Establishing functional brain networks using a nonlinear partial directed coherence method to predict epileptic seizures

Background: Epilepsy is a neurological disorder characterized by unpredictable seizures that can lead to severe health problems. EEG techniques have shown to be advantageous for studying and predicting epileptic seizures, thanks to their cost-effectiveness, non-invasiveness, portability and the capability for long-term monitoring. Linear and non-linear EEG analysis methods have been developed for the effective prediction of seizure onset, however both methods remain blind to underlying alterations of the structural and functional brain networks associated with epileptic seizures. Such information is employed in this study to develop novel method for epileptic seizure prediction. New Methods: In this study, nonlinear partial directed coherence (NPDC) was employed as measure of functional brain networks (FBNs) and analyzed to reveal the directional flow of epilepsy-linked brain activity. A novel prediction strategy was then developed for the prediction of epileptic seizures by introducing extracted network features to an extreme learning machine (ELM). Results: Results show that the proposed method achieved favorable performance across all subjects and in all EEG frequency bands, with best accuracy of 89.2% in beta band and an optimal prediction time of 1356.4 s in delta bands, which outperforms currently available approaches. Comparison with Existing Methods: Our NPDC based on FBNs methods approach surpasses the accuracy of pure graph theory and pure non-linear methods with a significantly increased prediction time. Conclusions: The findings of this study demonstrate that the proposed prediction strategy is suitable for the prediction of seizure onset.