EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning Method Using Temporal–Spectral–Spatial Feature Fusion for Epileptic Seizure Prediction

Shang Zhang, Guangda Liu, Jing Cai

Brain Sciences · 12.11.2026 · 16 (11) · 1237

DOI: 10.3390/brainsci16111237 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Brain Sciences, online erschienen am 12.11.2026. Verfasst von Shang Zhang und 2 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Development Plan Project of Jilin Province, 13th Five-Year Plan Science and Technology Project of the Education Department of Jilin Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Epilepsy is a recurrent cerebral disorder, and the sudden onset of seizures can result in accidental injuries or even life-threatening events for patients. In clinical practice, epileptic seizure prediction can provide warnings prior to the onset of seizures, alerting patients to take safety precautions and assisting neurologists in implementing timely interventions to suppress seizures. Therefore, accurate prediction is crucial for improving patients’ quality of life and clinical treatment outcomes. However, due to insufficient extraction of effective features from epileptic signals, the performance of prediction models is often limited.

Methods

In this study, a novel deep learning model was proposed that integrated temporal–spectral–spatial features to address this limitation. Wavelet convolutions and temporal convolutions were employed to achieve the temporal–spectral representation network. Subsequently, the fused features were further processed using bidirectional long short-term memory networks and a dynamic multigraph attention network based on time slices to extract temporal and spatial features for seizure prediction.

Results

The performance of the proposed model was comprehensively evaluated on the CHB-MIT and Siena databases using both segment-based and event-based evaluations. For the CHB-MIT database, the model achieved a sensitivity of 96.09 ± 8.83% and a false prediction rate of 0.021 ± 0.032/h. For the Siena database, the model demonstrated a sensitivity of 95.71 ± 7.87% and a false prediction rate of 0.028 ± 0.036/h. Furthermore, this study achieved patient-independent experiments for prediction evaluation.

Conclusions

The proposed model effectively achieves the fusion of multiple features and significantly enhances the prediction performance through multiple deep learning methods. For patient-independent experiments, the excellent prediction performance demonstrates the strong generalization ability.

Förderung

  • Science and Technology Development Plan Project of Jilin Province
  • 13th Five-Year Plan Science and Technology Project of the Education Department of Jilin Province

Zitieren

APA

Zhang, S., Liu, G., & Cai, J. (2026). Deep Learning Method Using Temporal–Spectral–Spatial Feature Fusion for Epileptic Seizure Prediction. Brain Sciences, 16(11), 1237. https://doi.org/10.3390/brainsci16111237

Vancouver

Zhang S, Liu G, Cai J. Deep Learning Method Using Temporal–Spectral–Spatial Feature Fusion for Epileptic Seizure Prediction. Brain Sciences. 2026;16(11):1237. doi:10.3390/brainsci16111237

BibTeX
@article{Zhang2026,
  author = {Zhang, Shang and Liu, Guangda and Cai, Jing},
  title = {Deep Learning Method Using Temporal–Spectral–Spatial Feature Fusion for Epileptic Seizure Prediction},
  journal = {Brain Sciences},
  year = {2026},
  volume = {16},
  number = {11},
  pages = {1237},
  doi = {10.3390/brainsci16111237}
}
Kostenlos starten →