Epileptic Seizure Prediction Using Patient-Adaptive Transformer Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mahdi, Mohamed, Baghdadi, Asma
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914427252506624
author Mahdi, Mohamed
Baghdadi, Asma
author_facet Mahdi, Mohamed
Baghdadi, Asma
contents Epileptic seizure prediction from electroencephalographic (EEG) recordings remains challenging due to strong inter-patient variability and the complex temporal structure of neural signals. This paper presents a patient-adaptive transformer framework for short-horizon seizure forecasting. The proposed approach employs a two-stage training strategy: self-supervised pretraining is first used to learn general EEG temporal representations through autoregressive sequence modeling, followed by patient-specific fine-tuning for binary prediction of seizure onset within a 30-second horizon. To enable transformer-based sequence learning, multichannel EEG signals are processed using noise-aware preprocessing and discretized into tokenized temporal sequences. Experiments conducted on subjects from the TUH EEG dataset demonstrate that the proposed method achieves validation accuracies above 90% and F1 scores exceeding 0.80 across evaluated patients, supporting the effectiveness of combining self-supervised representation learning with patient-specific adaptation for individualized seizure prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26821
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Epileptic Seizure Prediction Using Patient-Adaptive Transformer Networks
Mahdi, Mohamed
Baghdadi, Asma
Machine Learning
Artificial Intelligence
Epileptic seizure prediction from electroencephalographic (EEG) recordings remains challenging due to strong inter-patient variability and the complex temporal structure of neural signals. This paper presents a patient-adaptive transformer framework for short-horizon seizure forecasting. The proposed approach employs a two-stage training strategy: self-supervised pretraining is first used to learn general EEG temporal representations through autoregressive sequence modeling, followed by patient-specific fine-tuning for binary prediction of seizure onset within a 30-second horizon. To enable transformer-based sequence learning, multichannel EEG signals are processed using noise-aware preprocessing and discretized into tokenized temporal sequences. Experiments conducted on subjects from the TUH EEG dataset demonstrate that the proposed method achieves validation accuracies above 90% and F1 scores exceeding 0.80 across evaluated patients, supporting the effectiveness of combining self-supervised representation learning with patient-specific adaptation for individualized seizure prediction.
title Epileptic Seizure Prediction Using Patient-Adaptive Transformer Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.26821