A causal attention network with time frequency channel feature fusion for epileptic seizure prediction
Journal of Neuroscience Methods · 2026-04 · 428 · 110665
DOI: 10.1016/j.jneumeth.2025.110665 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neuroscience Methods, 2026-04. Verfasst von Yimin Qu und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, China. Hauptthemen laut MEDLINE: Electroencephalography, Seizures, Epilepsy, Signal Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
BACKGROUND: Epilepsy poses ongoing physical and mental threats and causes substantial economic burdens. Better seizure forecasting enables faster medical responses, improving patients' quality of life and lowering healthcare costs. Research mainly focuses on early forecasting within a short preictal window, often too brief for effective drug administration. A major challenge is that a longer preictal phase may resemble the interictal state, making differentiation difficult. NEW METHODS: We propose a causal attention network (CANet) with a longer interictal and preictal of 1 h and 2 h respectively as the research object. In the feature extraction, a dilated causal convolution network is employed to extract local features. Causal attention is innovatively incorporated into epilepsy prediction to capture global correlation features. The complementary integration of these two methods enhances feature extraction and enables a more precise distinction between interictal and preictal periods. A double-layer dynamic window algorithm is developed for seizure prediction. RESULTS: We evaluate the performance on Freiburg and CHB-MIT datasets. On the Freiburg dataset, the sensitivity(Sen) of the 1/2-hour preictal intervals was 100.00%/96.67%, with a false alarm rate per hour (FAR) of 0.0077/h/0.0472/h, and the average prediction time (APT) was 97.59 min. On the CHB-MIT dataset, we achieved Sen of 97.06%/92.31%, FAR of 0.0251/h/0.0666/h, and APT of 94.85 min, under the same conditions. COMPARISON WITH EXISTING METHODS AND CONCLUSION: Our approach outperforms most of the previous methods, and the intracranial EEG (Freiburg) can more effectively distinguish interictal and preictal periods than scalp EEG (CHB-MIT).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, China.
- Genome Analysis Laboratory of the Ministry of Agriculture and Rural Affairs, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, Shenzhen, China.
- College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, China. Electronic address: wangbin01@tyut.edu.cn.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Qu, Y., Rao, S., Li, T., Li, Y., Niu, Y., Chang, R., Chen, X., & Wang, B. (2026). A causal attention network with time frequency channel feature fusion for epileptic seizure prediction. Journal of Neuroscience Methods, 428, 110665. https://doi.org/10.1016/j.jneumeth.2025.110665
Vancouver
Qu Y, Rao S, Li T, Li Y, Niu Y, Chang R, et al. A causal attention network with time frequency channel feature fusion for epileptic seizure prediction. Journal of Neuroscience Methods. 2026;428:110665. doi:10.1016/j.jneumeth.2025.110665
BibTeX
@article{Qu2026,
author = {Qu, Yimin and Rao, Songhui and Li, Ting and Li, Ying and Niu, Yan and Chang, Ruiyun and Chen, Xianchuan and Wang, Bin},
title = {A causal attention network with time frequency channel feature fusion for epileptic seizure prediction},
journal = {Journal of Neuroscience Methods},
year = {2026},
volume = {428},
pages = {110665},
doi = {10.1016/j.jneumeth.2025.110665}
}
EUVIMED