Wajid Mumtaz

Review on EEG and ERP predictive biomarkers for major depressive disorder

Abstract The selection of suitable antidepressants for Major Depressive Disorder (MDD) has been challenging and is mainly based on subjective assessments that include minimal scientific evidence. Objective measures that are extracted from neuroimaging modalities such as electroencephalograms (EEGs) could be a potential solution to this problem. This approach is achieved by the successful prediction of antidepressant treatment efficacy early in the patients care. EEG-based relevant research studies have shown promising results. These studies are based on derived measures from EEG and event-related potentials (ERPs), which are called neurophysiological predictive biomarkers for MDD. This paper seeks to provide a detailed review on such research studies along with their possible limitations. In addition, this paper provides a comparison of these methods based on EEG/ERP common datasets from MDD and healthy controls. This paper also proposes recommendations to improve these methods, e.g., EEG integration with other modalities such as functional magnetic resonance imaging (fMRI) and magnetoencephalograms (MEG), to achieve better evidence of the efficacy than EEG alone, to eventually improve the treatment selection process.

Automatic diagnosis of alcohol use disorder using EEG features

Alcohol use disorder (AUD) has been considered as a social and health issue worldwide. More importantly, the screening of AUD patients has been challenging due to the subjectivity imparted by self-test reports. Automated methods involving neuroimaging modality such as quantitative electroencephalography (QEEG) have shown promising research results. However, the QEEG methods were developed only for alcohol dependents (AD) and healthy controls. Therefore, this study sought to propose a machine learning (ML) method to classify 1) between alcohol abusers and healthy controls, and 2) among healthy controls, alcohol abusers, and alcoholics. The proposed ML method involved QEEG feature extraction, selection of most relevant features, and classification of the study participants into their relevant groups. The study participants such as 12 alcohol abusers (mean age 56.70ź15.33 years), 18 alcoholics (mean age 46.80ź9.29 years), and 15 healthy controls (mean 42.67ź15.90 years) were recruited to acquire EEG data. The data were recorded during 10 minutes of eyes closed (EC) and eyes open (EO) conditions. Furthermore, the EEG data were utilized to extract QEEG features such as absolute power (AP) and relative power (RP). Methods such as t-test and principal component analysis (PCA) were employed to select most relevant QEEG features. Finally, the discriminant QEEG features were used as inputs to the classification models: Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Multilayer back-Propagation Network (MLP), and Logistic Model Trees (LMT), supported by 10-fold cross validation. As results, the LMT has achieved best performance rendering a classification accuracy (96%), sensitivity (97%) and specificity (93%). In addition, a further classification for each subgroup of AUD patients has achieved accuracy (>90%). In conclusion, the results implicated significant neurophysiological differences among alcohol abusers, alcoholics, and controls. Moreover, the AUD patients exhibited significantly decreased theta as compared with the healthy controls.

Evaluation of passive polarized stereoscopic 3D display for visual & mental fatigues.

Visual and mental fatigues induced by active shutter stereoscopic 3D (S3D) display have been reported using event-related brain potentials (ERP). An important question, that is whether such effects (visual & mental fatigues) can be found in passive polarized S3D display, is answered here. Sixty-eight healthy participants are divided into 2D and S3D groups and subjected to an oddball paradigm after being exposed to S3D videos with passive polarized display or 2D display. The age and fluid intelligence ability of the participants are controlled between the groups. ERP results do not show any significant differences between S3D and 2D groups to find the aftereffects of S3D in terms of visual and mental fatigues. Hence, we conclude that passive polarized S3D display technology may not induce visual and/or mental fatigue which may increase the cognitive load and suppress the ERP components.

Analysis of EEG signals regularity in adults during video game play in 2D and 3D

Video games have long been part of the entertainment industry. Nonetheless, it is not well known how video games can affect us with the advancement of 3D technology. The purpose of this study is to investigate the EEG signals regularity when playing video games in 2D and 3D modes. A total of 29 healthy subjects (24 male, 5 female) with mean age of 21.79 (1.63) years participated. Subjects were asked to play a car racing video game in three different modes (2D, 3D passive and 3D active). In 3D passive mode, subjects needed to wear a passive polarized glasses (cinema type) while for 3D active, an active shutter glasses was used. Scalp EEG data was recorded during game play using 19-channel EEG machine and linked ear was used as reference. After data were pre-processed, the signal irregularity for all conditions was computed. Two parameters were used to measure signal complexity for time series data: i) Hjorth-Complexity and ii) Composite Permutation Entropy Index (CPEI). Based on these two parameters, our results showed that the complexity level increased from eyes closed to eyes open condition; and further increased in the case of 3D as compared to 2D game play.

A review on EEG-based methods for screening and diagnosing alcohol use disorder

The screening test for alcohol use disorder (AUD) patients has been of subjective nature and could be misleading in particular cases such as a misreporting the actual quantity of alcohol intake. Although the neuroimaging modality such as electroencephalography (EEG) has shown promising research results in achieving objectivity during the screening and diagnosis of AUD patients. However, the translation of these findings for clinical applications has been largely understudied and hence less clear. This study advocates the use of EEG as a diagnostic and screening tool for AUD patients that may help the clinicians during clinical decision making. In this context, a comprehensive review on EEG-based methods is provided including related electrophysiological techniques reported in the literature. More specifically, the EEG abnormalities associated with the conditions of AUD patients are summarized. The aim is to explore the potentials of objective techniques involving quantities/features derived from resting EEG, event-related potentials or event-related oscillations data.

A Comparative Study of Different EEG Reference Choices for Diagnosing Unipolar Depression

The choice of an electroencephalogram (EEG) reference has fundamental importance and could be critical during clinical decision-making because an impure EEG reference could falsify the clinical measurements and subsequent inferences. In this research, the suitability of three EEG references was compared while classifying depressed and healthy brains using a machine-learning (ML)-based validation method. In this research, the EEG data of 30 unipolar depressed subjects and 30 age-matched healthy controls were recorded. The EEG data were analyzed in three different EEG references, the link-ear reference (LE), average reference (AR), and reference electrode standardization technique (REST). The EEG-based functional connectivity (FC) was computed. Also, the graph-based measures, such as the distances between nodes, minimum spanning tree, and maximum flow between the nodes for each channel pair, were calculated. An ML scheme provided a mechanism to compare the performances of the extracted features that involved a general framework such as the feature extraction (graph-based theoretic measures), feature selection, classification, and validation. For comparison purposes, the performance metrics such as the classification accuracies, sensitivities, specificities, and F scores were computed. When comparing the three references, the diagnostic accuracy showed better performances during the REST, while the LE and AR showed less discrimination between the two groups. Based on the results, it can be concluded that the choice of appropriate reference is critical during the clinical scenario. The REST reference is recommended for future applications of EEG-based diagnosis of mental illnesses.

Machine Learning Framework for the Detection of Mental Stress at Multiple Levels

Mental stress has become a social issue and could become a cause of functional disability during routine work. In addition, chronic stress could implicate several psychophysiological disorders. For example, stress increases the likelihood of depression, stroke, heart attack, and cardiac arrest. The latest neuroscience reveals that the human brain is the primary target of mental stress, because the perception of the human brain determines a situation that is threatening and stressful. In this context, an objective measure for identifying the levels of stress while considering the human brain could considerably improve the associated harmful effects. Therefore, in this paper, a machine learning (ML) framework involving electroencephalogram (EEG) signal analysis of stressed participants is proposed. In the experimental setting, stress was induced by adopting a well-known experimental paradigm based on the montreal imaging stress task. The induction of stress was validated by the task performance and subjective feedback. The proposed ML framework involved EEG feature extraction, feature selection (receiver operating characteristic curve, t-test and the Bhattacharya distance), classification (logistic regression, support vector machine and naïve Bayes classifiers) and tenfold cross validation. The results showed that the proposed framework produced 94.6% accuracy for two-level identification of stress and 83.4% accuracy for multiple level identification. In conclusion, the proposed EEG-based ML framework has the potential to quantify stress objectively into multiple levels. The proposed method could help in developing a computer-aided diagnostic tool for stress detection.

An EEG-based functional connectivity measure for automatic detection of alcohol use disorder

BACKGROUND The abnormal alcohol consumption could cause toxicity and could alter the human brains structure and function, termed as alcohol used disorder (AUD). Unfortunately, the conventional screening methods for AUD patients are subjective and manual. Hence, to perform automatic screening of AUD patients, objective methods are needed. The electroencephalographic (EEG) data have been utilized to study the differences of brain signals between alcoholics and healthy controls that could further developed as an automatic screening tool for alcoholics. METHOD In this work, resting-state EEG-derived features were utilized as input data to the proposed feature selection and classification method. The aim was to perform automatic classification of AUD patients and healthy controls. The validation of the proposed method involved real-EEG data acquired from 30 AUD patients and 30 age-matched healthy controls. The resting-state EEG-derived features such as synchronization likelihood (SL) were computed involving 19 scalp locations resulted into 513 features. Furthermore, the features were rank-ordered to select the most discriminant features involving a rank-based feature selection method according to a criterion, i.e., receiver operating characteristics (ROC). Consequently, a reduced set of most discriminant features was identified and utilized further during classification of AUD patients and healthy controls. In this study, three different classification models such as Support Vector Machine (SVM), Naïve Bayesian (NB), and Logistic Regression (LR) were used. RESULTS The study resulted into SVM classification accuracy=98%, sensitivity=99.9%, specificity=95%, and f-measure=0.97; LR classification accuracy=91.7%, sensitivity=86.66%, specificity=96.6%, and f-measure=0.90; NB classification accuracy=93.6%, sensitivity=100%, specificity=87.9%, and f-measure=0.95. CONCLUSION The SL features could be utilized as objective markers to screen the AUD patients and healthy controls.

A Study to Investigate Different EEG Reference Choices in Diagnosing Major Depressive Disorder

Choice of an electroencephalogram (EEG) reference is a critical issue during measurement of brain activity. An appropriate reference may improve efficiency during diagnosis of psychiatric conditions, e.g., major depressive disorder (MDD). In literature, various EEG references have been proposed, however, none of them is considered as gold-standard [1]. Therefore, this study aims to evaluate 3 EEG references including infinity reference (IR), average reference (AR) and link-ear (LE) reference based on EEG data acquired from 2 groups: the MDD patients and healthy subjects as controls. The experimental EEG data acquisition involved 2 physiological conditions: eyes closed (EC) and eyes open (EO). Originally, the data were recorded with LE reference and re-referenced to AR and IR. EEG features such as the inter-hemispheric coherences, inter-hemispheric asymmetries, and different frequency bands powers were computed. These EEG features were used as input data to train and test the logistic regression (LR) classifier and the linear kernel support vector machine (SVM). Finally, the results were presented as classification accuracies, sensitivities, and specificities while discriminating the MDD patients from a potential population of healthy controls. According to the results, AR has provided the maximum classification efficiencies for coherence and power based features. The case of asymmetry, IR and LE performed better than AR. The study concluded that the reference selection should include factors such as underlying EEG data, computed features and type of assessment performed.

Detrended fluctuation analysis for major depressive disorder

Clinical utility of Electroencephalography (EEG) based diagnostic studies is less clear for major depressive disorder (MDD). In this paper, a novel machine learning (ML) scheme was presented to discriminate the MDD patients and healthy controls. The proposed method inherently involved feature extraction, selection, classification and validation. The EEG data acquisition involved eyes closed (EC) and eyes open (EO) conditions. At feature extraction stage, the de-trended fluctuation analysis (DFA) was performed, based on the EEG data, to achieve scaling exponents. The DFA was performed to analyzes the presence or absence of long-range temporal correlations (LRTC) in the recorded EEG data. The scaling exponents were used as input features to our proposed system. At feature selection stage, 3 different techniques were used for comparison purposes. Logistic regression (LR) classifier was employed. The method was validated by a 10-fold cross-validation. As results, we have observed that the effect of 3 different reference montages on the computed features. The proposed method employed 3 different types of feature selection techniques for comparison purposes as well. The results show that the DFA analysis performed better in LE data compared with the IR and AR data. In addition, during Wilcoxon ranking, the AR performed better than LE and IR. Based on the results, it was concluded that the DFA provided useful information to discriminate the MDD patients and with further validation can be employed in clinics for diagnosis of MDD.