OSCR

Enhancing seizure prediction using a DC-SA-EBiLSTM framework with self-attention mechanism.

Overview

Authors: Shunyun Wang1, Jincan Zhang1, Wenna Chen2, Fei Xiang1, Hongwei Jiang2, Ganqin Du2
  1. College of Information Engineering, Henan University of Science and Technology, Luoyang, China
  2. The First Affiliated Hospital, and College of Clinical Medicine of Henan University of Science and Technology, Luoyang, China
Journal: Frontiers in neuroscience, volume 20, article 1856135
Dates: received 15 April 2026; accepted 22 May 2026; published online 5 June 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3389/fnins.2026.1856135 · PMID 42338796 · PMCID PMC13285407 · OpenAlex W7163638845
Open access: gold, a free copy (OpenAlex)
Categories: EEG (modality), epilepsy (population)
Methods: Spectral & time-frequency, Preprocessing, Machine learning, Statistics, Graphs, Complexity
Keywords: electroencephalography, feature extraction, hybrid model, seizure prediction, self-attention
Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Citations: not cited yet (Europe PMC); 56 references in the paper

Abstract

Background: Accurately predicting seizures remains challenging. With advances in smart medical technology, EEG-based monitoring has become essential. This study aims to improve prediction accuracy using a hybrid framework that models multiscale EEG characteristics.

Methods: EEG signals are decomposed into multiple sub-bands using the Discrete Wavelet Transform, and representative time-frequency and nonlinear features are extracted. These features are fed into a channel-centric model integrating depthwise separable convolution, self-attention, and an enhanced bidirectional long short-term memory network (DC-SA-EBiLSTM). The architecture integrates depthwise separable convolution for local spatial feature extraction, multi-head self-attention for global inter-channel dependencies, and an enhanced BiLSTM for channel-wise sequence modeling. The proposed method was evaluated on the CHB-MIT dataset using a 10-fold cross-validation protocol. An event-level leave-one-seizure-event-out validation was also conducted to assess alarm-based prediction performance.

Results: The proposed approach achieved an average accuracy of 95.89%, sensitivity of 96.70%, specificity of 95.48%, and AUC of 99.02%. In the event-level validation, the model achieved an event sensitivity of 95.96%, an average false alarm rate of 0.316 FPR/h, and a mean early warning time of 30.52 min.

Conclusion: The DC-SA-EBiLSTM framework effectively captures local and global inter-channel dependencies and provides a feature-driven approach for patient-specific preictal state prediction, showing potential for EEG-based seizure prediction.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data availability statement

Publicly available datasets were analyzed in this study. This data can be found here: The dataset analyzed in this study is the publicly available CHB-MIT Scalp EEG Database hosted on PhysioNet: https://physionet.org/content/chbmit/1.0.0/; DOI: 10.13026/C2K01R (https://doi.org/10.13026/C2K01R).

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 6 authors, 5 keywords, 54 references.

Cite

This paper

Wang, S., Zhang, J., Chen, W., Xiang, F., Jiang, H., & Du, G. (2026). Enhancing seizure prediction using a DC-SA-EBiLSTM framework with self-attention mechanism. Frontiers in neuroscience, 20, 1856135. https://doi.org/10.3389/fnins.2026.1856135

BibTeX

@article{wang2026enhancing,
author = {Wang, Shunyun and Zhang, Jincan and Chen, Wenna and Xiang, Fei and Jiang, Hongwei and Du, Ganqin},
title = {{Enhancing seizure prediction using a DC-SA-EBiLSTM framework with self-attention mechanism}},
journal = {Frontiers in neuroscience},
year = {2026},
month = jun,
volume = {20},
pages = {1856135},
publisher = {Frontiers Media SA},
issn = {1662-4548},
doi = {10.3389/fnins.2026.1856135},
url = {https://doi.org/10.3389/fnins.2026.1856135},
pmid = {42338796},
pmcid = {PMC13285407}
}

RIS

TY - JOUR
AU - Wang, Shunyun
AU - Zhang, Jincan
AU - Chen, Wenna
AU - Xiang, Fei
AU - Jiang, Hongwei
AU - Du, Ganqin
TI - Enhancing seizure prediction using a DC-SA-EBiLSTM framework with self-attention mechanism
T2 - Frontiers in neuroscience
J2 - Front Neurosci
PY - 2026
DA - 2026/06/05
VL - 20
SP - 1856135
SN - 1662-4548
PB - Frontiers Media SA
DO - 10.3389/fnins.2026.1856135
UR - https://doi.org/10.3389/fnins.2026.1856135
LA - en
ER -

CSL-JSON

{
"id": "10.3389/fnins.2026.1856135",
"type": "article-journal",
"title": "Enhancing seizure prediction using a DC-SA-EBiLSTM framework with self-attention mechanism",
"container-title": "Frontiers in neuroscience",
"author": [
{
"family": "Wang",
"given": "Shunyun"
},
{
"family": "Zhang",
"given": "Jincan"
},
{
"family": "Chen",
"given": "Wenna"
},
{
"family": "Xiang",
"given": "Fei"
},
{
"family": "Jiang",
"given": "Hongwei"
},
{
"family": "Du",
"given": "Ganqin"
}
],
"container-title-short": "Front Neurosci",
"volume": "20",
"page": "1856135",
"DOI": "10.3389/fnins.2026.1856135",
"PMID": "42338796",
"PMCID": "PMC13285407",
"ISSN": "1662-4548",
"publisher": "Frontiers Media SA",
"URL": "https://doi.org/10.3389/fnins.2026.1856135",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
5
]
]
}
}

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1186/s12911-024-02845-0
A hybrid CNN-Bi-LSTM model with feature fusion for accurate epilepsy seizure detection.
Journal: BMC medical informatics and decision making
In common: physionet.org/content/chbmit, epilepsy, EEG, 8 references
[2] doi:10.3389/fnins.2024.1468967
A review of epilepsy detection and prediction methods based on EEG signal processing and deep learning.
Journal: Frontiers in neuroscience
In common: epilepsy, EEG, 9 references
[3] doi:10.1038/s41598-025-97696-8
M-NIG: mobile network information gain for EEG-based epileptic seizure prediction.
Journal: Scientific reports
In common: physionet.org/content/chbmit, epilepsy, EEG, 6 references
[4] doi:10.1007/s40120-026-00924-0
Artificial Intelligence and Machine Learning in Pediatric Epilepsy: A Systematic Review.
Journal: Neurology and therapy
In common: DOI 10.13026/c2k01r, physionet.org/content/chbmit, epilepsy, EEG, 3 references
[5] doi:10.3389/fncom.2022.1059565
A multi-frame network model for predicting seizure based on sEEG and iEEG data.
Journal: Frontiers in computational neuroscience
In common: physionet.org/content/chbmit, epilepsy, EEG, 6 references
[6] doi:10.1038/s41598-025-88492-5
Synchronization-based graph spatio-temporal attention network for seizure prediction.
Journal: Scientific reports
In common: physionet.org/content/chbmit, epilepsy, EEG, 6 references
[7] doi:10.3389/fnins.2022.967116
Efficient graph convolutional networks for seizure prediction using scalp EEG.
Journal: Frontiers in neuroscience
In common: DOI 10.13026/c2k01r, epilepsy, EEG, 5 references
[8] doi:10.1016/j.isci.2026.117068 [code]
Directed graph neural networks with partial directed coherence for seizure prediction and epileptogenic network characterization.
Journal: iScience
In common: DOI 10.13026/c2k01r, physionet.org/content/chbmit, epilepsy, 3 references
[9] doi:10.1038/s41598-026-44536-y
PSD-LW-DCN: a generalizable power spectral density based lightweight deep convolutional neural network for seizure detection.
Journal: Scientific reports
In common: DOI 10.13026/c2k01r, physionet.org/content/chbmit, epilepsy, EEG, 2 references
[10] doi:10.3389/fnins.2025.1698960
A deep hybrid CSAE-GRU framework with two-stage balancing for automatic epileptic seizure detection using EEG-derived features.
Journal: Frontiers in neuroscience
In common: physionet.org/content/chbmit, epilepsy, EEG, 4 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.