LookAroundNet: Extending Temporal Context with Transformers for Clinically Viable EEG Seizure Detection

TL;DR

LookAroundNet is a transformer-based EEG seizure detection model that leverages extended temporal context and diverse training data to improve accuracy and generalization across various clinical settings, aiming for real-world deployment.

Contribution

The paper introduces LookAroundNet, a novel seizure detection approach using transformers with wider temporal context, demonstrating improved robustness and clinical viability across multiple datasets.

Findings

Achieves strong performance across diverse EEG datasets.

Generalizes well to unseen recording conditions.

Operates with computational efficiency suitable for clinical use.

Abstract

Automated seizure detection from electroencephalography (EEG) remains difficult due to the large variability of seizure dynamics across patients, recording conditions, and clinical settings. We introduce LookAroundNet, a transformer-based seizure detector that uses a wider temporal window of EEG data to model seizure activity. The seizure detector incorporates EEG signals before and after the segment of interest, reflecting how clinicians use surrounding context when interpreting EEG recordings. We evaluate the proposed method on multiple EEG datasets spanning diverse clinical environments, patient populations, and recording modalities, including routine clinical EEG and long-term ambulatory recordings, in order to study performance across varying data distributions. The evaluation includes publicly available datasets as well as a large proprietary collection of home EEG recordings, providing complementary views of controlled clinical data and unconstrained home-monitoring conditions. Our results show that LookAroundNet achieves strong performance across datasets, generalizes well to previously unseen recording conditions, and operates with computational costs compatible with real-world clinical deployment. The results indicate that extended temporal context, increased training data diversity, and model ensembling are key factors for improving performance. This work contributes to moving automatic seizure detection models toward clinically viable solutions.