Detection of spikes with artificial neural networks using raw EEG

Ozcan Ozdamar, T. Kalayci

Research output: Contribution to journalArticle

51 Citations (Scopus)

Abstract

Artificial neural networks (ANN) using raw electroencephalogram (EEG) data were developed and tested off-line to detect transient epileptiform discharges (spike and spike/wave) and EMG activity in an ongoing EEG. In the present study, a feedforward ANN with a variable number of input and hidden layer units and two output units was used to optimize the detection system. The ANN system was trained and tested with the backpropagation algorithm using a large data set of exemplars. The effects of different EEG time windows and the number of hidden layer neurons were examined using rigorous statistical tests for optimum detection sensitivity and selectivity. The best ANN configuration occurred with an input time window of 150 msec (30 input units) and six hidden layer neurons. This input interval contained information on the wave component of the epileptiform discharge which improved detection. Two-dimensional receiver operating curves were developed to define the optimum threshold parameters for best detection. Comparison with previous networks using raw EEG showed improvement in both sensitivity and selectivity. This study showed that raw EEG can be successfully used to train ANNs to detect epileptogenic discharges with a high success rate without resorting to experimenter-selected parameters which may limit the efficiency of the system.

Original languageEnglish
Pages (from-to)122-142
Number of pages21
JournalComputers and Biomedical Research
Volume31
Issue number2
DOIs
StatePublished - Apr 1 1998

Fingerprint

Electroencephalography
Neural networks
Neurons
Backpropagation algorithms
Statistical tests

Keywords

  • Artificial neural networks
  • Automated spike detection

ASJC Scopus subject areas

  • Medicine (miscellaneous)

Cite this

Detection of spikes with artificial neural networks using raw EEG. / Ozdamar, Ozcan; Kalayci, T.

In: Computers and Biomedical Research, Vol. 31, No. 2, 01.04.1998, p. 122-142.

Research output: Contribution to journalArticle

@article{0423eedf3d1f4559a82e81e7a195b77f,
title = "Detection of spikes with artificial neural networks using raw EEG",
abstract = "Artificial neural networks (ANN) using raw electroencephalogram (EEG) data were developed and tested off-line to detect transient epileptiform discharges (spike and spike/wave) and EMG activity in an ongoing EEG. In the present study, a feedforward ANN with a variable number of input and hidden layer units and two output units was used to optimize the detection system. The ANN system was trained and tested with the backpropagation algorithm using a large data set of exemplars. The effects of different EEG time windows and the number of hidden layer neurons were examined using rigorous statistical tests for optimum detection sensitivity and selectivity. The best ANN configuration occurred with an input time window of 150 msec (30 input units) and six hidden layer neurons. This input interval contained information on the wave component of the epileptiform discharge which improved detection. Two-dimensional receiver operating curves were developed to define the optimum threshold parameters for best detection. Comparison with previous networks using raw EEG showed improvement in both sensitivity and selectivity. This study showed that raw EEG can be successfully used to train ANNs to detect epileptogenic discharges with a high success rate without resorting to experimenter-selected parameters which may limit the efficiency of the system.",
keywords = "Artificial neural networks, Automated spike detection",
author = "Ozcan Ozdamar and T. Kalayci",
year = "1998",
month = "4",
day = "1",
doi = "10.1006/cbmr.1998.1475",
language = "English",
volume = "31",
pages = "122--142",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Detection of spikes with artificial neural networks using raw EEG

AU - Ozdamar, Ozcan

AU - Kalayci, T.

PY - 1998/4/1

Y1 - 1998/4/1

N2 - Artificial neural networks (ANN) using raw electroencephalogram (EEG) data were developed and tested off-line to detect transient epileptiform discharges (spike and spike/wave) and EMG activity in an ongoing EEG. In the present study, a feedforward ANN with a variable number of input and hidden layer units and two output units was used to optimize the detection system. The ANN system was trained and tested with the backpropagation algorithm using a large data set of exemplars. The effects of different EEG time windows and the number of hidden layer neurons were examined using rigorous statistical tests for optimum detection sensitivity and selectivity. The best ANN configuration occurred with an input time window of 150 msec (30 input units) and six hidden layer neurons. This input interval contained information on the wave component of the epileptiform discharge which improved detection. Two-dimensional receiver operating curves were developed to define the optimum threshold parameters for best detection. Comparison with previous networks using raw EEG showed improvement in both sensitivity and selectivity. This study showed that raw EEG can be successfully used to train ANNs to detect epileptogenic discharges with a high success rate without resorting to experimenter-selected parameters which may limit the efficiency of the system.

AB - Artificial neural networks (ANN) using raw electroencephalogram (EEG) data were developed and tested off-line to detect transient epileptiform discharges (spike and spike/wave) and EMG activity in an ongoing EEG. In the present study, a feedforward ANN with a variable number of input and hidden layer units and two output units was used to optimize the detection system. The ANN system was trained and tested with the backpropagation algorithm using a large data set of exemplars. The effects of different EEG time windows and the number of hidden layer neurons were examined using rigorous statistical tests for optimum detection sensitivity and selectivity. The best ANN configuration occurred with an input time window of 150 msec (30 input units) and six hidden layer neurons. This input interval contained information on the wave component of the epileptiform discharge which improved detection. Two-dimensional receiver operating curves were developed to define the optimum threshold parameters for best detection. Comparison with previous networks using raw EEG showed improvement in both sensitivity and selectivity. This study showed that raw EEG can be successfully used to train ANNs to detect epileptogenic discharges with a high success rate without resorting to experimenter-selected parameters which may limit the efficiency of the system.

KW - Artificial neural networks

KW - Automated spike detection

UR - http://www.scopus.com/inward/record.url?scp=0031959244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031959244&partnerID=8YFLogxK

U2 - 10.1006/cbmr.1998.1475

DO - 10.1006/cbmr.1998.1475

M3 - Article

C2 - 9570903

AN - SCOPUS:0031959244

VL - 31

SP - 122

EP - 142

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

IS - 2

ER -