Prediction of epilepsy surgery outcome using foramen ovale EEG – A machine learning approach

•We analyzed EEG data recorded from foramen ovale and epidural peg electrodes to predict post-surgical seizure freedom.•For patients with seizure onset on foramen ovale electrodes, a computational approach is helpful in outcome prediction.•Our model based on EEG data from bilateral mesial temporal regions outperformed prediction based on clinical and scalp EEG.•The most important features for outcome prediction were spectral power in the gamma and high gamma range.•Machine learning based surgical outcome prediction is possible with data from a minimally invasive EEG diagnostic modality.