EUVIMEDEUVIMED entdecken
Crossref

Seizure forecasting with multiple timescales and features

Yueyang Liu iD, Artemio Soto-Breceda iD, Philippa Karoly iD, David B Grayden iD, Mark J Cook iD, Dean R Freestone iD, Daniel Schmidt iD, Levin Kuhlmann iD

Epilepsia · 2026

DOI: 10.1002/epi.70076 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Epilepsia, 2026. Verfasst von Yueyang Liu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Monash University, Clayton, Victoria, Australia. Hauptthemen laut MEDLINE: Electroencephalography, Seizures, Machine Learning, Brain. Die Arbeit nennt 48 Literaturangaben. Gefördert von: Australian Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Forecasting epileptic seizures is a difficult task. Studies of seizure prediction have investigated many different EEG features, but none of them have been useful enough to be applied in clinical practice beyond trials. Moreover, most of these features have been applied to short‐term intracranial EEG (iEEG) recordings, limiting the possibility of reliable statistical evaluation. This paper proposes a machine learning algorithm to forecast an epileptic seizure 2‐4 mins before seizure. This allows patients to seek help, or stimulation devices to work.

Methods

This paper investigates a large subset of features from the past and present to unravel which features and feature analysis methods will yield the best performance on long‐term iEEG recordings (from 14 patients with focal epilepsy) and thus provide the most reliable step toward clinical utility. Specifically, this study implements a multiple long‐time scale cycle feature analysis framework for seizure forecasting that considers the state‐of‐the‐art time series features of critical slowing down (autocorrelation and variance) as well as interictal epileptiform discharge (IED) / spike rate, High Frequency Activity (HFA), seven different univariate features, and three Neural Mass Model (NMM) features based on brain dynamics.

Results

Seizure phase histograms of all the features are then analyzed to investigate each feature’s potential for seizure forecasting by evaluating corresponding synchronization indices (SI) on fast (40 minutes to 2 days) and slow (2+ days) wideband time scales. Out of all combinations considered, the overall performance comparison across patients highlights that ‘autocorrelation + variance + NMM + spike rate’ features achieve the highest average AUC of 0.83, showcasing its performance in forecasting seizures. Significance A model is proposed that has a similar performance compared to the state‐of‐the‐art method, without the need of selecting the best channel prior to model building. Light is also shed on the comparative performance on long‐term recordings of many of the seizure forecasting features considered in the past.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographySeizuresMachine LearningBrainHumansForecastingPrediction AlgorithmsPredictive Learning ModelsAlgorithmsTime Factors

Stichwörter der Autor:innen

EEG feature analysiscritical slowing downdynamical systemsepileptic seizure forecastingneural filtering

Autor:innen und Institutionen

  • Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Monash University, Clayton, Victoria, Australia.
  • Department of Biomedical Engineering and Graeme Clark Institute, University of Melbourne, Melbourne, Victoria, Australia.
  • Department of Medicine, St. Vincent's Hospital, University of Melbourne, Fitzroy, Victoria, Australia.
  • Seer Medical, Melbourne, Victoria, Australia.

ORCID-Profile: Yueyang Liu, Artemio Soto-Breceda, Philippa Karoly, David B Grayden, Mark J Cook, Dean R Freestone, Daniel Schmidt, Levin Kuhlmann

Förderung

  • Australian Research Council

Zitieren

APA

Liu, Y., Soto-Breceda, A., Karoly, P., Grayden, D. B., Cook, M. J., Freestone, D. R., Schmidt, D., & Kuhlmann, L. (2026). Seizure forecasting with multiple timescales and features. Epilepsia. https://doi.org/10.1002/epi.70076

Vancouver

Liu Y, Soto-Breceda A, Karoly P, Grayden DB, Cook MJ, Freestone DR, et al. Seizure forecasting with multiple timescales and features. Epilepsia. 2026. doi:10.1002/epi.70076

BibTeX
@article{Liu2026,
  author = {Liu, Yueyang and Soto-Breceda, Artemio and Karoly, Philippa and Grayden, David B and Cook, Mark J and Freestone, Dean R and Schmidt, Daniel and Kuhlmann, Levin},
  title = {Seizure forecasting with multiple timescales and features},
  journal = {Epilepsia},
  year = {2026},
  doi = {10.1002/epi.70076}
}
Kostenlos starten →