was established. The nonlinear-feature/XGBoost framework provides interpretable benchmark segment classification evidence. Because EEG is modeled as a stochastic process and the dataset is small and heterogeneous, the SHAP attributions do not establish physiological causality or clinical diagnostic validity.

Schlagwörter

Stichwörter der Autor:innen

EEGSHAPXGBoostnonlinear dynamic

Autor:innen und Institutionen

  • School of Medical Information, Wannan Medical University, Wuhu 241002, China.
  • Anhui Province High-Quality Dataset Construction Base for Smart Healthcare, Wuhu 241002, China.
  • Institute of Medical Artificial Intelligence, Wannan Medical University, Wuhu 241002, China.

Förderung

  • Anhui Provincial Department of Education
  • University Natural Science Research Project of Anhui Province
  • Anhui Province New Era Talent Cultivation Quality Engineering Project
  • Anhui Provincial Quality Engineering Project

Zitieren

APA

Lu, X., Lou, H., Jin, X., & Zhang, B. (2026). XGBoost Classification of Epileptic EEG Using Nonlinear Dynamical Features and SHAP. Entropy, 28(8), 920. https://doi.org/10.3390/e28080920

Vancouver

Lu X, Lou H, Jin X, Zhang B. XGBoost Classification of Epileptic EEG Using Nonlinear Dynamical Features and SHAP. Entropy. 2026;28(8):920. doi:10.3390/e28080920

BibTeX
@article{Lu2026,
  author = {Lu, Xiaojie and Lou, Hui and Jin, Xiaoyang and Zhang, Bianmei},
  title = {XGBoost Classification of Epileptic EEG Using Nonlinear Dynamical Features and SHAP},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {8},
  pages = {920},
  doi = {10.3390/e28080920}
}
Kostenlos starten →