Low-gamma wavelet entropy as a contextual signature descriptor of the epileptogenic zone in peri-onset SEEG

In drug-resistant focal epilepsy, surgery - which requires accurate localization of the seizure origin - is the only curative treatment. When non-invasive exploration fails, stereo-electroencephalography (SEEG) provides the best a priori localization but clinical practice still relies on subjective and perfectible visual analysis.

This work investigates whether wavelet-based entropy features with contextual descriptors, from peri-onset of SEEG-recorded seizures can characterize the region to remove. For interpretability, a logistic regression classifier is trained.

Leave-One-Subject-Out cross-validation on a post-surgery seizure-free cohort shows good performance (sensitivity: 89% [95% CI: 68-97], specificity: 91% [95% CI: 87-95]) in identifying epileptogenic sensors. The model flags 14% of contacts, capturing 86% of the reference. Frequency content in the 40-80$\,\mathrm{\mathbf{Hz}}$ band appears particularly informative.

The proposed method enables accurate and interpretable identification of epileptogenic contacts, with potential for patient-level screening pending validation on larger datasets.

An efficient, parsimonious, and explainable model can support more targeted surgical decision-making while reducing the SEEG review burden and improving outcomes.