eduzhai > Applied Sciences > Engineering >

Towards Early Diagnosis of Epilepsy from EEG Data

  • Save

... pages left unread,continue reading

Document pages: 15 pages

Abstract: Epilepsy is one of the most common neurological disorders, affecting about 1 of the population at all ages. Detecting the development of epilepsy, i.e.,epileptogenesis (EPG), before any seizures occur could allow for earlyinterventions and potentially more effective treatments. Here, we investigateif modern machine learning (ML) techniques can detect EPG from intra-cranialelectroencephalography (EEG) recordings prior to the occurrence of anyseizures. For this we use a rodent model of epilepsy where EPG is triggered byelectrical stimulation of the brain. We propose a ML framework for EPGidentification, which combines a deep convolutional neural network (CNN) with aprediction aggregation method to obtain the final classification decision.Specifically, the neural network is trained to distinguish five second segmentsof EEG recordings taken from either the pre-stimulation period or thepost-stimulation period. Due to the gradual development of epilepsy, there isenormous overlap of the EEG patterns before and after the stimulation. Hence, aprediction aggregation process is introduced, which pools predictions over alonger period. By aggregating predictions over one hour, our approach achievesan area under the curve (AUC) of 0.99 on the EPG detection task. Thisdemonstrates the feasibility of EPG prediction from EEG recordings.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×