Patient-specific epileptic seizure prediction from EEG using EMD-SVD reconstruction and a ResNeXt-attention BiLSTM network
Background Epileptic seizure prediction from scalp electroencephalography (EEG) may provide useful warning time. However, EEG noise and non-stationarity complicate the identification of preictal patterns, motivating effective signal preprocessing and feature learning for patient-specific prediction. Methods A patient-specific seizure prediction framework was evaluated using 19 retained cases from the CHB-MIT Scalp EEG Database. Models were trained and evaluated separately for each case using stratified five-fold cross-validation within that case. EEG signals were filtered, decomposed using empirical mode decomposition (EMD), and adaptively reconstructed using singular value decomposition (SVD). Short-time Fourier transform (STFT) spectrograms were encoded using an ImageNet-pretrained ResNeXt101 network, and the resulting feature vectors were classified using an attention-based bidirectional long short-term memory (BiLSTM) network. Performance was compared with conventional filtering and fixed-IMF reconstruction under the same within-case evaluation protocol. Results The proposed framework achieved mean accuracy, precision, recall (sensitivity), and area under the receiver operating characteristic curve (AUC) of 96.35%, 95.98%, 94.59%, and 95.93%, respectively. Ablation experiments showed that EMD-SVD reconstruction provided more stable training behavior and better overall predictive performance than the two alternative preprocessing strategies.
Authors
- Wenna Chen
- Jincan Zhang (ORCID: https://orcid.org/0000-0002-3520-4236)
- Kun Zhang (ORCID: https://orcid.org/0009-0009-0435-8441)
- Hongwei Jiang
- Ganqin Du
- Haobo Wei
Institutions
- Henan University of Science and Technology (CN)
- First Affiliated Hospital of Henan University of Science and Technology (CN)
Publication Details
- Journal
- Frontiers in Neuroscience
- Published
- 2026-11-16
- DOI
- https://doi.org/10.3389/fnins.2026.1984663
- Primary Topic
- EEG and Brain-Computer Interfaces
- Type
- article
- Field-Weighted Citation Impact
- 0.00