A Wavelet-Statistical Features Approach for Nonconvulsive Seizure Detection

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

The detection of nonconvulsive seizures (NCSz) is a challenge because of the lack of physical symptoms, which may delay the diagnosis of the disease. Many researchers have reported automatic detection of seizures. However, few investigators have concentrated on detection of NCSz. This article proposes a method for reliable detection of NCSz. The electroencephalography (EEG) signal is usually contaminated by various nonstationary noises. Signal denoising is an important preprocessing step in the analysis of such signals. In this study, a new wavelet-based denoising approach using cubical thresholding has been proposed to reduce noise from the EEG signal prior to analysis. Three statistical features were extracted from wavelet frequency bands, encompassing the frequency range of 0 to 8, 8 to 16, 16 to 32, and 0 to 32 Hz. Extracted features were used to train linear classifier to discriminate between normal and seizure EEGs. The performance of the method was tested on a database of nine patients with 24 seizures in 80 hours of EEG recording. All the seizures were successfully detected, and false positive rate was found to be 0.7 per hour.

Related collections

Most cited references 43

Record: found
Abstract: found
Article: not found

Application of non-linear and wavelet based features for the automated identification of epileptic EEG signals.

U. Rajendra Acharya, Jasjit S. Suri, Ratna Yanti … (2012)

Epilepsy, a neurological disorder, is characterized by the recurrence of seizures. Electroencephalogram (EEG) signals, which are used to detect the presence of seizures, are non-linear and dynamic in nature. Visual inspection of the EEG signals for detection of normal, interictal, and ictal activities is a strenuous and time-consuming task due to the huge volumes of EEG segments that have to be studied. Therefore, non-linear methods are being widely used to study EEG signals for the automatic monitoring of epileptic activities. The aim of our work is to develop a Computer Aided Diagnostic (CAD) technique with minimal pre-processing steps that can classify all the three classes of EEG segments, namely normal, interictal, and ictal, using a small number of highly discriminating non-linear features in simple classifiers. To evaluate the technique, segments of normal, interictal, and ictal EEG segments (100 segments in each class) were used. Non-linear features based on the Higher Order Spectra (HOS), two entropies, namely the Approximation Entropy (ApEn) and the Sample Entropy (SampEn), and Fractal Dimension and Hurst Exponent were extracted from the segments. Significant features were selected using the ANOVA test. After evaluating the performance of six classifiers (Decision Tree, Fuzzy Sugeno Classifier, Gaussian Mixture Model, K-Nearest Neighbor, Support Vector Machine, and Radial Basis Probabilistic Neural Network) using a combination of the selected features, we found that using a set of all the selected six features in the Fuzzy classifier resulted in 99.7% classification accuracy. We have demonstrated that our technique is capable of achieving high accuracy using a small number of features that accurately capture the subtle differences in the three different types of EEG (normal, interictal, and ictal) segments. The technique can be easily written as a software application and used by medical professionals without any extensive training and cost. Such software can evolve into an automatic seizure monitoring application in the near future and can aid the doctors in providing better and timely care for the patients suffering from epilepsy.

0 comments Cited 69 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Fractality analysis of frontal brain in major depressive disorder.

Mehran Ahmadlou, Hojjat Adeli, Amir Adeli (2012)

EEGs of the frontal brain of patients diagnosed with major depressive disorder (MDD) have been investigated in recent years using linear methods but not based on nonlinear methods. This paper presents an investigation of the frontal brain of MDD patients using the wavelet-chaos methodology and Katz's and Higuchi's fractal dimensions (KFD and HFD) as measures of nonlinearity and complexity. EEGs of the frontal brain of healthy adults and MDD patients are decomposed into 5 EEG sub-bands employing a wavelet filter bank, and the FDs of the band-limited as well as those of their 5 sub-bands are computed. Then, using the ANOVA statistical test, HFDs and KFDs of the left and right frontal lobes in EEG full-band and sub-bands of MDD and healthy groups are compared in order to discover the FDs showing the most meaningful differences between the two groups. Finally, the discovered FDs are used as input to a classifier, enhanced probabilistic neural network (EPNN), to discriminate the MDD from healthy EEGs. The results of HFD show higher complexity of left, right and overall frontal lobes of the brain of MDD compared with non-MDD in beta and gamma sub-bands. Moreover, it is observed that HFD of the beta band is more discriminative than HFD of the gamma band for discriminating MDD and non-MDD participants, while the KFD did not show any meaningful difference. A high accuracy of 91.3% is achieved for classification of MDD and non-MDD EEGs based on HFDs of left, right, and overall frontal brain beta sub-band. The findings of this research, however, should be considered tentative because of limited data available to the authors. Copyright © 2012 Elsevier B.V. All rights reserved.

0 comments Cited 63 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Persistent nonconvulsive status epilepticus after the control of convulsive status epilepticus.

D Ko, A Towne, G A DeLorenzo … (1998)

Convulsive status epilepticus (CSE) is a major medical and neurological emergency that is associated with significant morbidity and mortality. Despite this high morbidity and mortality, most acute care facilities in the United States cannot evaluate patients with EEG monitoring during or immediately after SE. The present study was initiated to determine whether control of CSE by standard treatment protocols was sufficient to terminate electrographic seizures. One hundred sixty-four prospective patients were evaluated at the Medical College of Virginia/VCU Status Epilepticus Program. Continuous EEG monitoring was performed for a minimum of 24 h after clinical control of CSE. SE and seizure types were defined as described previously. A standardized data form entry system was compiled for each patient and used to evaluate the data collected. After CSE was controlled, continuous EEG monitoring demonstrated that 52% of the patients had no after-SE ictal discharges (ASIDS) and manifested EEG patterns of generalized slowing, attenuation, periodic lateralizing epileptiform discharges (PLEDS), focal slowing, and/or burst suppression. The remaining 48% demonstrated persistent electrographic seizures. More than 14% of the patients manifested nonconvulsive SE (NCSE) predominantly of the complex partial NCSE seizure (CPS) type (2). These patients were comatose and showed no overt clinical signs of convulsive activity. Clinical detection of NCSE in these patients would not have been possible with routine neurological evaluations without use of EEG monitoring. The clinical presentation, mortality, morbidity, and demographic information on this population are reported. Our results demonstrate that EEG monitoring after treatment of CSE is essential to recognition of persistent electrographic seizures and NCSE unresponsive to routine therapeutic management of CSE. These findings also suggest that EEG monitoring immediately after control of CSE is an important diagnostic test to guide treatment plans and to evaluate prognosis in the management of SE.