||Seizure Prediction on the Basis of iEEG Recordings
||Duun-Henriksen, Jonas (Biomedical Engineering, Department of Electrical Engineering, Technical University of Denmark, DTU, DK-2800 Kgs. Lyngby, Denmark)
||Technical University of Denmark, DTU, DK-2800 Kgs. Lyngby, Denmark
||Approximately 1% of the world’s population suffers from epilepsy. Of these, 25% cannot
be treated satisfactory with existing treatment methods. This corresponds to more than
13.000 people in Denmark who are disabled by the sudden, unforeseen onset of a seizure.
The current project evaluated the feasibility of providing an algorithm that could warn
a patient of a forthcoming seizure based on iEEG recordings. From a literary study, the
mean phase coherence (MPC) feature was found to be the most promising. This feature
was implemented and tested in a rigorously, out-of-sample manner on 21 patients with
4.1 seizures in average to assess its predictive performance. A sensitivity of 0.55 and a
specificity of 0.62 were obtained after optimization of threshold value and localization
of electrodes for all patients. These results are just better than a random predictor. To
improve the results the parameters need to be optimized for each patient individually. Before
this can be done, a larger database with more seizures recorded per patient is needed.
While it was not possible to make a final conclusion on the feasibility of seizure prediction,
the author does believe that at least some patients will be able to gain advantage of
seizure prediction, though the field still needs further investigation.
||Technical University of Denmark (DTU) : Kgs. Lyngby, Denmark
Creation date: 2010-06-29
Update date: 2011-04-11