Kernel machines for epilepsy diagnosis via EEG signal classification: A comparative study

Objective: We carry out a systematic assessment on a suite of kernel-based learning machines while coping with the task of epilepsy diagnosis through automatic electroencephalogram (EEG) signal classification. Methods and materials: The kernel machines investigated include the standard support vector machine (SVM), the least squares SVM, the Lagrangian SVM, the smooth SVM, the proximal SVM, and the relevance vector machine. An extensive series of experiments was conducted on publicly available data, whose clinical EEG recordings were obtained from five normal subjects and five epileptic patients. The performance levels delivered by the different kernel machines are contrasted in terms of the criteria of predictive accuracy, sensitivity to the kernel function/parameter value, and sensitivity to the type of features extracted from the signal. For this purpose, 26 values for the kernel parameter (radius) of two well-known kernel functions (namely. Gaussian and exponential radial basis functions) were considered as well as 21 types of features extracted from the EEG signal, including statistical values derived from the discrete wavelet transform, Lyapunov exponents, and combinations thereof. Results: We first quantitatively assess the impact of the choice of the wavelet basis on the quality of the features extracted. Four wavelet basis functions were considered in this study. Then, we provide the average accuracy (i.e., cross-validation error) values delivered by 252 kernel machine configurations; in particular, 40%/35% of the best-calibrated models of the standard and least squares SVMs reached 100% accuracy rate for the two kernel functions considered. Moreover, we show the sensitivity profiles exhibited by a large sample of the configurations whereby one can visually inspect their levels of sensitiveness to the type of feature and to the kernel function/parameter value. Conclusions: Overall, the results evidence that all kernel machines are competitive in terms of accuracy, with the standard and least squares SVMs prevailing more consistently. Moreover, the choice of the kernel function and parameter value as well as the choice of the feature extractor are critical decisions to be taken, albeit the choice of the wavelet family seems not to be so relevant. Also, the statistical values calculated over the Lyapunov exponents were good sources of signal representation, but not as informative as their wavelet counterparts. Finally, a typical sensitivity profile has emerged among all types of machines, involving some regions of stability separated by zones of sharp variation, with some kernel parameter values clearly associated with better accuracy rates (zones of optimality). (C) 2011 Elsevier B.V. All rights reserved.

A Nonstationary Model of Newborn EEG

The detection of seizure in the newborn is a critical aspect of neurological research. Current automatic detection techniques are difficult to assess due to the problems associated with acquiring and labelling newborn electroencephalogram (EEG) data. A realistic model for newborn EEG would allow confident development, assessment and comparison of these detection techniques. This paper presents a model for newborn EEG that accounts for its self-similar and non-stationary nature. The model consists of background and seizure sub-models. The newborn EEG background model is based on the short-time power spectrum with a time-varying power law. The relationship between the fractal dimension and the power law of a power spectrum is utilized for accurate estimation of the short-time power law exponent. The newborn EEG seizure model is based on a well-known time-frequency signal model. This model addresses all significant time-frequency characteristics of newborn EEG seizure which include; multiple components or harmonics, piecewise linear instantaneous frequency laws and harmonic amplitude modulation. Estimates of the parameters of both models are shown to be random and are modelled using the data from a total of 500 background epochs and 204 seizure epochs. The newborn EEG background and seizure models are validated against real newborn EEG data using the correlation coefficient. The results show that the output of the proposed models has a higher correlation with real newborn EEG than currently accepted models (a 10% and 38% improvement for background and seizure models, respectively).

EEG-based Brain-Computer Interfaces: An Overview of Basic Concepts and Clinical Applications in Neurorehabilitation

Some patients are no longer able to communicate effectively or even interact with the outside world in ways that most of us take for granted. In the most severe cases, tetraplegic or post-stroke patients are literally `locked in` their bodies, unable to exert any motor control after, for example, a spinal cord injury or a brainstem stroke, requiring alternative methods of communication and control. But we suggest that, in the near future, their brains may offer them a way out. Non-invasive electroencephalogram (EEG)-based brain-computer interfaces (BCD can be characterized by the technique used to measure brain activity and by the way that different brain signals are translated into commands that control an effector (e.g., controlling a computer cursor for word processing and accessing the internet). This review focuses on the basic concepts of EEG-based BC!, the main advances in communication, motor control restoration and the down-regulation of cortical activity, and the mirror neuron system (MNS) in the context of BCI. The latter appears to be relevant for clinical applications in the coming years, particularly for severely limited patients. Hypothetically, MNS could provide a robust way to map neural activity to behavior, representing the high-level information about goals and intentions of these patients. Non-invasive EEG-based BCIs allow brain-derived communication in patients with amyotrophic lateral sclerosis and motor control restoration in patients after spinal cord injury and stroke. Epilepsy and attention deficit and hyperactive disorder patients were able to down-regulate their cortical activity. Given the rapid progression of EEG-based BCI research over the last few years and the swift ascent of computer processing speeds and signal analysis techniques, we suggest that emerging ideas (e.g., MNS in the context of BC!) related to clinical neuro-rehabilitation of severely limited patients will generate viable clinical applications in the near future.

Preprocessing and time-frequency analysis of newborn EEG seizures

Neurological disease or dysfunction in newborn infants is often first manifested by seizures. Prolonged seizures can result in impaired neurodevelopment or even death. In adults, the clinical signs of seizures are well defined and easily recognized. In newborns, however, the clinical signs are subtle and may be absent or easily missed without constant close observation. This article describes the use of adaptive signal processing techniques for removing artifacts from newborn electroencephalogram (EEG) signals. Three adaptive algorithms have been designed in the context of EEG signals. This preprocessing is necessary before attempting a fine time-frequency analysis of EEG rhythmical activities, such as electrical seizures, corrupted by high amplitude signals. After an overview of newborn EEG signals, the authors describe the data acquisition set-up. They then introduce the basic physiological concepts related to normal and abnormal newborn EEGs and discuss the three adaptive algorithms for artifact removal. They also present time-frequency representations (TFRs) of seizure signals and discuss the estimation and modeling of the instantaneous frequency related to the main ridge of the TFR.

Effects of Age-Related Cognitive Deficits on EEG Phase Coherence

Body and brain undergo several changes with aging. One of these changes is the loss of neuroplasticity, which leads to the decrease of cognitive abilities. Hence the necessity of stopping or reversing these changes is of utmost importance to contemporary society. In the present work, electroencephalogram (EEG) markers of cognitive decline are sought whilst the subjects perform the Wisconsin Card Sorting Test (WCST). Considering the expected age-related cognitive deficits, WCST was applied to young and elder participants. The results suggest that coherence on theta and alpha EEG rhythms decrease with aging and increase with performance. Additionally, theta phase coherence seems more sensitive to performance, while alpha synchronization appears as a potential ageing marker.

Análise da sonolência na condução rodoviária a partir de sinais EEG

A Sociedade Europeia de Pesquisa do Sono realizou muito recentemente um estudo, onde mostrou que a prevalência média de adormecimento ao volante nos últimos 2 anos foi de 17%. Além disto, tem sido provado por todo o mundo que a sonolência durante a condução é uma das principais causas de acidentes de trânsito. Torna-se assim conveniente, o desenvolvimento de sistemas que analisem a suscetibilidade de um determinado condutor para adormecer no trânsito, bem como de ferramentas que monitorem em tempo real o estado físico e mental do condutor, para alertarem nos momentos críticos. Apesar do estudo do sono se ter iniciado há vários anos, a maioria das investigações focaram-se no ciclo normal do sono, estudando os indivíduos de forma relaxada e de olhos fechados. Só mais recentemente, têm surgido os estudos que se focam nas situações de sonolência em atividade, como _e o caso da condução. Uma grande parte Dos estudos da sonolência em condução têm utilizado a eletroencefalografia (EEG), de forma a perceber se existem alterações nas diferentes bandas de frequência desta, que possam indicar o estado de sonolência do condutor. Além disso, a evolução da sonolência a partir de alterações no piscar dos olhos (que podem ser vistas nos sinais EEG) também tem sido alvo de grande pesquisa, tendo vindo a revelar resultados bastante promissores. Neste contexto e em parceria com a empresa HealthyRoad, esta tese está integrada no projeto HealthyDrive, que visa o desenvolvimento de um sistema de alerta e deteção de sinais de fadiga e sonolência nos condutores de veículos automóveis. A contribuição desta tese no projeto prendeu-se com o estudo da sonolência dos indivíduos em condução a partir de sinais EEG, para desta forma investigar possíveis indicadores dos diferentes níveis desta que possam ser utilizados pela empresa no projeto. Foram recolhidos e analisados 17 sinais EEG de indivíduos em simulação de condução. Além disso foram desenvolvidos dois métodos de análise destes sinais: O primeiro para a deteção e análise dos piscar de olhos a partir de EEG, o segundo para análise do espetro de potência. Ambos os métodos foram utilizados para analisar os sinais recolhidos e investigar que tipo de relação existe entre a sonolência do condutor e as alterações nos piscares dos olhos, bem como as alterações do espetro do EEG. Os resultados mostraram uma correlação entre a duração do piscar de olhos e a sonolência do condutor. Com o aumento da sonolência velicou-se um aumento da duração do piscar, desencadeado principalmente pelo aumento na duração de fecho, que chegou aos 51.2%. Em relação ao espectro de potência, os resultados sugerem que a potência relativa de todas as bandas analisadas fornecem informações relevantes sobre a sonolência do condutor. Além disso, o parâmetro (_+_)/_ demostrou estar relacionado com variações da sonolência, diminuindo com o seu avanço e aumentando significativamente (111%) no instante em que os condutores adormeceram.

Interictal Spike EEG Source Analysis in Hypothalamic Hamartoma Epilepsy

Objective: The epilepsy associated with the hypothalamic hamartomas constitutes a syndrome with peculiar seizures, usually refractory to medical therapy, mild cognitive delay, behavioural problems and multifocal spike activity in the scalp electroencephalogram (EEG). The cortical origin of spikes has been widely assumed but not specifically demonstrated. Methods: We present results of a source analysis of interictal spikes from 4 patients (age 2–25 years) with epilepsy and hypothalamic hamartoma, using EEG scalp recordings (32 electrodes) and realistic boundary element models constructed from volumetric magnetic resonance imaging (MRIs). Multifocal spike activity was the most common finding, distributed mainly over the frontal and temporal lobes. A spike classification based on scalp topography was done and averaging within each class performed to improve the signal to noise ratio. Single moving dipole models were used, as well as the Rap-MUSIC algorithm. Results: All spikes with good signal to noise ratio were best explained by initial deep sources in the neighbourhood of the hamartoma, with late sources located in the cortex. Not a single patient could have his spike activity explained by a combination of cortical sources. Conclusions: Overall, the results demonstrate a consistent origin of spike activity in the subcortical region in the neighbourhood of the hamartoma, with late spread to cortical areas.

Quantification of the TMS-EEG response in epilepsy

Dissertação para obtenção do Grau de Mestre em Engenharia Biomédica

Age effects on EEG correlates of the Wisconsin card sorting test

Body and brain undergo several changes with aging. One of the domains in which these changes are more remarkable relates with cognitive performance. In the present work, electroencephalogram (EEG) markers (power spectral density and spectral coherence) of age-related cognitive decline were sought whilst the subjects performed the Wisconsin Card Sorting Test (WCST). Considering the expected age-related cognitive deficits, WCST was applied to young, mid-age and elderly participants, and the theta and alpha frequency bands were analyzed. From the results herein presented, higher theta and alpha power were found to be associated with a good performance in the WCST of younger subjects. Additionally, higher theta and alpha coherence were also associated with good performance and were shown to decline with age and a decrease in alpha peak frequency seems to be associated with aging. Additionally, inter-hemispheric long-range coherences and parietal theta power were identified as age-independent EEG correlates of cognitive performance. In summary, these data reveals age-dependent as well as age-independent EEG correlates of cognitive performance that contribute to the understanding of brain aging and related cognitive deficits.

Sleep EEG changes after middle cerebral artery infarcts in mice: different effects of striatal and cortical lesions.

STUDY OBJECTIVES: Hemispheric stroke in humans is associated with sleep-wake disturbances and sleep electroencephalogram (EEG) changes. The correlation between these changes and stroke extent remains unclear. In the absence of experimental data, we assessed sleep EEG changes after focal cerebral ischemia of different extensions in mice. DESIGN: Following electrode implantation and baseline sleep-wake EEG recordings, mice were submitted to sham surgery (control group), 30 minutes of intraluminal middle cerebral artery (MCA) occlusion (striatal stroke), or distal MCA electrocoagulation (cortical stroke). One and 12 days after stroke, sleep-wake EEG recordings were repeated. The EEG recorded from the healthy hemisphere was analyzed visually and automatically (fast Fourier analysis) according to established criteria. MEASUREMENTS AND RESULTS: Striatal stroke induced an increase in non-rapid eye movement (NREM) sleep and a reduction of rapid eye movement sleep. These changes were detectable both during the light and the dark phase at day 1 and persisted until day 12 after stroke. Cortical stroke induced a less-marked increase in NREM sleep, which was present only at day 1 and during the dark phase. In cortical stroke, the increase in NREM sleep was associated in the wake EEG power spectra, with an increase in the theta and a reduction in the beta activity. CONCLUSION: Cortical and striatal stroke lead to different sleep-wake EEG changes in mice, which probably reflect variable effects on sleep-promoting and wakefulness-maintaining neuronal networks.

Evaluation of two minimally invasive techniques for electroencephalogram recording in wild or freely behaving animals.

Insight into the function of sleep may be gained by studying animals in the ecological context in which sleep evolved. Until recently, technological constraints prevented electroencephalogram (EEG) studies of animals sleeping in the wild. However, the recent development of a small recorder (Neurologger 2) that animals can carry on their head permitted the first recordings of sleep in nature. To facilitate sleep studies in the field and to improve the welfare of experimental animals, herein, we test the feasibility of using minimally invasive surface and subcutaneous electrodes to record the EEG in barn owls. The EEG and behaviour of four adult owls in captivity and of four chicks in a nest box in the field were recorded. We scored a 24-h period for each adult bird for wakefulness, slow-wave sleep (SWS), and rapid-eye movement (REM) sleep using 4 s epochs. Although the quality and stability of the EEG signals recorded via subcutaneous electrodes were higher when compared to surface electrodes, the owls' state was readily identifiable using either electrode type. On average, the four adult owls spent 13.28 h awake, 9.64 h in SWS, and 1.05 h in REM sleep. We demonstrate that minimally invasive methods can be used to measure EEG-defined wakefulness, SWS, and REM sleep in owls and probably other animals.

Electroencephalogram changes during inhalation with nitric oxide in the pediatric intensive care patient--a preliminary report.

OBJECTIVES: Although endogenous nitric oxide (NO) is an excitatory mediator in the central nervous system, inhaled NO is not considered to cause neurologic side effects because of its short half-life. This study was motivated by a recent case report about neurologic symptoms and our own observation of severe electroencephalogram (EEG) abnormalities during NO inhalation. DESIGN: Blind, retrospective analyses of EEGs which were registered before, during, and after NO inhalation. EEG was classified in a 5-point rating system by an independent electroencephalographer who was blinded to the patients' clinical histories. Comparisons were made with the previous evaluation documented at recording. Other EEG-influencing parameters such as oxygen saturation, hemodynamics, electrolytes, and pH were evaluated. SETTING: Pediatric intensive care unit of a tertiary care university children's hospital. PATIENTS: Eleven ventilated, long-term paralyzed, sedated children (1 mo to 14 yrs) who had EEG or clinical assessment before NO treatment and EEG during NO inhalation. They were divided into two groups according to the NO-indication (e.g., congenital heart defect, acute respiratory distress syndrome). MEASUREMENTS AND MAIN RESULTS: All 11 patients had an abnormal EEG during NO inhalation. EEG-controls without NO showed remarkable improvement. EEG abnormalities were background slowing, low voltage, suppression burst (n = 2), and sharp waves (n = 2) independent of patients' age, NO-indication, and other EEG-influencing parameters. CONCLUSIONS: These preliminary data suggest the occurrence of EEG-abnormalities after application of inhaled NO in critically ill children. We found no correlation with other potential EEG-influencing parameters, although clinical state, medication, or hypoxemia might contribute. Comprehensive, prospective, clinical assessment regarding a causal relationship between NO-inhalation and EEG-abnormalities and their clinical importance is needed.

A novel method for automated classification of epileptiform activity in the human electroencephalogram-based on independent component analysis.

Diagnosis of several neurological disorders is based on the detection of typical pathological patterns in the electroencephalogram (EEG). This is a time-consuming task requiring significant training and experience. Automatic detection of these EEG patterns would greatly assist in quantitative analysis and interpretation. We present a method, which allows automatic detection of epileptiform events and discrimination of them from eye blinks, and is based on features derived using a novel application of independent component analysis. The algorithm was trained and cross validated using seven EEGs with epileptiform activity. For epileptiform events with compensation for eyeblinks, the sensitivity was 65 +/- 22% at a specificity of 86 +/- 7% (mean +/- SD). With feature extraction by PCA or classification of raw data, specificity reduced to 76 and 74%, respectively, for the same sensitivity. On exactly the same data, the commercially available software Reveal had a maximum sensitivity of 30% and concurrent specificity of 77%. Our algorithm performed well at detecting epileptiform events in this preliminary test and offers a flexible tool that is intended to be generalized to the simultaneous classification of many waveforms in the EEG.

Language Regression Associated With Autistic Regression and Electroencephalographic (EEG) Abnormalities: A Prospective Study.

We report a boy, referred at 25 months following a dramatic isolated language regression antedating autistic-like symptomatology. His sleep electroencephalogram (EEG) showed persistent focal epileptiform activity over the left parietal and vertex areas never associated with clinical seizures. He was started on adrenocorticotropic hormone (ACTH) with a significant improvement in language, behavior, and in EEG discharges in rapid eye movement (REM) sleep. Later course was characterized by fluctuations/regressions in language and behavior abilities, in phase with recrudescence of EEG abnormalities prompting additional ACTH courses that led to remarkable decrease in EEG abnormalities, improvement in language, and to a lesser degree, in autistic behavior. The timely documentation of regression episodes suggesting an "atypical" autistic regression, striking therapy-induced improvement, fluctuation of symptomatology over time could be ascribed to recurrent and persisting EEG abnormalities.

Evolution of source EEG synchronization in early Alzheimer's disease.

Alzheimer's disease (AD) disrupts functional connectivity in distributed cortical networks. We analyzed changes in the S-estimator, a measure of multivariate intraregional synchronization, in electroencephalogram (EEG) source space in 15 mild AD patients versus 15 age-matched controls to evaluate its potential as a marker of AD progression. All participants underwent 2 clinical evaluations and 2 EEG recording sessions on diagnosis and after a year. The main effect of AD was hyposynchronization in the medial temporal and frontal regions and relative hypersynchronization in posterior cingulate, precuneus, cuneus, and parietotemporal cortices. However, the S-estimator did not change over time in either group. This result motivated an analysis of rapidly progressing AD versus slow-progressing patients. Rapidly progressing AD patients showed a significant reduction in synchronization with time, manifest in left frontotemporal cortex. Thus, the evolution of source EEG synchronization over time is correlated with the rate of disease progression and should be considered as a cost-effective AD biomarker.