Seizure prediction with spectral power of time/space-differential EEG signals using cost-sensitive support vector machine

Abstract

A patient-specific seizure prediction algorithm is proposed using a classifier to differentiate preictal from interictal ECoG signals. Spectral power of ECoG processed in four different fashions are used as features: raw, time-differential, space-differential, and time/space-differential ECoG. The features are classified using cost-sensitive support vector machines by the double cross-validation methodology. The proposed algorithm has been applied to ECoG recordings of 18 patients in the Freiburg EEG database, totaling 80 seizures and 437-hour-long interictal recordings. Classification with the feature obtained from time/space-differential ECoG demonstrates performance of 86.25% sensitivity and 0.1281 false positives per hour in out-of-sample testing.