Low-Complexity Seizure Prediction From iEEG/sEEG Using Spectral Power and Ratios of Spectral Power

Zisheng Zhang, Keshab K Parhi

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

Prediction of seizures is a difficult problem as the EEG patterns are not wide-sense stationary and change from seizure to seizure, electrode to electrode, and from patient to patient. This paper presents a novel patient-specific algorithm for prediction of seizures in epileptic patients from either one or two single-channel or bipolar channel intra-cranial or scalp electroencephalogram (EEG) recordings with low hardware complexity. Spectral power features are extracted and their ratios are computed. For each channel, a total of 44 features including 8 absolute spectral powers, 8 relative spectral powers and 28 spectral power ratios are extracted every two seconds using a 4-second window with a 50% overlap. These features are then ranked and selected in a patient-specific manner using a two-step feature selection. Selected features are further processed by a second-order Kalman filter and then input to a linear support vector machine (SVM) classifier. The algorithm is tested on the intra-cranial EEG (iEEG) from the Freiburg database and scalp EEG (sEEG) from the MIT Physionet database. The Freiburg database contains 80 seizures among 18 patients in 427 hours of recordings. The MIT EEG database contains 78 seizures from 17 children in 647 hours of recordings. It is shown that the proposed algorithm can achieve a sensitivity of 100% and an average false positive rate (FPR) of 0.0324 per hour for the iEEG (Freiburg) database and a sensitivity of 98.68% and an average FPR of 0.0465 per hour for the sEEG (MIT) database. These results are obtained with leave-one-out cross-validation where the seizure being tested is always left out from the training set. The proposed algorithm also has a low complexity as the spectral powers can be computed using FFT. The area and power consumption of the proposed linear SVM are 2 to 3 orders of magnitude less than a radial basis function kernel SVM (RBF-SVM) classifier. Furthermore, the total energy consumption of a system using linear SVM is reduced by 8% to 23% compared to system using RBF-SVM.

Original languageEnglish (US)
Article number7307237
Pages (from-to)693-706
Number of pages14
JournalIEEE Transactions on Biomedical Circuits and Systems
Volume10
Issue number3
DOIs
StatePublished - Jun 1 2016

Fingerprint

Electroencephalography
Support vector machines
Classifiers
Electrodes
Kalman filters
Fast Fourier transforms
Feature extraction
Electric power utilization
Energy utilization
Hardware

Keywords

  • Branch and bound
  • Linear separability
  • Low-complexity architecture
  • Power spectral density
  • Ratio of spectral power
  • Seizure prediction

Cite this

Low-Complexity Seizure Prediction From iEEG/sEEG Using Spectral Power and Ratios of Spectral Power. / Zhang, Zisheng; Parhi, Keshab K.

In: IEEE Transactions on Biomedical Circuits and Systems, Vol. 10, No. 3, 7307237, 01.06.2016, p. 693-706.

Research output: Contribution to journalArticle

@article{ba9d02b4b1624c8a8a89b8b0f1860572,
title = "Low-Complexity Seizure Prediction From iEEG/sEEG Using Spectral Power and Ratios of Spectral Power",
abstract = "Prediction of seizures is a difficult problem as the EEG patterns are not wide-sense stationary and change from seizure to seizure, electrode to electrode, and from patient to patient. This paper presents a novel patient-specific algorithm for prediction of seizures in epileptic patients from either one or two single-channel or bipolar channel intra-cranial or scalp electroencephalogram (EEG) recordings with low hardware complexity. Spectral power features are extracted and their ratios are computed. For each channel, a total of 44 features including 8 absolute spectral powers, 8 relative spectral powers and 28 spectral power ratios are extracted every two seconds using a 4-second window with a 50{\%} overlap. These features are then ranked and selected in a patient-specific manner using a two-step feature selection. Selected features are further processed by a second-order Kalman filter and then input to a linear support vector machine (SVM) classifier. The algorithm is tested on the intra-cranial EEG (iEEG) from the Freiburg database and scalp EEG (sEEG) from the MIT Physionet database. The Freiburg database contains 80 seizures among 18 patients in 427 hours of recordings. The MIT EEG database contains 78 seizures from 17 children in 647 hours of recordings. It is shown that the proposed algorithm can achieve a sensitivity of 100{\%} and an average false positive rate (FPR) of 0.0324 per hour for the iEEG (Freiburg) database and a sensitivity of 98.68{\%} and an average FPR of 0.0465 per hour for the sEEG (MIT) database. These results are obtained with leave-one-out cross-validation where the seizure being tested is always left out from the training set. The proposed algorithm also has a low complexity as the spectral powers can be computed using FFT. The area and power consumption of the proposed linear SVM are 2 to 3 orders of magnitude less than a radial basis function kernel SVM (RBF-SVM) classifier. Furthermore, the total energy consumption of a system using linear SVM is reduced by 8{\%} to 23{\%} compared to system using RBF-SVM.",
keywords = "Branch and bound, Linear separability, Low-complexity architecture, Power spectral density, Ratio of spectral power, Seizure prediction",
author = "Zisheng Zhang and Parhi, {Keshab K}",
year = "2016",
month = "6",
day = "1",
doi = "10.1109/TBCAS.2015.2477264",
language = "English (US)",
volume = "10",
pages = "693--706",
journal = "IEEE Transactions on Biomedical Circuits and Systems",
issn = "1932-4545",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Low-Complexity Seizure Prediction From iEEG/sEEG Using Spectral Power and Ratios of Spectral Power

AU - Zhang, Zisheng

AU - Parhi, Keshab K

PY - 2016/6/1

Y1 - 2016/6/1

N2 - Prediction of seizures is a difficult problem as the EEG patterns are not wide-sense stationary and change from seizure to seizure, electrode to electrode, and from patient to patient. This paper presents a novel patient-specific algorithm for prediction of seizures in epileptic patients from either one or two single-channel or bipolar channel intra-cranial or scalp electroencephalogram (EEG) recordings with low hardware complexity. Spectral power features are extracted and their ratios are computed. For each channel, a total of 44 features including 8 absolute spectral powers, 8 relative spectral powers and 28 spectral power ratios are extracted every two seconds using a 4-second window with a 50% overlap. These features are then ranked and selected in a patient-specific manner using a two-step feature selection. Selected features are further processed by a second-order Kalman filter and then input to a linear support vector machine (SVM) classifier. The algorithm is tested on the intra-cranial EEG (iEEG) from the Freiburg database and scalp EEG (sEEG) from the MIT Physionet database. The Freiburg database contains 80 seizures among 18 patients in 427 hours of recordings. The MIT EEG database contains 78 seizures from 17 children in 647 hours of recordings. It is shown that the proposed algorithm can achieve a sensitivity of 100% and an average false positive rate (FPR) of 0.0324 per hour for the iEEG (Freiburg) database and a sensitivity of 98.68% and an average FPR of 0.0465 per hour for the sEEG (MIT) database. These results are obtained with leave-one-out cross-validation where the seizure being tested is always left out from the training set. The proposed algorithm also has a low complexity as the spectral powers can be computed using FFT. The area and power consumption of the proposed linear SVM are 2 to 3 orders of magnitude less than a radial basis function kernel SVM (RBF-SVM) classifier. Furthermore, the total energy consumption of a system using linear SVM is reduced by 8% to 23% compared to system using RBF-SVM.

AB - Prediction of seizures is a difficult problem as the EEG patterns are not wide-sense stationary and change from seizure to seizure, electrode to electrode, and from patient to patient. This paper presents a novel patient-specific algorithm for prediction of seizures in epileptic patients from either one or two single-channel or bipolar channel intra-cranial or scalp electroencephalogram (EEG) recordings with low hardware complexity. Spectral power features are extracted and their ratios are computed. For each channel, a total of 44 features including 8 absolute spectral powers, 8 relative spectral powers and 28 spectral power ratios are extracted every two seconds using a 4-second window with a 50% overlap. These features are then ranked and selected in a patient-specific manner using a two-step feature selection. Selected features are further processed by a second-order Kalman filter and then input to a linear support vector machine (SVM) classifier. The algorithm is tested on the intra-cranial EEG (iEEG) from the Freiburg database and scalp EEG (sEEG) from the MIT Physionet database. The Freiburg database contains 80 seizures among 18 patients in 427 hours of recordings. The MIT EEG database contains 78 seizures from 17 children in 647 hours of recordings. It is shown that the proposed algorithm can achieve a sensitivity of 100% and an average false positive rate (FPR) of 0.0324 per hour for the iEEG (Freiburg) database and a sensitivity of 98.68% and an average FPR of 0.0465 per hour for the sEEG (MIT) database. These results are obtained with leave-one-out cross-validation where the seizure being tested is always left out from the training set. The proposed algorithm also has a low complexity as the spectral powers can be computed using FFT. The area and power consumption of the proposed linear SVM are 2 to 3 orders of magnitude less than a radial basis function kernel SVM (RBF-SVM) classifier. Furthermore, the total energy consumption of a system using linear SVM is reduced by 8% to 23% compared to system using RBF-SVM.

KW - Branch and bound

KW - Linear separability

KW - Low-complexity architecture

KW - Power spectral density

KW - Ratio of spectral power

KW - Seizure prediction

UR - http://www.scopus.com/inward/record.url?scp=84945915377&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945915377&partnerID=8YFLogxK

U2 - 10.1109/TBCAS.2015.2477264

DO - 10.1109/TBCAS.2015.2477264

M3 - Article

VL - 10

SP - 693

EP - 706

JO - IEEE Transactions on Biomedical Circuits and Systems

JF - IEEE Transactions on Biomedical Circuits and Systems

SN - 1932-4545

IS - 3

M1 - 7307237

ER -