Improving the ripple classification in focal pediatric epilepsy: identifying pathological high-frequency oscillations by Gaussian mixture model clustering.


Por: Migliorelli C, Romero S, Bachiller A, Aparicio J, Alonso-Lopez JF, Mañanas MA and San Antonio-Arce MV

Publicada: 31 ago 2021 Ahead of Print: 31 ago 2021
Resumen:
Objective. High-frequency oscillations (HFOs) have emerged as a promising clinical biomarker for presurgical evaluation in childhood epilepsy. HFOs are commonly classified in stereo-encephalography as ripples (80-200 Hz) and fast ripples (200-500 Hz). Ripples are less specific and not so directly associated with epileptogenic activity because of their physiological and pathological origin. The aim of this paper is to distinguish HFOs in the ripple band and to improve the evaluation of the epileptogenic zone (EZ).Approach. This study constitutes a novel modeling approach evaluated in ten patients from Sant Joan de Deu Pediatric Hospital (Barcelona, Spain), with clearly-defined seizure onset zones (SOZ) during presurgical evaluation. A subject-by-subject basis analysis is proposed: a probabilistic Gaussian mixture model (GMM) based on the combination of specific ripple features is applied for estimating physiological and pathological ripple subpopulations.Main Results. Clear pathological and physiological ripples are identified. Features differ considerably among patients showing within-subject variability, suggesting that individual models are more appropriate than a traditional whole-population approach. The difference in rates inside and outside the SOZ for pathological ripples is significantly higher than when considering all the ripples. These significant differences also appear in signal segments without epileptiform activity. Pathological ripple rates show a sharp decline from SOZ to non-SOZ contacts and a gradual decrease with distance.Significance. This novel individual GMM approach improves ripple classification and helps to refine the delineation of the EZ, as well as being appropriate to investigate the interaction of epileptogenic and propagation networks.

Filiaciones:
Migliorelli C:
 Centro de Investigación Biomédica en Red, Madrid, Madrid, Comunidad de Madrid, 28029, SPAIN

Romero S:
 Automatic Control Department (ESAII), Universitat Politecnica de Catalunya, Barcelona, Barcelona, Catalunya, 08034, SPAIN

Bachiller A:
 Automatic Control Department, Universitat Politecnica de Catalunya, EDIFICI H, AVDA. DIAGONAL, 647, Office 4.26, Barcelona, Catalunya, 08034, SPAIN

Aparicio J:
 Epilepsy Unit, Department of Neuropediatrics, Hospital Sant Joan de Déu, hospital Sant Joan de Deu, Barcelona, Catalunya, 08000, SPAIN

Alonso-Lopez JF:
 Universitat Politecnica de Catalunya, Barcelona, Barcelona, Catalunya, 08034, SPAIN

Mañanas MA:
 Departamento de Ingeniería de Sistemas, Universitat Politecnica de Catalunya, Barcelona, Barcelona, Catalunya, 08034, SPAIN

San Antonio-Arce MV:
 Freiburg Epilepsy Center, University of Freiburg, Freiburg, Freiburg im Breisgau, Baden-Württemberg, 79085, GERMANY
ISSN: 17412560





Journal of Neural Engineering
Editorial
IOP Publishing Ltd, No.2 The Distillery, Glassfields, Avon Street, Bristol BS2 0GR, ENGLAND, Reino Unido
Tipo de documento: Article
Volumen: 18 Número: 4
Páginas:
WOS Id: 000693222600001
ID de PubMed: 34384061
imagen Open Access

MÉTRICAS