# Epileptic Seizure Prediction Using Patient-Adaptive Transformer Networks

arXiv: https://arxiv.org/abs/2603.26821 · HTML: https://mlsanity.com/paper/2603.26821/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 14 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [EEG2Rep: Enhancing Self-supervised EEG Representation Through Informative Masked Inputs](https://mlsanity.com/paper/2402.17772/) (2024)
- [Self-supervised Learning for Electroencephalogram: A Systematic Survey](https://mlsanity.com/paper/2401.05446/) (2024)
- [BioSerenity-E1: a self-supervised EEG model for medical applications](https://mlsanity.com/paper/2503.10362/) (2025)
- [Epileptic Seizure Prediction: A Semi-Dilated Convolutional Neural Network Architecture](https://mlsanity.com/paper/2007.11716/) (2020)
- [Enhancing Representation Learning of EEG Data with Masked Autoencoders](https://mlsanity.com/paper/2408.05375/) (2024)

## Abstract (arXiv)

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.