Measure profile surrogates: a method to validate the performance of epileptic seizure prediction algorithms

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Kreuz, Thomas
• dc.contributor.author Andrzejak, Ralph Gregor
• dc.contributor.author Mormann, Florian
• dc.contributor.author Kraskov, Alexander
• dc.contributor.author Stögbauer, Harald
• dc.contributor.author Elger, Christian E.
• dc.contributor.author Lehnertz, Klaus
• dc.contributor.author Grassberger, Peter
• dc.date.accessioned 2020-02-13T18:07:08Z
• dc.date.available 2020-02-13T18:07:08Z
• dc.date.issued 2004
• dc.description.abstract In a growing number of publications it is claimed that epileptic seizures can be predicted by analyzing the electroencephalogram (EEG) with different characterizing measures. However, many of these studies suffer from a severe lack of statistical validation. Only rarely are results passed to a statistical test and verified against some null hypothesis H 0 in order to quantify their significance. In this paper we propose a method to statistically validate the performance of measures used to predict epileptic seizures. From measure profiles rendered by applying a moving-window technique to the electroencephalogram we first generate an ensemble of surrogates by a constrained randomization using simulated annealing. Subsequently the seizure prediction algorithm is applied to the original measure profile and to the surrogates. If detectable changes before seizure onset exist, highest performance values should be obtained for the original measure profiles and the null hypothesis. “The measure is not suited for seizure prediction” can be rejected. We demonstrate our method by applying two measures of synchronization to a quasicontinuous EEG recording and by evaluating their predictive performance using a straightforward seizure prediction statistics. We would like to stress that the proposed method is rather universal and can be applied to many other prediction and detection problems.en
• dc.description.sponsorship This work was supported by the Deutsche Forschungsgemeinschaft (Grant No. SFB TR3).
• dc.format.mimetype application/pdf
• dc.identifier.citation Kreuz T, Andrzejak RG, Mormann F, Kraskov A, Stogbauer H, Elger CE, Lehnertz K, Grassberger P. Measure profile surrogates: a method to validate the performance of epileptic seizure prediction algorithms. Phys Rev E. 2004;69:061915. DOI: 10.1103/PhysRevE.69.061915
• dc.identifier.doi http://dx.doi.org/10.1103/PhysRevE.69.061915
• dc.identifier.issn 2470-0045
• dc.identifier.uri http://hdl.handle.net/10230/43596
• dc.language.iso eng
• dc.publisher American Physical Society
• dc.relation.ispartof Physical Review E. 2004;69:061915.
• dc.rights © American Physical Society. Published article available at https://journals.aps.org/pre/abstract/10.1103/PhysRevE.69.061915
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Nonlinear signal analysisen
• dc.subject.keyword Synchronization
• dc.title Measure profile surrogates: a method to validate the performance of epileptic seizure prediction algorithms
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/publishedVersion