Recurrent neural network based prediction of epileptic seizures in intra- and extracranial EEG

Predicting the onset of epileptic seizure is an important and difficult bio medical problem, which has attracted substantial attention of the intellige nt computing community over the past two decades. We apply recurrent neural networks (RNN) combined with signal wavelet decomposition to the problem. We input raw EEG and its wavelet-decomposed subbands into RNN training/test ing, as opposed to specific signal features extracted from EEG. To the best of our knowledge this approach has never been attempted before. The data u sed included both scalp and intracranial EEG recordings obtained from two e pileptic patients. We demonstrate that the existence of a "preictal" stage (immediately preceding seizure) of some minutes duration is quite feasible. (C) 2000 Elsevier Science B.V. All rights reserved.