EEG parameters as endpoints in epilepsy clinical trials - An expert panel opinion paper

Buchhalter, Jeffrey; Neuray, Caroline; Cheng, Jocelyn; D’Cruz, O’Neill F.; Datta, Alexandre N.; Dlugos, Dennis J.; French, Jacqueline; Haubenberger, Dietrich; Hulihan, Joseph; Klein, Pavel; Komorowski, Robert W.; Kramer, Lynn D.; Lothe, Amélie; Nabbout, Rima; Perucca, Emilio; Ark, Peter van der

doi:10.1016/j.eplepsyres.2022.107028

Cited by 5 publications

(2 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results indicate that the features that we extracted from the EEG signal are more affected by seizure propensity (risk of having seizure recurrence) than past seizures. Ultimately, all these outcomes depend on the imperfect reporting of seizures by patients 50 ; there is promise that in the future, more objective outcomes could directly benefit predictive models in epilepsy 51 .…”

Section: Discussionmentioning

confidence: 99%

Machine-learning for the prediction of one-year seizure recurrence based on routine electroencephalography

Lemoine,

Toffa,

Pelletier-Mc Duff

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Predicting seizure recurrence risk is critical to the diagnosis and management of epilepsy. Routine electroencephalography (EEG) is a cornerstone of the estimation of seizure recurrence risk. However, EEG interpretation relies on the visual identification of interictal epileptiform discharges (IEDs) by neurologists, with limited sensitivity. Automated processing of EEG could increase its diagnostic yield and accessibility. The main objective was to develop a prediction model based on automated EEG processing to predict one-year seizure recurrence in patients undergoing routine EEG. We retrospectively selected a consecutive cohort of 517 patients undergoing routine EEG at our institution (training set) and a separate, temporally shifted cohort of 261 patients (testing set). We developed an automated processing pipeline to extract linear and non-linear features from the EEGs. We trained machine learning algorithms on multichannel EEG segments to predict one-year seizure recurrence. We evaluated the impact of IEDs and clinical confounders on performances and validated the performances on the testing set. The receiver operating characteristic area-under-the-curve for seizure recurrence after EEG in the testing set was 0.63 (95% CI 0.55–0.71). Predictions were still significantly above chance in EEGs with no IEDs. Our findings suggest that there are changes other than IEDs in the EEG signal embodying seizure propensity.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine-learning for the prediction of one-year seizure recurrence based on routine electroencephalography

Lemoine,

Toffa,

Pelletier-Mc Duff

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Long-term automated counting of GPFA events may have potential benefit for the prediction of seizure events or titration of therapies, as has been demonstrated in other epilepsies [26][27][28] . Furthermore, there is increasing interest in the use of EEG measurements as trial endpoints for studying the effects of interventions, which would benefit immensely from automated review processes 21 .…”

Section: Discussionmentioning

confidence: 99%