Detecting drowsiness in drivers, especially multi-level drowsiness, is a difficult problem that is often approached using neurophysiological signals as the basis for building a reliable system In this context, electroencephalogram (EEG) signals are the most important source of data to achieve successful detection In this paper, we first review EEG signal features used in the literature for a variety of tasks, then we focus on reviewing the applications of EEG features and deep learning approaches in driver drowsiness detection, and finally we discuss the open challenges and opportunities in improving driver drowsiness detection based on EEG We show that the number of studies on driver drowsiness detection systems has increased in recent years and that future systems need to consider the wide variety of EEG signal features and deep learning approaches to increase the accuracy of detection

https://www.mdpi.com/1424-8220/21/11/3786/pdf

A Review of EEG Signal Features and Their Application in Driver Drowsiness Detection Systems

Neuropsychology of bipolar disorder

The Electrophysiology Professional Interest Area (EPIA) and Global Brain Consortium endorsed recommendations on candidate electroencephalography (EEG) measures for Alzheimer's disease (AD) clinical trials. The Panel reviewed the field literature. As most consistent findings, AD patients with mild cognitive impairment and dementia showed abnormalities in peak frequency, power, and “interrelatedness” at posterior alpha (8-12 Hz) and widespread delta (< 4 Hz) and theta (4-8 Hz) rhythms in relation to disease progression and interventions. The following consensus statements were subscribed: (1) Standardization of instructions to patients, resting state EEG (rsEEG) recording methods, and selection of artifact-free rsEEG periods are needed; (2) power density and “interrelatedness” rsEEG measures (e.g., directed transfer function, phase lag index, linear lagged connectivity, etc.) at delta, theta, and alpha frequency bands may be use for stratification of AD patients and monitoring of disease progression and intervention; and (3) international multisectoral initiatives are mandatory for regulatory purposes.

Measures of resting state EEG rhythms for clinical trials in Alzheimer's disease: Recommendations of an expert panel

Alzheimer's Disease (AD) is a neurodegenerative disorder and the most common type of dementia with a great prevalence in western countries. The diagnosis of AD and its progression is performed through a variety of clinical procedures including neuropsychological and physical examination, Electroencephalographic (EEG) recording, brain imaging and blood analysis. During the last decades, analysis of the electrophysiological dynamics in AD patients has gained great research interest, as an alternative and cost-effective approach. This paper summarizes recent publications focusing on (a) AD detection and (b) the correlation of quantitative EEG features with AD progression, as it is estimated by Mini Mental State Examination (MMSE) score. A total of 49 experimental studies published from 2009 until 2020, which apply machine learning algorithms on resting state EEG recordings from AD patients, are reviewed. Results of each experimental study are presented and compared. The majority of the studies focus on AD detection incorporating Support Vector Machines, while deep learning techniques have not yet been applied on large EEG datasets. Promising conclusions for future studies are presented.

Machine Learning Algorithms and Statistical Approaches for Alzheimer's Disease Analysis Based on Resting-State EEG Recordings: A Systematic Review.

Alzheimer's disease (AD) consists of the gradual process of decreasing volume and quality of neuron connection in the brain, which consists of gradual synaptic integrity and loss of cognitive functions. In recent years, there has been significant attention in AD classification and early detection with machine learning algorithms. There are different neuroimaging techniques for capturing data and using it for the classification task. Input data as images will help machine learning models to detect different biomarkers for AD classification. This marker has a more critical role for AD detection than other diseases because beta-amyloid can extract complex structures with some metal ions. Most researchers have focused on using 3D and 4D convolutional neural networks for AD classification due to reasonable amounts of data. Also, combination neuroimaging techniques like functional magnetic resonance imaging and positron emission tomography for AD detection have recently gathered much attention. However, gathering a combination of data can be expensive, complex, and tedious. For time consumption reasons, most patients prefer to throw one of the neuroimaging techniques. So, in this review article, we have surveyed different research studies with various neuroimaging techniques and ML methods to see the effect of using combined data as input. The result has shown that the use of the combination method would increase the accuracy of AD detection. Also, according to the sensitivity metrics from different machine learning methods, MRI and fMRI showed promising results.

/pdf/single-and-combined-neuroimaging-techniques-for-alzheimer-s-1jlw8rdsov.pdf

Single and Combined Neuroimaging Techniques for Alzheimer's Disease Detection.

Alzheimer's disease (AD) is a degenerative brain disease with a high and irreversible incidence. In recent years, because brain signals have complex nonlinear dynamics, there has been growing interest in studying complex changes in the time series of brain signals in patients with AD. We reviewed studies of complexity analyses of single-channel time series from electroencephalogram (EEG), magnetoencephalogram (MEG), and functional magnetic resonance imaging (fMRI) in AD and determined future research directions. A systematic literature search for 2000-2019 was performed in the Web of Science and PubMed databases, resulting in 126 identified studies. Compared to healthy individuals, the signals from AD patients have less complexity and more predictable oscillations, which are found mainly in the left parietal, occipital, right frontal, and temporal regions. This complexity is considered a potential biomarker for accurately responding to the functional lesion in AD. The current review helps to reveal the patterns of dysfunction in the brains of patients with AD and to investigate whether signal complexity can be used as a biomarker to accurately respond to the functional lesion in AD. We proposed further studies in the signal complexities of AD patients, including investigating the reliability of complexity algorithms and the spatial patterns of signal complexity. In conclusion, the current review helps to better understand the complexity of abnormalities in the AD brain and provide useful information for AD diagnosis.

https://www.mdpi.com/1099-4300/22/2/239/pdf

Complexity Analysis of EEG, MEG, and fMRI in Mild Cognitive Impairment and Alzheimer's Disease: A Review.

BACKGROUND Schizophrenia (SC) and bipolar disorder (BP) share elements of symptoms and the underlying neural mechanisms for both remain unclear. Recently, the complexity of spontaneous functional MRI (fMRI) signals in brain activity has been investigated in SC and BP using multiscale sample entropy (MSE) with inconsistent results. PURPOSE To perform MSE analysis across five time scales to assess differences in resting-state fMRI signal complexity in SC, BP, and normal controls (NC). STUDY TYPE Retrospective. POPULATION Fifty SC, 49 BP, and 49 NC. FIELD STRENGTH/SEQUENCE A 3 T, T2* weighted echo planar imaging (EPI) sequence. ASSESSMENT The mean MSEs of all gray matter (GM) and of 12 regions of interest (ROIs) were extracted using masks across the five scales. The regional homogeneity (ReHo) and amplitude of low-frequency fluctuation (ALFF) in these ROIs were also determined and the relationship between the three measures was investigated. The correlations between cognitive assessment scores and MSE values were also explored. STATISTICAL TESTS Bonferroni correction, One-way ANOVA, Spearman rank correlation coefficient (r), Gaussian random field (GRF) correction. RESULTS There were decreased GM MSE values in the patient groups (F = 9.629, P   0.282, P   0.278, P < 0.05). Furthermore, median temporal MSE (r = -0.321, P < 0.05) on scale 3 and (r = -0.307, P < 0.05) on scale 4 and median cingulate MSE (r = -0.337, P < 0.05) on scale 5 was significantly negatively correlated with cognitive assessment scores. DATA CONCLUSION These data highlight different patterns of brain signal intensity complexity in SC and BP. LEVEL OF EVIDENCE 1 TECHNICAL EFFICACY: Stage 1.

Altered Complexity of Spontaneous Brain Activity in Schizophrenia and Bipolar Disorder Patients

Attention-deficit/hyperactivity disorder (ADHD) has been reported exist abnormal topology structure in the brain network. However, these studies often treated the brain as a static monolithic structure, and dynamic characteristics were ignored. Here, we investigated how the dynamic network reconfiguration in ADHD patients differs from that in healthy people. Specifically, we acquired resting-state functional magnetic resonance imaging data from a public dataset including 40 ADHD patients and 50 healthy people. A novel model of a "time-varying multilayer network" and metrics of recruitment and integration were applied to describe group differences. The results showed that the integration scores of ADHD patients were significantly lower than those of controls at every level. The recruitment scores were lower than healthy people except for the whole-brain level. It is worth noting that the subcortical network and the thalamus in ADHD patients exhibited reduced alliance preference both within and between functional networks. In addition, we also found that recruitment and integration coefficients showed a significant correlation with symptom severity in some regions. Our results demonstrate that the capability to communicate within or between some functional networks is impaired in ADHD patients. These evidences provide a new opportunity for studying the characteristics of ADHD brain networks.

Analysis of Dynamic Network Reconfiguration in Adults with Attention-Deficit/Hyperactivity Disorder Based Multilayer Network.

Neuroimaging studies suggest disrupted connections of the brain white matter (WM) network in bipolar disorder (BD). A group of highly interconnected high-density structures, termed the 'rich club,' represents an important network for brain functioning. Recent works have revealed abnormal rich club organization in brain networks in BD. However, little is known regarding changes in the rich club organization of the hemispheric WM network in BD. Forty-nine BD patients and fifty-five age- and sex-matched normal controls (NCs) underwent diffusion tensor imaging (DTI). Graph theory approaches were applied to quantify group-specific rich club organization and nodal degree of hemispheric WM networks. We demonstrated that rich club organization of hemispheric WM networks in BD was disrupted, with disrupted feeder and local connections among hub and peripheral regions located in the default mode network (DMN) and the control execution network (CEN). In addition, BD patients showed abnormal asymmetry in the feeder and local connections, involving the hub and peripheral regions associated with emotion regulation and visuospatial functions. Moreover, the clinical symptoms of BD showed a significant correlation with the aberrant asymmetry in the regional degree of peripheral regions. These findings reveal that BD is closely associated with disrupted feeder and local connections but no alteration in rich-club connections in the rich club organization of hemispheric WM networks and provide novel insight into the changes of brain functions in BD.

/pdf/disrupted-rich-club-organization-of-hemispheric-white-matter-aa1mus5r2k.pdf

Disrupted Rich Club Organization of Hemispheric White Matter Networks in Bipolar Disorder.

Research has shown that abnormal brain networks in patients with schizophrenia appear at different frequencies, but the relationship between these different frequencies is unclear. Therefore, it is necessary to use a multilayer network model to evaluate the integration of information from different frequency bands. To explore the mechanism of integration and separation in the multilayer network of schizophrenia, we constructed multilayer frequency brain network models in 50 patients with schizophrenia and 69 healthy subjects, and the entropy of the multiplex degree (EMD) and multilayer clustering coefficient (MCC) were calculated. The results showed that the ability to integrate and separate information in the multilayer network of patients was significantly higher than that of normal people. This difference was mainly reflected in the default mode network, sensorimotor network, subcortical network, and visual network. Among them, the subcortical network was different in both MCC and EMD outcomes. Furthermore, differences were found in the posterior cingulate gyrus, hippocampus, amygdala, putamen, pallidum, and thalamus. The thalamus and posterior cingulate gyrus were associated with the patient’s symptom scores. Our results showed that the cross-frequency interaction ability of patients with schizophrenia was significantly enhanced, among which the subcortical network was the most active. This interaction may serve as a compensation mechanism for intralayer dysfunction.

https://www.mdpi.com/2076-3425/12/3/368/pdf?version=1647014880

Jing Wei

Papers

Complexity Analysis of EEG, MEG, and fMRI in Mild Cognitive Impairment and Alzheimer's Disease: A Review.

Altered Complexity of Spontaneous Brain Activity in Schizophrenia and Bipolar Disorder Patients

Analysis of Dynamic Network Reconfiguration in Adults with Attention-Deficit/Hyperactivity Disorder Based Multilayer Network.

Disrupted Rich Club Organization of Hemispheric White Matter Networks in Bipolar Disorder.

Functional Integration and Segregation in a Multilayer Network Model of Patients with Schizophrenia