EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY-NC-ND 4.0

Diagnosing Epilepsy with Normal Interictal EEG Using Dynamic Network Models

Patrick Myers iD, Kristin M Gunnarsdottir, Adam Li, Vlad Razskazovskiy, Jeff Craley, Alana Chandler, Dale Wyeth, Edmund Wyeth, Kareem A Zaghloul, Sara K Inati, Jennifer L Hopp, Babitha Haridas und 7 weitere

Annals of Neurology · 2025-05 · 97 (5) · 907-918

DOI: 10.1002/ana.27168 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Annals of Neurology, online erschienen am 16.01.2025. Verfasst von Patrick Myers und 18 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA. Hauptthemen laut MEDLINE: Electroencephalography, Epilepsy, Neural Networks, Computer. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NINDS NIH HHS, The Louis B. Thalheimer Fund for Translational Research, National Institute of Neurological Disorders and Stroke.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Whereas a scalp electroencephalogram (EEG) is important for diagnosing epilepsy, a single routine EEG is limited in its diagnostic value. Only a small percentage of routine EEGs show interictal epileptiform discharges (IEDs) and overall misdiagnosis rates of epilepsy are 20% to 30%. We aim to demonstrate how network properties in EEG recordings can be used to improve the speed and accuracy differentiating epilepsy from mimics, such as functional seizures – even in the absence of IEDs.

Methods

In this multicenter study, we analyzed routine scalp EEGs from 218 patients with suspected epilepsy and normal initial EEGs. The patients’ diagnoses were later confirmed based on an epilepsy monitoring unit (EMU) admission. About 46% ultimately being diagnosed with epilepsy and 54% with non‐epileptic conditions. A logistic regression model was trained using spectral and network‐derived EEG features to differentiate between epilepsy and non‐epilepsy. Of the 218 patients, 90% were used for training and 10% were held out for testing. Within the training set, 10‐fold cross validation was performed. The resulting tool was named “EpiScalp.” Results EpiScalp achieved an area under the curve (AUC) of 0.940, an accuracy of 0.904, a sensitivity of 0.835, and a specificity of 0.963 in classifying patients as having epilepsy or not.

Interpretation

EpiScalp provides an accurate diagnostic aid from a single initial EEG recording, even in more challenging epilepsy cases with normal initial EEGs. This may represent a paradigm shift in epilepsy diagnosis by deriving an objective measure of epilepsy likelihood from previously uninformative EEGs. ANN NEUROL 2025;97:907–918

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyEpilepsyNeural Networks, ComputerHumansMaleFemaleAdultMiddle AgedYoung AdultAdolescentAgedChild

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA.
  • Institute for Computational Medicine, Johns Hopkins University, Baltimore, MD, USA.
  • Neurosurgery and Epilepsy Center, University of Pittsburgh Medical Center, Pittsburgh, PA, USA.
  • Division of Epilepsy, Thomas Jefferson University Hospital, Philadelphia, PA, USA.
  • Surgical Neurology Branch, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA.
  • Department of Neurology, University of Maryland Medical Center, Baltimore, MD, USA.

ORCID-Profile: Patrick Myers

Förderung

  • NINDS NIH HHS
  • The Louis B. Thalheimer Fund for Translational Research
  • National Institute of Neurological Disorders and Stroke

Zitieren

APA

Myers, P., Gunnarsdottir, K. M., Li, A., Razskazovskiy, V., Craley, J., Chandler, A., Wyeth, D., Wyeth, E., Zaghloul, K. A., Inati, S. K., Hopp, J. L., Haridas, B., Gonzalez-Martinez, J., Bagíc, A., Kang, J. Y., Sperling, M. R., Barot, N., Sarma, S. V., & Husari, K. S. (2025). Diagnosing Epilepsy with Normal Interictal EEG Using Dynamic Network Models. Annals of Neurology, 97(5), 907-918. https://doi.org/10.1002/ana.27168

Vancouver

Myers P, Gunnarsdottir KM, Li A, Razskazovskiy V, Craley J, Chandler A, et al. Diagnosing Epilepsy with Normal Interictal EEG Using Dynamic Network Models. Annals of Neurology. 2025;97(5):907-918. doi:10.1002/ana.27168

BibTeX
@article{Myers2025,
  author = {Myers, Patrick and Gunnarsdottir, Kristin M and Li, Adam and Razskazovskiy, Vlad and Craley, Jeff and Chandler, Alana and Wyeth, Dale and Wyeth, Edmund and Zaghloul, Kareem A and Inati, Sara K and Hopp, Jennifer L and Haridas, Babitha and Gonzalez-Martinez, Jorge and Bagíc, Anto and Kang, Joon-Yi and Sperling, Michael R and Barot, Niravkumar and Sarma, Sridevi V and Husari, Khalil S},
  title = {Diagnosing Epilepsy with Normal Interictal EEG Using Dynamic Network Models},
  journal = {Annals of Neurology},
  year = {2025},
  volume = {97},
  number = {5},
  pages = {907--918},
  doi = {10.1002/ana.27168}
}
Kostenlos starten →