Self‐supervised data‐driven approach defines pathological high‐frequency oscillations in epilepsy
Epilepsia · 2025-11 · 66 (11) · 4434-4450
DOI: 10.1111/epi.18545 ↗Kurz gefasst
Fachartikel in der Zeitschrift Epilepsia, online erschienen am 12.07.2025. Verfasst von Yipeng Zhang und 19 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, University of California, Los Angeles (UCLA), Los Angeles, California, USA. Hauptthemen laut MEDLINE: Epilepsy, Electrocorticography, Brain Waves, Brain. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NINDS NIH HHS, NCATS NIH HHS, Children's Discovery and Innovation Institute, University of California, Los Angeles.
Abstract (Originalsprache)
Objective
Interictal high‐frequency oscillations (HFOs) are a promising neurophysiological biomarker of the epileptogenic zone (EZ). However, objective criteria for distinguishing pathological from physiological HFOs remain elusive, hindering clinical application. We investigated whether the distinct mechanisms underlying pathological and physiological HFOs are encapsulated in their signal morphology in intracranial electroencephalographic (iEEG) recordings and whether this distinction could be captured by a deep generative model.
Methods
In a retrospective cohort of 185 epilepsy patients who underwent iEEG monitoring, we analyzed 686 410 HFOs across 18 265 brain contacts. To learn morphological characteristics, each event was transformed into a time–frequency plot and input into a variational autoencoder. We characterized latent space clusters containing morphologically defined putative pathological HFOs (mpHFOs) using interpretability analysis, including latent space disentanglement and time‐domain perturbation. We built a predictive model to forecast postoperative seizure outcomes at 12 months based on the resection status of brain regions exhibiting mpHFOs. This model was compared to current clinical standards that evaluate outcomes based on the extent of seizure onset zone (SOZ) removal. Results mpHFOs showed strong associations with expert‐defined spikes and were predominantly located within the SOZ. The interpretability analysis discovered novel pathological features, including high power in the gamma (30–80 Hz) and ripple (>80 Hz) bands centered on the event with spike‐like activity. These characteristics were consistent across multiple variables, including institution, electrode type, patient demographics, and anatomical location. Predicting postoperative seizure outcomes using the resection ratio of mpHFOs outperformed unclassified HFOs (F1 = .72 vs. .68, p < .01) and matched current clinical standards using SOZ resection (F1 = .74, p = .76). Combining mpHFO data with demographic and SOZ resection status further improved prediction performance (F1 = .83, p < .01). Significance Our data‐driven approach using the generative artificial intelligence model yielded a novel, explainable definition of pathological HFOs, which has the potential to further enhance the clinical use of HFOs for EZ delineation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, University of California, Los Angeles (UCLA), Los Angeles, California, USA.
- Division of Pediatric Neurology, Department of Pediatrics, UCLA Mattel Children's Hospital, David Geffen School of Medicine at UCLA, Los Angeles, California, USA.
- Department of Pediatrics and Neurology, Children's Hospital of Michigan, Wayne State University School of Medicine, Detroit, Michigan, USA.
- UCLA Children's Discovery and Innovation Institute, Los Angeles, California, USA.
- Division of Neuroradiology, Department of Radiology, UCLA Medical Center, David Geffen School of Medicine, Los Angeles, California, USA.
- Department of Neurosurgery, UCLA Medical Center, David Geffen School of Medicine, Los Angeles, California, USA.
ORCID-Profile: Yipeng Zhang, Naoto Kuroda, Shaun A Hussain, Aria Fallah, Eishi Asano, Vwani Roychowdhury, Hiroki Nariai
Förderung
- NINDS NIH HHS
- NCATS NIH HHS
- Children's Discovery and Innovation Institute, University of California, Los Angeles
- National Center for Advancing Translational Sciences
- National Institute of Neurological Disorders and Stroke
Zitieren
APA
Zhang, Y., Daida, A., Liu, L., Kuroda, N., Ding, Y., Oana, S., Kanai, S., Monsoor, T., Duan, C., Hussain, S. A., Qiao, J. X., Salamon, N., Fallah, A., Sim, M. S., Sankar, R., Staba, R. J., Engel, J., Asano, E., Roychowdhury, V., & Nariai, H. (2025). Self‐supervised data‐driven approach defines pathological high‐frequency oscillations in epilepsy. Epilepsia, 66(11), 4434-4450. https://doi.org/10.1111/epi.18545
Vancouver
Zhang Y, Daida A, Liu L, Kuroda N, Ding Y, Oana S, et al. Self‐supervised data‐driven approach defines pathological high‐frequency oscillations in epilepsy. Epilepsia. 2025;66(11):4434-4450. doi:10.1111/epi.18545
BibTeX
@article{Zhang2025,
author = {Zhang, Yipeng and Daida, Atsuro and Liu, Lawrence and Kuroda, Naoto and Ding, Yuanyi and Oana, Shingo and Kanai, Sotaro and Monsoor, Tonmoy and Duan, Chenda and Hussain, Shaun A and Qiao, Joe X and Salamon, Noriko and Fallah, Aria and Sim, Myung Shin and Sankar, Raman and Staba, Richard J and Engel, Jerome and Asano, Eishi and Roychowdhury, Vwani and Nariai, Hiroki},
title = {Self‐supervised data‐driven approach defines pathological high‐frequency oscillations in epilepsy},
journal = {Epilepsia},
year = {2025},
volume = {66},
number = {11},
pages = {4434--4450},
doi = {10.1111/epi.18545}
}
EUVIMED