Automatic detection of epileptic EEG signals using higher order cumulant features

The unpredictability of the occurrence of epileptic seizures makes it difficult to detect and treat this condition effectively. An automatic system that characterizes epileptic activities in EEG signals would allow patients or the people near them to take appropriate precautions, would allow clinicians to better manage the condition, and could provide more insight into these phenomena thereby revealing important clinical information. Various methods have been proposed to detect epileptic activity in EEG recordings. Because of the nonlinear and dynamic nature of EEG signals, the use of nonlinear Higher Order Spectra (HOS) features is a seemingly promising approach. This paper presents the methodology employed to extract HOS features (specifically, cumulants) from normal, interictal, and epileptic EEG segments and to use significant features in classifiers for the detection of these three classes. In this work, 300 sets of EEG data belonging to the three classes were used for feature extraction and classifier development and evaluation. The results show that the HOS based measures have unique ranges for the different classes with high confidence level (p-value < 0.0001). On evaluating several classifiers with the significant features, it was observed that the Support Vector Machine (SVM) presented a high detection accuracy of 98.5% thereby establishing the possibility of effective EEG segment classification using the proposed technique.     

Segmentation of EEG during sleep using time-varying autoregressive modeling

Time-varying AR modeling is applied to sleep EEG signal, in order to perform parameter estimation and detect changes in the signal characteristics (segmentation). Several types of basis functions have been analyzed to determine how closely they can approximate parameter changes characteristics of the EEG signal. The TV-AR model was applied to a large number of simulated signal segments, in order to examine the behaviour of the estimation under various conditions such as variations in the EEG parameters and in the location of segment boundaries, and different orders of the basis functions. The set of functions that is the basis for the Discrete Cosine Transform (DCT), and the Walsh functions were found to be the most efficient in the estimation of the model parameters. A segmentation algorithm based on an “Identification function” calculated from the estimated model parameters is suggested.     

Automated diagnosis of epileptic EEG using entropies

Epilepsy is a neurological disorder characterized by the presence of recurring seizures. Like many other neurological disorders, epilepsy can be assessed by the electroencephalogram (EEG). The EEG signal is highly non-linear and non-stationary, and hence, it is difficult to characterize and interpret it. However, it is a well-established clinical technique with low associated costs. In this work, we propose a methodology for the automatic detection of normal, pre-ictal, and ictal conditions from recorded EEG signals. Four entropy features namely Approximate Entropy (ApEn), Sample Entropy (SampEn), Phase Entropy 1 (S1), and Phase Entropy 2 (S2) were extracted from the collected EEG signals. These features were fed to seven different classifiers: Fuzzy Sugeno Classifier (FSC), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Probabilistic Neural Network (PNN), Decision Tree (DT), Gaussian Mixture Model (GMM), and Naive Bayes Classifier (NBC). Our results show that the Fuzzy classifier was able to differentiate the three classes with a high accuracy of 98.1%. Overall, compared to previous techniques, our proposed strategy is more suitable for diagnosis of epilepsy with higher accuracy.     

Nonlinear analysis of EEG signals at different mental states

Background  

The EEG (Electroencephalogram) is a representative signal containing information about the condition of the brain. The shape of the wave may contain useful information about the state of the brain. However, the human observer can not directly monitor these subtle details. Besides, since bio-signals are highly subjective, the symptoms may appear at random in the time scale. Therefore, the EEG signal parameters, extracted and analyzed using computers, are highly useful in diagnostics. This work discusses the effect on the EEG signal due to music and reflexological stimulation.     

Comparative study of nonlinear properties of EEG signals of normal persons and epileptic patients

Background  

Investigation of the functioning of the brain in living systems has been a major effort amongst scientists and medical practitioners. Amongst the various disorder of the brain, epilepsy has drawn the most attention because this disorder can affect the quality of life of a person. In this paper we have reinvestigated the EEGs for normal and epileptic patients using surrogate analysis, probability distribution function and Hurst exponent.     

Application of recurrence quantification analysis for the automated identification of epileptic EEG signals

Epilepsy is a common neurological disorder that is characterized by the recurrence of seizures. Electroencephalogram (EEG) signals are widely used to diagnose seizures. Because of the non-linear and dynamic nature of the EEG signals, it is difficult to effectively decipher the subtle changes in these signals by visual inspection and by using linear techniques. Therefore, non-linear methods are being researched to analyze the EEG signals. In this work, we use the recorded EEG signals in Recurrence Plots (RP), and extract Recurrence Quantification Analysis (RQA) parameters from the RP in order to classify the EEG signals into normal, ictal, and interictal classes. Recurrence Plot (RP) is a graph that shows all the times at which a state of the dynamical system recurs. Studies have reported significantly different RQA parameters for the three classes. However, more studies are needed to develop classifiers that use these promising features and present good classification accuracy in differentiating the three types of EEG segments. Therefore, in this work, we have used ten RQA parameters to quantify the important features in the EEG signals.These features were fed to seven different classifiers: Support vector machine (SVM), Gaussian Mixture Model (GMM), Fuzzy Sugeno Classifier, K-Nearest Neighbor (KNN), Naive Bayes Classifier (NBC), Decision Tree (DT), and Radial Basis Probabilistic Neural Network (RBPNN). Our results show that the SVM classifier was able to identify the EEG class with an average efficiency of 95.6%, sensitivity and specificity of 98.9% and 97.8%, respectively.     

Application of a dissimilarity index of EEG and its sub-bands on prediction of induced epileptic seizures from rat's EEG signals

ObjectiveEpileptic seizures are defined as manifest of excessive and hyper-synchronous activity of neurons in the cerebral cortex that cause frequent malfunction of the human central nervous system. Therefore, finding precursors and predictors of epileptic seizure is of utmost clinical relevance to reduce the epileptic seizure induced nervous system malfunction consequences. Researchers for this purpose may even guide us to a deep understanding of the seizure generating mechanisms. The goal of this paper is to predict epileptic seizures in epileptic rats.MethodsSeizures were induced in rats using pentylenetetrazole (PTZ) model. EEG signals in interictal, preictal, ictal and postictal periods were then recorded and analyzed to predict epileptic seizures. Epileptic seizures were predicted by calculating an index in consecutive windows of EEG signal and comparing the index with a threshold. In this work, a newly proposed dissimilarity index called Bhattacharyya Based Dissimilarity Index (BBDI), dynamical similarity index and fuzzy similarity index were investigated.ResultsBBDI, dynamical similarity index and fuzzy similarity index were examined on case and control groups and compared to each other. The results show that BBDI outperforms dynamical and fuzzy similarity indices. In order to improve the results, EEG sub-bands were also analyzed. The best result achieved when the proposed dissimilarity index was applied on Delta sub-band that predicts epileptic seizures in all rats with a mean of 299.5 s.ConclusionThe dissimilarity of neural network activity between reference window and present window of EEG signal has a significant increase prior to an epileptic seizure and the proposed dissimilarity index (BBDI) can reveal this variation to predict epileptic seizures. In addition, analyzing EEG sub-bands results in more accurate information about constituent neuronal activities underlying the EEG since certain changes in EEG signal may be amplified when each sub-band is analyzed separately.SignificanceThis paper presents application of a dissimilarity index (BBDI) on EEG signals and its sub-bands to predict PTZ-induced epileptic seizures in rats. Based on the results of this work, BBDI will predict epileptic seizures more accurately and more reliably compared to current indices that increases epileptic patient comfort and improves patient outcomes.     

Classification of mental tasks from EEG signals using extreme learning machine

In this paper, a recently developed machine learning algorithm referred to as Extreme Learning Machine (ELM) is used to classify five mental tasks from different subjects using electroencephalogram (EEG) signals available from a well-known database. Performance of ELM is compared in terms of training time and classification accuracy with a Backpropagation Neural Network (BPNN) classifier and also Support Vector Machines (SVMs). For SVMs, the comparisons have been made for both 1-against-1 and 1-against-all methods. Results show that ELM needs an order of magnitude less training time compared with SVMs and two orders of magnitude less compared with BPNN. The classification accuracy of ELM is similar to that of SVMs and BPNN. The study showed that smoothing of the classifiers' outputs can significantly improve their classification accuracies.     

The modeling of rat EEG signals in absence epilepsy in the analysis of brain connectivity

Simple models that describe some features of the electrical brain activity in rats with genetic absence epilepsy recorded before and after an epileptic seizure have been proposed in this study. These models can help to analyze the efficiency of the Granger causality analysis of the directional connectivity determination. The comparison of the results of the experimental and modeled signal analysis, on one hand, reveals a number of artifacts of this method, and on the other hand, proves its effectiveness in the research on absence epilepsy mechanisms.     

Identifying an increased risk of epileptic seizures using a multi-feature EEG–ECG classification

Epilepsy, a neurological disorder in which patients suffer from recurring seizures, affects approximately 1% of the world population. In spite of available drug and surgical treatment options, more than 25% of individuals with epilepsy have seizures that are uncontrollable. For these patients with intractable epilepsy, the unpredictability of seizure occurrence underlies an enhanced risk of sudden unexpected death or morbidity. A system that could warn the patient of the impending event or trigger an antiepileptic device would dramatically increase the quality of life for those patients. Here, we proposed a patient-specific algorithm for possible seizure warning using machine learning classification of 34 algorithmic features derived from EEG–ECG recordings. We evaluated our algorithm on unselected and continuous recordings of 12 patients (total of 108 seizures and 3178-h). Good out-of-sample performances were observed around 25% of the patients with an average preictal period around 30 min and independently of the EEG type (scalp or intracranial). Inspection of the most discriminative EEG–ECG features revealed that good classification rates reflected specific physiological precursors, particularly related to certain stages of sleep. From these observations, we conclude that our algorithmic strategy enables a quantitative way to identify “pro-ictal” states with a high risk of seizure generation.     

Travelling waves and EEG patterns during epileptic seizure: analysis with an integrate-and-fire neural network

Epilepsy is characterized by paradoxical patterns of neural activity. They may cause different types of electroencephalogram (EEG), which dynamically change in shape and frequency content during the temporal evolution of seizure. It is generally assumed that these epileptic patterns may originate in a network of strongly interconnected neurons, when excitation dominates over inhibition. The aim of this work is to use a neural network composed of 50 x 50 integrate-and-fire neurons to analyse which parameter alterations, at the level of synapse topology, may induce network instability and epileptic-like discharges, and to study the corresponding spatio-temporal characteristics of electrical activity in the network. We assume that a small group of central neurons is stimulated by a depolarizing current (epileptic focus) and that neurons are connected via a Mexican-hat topology of synapses. A signal representative of cortical EEG (ECoG) is simulated by summing the membrane potential changes of all neurons. A sensitivity analysis on the parameters describing the synapse topology shows that an increase in the strength and in spatial extension of excitatory vs. inhibitory synapses may cause the occurrence of travelling waves, which propagate along the network. These propagating waves may cause EEG patterns with different shape and frequency, depending on the particular parameter set used during the simulations. The resulting model EEG signals include irregular rhythms with large amplitude and a wide frequency content, low-amplitude high-frequency rapid discharges, isolated or repeated bursts, and low-frequency quasi-sinusoidal patterns. A slow progressive temporal variation in a single parameter may cause the transition from one pattern to another, thus generating a highly non-stationary signal which resembles that observed during ECoG measurements. These results may help to elucidate the mechanisms at the basis of some epileptic discharges, and to relate rapid changes in EEG patterns with the underlying alterations at the network level.     

The prediction of EEG signals using a feedback-structured adaptive rational function filter

 In this article, we present a feedback-structured adaptive rational function filter based on a recursive modified Gram-Schmidt algorithm and apply it to the prediction of an EEG signal that has nonlinear and nonstationary characteristics. For the evaluation of the prediction performance, the proposed filter is compared with other methods, where a single-step prediction and a multi-step prediction are considered for a short-term prediction, and the prediction performance is assessed in normalized mean square error. The experimental results show that the proposed filter shows better performance than other methods considered for the short-term prediction of EEG signals. Received: 22 September 1998 / Accepted in revised form: 29 February 2000     

The methods of automatic analysis of epileptic EEG

The methods of automatic evaluation of epileptic EEG are reviewed. The aims of the computer analysis of seizure activity and different approaches to this problem are presented.     

Analysis of long range dependence in the EEG signals of Alzheimer patients

Alzheimer’s disease (AD), a cognitive disability is analysed using a long range dependence parameter, hurst exponent (HE), calculated based on the time domain analysis of the measured electrical activity of brain. The electroencephalogram (EEG) signals of controls and mild cognitive impairment (MCI)-AD patients are evaluated under normal resting and mental arithmetic conditions. Simultaneous low pass filtering and total variation denoising algorithm is employed for preprocessing. Larger values of HE observed in the right hemisphere of the brain for AD patients indicated a decrease in irregularity of the EEG signal under cognitive task conditions. Correlations between HE and the neuropsychological indices are analysed using bivariate correlation analysis. The observed reduction in the values of Auto mutual information and cross mutual information in the local antero-frontal and distant regions in the brain hemisphere indicates the loss of information transmission in MCI-AD patients.     

Analysis of yeast diversity during spontaneous and induced alcoholic fermentations

The diversity of yeast species and strains was monitored by physiological tests and a simplified method of karyotyping of yeast chromosomes. During the first phase of investigated alcoholic fermentations, the yeast species Metschnikowia pulcherrima and Hanseniaspora uvarum were predominant, irrespective of the origin of the grape must. At the beginning of fermentation H. uvarum was even present in the case of induced fermentations with dried yeast. Middle and end phase of the alcoholic fermentation were clearly dominated by the yeast species Saccharomyces cerevisiae . In the case of spontaneous fermentations, several different strains of S. cerevisiae were present and competed with each other, whereas in induced fermentations only the inoculated strain of S. cerevisiae was observed. A competition of strains of S. cerevisiae also occurred during the fermentation with dried yeast product consisting of two different strains. An effect of H. uvarum on taste and flavour of wines can be postulated according to the frequency of its appearance during the first phase of fermentation. With the method of rapid karyotyping and supplementary physiological tests it was possible to make reliable assertions about the yeast diversity during alcoholic fermentation.     

Incidence of seizures and EEG abnormalities among offspring of epileptic patients

Summary The marriage rate of epileptic patients was 62% in males und 78% in females. Compared with the rates in the general population, the male patients had a 15% lower rate, but there was no difference in females. There were 263 patients with at least one offspring selected for the study. There were 243 sons and 272 daughters (506 total, 1.9 per patient). Distribution by types of seizure was awakening grand mal, absence or myoclonic petit mal in 24%, grand mal with no aura in 21%, grand mal during sleep in 23%, diffuse grand mal in 7%, grand mal with aura in 13%, psychomotor seizure in 9%, and focal seizure in 3%. The probands were composed of 79% idiopathic and 21% symptomatic in pathogenetic classification. An epileptic EEG abnormality was demonstrated in 22% of male and 44% of female probands.The incidence of seizures among offspring was 2.4% (4.2% age-corrected) in a narrow sense (epilepsy) and 9.1% in a broad sense including febrile convulsions. The latter morbidity was 11.0% for the idiopathic and 3.2% for the symptomatic group; 11.0% for female and 6.9% for male probands; 10.2% for sons and 8.1% for daughters. The figure was higher for the probands with the age range at onset of seizure of 0–4 years (20.6%) and 20–29 years (12.6%) than for those with other age ranges; higher for those with awakening grand mal, absence, myoclonic petit mal, or grand mal with no aura than for those with other types of seizure; and higher for those with family history of epilepsy than those without it.Possible correlation of types of seizure between probands and offspring was demonstrated. Thirty-seven percent of offspring exhibited epileptic EEG abnormalities, and the ratio of epileptic EEG abnormalities to clinical manifestation is about 4:1.Possible existence of familial aggregation of EEG abnormalities and of two kinds of families with large or small epileptic predisposition was indicated.The importance of the role of hereditary and environmental factors in epileptic pathogenesis is proved, and the results of an investigation of congenital malformation among offspring of epileptic mothers are presented. These results were considered to be useful for genetic counseling of epileptic patients.