Spatio-Temporal Attention Network for Epileptic Seizure Prediction
This work addresses the critical need for accurate, patient-specific seizure prediction to enable timely clinical interventions for epilepsy patients, showing incremental improvements over existing methods.
The study tackled the problem of predicting epileptic seizures by developing a Spatio-Temporal Attention Network (STAN) that models EEG signal correlations, achieving 96.6% sensitivity with a 0.011/h false detection rate on the CHB-MIT dataset and 94.2% sensitivity with 0.063/h on the MSSM dataset, significantly outperforming state-of-the-art methods.
In this study, we present a deep learning framework that learns complex spatio-temporal correlation structures of EEG signals through a Spatio-Temporal Attention Network (STAN) for accurate predictions of onset of seizures for Epilepsy patients. Unlike existing methods, which rely on feature engineering and/or assume fixed preictal durations, our approach simultaneously models spatio-temporal correlations through STAN and employs an adversarial discriminator to distinguish preictal from interictal attention patterns, enabling patient-specific learning. Evaluation on CHB-MIT and MSSM datasets demonstrates 96.6\% sensitivity with 0.011/h false detection rate on CHB-MIT, and 94.2% sensitivity with 0.063/h FDR on MSSM, significantly outperforming state-of-the-art methods. The framework reliably detects preictal states at least 15 minutes before an onset, with patient-specific windows extending to 45 minutes, providing sufficient intervention time for clinical applications.