Epilepsy Prediction via Time-Frequency Features and Multi-Scale Hybrid Neural Networks.

The prediction of epileptic seizures heavily depends on the precise embedding and classification of complex, multi-dimensional electroencephalogram (EEG) signals. Due to individual variability and the dynamic non-linear nature of EEG signals, extracting highly discriminative spatiotemporal features...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Medical Systems Vol. 49; no. 1; pp. 1 - 19
Autores principales: Chang, Wenwen, Ji, Bingyang, Li, Dandan, Zhen, Lei, Wei, Yaxuan, Liu, Xuan, Yan, Guanghui
Formato: equations & formulas pictorial research tables/charts Journal Article
Publicado: Springer Nature 6/25/2025
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=186157113&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 186157113
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        01485598
        4N0
      jtl: Journal of Medical Systems
      issn: 01485598
      maglogo: N
    pubinfo:
      dt: 6/25/2025
      vid: 49
      iid: 1
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        186157113
        186157113
        186157113
        10.1007/s10916-025-02224-w
        186157113
      ppf: 1
      ppct: 18
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Epilepsy Prediction via Time-Frequency Features and Multi-Scale Hybrid Neural Networks.
      aug:
        au:
          Chang, Wenwen
          Ji, Bingyang
          Li, Dandan
          Zhen, Lei
          Wei, Yaxuan
          Liu, Xuan
          Yan, Guanghui
        affil: https://ror.org/03144pv92 School of Electrical and Information Engineering, Lanzhou Jiaotong University, 730070, Lanzhou, China
      sug:
        subj:
          Epilepsy Risk Factors
          Risk Assessment Methods
          Prediction Models Evaluation
          Electroencephalography
          Convolutional Neural Networks
          Human
          Funding Source
          Sensitivity and Specificity
          Electrodes, Implanted
          Algorithms
          Brain Mapping
          Diagnosis, Computer Assisted
          Calibration
          Validity
      ab: The prediction of epileptic seizures heavily depends on the precise embedding and classification of complex, multi-dimensional electroencephalogram (EEG) signals. Due to individual variability and the dynamic non-linear nature of EEG signals, extracting highly discriminative spatiotemporal features is a core challenge in this field. In this study, to address this issue, we proposed a novel architecture based on the Epilepsy Prediction using Multi-Scale Hybrid Neural Network (EPM-HNN), which integrates adaptive channel weighting, multi-scale spatial feature extraction, and bidirectional temporal dependency modeling. Specifically, we incorporated a sliding window mechanism with spatiotemporal resolution into the feature extraction process, enhancing the model's sensitivity to neural dynamics across frequency bands and improving its ability to capture micro-patterns. We used the Res2Net-50 multi-scale feature extractor to enhance the convolutional neural network's capacity to process complex local micro-features, such as polyspike-and-slow-wave complexes. Additionally, we introduced Squeeze-and-Excitation Networks (SENet) to adaptively capture potential effective features between different EEG channels. This dynamic weighting mechanism based on adaptive attention demonstrates strong robustness and high generalization across individual subject data. Furthermore, we proposed a non-single-subject, non-specific cross-subject training and testing method, demonstrating its ability to combat overfitting when addressing differences in data distribution. Experiments on the CHB-MIT scalp EEG dataset achieved an overall prediction accuracy of 97.7%, validating the effectiveness of the proposed EPM-HNN architecture.
      pubtype: Academic Journal
      doctype:
        equations & formulas
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N