Seizure prediction using long-term fragmented intracranial canine and human EEG recordings

Zisheng Zhang, Keshab K. Parhi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

This paper presents a novel patient-specific algorithm for prediction of seizures in epileptic patients. Spectral power features, including relative spectral powers and spectral power ratios, and cross correlation coefficients between all pairs of electrodes, are extracted as two independent feature sets. Both feature sets are selected independently in a patient-specific manner by classification and regression tree (CART). Selected features are further processed by a second-order Kalman filter and then input independently to three different classifiers which include AdaBoost, radial basis function kernel support vector machine (RBF-SVM) and artificial neural network (ANN). The algorithm is tested on the intra-cranial EEG (iEEG) from the recent American Epilepsy Society Seizure Prediction Challenge database. Intracranial EEG was recorded from five dogs and two patients. These datasets have varying numbers of electrodes and are sampled at different sampling frequencies. It is shown that the spectral feature set achieves a mean AUC of 0.7538, 0.7739, and 0.7948 for AdaBoost, SVM, and ANN, respectively. The correlation coefficients feature set achieves a mean AUC of 0.6640, 0.7403, and 0.7875 for AdaBoost, SVM, and ANN, respectively. The combined best results which use patient-specific feature sets achieve a mean AUC of 0.7603, 0.8472, and 0.8884 for AdaBoost, SVM, and ANN, respectively.

Original languageEnglish (US)
Title of host publicationConference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages361-365
Number of pages5
ISBN (Electronic)9781538639542
DOIs
StatePublished - Mar 1 2017
Event50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 - Pacific Grove, United States
Duration: Nov 6 2016Nov 9 2016

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)1058-6393

Other

Other50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
CountryUnited States
CityPacific Grove
Period11/6/1611/9/16

Fingerprint Dive into the research topics of 'Seizure prediction using long-term fragmented intracranial canine and human EEG recordings'. Together they form a unique fingerprint.

  • Cite this

    Zhang, Z., & Parhi, K. K. (2017). Seizure prediction using long-term fragmented intracranial canine and human EEG recordings. In M. B. Matthews (Ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 (pp. 361-365). [7869060] (Conference Record - Asilomar Conference on Signals, Systems and Computers). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2016.7869060