.png){kind=icon}
返回
An EEG-Based Seizure Prediction Model Encoding Brain Network Temporal Dynamics
.png){kind=icon}
PRE
AI
DOI：10.1109/JBHI.2025.3584861.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
EEG-based seizure prediction enables timely treatment for patients, but its performance is limited by the difficulty in effectively characterizing the temporal dynamics of epileptic brain networks. Metastability, which describes recurring topographical patterns of spontaneous neural activity over time, provides a unique perspective for capturing the dynamic evolution before seizure onset. In this study, we propose a seizure prediction model that fuses consistent epileptic network processes across subjects into a higher-order latent space. Specifically, we first construct metastable transition patterns to identify the recurrent network states over time. Through adversarial feature learning, we then impose the metastability prior on the latent embedding space encoded via a variational autoencoder (VAE), while leveraging the maximum mean discrepancy measure (MMD) to further mitigate the patient gap. The latent representation, endowed with physiological priors, is ultimately utilized for patient-independent seizure prediction. We evaluate our method on two publicly available and one clinical scalp EEG datasets. Compared to the existing methods, our method has improved AUC, sensitivity, and specificity on CHB-MIT dataset by approximately 9%, 5%, and 5%, respectively. Our method shows that combining brain network-based physiological prior with deep learning for EEG representation learning is a brand-new strategy for associating seizures with complex brain network variations, enabling reliable patient-independent seizure prediction.
Keyword:
Electroencephalography
Brain modeling
Recording
Predictive models
Scalp
Hospitals
Epilepsy
Medical diagnostic imaging
Training
Representation learning
Adversarial inference
electroencephalogram (EEG)
metastability analysis
seizure prediction
期刊
IF:
6.8
论文数:
4.7K
被引数:
2.0W
机构
引用论文
A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals使用EEG信号预测癫痫发作的长短期记忆深度学习网络
PREAI
分享收藏Cognitive performance in healthy older adults relates to spontaneous switching between states of functional connectivity during rest.png)
SCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏Dynamic reconfiguration of frequency-specific cortical coactivation patterns during psychedelic and anesthetized states induced by ketamineNeuroImageOAAI
NeuroImageIF0
OAAI分享收藏分享收藏Early seizure spread and epilepsy surgery: A systematic review早期癫痫发作扩散与癫痫手术: 一项系统综述EPILEPSIAOAAI
EPILEPSIAIF6.6
OAAI分享收藏
查看更多内容