Abstract
Electrocardiogram (ECG) recordings, lasting hours before epileptic seizures, have been studied in the search for evidence of the existence of a preictal interval that follows a normal ECG trace and precedes the seizure’s clinical manifestation. The preictal interval has not yet been clinically parametrized. Furthermore, the duration of this interval varies for seizures both among patients and from the same patient. In this study, we performed a heart rate variability (HRV) analysis to investigate the discriminative power of the features of HRV in the identification of the preictal interval. HRV information extracted from the linear time and frequency domains as well as from nonlinear dynamics were analysed. We inspected data from 238 temporal lobe seizures recorded from 41 patients with drug-resistant epilepsy from the EPILEPSIAE database. Unsupervised methods were applied to the HRV feature dataset, thus leading to a new perspective in preictal interval characterization. Distinguishable preictal behaviour was exhibited by 41% of the seizures and 90% of the patients. Half of the preictal intervals were identified in the 40 min before seizure onset. The results demonstrate the potential of applying clustering methods to HRV features to deepen the current understanding of the preictal state.
Highlights
Electrocardiogram (ECG) recordings, lasting hours before epileptic seizures, have been studied in the search for evidence of the existence of a preictal interval that follows a normal ECG trace and precedes the seizure’s clinical manifestation
Epileptic patients suffering from drug-resistant epilepsy (DRE) have their daily lives disrupted by the occurrence of sudden seizures
This study is a proof of concept that is, to the best of our knowledge, the first attempt to apply unsupervised learning methods to heart rate variability (HRV)-derived features in characterizing the preictal interval
Summary
Electrocardiogram (ECG) recordings, lasting hours before epileptic seizures, have been studied in the search for evidence of the existence of a preictal interval that follows a normal ECG trace and precedes the seizure’s clinical manifestation. A solution involving the integration of seizure prediction models into a warning device could allow for the minimization of possible injuries and anxiety levels resulting from the unpredictability of epileptic seizures[2,3,4] Envisioning such a solution, several studies have presented seizure prediction approaches designed to capture preictal electroencephalogram (EEG) patterns reflecting the transition from the normal brain state (interictal) to a state of hypersynchronous neural activity (ictal)[5,6]. The supervised prediction methodologies developed to date perform an “empirical search” by testing different integer preictal durations and selecting the duration that corresponds to the best model performance. This approach is highly dependent on accurate labelling. Unsupervised methodologies may provide a significant contribution to the characterization of the preictal interval, potentially addressing the preictal variability seen among patients and among seizures in the same patient
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
