Interictal EEG source connectivity to localize the epileptogenic zone in patients with drug‐resistant epilepsy: A machine learning approach
Epilepsia · 2024-04 · 65 (4) · 944-960
DOI: 10.1111/epi.17898 ↗Kurz gefasst
Fachartikel in der Zeitschrift Epilepsia, online erschienen am 06.02.2024. Verfasst von Georgios Ntolkeras und 10 weiteren Autor:innen. Beteiligte Einrichtung: Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Department of Medicine, Boston Children's Hospital, Harva…. Hauptthemen laut MEDLINE: Electroencephalography, Drug Resistant Epilepsy. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NINDS NIH HHS, NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Objective
To deconstruct the epileptogenic networks of patients with drug‐resistant epilepsy (DRE) using source functional connectivity (FC) analysis; unveil the FC biomarkers of the epileptogenic zone (EZ); and develop machine learning (ML) models to estimate the EZ using brief interictal electroencephalography (EEG) data.
Methods
We analyzed scalp EEG from 50 patients with DRE who had surgery. We reconstructed the activity (electrical source imaging [ESI]) of virtual sensors (VSs) across the whole cortex and computed FC separately for epileptiform and non‐epileptiform EEG epochs (with or without spikes). In patients with good outcome (Engel 1a), four cortical regions were defined: EZ (resection) and three non‐epileptogenic zones (NEZs) in the same and opposite hemispheres. Region‐specific FC features in six frequency bands and three spatial ranges (long, short, inner) were compared between regions (Wilcoxon sign‐rank). We developed ML classifiers to identify the VSs in the EZ using VS‐specific FC features. Cross‐validation was performed using good outcome data. Performance was compared with poor outcomes and interictal spike localization.
Results
FC differed between EZ and NEZs ( p < .05) during non‐epileptiform and epileptiform epochs, showing higher FC in the EZ than its homotopic contralateral NEZ. During epileptiform epochs, the NEZ in the epileptogenic hemisphere showed higher FC than its contralateral NEZ. In good outcome patients, the ML classifiers reached 75% accuracy to the resection (91% sensitivity; 74% specificity; distance from EZ: 38 mm) using epileptiform epochs (gamma and beta frequency bands) and 62% accuracy using broadband non‐epileptiform epochs, both outperforming spike localization (accuracy = 47%; p < .05; distance from EZ: 57 mm). Lower performance was seen in poor outcomes. Significance We present an FC approach to extract EZ biomarkers from brief EEG data. Increased FC in various frequencies characterized the EZ during epileptiform and non‐epileptiform epochs. FC‐based ML models identified the resection better in good than poor outcome patients, demonstrating their potential for presurgical use in pediatric DRE.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Department of Medicine, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
- Department of Neurology, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
- Division of Epilepsy and Clinical Neurophysiology, Department of Neurology, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
- Division of Epilepsy Surgery, Department of Neurosurgery, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
- Jane and John Justin Institute for Mind Health, Cook Children's Health Care System, Fort Worth, Texas, USA.
- Division of Neuroradiology, Department of Radiology, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
ORCID-Profile: Georgios Ntolkeras, Phillip L Pearl, Christos Papadelis, Eleonora Tamilia
Förderung
- NINDS NIH HHS
- NIH HHS
- National Institutes of Health
Zitieren
APA
Ntolkeras, G., Makaram, N., Bernabei, M., De La Vega, A. C., Bolton, J., Madsen, J. R., Stone, S. S. D., Pearl, P. L., Papadelis, C., Grant, E. P., & Tamilia, E. (2024). Interictal EEG source connectivity to localize the epileptogenic zone in patients with drug‐resistant epilepsy: A machine learning approach. Epilepsia, 65(4), 944-960. https://doi.org/10.1111/epi.17898
Vancouver
Ntolkeras G, Makaram N, Bernabei M, De La Vega AC, Bolton J, Madsen JR, et al. Interictal EEG source connectivity to localize the epileptogenic zone in patients with drug‐resistant epilepsy: A machine learning approach. Epilepsia. 2024;65(4):944-960. doi:10.1111/epi.17898
BibTeX
@article{Ntolkeras2024,
author = {Ntolkeras, Georgios and Makaram, Navaneethakrishna and Bernabei, Matteo and De La Vega, Aime Cristina and Bolton, Jeffrey and Madsen, Joseph R and Stone, Scellig S D and Pearl, Phillip L and Papadelis, Christos and Grant, Ellen P and Tamilia, Eleonora},
title = {Interictal EEG source connectivity to localize the epileptogenic zone in patients with drug‐resistant epilepsy: A machine learning approach},
journal = {Epilepsia},
year = {2024},
volume = {65},
number = {4},
pages = {944--960},
doi = {10.1111/epi.17898}
}
EUVIMED