Spectral and complexity analysis of scalp EEG characteristics for mild cognitive impairment and early Alzheimer's disease

Brain health in diverse settings: How age, demographics and cognition shape brain function

Diversity in brain health is influenced by individual differences in demographics and cognition. However, most studies on brain health and diseases have typically controlled for these factors rather than explored their potential to predict brain signals. Here, we assessed the role of individual differences in demographics (age, sex, and education; n = 1298) and cognition (n = 725) as predictors of different metrics usually used in case-control studies. These included power spectrum and aperiodic (1/f slope, knee, offset) metrics, as well as complexity (fractal dimension estimation, permutation entropy, Wiener entropy, spectral structure variability) and connectivity (graph-theoretic mutual information, conditional mutual information, organizational information) from the source space resting-state EEG activity in a diverse sample from the global south and north populations. Brain-phenotype models were computed using EEG metrics reflecting local activity (power spectrum and aperiodic components) and brain dynamics and interactions (complexity and graph-theoretic measures). Electrophysiological brain dynamics were modulated by individual differences despite the varied methods of data acquisition and assessments across multiple centers, indicating that results were unlikely to be accounted for by methodological discrepancies. Variations in brain signals were mainly influenced by age and cognition, while education and sex exhibited less importance. Power spectrum activity and graph-theoretic measures were the most sensitive in capturing individual differences. Older age, poorer cognition, and being male were associated with reduced alpha power, whereas older age and less education were associated with reduced network integration and segregation. Findings suggest that basic individual differences impact core metrics of brain function that are used in standard case-control studies. Considering individual variability and diversity in global settings would contribute to a more tailored understanding of brain function.

Studying the Alzheimer's disease continuum using EEG and fMRI in single-modality and multi-modality settings

Alzheimer's disease (AD) is a biological, clinical continuum that covers the preclinical, prodromal, and clinical phases of the disease. Early diagnosis and identification of the stages of Alzheimer's disease (AD) are crucial in clinical practice. Ideally, biomarkers should reflect the underlying process (pathological or otherwise), be reproducible and non-invasive, and allow repeated measurements over time. However, the currently known biomarkers for AD are not suitable for differentiating the stages and predicting the trajectory of disease progression. Some objective parameters extracted using electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) are widely applied to diagnose the stages of the AD continuum. While electroencephalography (EEG) has a high temporal resolution, fMRI has a high spatial resolution. Combined EEG and fMRI (EEG-fMRI) can overcome single-modality drawbacks and obtain multi-dimensional information simultaneously, and it can help explore the hemodynamic changes associated with the neural oscillations that occur during information processing. This technique has been used in the cognitive field in recent years. This review focuses on the different techniques available for studying the AD continuum, including EEG and fMRI in single-modality and multi-modality settings, and the possible future directions of AD diagnosis using EEG-fMRI.

Investigating the effects of chiropractic care on resting-state EEG of MCI patients

Introduction

Mild cognitive impairment (MCI) is a stage between health and dementia, with various symptoms including memory, language, and visuospatial impairment. Chiropractic, a manual therapy that seeks to improve the function of the body and spine, has been shown to affect sensorimotor processing, multimodal sensory processing, and mental processing tasks.

Methods

In this paper, the effect of chiropractic intervention on Electroencephalogram (EEG) signals in patients with mild cognitive impairment was investigated. EEG signals from two groups of patients with mild cognitive impairment (n = 13 people in each group) were recorded pre- and post-control and chiropractic intervention. A comparison of relative power was done with the support vector machine (SVM) method and non-parametric cluster-based permutation test showing the two groups could be separately identified with high accuracy.

Results

The highest accuracy was obtained in beta2 (25-35 Hz) and theta (4-8 Hz) bands. A comparison of different brain areas with the SVM method showed that the intervention had a greater effect on frontal areas. Also, interhemispheric coherence in all regions increased significantly after the intervention. The results of the Wilcoxon test showed that intrahemispheric coherence changes in frontal-occipital, frontal-temporal and right temporal-occipital regions were significantly different in two groups.

Discussion

Comparison of the results obtained from chiropractic intervention and previous studies shows that chiropractic intervention can have a positive effect on MCI disease and using this method may slow down the progression of mild cognitive impairment to Alzheimer's disease.

Exploring the disruptions of the neurophysiological organization in Alzheimer's disease: An integrative approach

BACKGROUND AND OBJECTIVE

Alzheimer's disease (AD) is a neurological disorder that impairs brain functions associated with cognition, memory, and behavior. Noninvasive neurophysiological techniques like magnetoencephalography (MEG) and electroencephalography (EEG) have shown promise in reflecting brain changes related to AD. These techniques are usually assessed at two levels: local activation (spectral, nonlinear, and dynamic properties) and global synchronization (functional connectivity, frequency-dependent network, and multiplex network organization characteristics). Nonetheless, the understanding of the organization formed by the existing relationships between these levels, henceforth named neurophysiological organization, remains unexplored. This work aims to assess the alterations AD causes in the resting-state neurophysiological organization.

METHODS

To that end, three datasets from healthy controls (HC) and patients with dementia due to AD were considered: MEG database (55 HC and 87 patients with AD), EEG1 database (51 HC and 100 patients with AD), and EEG2 database (45 HC and 82 patients with AD). To explore the alterations induced by AD in the relationships between several features extracted from M/EEG data, association networks (ANs) were computed. ANs are graphs, useful to quantify and visualize the intricate relationships between multiple features.

RESULTS

Our results suggested a disruption in the neurophysiological organization of patients with AD, exhibiting a greater inclination towards the local activation level; and a significant decrease in the complexity and diversity of the ANs (p-value ¡ 0.05, Mann-Whitney U-test, Bonferroni correction). This effect might be due to a shift of the neurophysiological organization towards more regular configurations, which may increase its vulnerability. Moreover, our findings support the crucial role played by the local activation level in maintaining the stability of the neurophysiological organization. Classification performance exhibited accuracy values of 83.91%, 73.68%, and 72.65% for MEG, EEG1, and EEG2 databases, respectively.

CONCLUSION

This study introduces a novel, valuable methodology able to integrate parameters characterize different properties of the brain activity and to explore the intricate organization of the neurophysiological organization at different levels. It was noted that AD increases susceptibility to changes in functional neural organization, suggesting a greater ease in the development of severe impairments. Therefore, ANs could facilitate a deeper comprehension of the complex interactions in brain function from a global standpoint.

Is EEG Entropy a Useful Measure for Alzheimer's Disease?

BACKGROUND

The number of individuals diagnosed with Alzheimer's disease (AD) has increased, and it is estimated to continue rising in the coming years. The diagnosis of this disease is challenging due to variations in onset and course, its diverse clinical manifestations, and the indications for measuring deposit biomarkers. Hence, there is a need to develop more precise and less invasive diagnostic tools. Multiple studies have considered using electroencephalography (EEG) entropy measures as an indicator of the onset and course of AD. Entropy is deemed suitable as a potential indicator based on the discovery that variations in its complexity can be associated with specific pathologies such as AD.

METHODOLOGY

Following PRISMA guidelines, a literature search was conducted in 4 scientific databases, and 40 articles were analyzed after discarding and filtering.

RESULTS

There is a diversity in entropy measures; however, Sample Entropy (SampEn) and Multiscale Entropy (MSE) are the most widely used (21/40). In general, it is found that when comparing patients with controls, patients exhibit lower entropy (20/40) in various areas. Findings of correlation with the level of cognitive decline are less consistent, and with neuropsychiatric symptoms (2/40) or treatment response less explored (2/40), although most studies show lower entropy with greater severity. Machine learning-based studies show good discrimination capacity.

CONCLUSIONS

There is significant difficulty in comparing multiple studies due to their heterogeneity; however, changes in Multiscale Entropy (MSE) scales or a decrease in entropy levels are considered useful for determining the presence of AD and measuring its severity.

Neural markers of reduced arousal and consciousness in mild cognitive impairment

OBJECTIVES

People with Alzheimer's Disease (AD) experience changes in their level and content of consciousness, but there is little research on biomarkers of consciousness in pre-clinical AD and Mild Cognitive Impairment (MCI). This study investigated whether levels of consciousness are decreased in people with MCI.

METHODS

A multi-site site magnetoencephalography (MEG) dataset, BIOFIND, comprising 83 people with MCI and 83 age matched controls, was analysed. Arousal (and drowsiness) was assessed by computing the theta-alpha ratio (TAR). The Lempel-Ziv algorithm (LZ) was used to quantify the information content of brain activity, with higher LZ values indicating greater complexity and potentially a higher level of consciousness.

RESULTS

LZ was lower in the MCI group versus controls, indicating a reduced level of consciousness in MCI. TAR was higher in the MCI group versus controls, indicating a reduced level of arousal (i.e. increased drowsiness) in MCI. LZ was also found to be correlated with mini-mental state examination (MMSE) scores, suggesting an association between cognitive impairment and level of consciousness in people with MCI.

CONCLUSIONS

A decline in consciousness and arousal can be seen in MCI. As cognitive impairment worsens, measured by MMSE scores, levels of consciousness and arousal decrease. These findings highlight how monitoring consciousness using biomarkers could help understand and manage impairments found at the preclinical stages of AD. Further research is needed to explore markers of consciousness between people who progress from MCI to dementia and those who do not, and in people with moderate and severe AD, to promote person-centred care.

Effect of Atypical Sleep EEG Patterns on Weaning From Prolonged Mechanical Ventilation

BACKGROUND

Approximately one-third of acute ICU patients display atypical sleep patterns that cannot be interpreted by using standard EEG criteria for sleep. Atypical sleep patterns have been associated with poor weaning outcomes in acute ICUs.

RESEARCH QUESTION

Do patients being weaned from prolonged mechanical ventilation experience atypical sleep EEG patterns, and are these patterns linked with weaning outcomes?

STUDY DESIGN AND METHODS

EEG power spectral analysis during wakefulness and overnight polysomnogram were performed on alert, nondelirious patients at a long-term acute care facility.

RESULTS

Forty-four patients had been ventilated for a median duration of 38 days at the time of the polysomnogram study. Eleven patients (25%) exhibited atypical sleep EEG. During wakefulness, relative EEG power spectral analysis revealed higher relative delta power in patients with atypical sleep than in patients with usual sleep (53% vs 41%; P < .001) and a higher slow-to-fast power ratio during wakefulness: 4.39 vs 2.17 (P < .001). Patients with atypical sleep displayed more subsyndromal delirium (36% vs 6%; P = .027) and less rapid eye movement sleep (4% vs 11% total sleep time; P < .02). Weaning failure was more common in the atypical sleep group than in the usual sleep group: 91% vs 45% (P = .013).

INTERPRETATION

This study provides the first evidence that patients in a long-term acute care facility being weaned from prolonged ventilation exhibit atypical sleep EEG patterns that are associated with weaning failure. Patients with atypical sleep EEG patterns had higher rates of subsyndromal delirium and slowing of the wakeful EEG, suggesting that these two findings represent a biological signal for brain dysfunction.

Electroencephalography-based classification of Alzheimer's disease spectrum during computer-based cognitive testing

Alzheimer's disease (AD) is a progressive disease leading to cognitive decline, and to prevent it, researchers seek to diagnose mild cognitive impairment (MCI) early. Particularly, non-amnestic MCI (naMCI) is often mistaken for normal aging as the representative symptom of AD, memory decline, is absent. Subjective cognitive decline (SCD), an intermediate step between normal aging and MCI, is crucial for prediction or early detection of MCI, which determines the presence of AD spectrum pathology. We developed a computer-based cognitive task to classify the presence or absence of AD pathology and stage within the AD spectrum, and attempted to perform multi-stage classification through electroencephalography (EEG) during resting and memory encoding state. The resting and memory-encoding states of 58 patients (20 with SCD, 10 with naMCI, 18 with aMCI, and 10 with AD) were measured and classified into four groups. We extracted features that could reflect the phase, spectral, and temporal characteristics of the resting and memory-encoding states. For the classification, we compared nine machine learning models and three deep learning models using Leave-one-subject-out strategy. Significant correlations were found between the existing neurophysiological test scores and performance of our computer-based cognitive task for all cognitive domains. In all models used, the memory-encoding states realized a higher classification performance than resting states. The best model for the 4-class classification was cKNN. The highest accuracy using resting state data was 67.24%, while it was 93.10% using memory encoding state data. This study involving participants with SCD, naMCI, aMCI, and AD focused on early Alzheimer's diagnosis. The research used EEG data during resting and memory encoding states to classify these groups, demonstrating the significance of cognitive process-related brain waves for diagnosis. The computer-based cognitive task introduced in the study offers a time-efficient alternative to traditional neuropsychological tests, showing a strong correlation with their results and serving as a valuable tool to assess cognitive impairment with reduced bias.

Quantitative electroencephalography (qEEG), apolipoprotein A-I (APOA-I), and apolipoprotein epsilon 4 (APOE ɛ4) alleles for the diagnosis of mild cognitive impairment and Alzheimer's disease

INTRODUCTION

Alzheimer's disease (AD) is the most common type of dementia. Amnestic mild cognitive impairment (aMCI), a pre-dementia stage is an important stage for early diagnosis and intervention. This study aimed to investigate the diagnostic value of qEEG, APOA-I, and APOE ɛ4 allele in aMCI and AD patients and found the correlation between qEEG (Delta + Theta)/(Alpha + Beta) ratio (DTABR) and different cognitive domains.

METHODS

All participants were divided into three groups: normal controls (NCs), aMCI, and AD, and all received quantitative electroencephalography (qEEG), neuropsychological scale assessment, apolipoprotein epsilon 4 (APOE ɛ4) alleles, and various blood lipid indicators. Different statistical methods were used for different data.

RESULTS

The cognitive domains except executive ability were all negatively correlated with DTABR in different brain regions while executive ability was positively correlated with DTABR in several brain regions, although without statistical significance. The consequences confirmed that the DTABR of each brain area were related to MMSE, MoCA, instantaneous memory, and the language ability (p < 0.05), and the DTABR in the occipital area was relevant to all cognitive domains (p < 0.01) except executive function (p = 0.272). Also, occipital DTABR was most correlated with language domain when tested by VFT with a moderate level (r = 0.596, p < 0.001). There were significant differences in T3, T5, and P3 DTABR between both AD and NC and aMCI and NCs. As for aMCI diagnosis, the maximum AUC was achieved when using T3 combined with APOA-I and APOE ε4 (0.855) and the maximum AUC was achieved when using T5 combined with APOA-I and APOE ε4 (0.889) for AD diagnosis.

CONCLUSION

These findings highlight that APOA-I, APOE ɛ4, and qEEG play an important role in aMCI and AD diagnosis. During AD continuum, qEEG DTABR should be taken into consideration for the early detection of AD risk.

Personalized modeling of Alzheimer's disease progression estimates neurodegeneration severity from EEG recordings

INTRODUCTION

Early identification of Alzheimer's disease (AD) is necessary for a timely onset of therapeutic care. However, cortical structural alterations associated with AD are difficult to discern.

METHODS

We developed a cortical model of AD-related neurodegeneration accounting for slowing of local dynamics and global connectivity degradation. In a monocentric study we collected electroencephalography (EEG) recordings at rest from participants in healthy (HC, n = 17), subjective cognitive decline (SCD, n = 58), and mild cognitive impairment (MCI, n = 44) conditions. For each patient, we estimated neurodegeneration model parameters based on individual EEG recordings.

RESULTS

Our model outperformed standard EEG analysis not only in discriminating between HC and MCI conditions (F1 score 0.95 vs 0.75) but also in identifying SCD patients with biological hallmarks of AD in the cerebrospinal fluid (recall 0.87 vs 0.50).

DISCUSSION

Personalized models could (1) support classification of MCI, (2) assess the presence of AD pathology, and (3) estimate the risk of cognitive decline progression, based only on economical and non-invasive EEG recordings.

Highlights

Personalized cortical model estimating structural alterations from EEG recordings.Discrimination of Mild Cognitive Impairment (MCI) and Healthy (HC) subjects (95%)Prediction of biological markers of Alzheimer's in Subjective Decline (SCD) Subjects (87%)Transition correctly predicted for 3/3 subjects that converted from SCD to MCI after 1y.

Novel methodology for detection and prediction of mild cognitive impairment using resting-state EEG

BACKGROUND

Early discrimination and prediction of cognitive decline are crucial for the study of neurodegenerative mechanisms and interventions to promote cognitive resiliency.

METHODS

Our research is based on resting-state electroencephalography (EEG) and the current dataset includes 137 consensus-diagnosed, community-dwelling Black Americans (ages 60-90 years, 84 healthy controls [HC]; 53 mild cognitive impairment [MCI]) recruited through Wayne State University and Michigan Alzheimer's Disease Research Center. We conducted multiscale analysis on time-varying brain functional connectivity and developed an innovative soft discrimination model in which each decision on HC or MCI also comes with a connectivity-based score.

RESULTS

The leave-one-out cross-validation accuracy is 91.97% and 3-fold accuracy is 91.17%. The 9 to 18 months' progression trend prediction accuracy over an availability-limited subset sample is 84.61%.

CONCLUSION

The EEG-based soft discrimination model demonstrates high sensitivity and reliability for MCI detection and shows promising capability in proactive prediction of people at risk of MCI before clinical symptoms may occur.

PET-validated EEG-machine learning algorithm predicts brain amyloid pathology in pre-dementia Alzheimer's disease

Developing reliable biomarkers is important for screening Alzheimer's disease (AD) and monitoring its progression. Although EEG is non-invasive direct measurement of brain neural activity and has potentials for various neurologic disorders, vulnerability to noise, difficulty in clinical interpretation and quantification of signal information have limited its clinical application. There have been many research about machine learning (ML) adoption with EEG, but the accuracy of detecting AD is not so high or not validated with Aβ PET scan. We developed EEG-ML algorithm to detect brain Aβ pathology among subjective cognitive decline (SCD) or mild cognitive impairment (MCI) population, and validated it with Aβ PET. 19-channel resting-state EEG and Aβ PET were collected from 311 subjects: 196 SCD(36 Aβ +, 160 Aβ -), 115 MCI(54 Aβ +, 61Aβ -). 235 EEG data were used for training ML, and 76 for validation. EEG features were standardized for age and sex. Multiple important features sets were selected by 6 statistics analysis. Then, we trained 8 multiple machine learning for each important features set. Meanwhile, we conducted paired t-test to find statistically different features between amyloid positive and negative group. The best model showed 90.9% sensitivity, 76.7% specificity and 82.9% accuracy in MCI + SCD (33 Aβ +, 43 Aβ -). Limited to SCD, 92.3% sensitivity, 75.0% specificity, 81.1% accuracy (13 Aβ +, 24 Aβ -). 90% sensitivity, 78.9% specificity and 84.6% accuracy for MCI (20 Aβ +, 19 Aβ -). Similar trends of EEG power have been observed from the group comparison between Aβ + and Aβ -, and between MCI and SCD: enhancement of frontal/ frontotemporal theta; attenuation of mid-beta in centroparietal areas. The present findings suggest that accurate classification for beta-amyloid accumulation in the brain based on QEEG alone could be possible, which implies that QEEG is a promising biomarker for beta-amyloid. Since QEEG is more accessible, cost-effective, and safer than amyloid PET, QEEG-based biomarkers may play an important role in the diagnosis and treatment of AD. We expect specific patterns in QEEG could play an important role to predict future progression of cognitive impairment in the preclinical stage of AD. Further feature engineering and validation with larger dataset is recommended.

Primate brain pattern-based automated Alzheimer's disease detection model using EEG signals

Electroencephalography (EEG) may detect early changes in Alzheimer's disease (AD), a debilitating progressive neurodegenerative disease. We have developed an automated AD detection model using a novel directed graph for local texture feature extraction with EEG signals. The proposed graph was created from a topological map of the macroscopic connectome, i.e., neuronal pathways linking anatomo-functional brain segments involved in visual object recognition and motor response in the primate brain. This primate brain pattern (PBP)-based model was tested on a public AD EEG signal dataset. The dataset comprised 16-channel EEG signal recordings of 12 AD patients and 11 healthy controls. While PBP could generate 448 low-level features per one-dimensional EEG signal, combining it with tunable q-factor wavelet transform created a multilevel feature extractor (which mimicked deep models) to generate 8,512 (= 448 × 19) features per signal input. Iterative neighborhood component analysis was used to choose the most discriminative features (the number of optimal features varied among the individual EEG channels) to feed to a weighted k-nearest neighbor (KNN) classifier for binary classification into AD vs. healthy using both leave-one subject-out (LOSO) and tenfold cross-validations. Iterative majority voting was used to compute subject-level general performance results from the individual channel classification outputs. Channel-wise, as well as subject-level general results demonstrated exemplary performance. In addition, the model attained 100% and 92.01% accuracy for AD vs. healthy classification using the KNN classifier with tenfold and LOSO cross-validations, respectively. Our developed multilevel PBP-based model extracted discriminative features from EEG signals and paved the way for further development of models inspired by the brain connectome.

Deep learning-based EEG analysis to classify normal, mild cognitive impairment, and dementia: algorithms and dataset

For automatic EEG diagnosis, this paper presents a new EEG data set with well-organized clinical annotations called Chung-Ang University Hospital EEG (CAUEEG), which has event history, patient's age, and corresponding diagnosis labels. We also designed two reliable evaluation tasks for the low-cost, non-invasive diagnosis to detect brain disorders: i) CAUEEG-Dementia with normal, mci, and dementia diagnostic labels and ii) CAUEEG-Abnormal with normal and abnormal. Based on the CAUEEG dataset, this paper proposes a new fully end-to-end deep learning model, called the CAUEEG End-to-end Deep neural Network (CEEDNet). CEEDNet pursues to bring all the functional elements for the EEG analysis in a seamless learnable fashion while restraining non-essential human intervention. Extensive experiments showed that our CEEDNet significantly improves the accuracy compared with existing methods, such as machine learning methods and Ieracitano-CNN (Ieracitano et al., 2019), due to taking full advantage of end-to-end learning. The high ROC-AUC scores of 0.9 on CAUEEG-Dementia and 0.86 on CAUEEG-Abnormal recorded by our CEEDNet models demonstrate that our method can lead potential patients to early diagnosis through automatic screening.

Neural biomarker diagnosis and prediction to mild cognitive impairment and Alzheimer's disease using EEG technology

BACKGROUND

Electroencephalogram (EEG) has emerged as a non-invasive tool to detect the aberrant neuronal activity related to different stages of Alzheimer's disease (AD). However, the effectiveness of EEG in the precise diagnosis and assessment of AD and its preclinical stage, amnestic mild cognitive impairment (MCI), has yet to be fully elucidated. In this study, we aimed to identify key EEG biomarkers that are effective in distinguishing patients at the early stage of AD and monitoring the progression of AD.

METHODS

A total of 890 participants, including 189 patients with MCI, 330 patients with AD, 125 patients with other dementias (frontotemporal dementia, dementia with Lewy bodies, and vascular cognitive impairment), and 246 healthy controls (HC) were enrolled. Biomarkers were extracted from resting-state EEG recordings for a three-level classification of HC, MCI, and AD. The optimal EEG biomarkers were then identified based on the classification performance. Random forest regression was used to train a series of models by combining participants' EEG biomarkers, demographic information (i.e., sex, age), CSF biomarkers, and APOE phenotype for assessing the disease progression and individual's cognitive function.

RESULTS

The identified EEG biomarkers achieved over 70% accuracy in the three-level classification of HC, MCI, and AD. Among all six groups, the most prominent effects of AD-linked neurodegeneration on EEG metrics were localized at parieto-occipital regions. In the cross-validation predictive analyses, the optimal EEG features were more effective than the CSF + APOE biomarkers in predicting the age of onset and disease course, whereas the combination of EEG + CSF + APOE measures achieved the best performance for all targets of prediction.

CONCLUSIONS

Our study indicates that EEG can be used as a useful screening tool for the diagnosis and disease progression evaluation of MCI and AD.

Selection of the optimal channel configuration for implementing wearable EEG devices for the diagnosis of mild cognitive impairment

Background

Early diagnosis of mild cognitive impairment (MCI) is essential for timely treatment planning. With recent advances in the wearable technology, interest has increasingly shifted toward computer-aided self-diagnosis of MCI using wearable electroencephalography (EEG) devices in daily life. However, no study so far has investigated the optimal electrode configurations for the efficient diagnosis of MCI while considering the design factors of wearable EEG devices. In this study, we aimed to determine the optimal channel configurations of wearable EEG devices for the computer-aided diagnosis of MCI.

Method

We employed an EEG dataset collected from 21 patients with MCI and 21 healthy control subjects. After evaluating the classification accuracies for all possible electrode configurations for the two-, four-, six-, and eight-electrode conditions using a support vector machine, the optimal electrode configurations that provide the highest diagnostic accuracy were suggested for each electrode condition.

Results

The highest classification accuracies of 74.04% ± 4.82, 82.43% ± 6.14, 86.28% ± 2.81, and 86.85% ± 4.97 were achieved for the optimal two-, four-, six-, and eight-electrode configurations, respectively, which demonstrated the possibility of precise machine-learning-based diagnosis of MCI with a limited number of EEG electrodes. Additionally, further simulations with the EEG dataset revealed that the optimal electrode configurations had significantly higher classification accuracies than commercial EEG devices with the same number of electrodes, which suggested the importance of electrode configuration optimization for wearable EEG devices based on clinical EEG datasets.

Conclusions

This study highlighted that the optimization of the electrode configuration, assuming the wearable EEG devices can potentially be utilized for daily life monitoring of MCI, is necessary to enhance the performance and portability.

Automatic Diagnosis of Mild Cognitive Impairment Based on Spectral, Functional Connectivity, and Nonlinear EEG-Based Features

Accurate and early diagnosis of mild cognitive impairment (MCI) is necessary to prevent the progress of Alzheimer's and other kinds of dementia. Unfortunately, the symptoms of MCI are complicated and may often be misinterpreted as those associated with the normal ageing process. To address this issue, many studies have proposed application of machine learning techniques for early MCI diagnosis based on electroencephalography (EEG). In this study, a machine learning framework for MCI diagnosis is proposed in this study, which extracts spectral, functional connectivity, and nonlinear features from EEG signals. The sequential backward feature selection (SBFS) algorithm is used to select the best subset of features. Several classification models and different combinations of feature sets are measured to identify the best ones for the proposed framework. A dataset of 16 and 18 EEG data of normal and MCI subjects is used to validate the proposed system. Metrics including accuracy (AC), sensitivity (SE), specificity (SP), F1-score (F1), and false discovery rate (FDR) are evaluated using 10-fold crossvalidation. An average AC of 99.4%, SE of 98.8%, SP of 100%, F1 of 99.4%, and FDR of 0% have been provided by the best performance of the proposed framework using the linear support vector machine (LSVM) classifier and the combination of all feature sets. The acquired results confirm that the proposed framework provides an accurate and robust performance for recognizing MCI cases and outperforms previous approaches. Based on the obtained results, it is possible to be developed in order to use as a computer-aided diagnosis (CAD) tool for clinical purposes.

An Automated Approach for the Detection of Alzheimer's Disease From Resting State Electroencephalography

Early detection is crucial to control the progression of Alzheimer's disease and to postpone intellectual decline. Most current detection techniques are costly, inaccessible, or invasive. Furthermore, they require laborious analysis, what delays the start of medical treatment. To overcome this, researchers have recently investigated AD detection based on electroencephalography, a non-invasive neurophysiology technique, and machine learning algorithms. However, these approaches typically rely on manual procedures such as visual inspection, that requires additional personnel for the analysis, or on cumbersome EEG acquisition systems. In this paper, we performed a preliminary evaluation of a fully-automated approach for AD detection based on a commercial EEG acquisition system and an automated classification pipeline. For this purpose, we recorded the resting state brain activity of 26 participants from three groups: mild AD, mild cognitive impairment (MCI-non-AD), and healthy controls. First, we applied automated data-driven algorithms to reject EEG artifacts. Then, we obtained spectral, complexity, and entropy features from the preprocessed EEG segments. Finally, we assessed two binary classification problems: mild AD vs. controls, and MCI-non-AD vs. controls, through leave-one-subject-out cross-validation. The preliminary results that we obtained are comparable to the best reported in literature, what suggests that AD detection could be automatically detected through automated processing and commercial EEG systems. This is promising, since it may potentially contribute to reducing costs related to AD screening, and to shortening detection times, what may help to advance medical treatment.

A self-driven approach for multi-class discrimination in Alzheimer's disease based on wearable EEG

Early detection is critical to control Alzheimer's disease (AD) progression and postpone cognitive decline. Traditional medical procedures such as magnetic resonance imaging are costly, involve long waiting lists, and require complex analysis. Alternatively, for the past years, researchers have successfully evaluated AD detection approaches based on machine learning and electroencephalography (EEG). Nonetheless, these approaches frequently rely upon manual processing or involve non-portable EEG hardware. These aspects are suboptimal regarding automated diagnosis, since they require additional personnel and hinder portability. In this work, we report the preliminary evaluation of a self-driven AD multi-class discrimination approach based on a commercial EEG acquisition system using sixteen channels. For this purpose, we recorded the EEG of three groups of participants: mild AD, mild cognitive impairment (MCI) non-AD, and controls, and we implemented a self-driven analysis pipeline to discriminate the three groups. First, we applied automated artifact rejection algorithms to the EEG recordings. Then, we extracted power, entropy, and complexity features from the preprocessed epochs. Finally, we evaluated a multi-class classification problem using a multi-layer perceptron through leave-one-subject-out cross-validation. The preliminary results that we obtained are comparable to the best in literature (0.88 F1-score), what suggests that AD can potentially be detected through a self-driven approach based on commercial EEG and machine learning. We believe this work and further research could contribute to opening the door for the detection of AD in a single consultation session, therefore reducing the costs associated to AD screening and potentially advancing medical treatment.

Task-state EEG signal classification for spatial cognitive evaluation based on multi-scale high-density convolutional neural network

In this study, a multi-scale high-density convolutional neural network (MHCNN) classification method for spatial cognitive ability assessment was proposed, aiming at achieving the binary classification of task-state EEG signals before and after spatial cognitive training. Besides, the multi-dimensional conditional mutual information method was used to extract the frequency band features of the EEG data. And the coupling features under the combination of multi-frequency bands were transformed into multi-spectral images. At the same time, the idea of Densenet was introduced to improve the multi-scale convolutional neural network. Firstly, according to the discreteness of multispectral EEG image features, two-scale convolution kernels were used to calculate and learn useful channel and frequency band feature information in multispectral image data. Secondly, to enhance feature propagation and reduce the number of parameters, the dense network was connected after the multi-scale convolutional network, and the learning rate change function of the stochastic gradient descent algorithm was optimized to objectively evaluate the training effect. The experimental results showed that compared with the classical convolution neural network (CNN) and multi-scale convolution neural network, the proposed MHCNN had better classification performance in the six frequency band combinations with the highest accuracy of 98%: Theta-Alpha2-Gamma, Alpha2-Beta2-Gamma, Beta1-Beta2-Gamma, Theta-Beta2-Gamma, Theta-Alpha1-Gamma, and Alpha1-Alpha2-Gamma. By comparing the classification results of six frequency band combinations, it was found that the combination of the Theta-Beta2-Gamma band had the best classification effect. The MHCNN classification method proposed in this research could be used as an effective biological indicator of spatial cognitive training effect and could be extended to other brain function evaluations.

Sharpening Working Memory With Real-Time Electrophysiological Brain Signals: Which Neurofeedback Paradigms Work?

Growing evidence supports the idea that the ultimate biofeedback is to reward sensory pleasure (e.g., enhanced visual clarity) in real-time to neural circuits that are associated with a desired performance, such as excellent memory retrieval. Neurofeedback is biofeedback that uses real-time sensory reward to brain activity associated with a certain performance (e.g., accurate and fast recall). Working memory is a key component of human intelligence. The challenges are in our current limited understanding of neurocognitive dysfunctions as well as in technical difficulties for closed-loop feedback in true real-time. Here we review recent advancements of real time neurofeedback to improve memory training in healthy young and older adults. With new advancements in neuromarkers of specific neurophysiological functions, neurofeedback training should be better targeted beyond a single frequency approach to include frequency interactions and event-related potentials. Our review confirms the positive trend that neurofeedback training mostly works to improve memory and cognition to some extent in most studies. Yet, the training typically takes multiple weeks with 2-3 sessions per week. We review various neurofeedback reward strategies and outcome measures. A well-known issue in such training is that some people simply do not respond to neurofeedback. Thus, we also review the literature of individual differences in psychological factors e.g., placebo effects and so-called "BCI illiteracy" (Brain Computer Interface illiteracy). We recommend the use of Neural modulation sensitivity or BCI insensitivity in the neurofeedback literature. Future directions include much needed research in mild cognitive impairment, in non-Alzheimer's dementia populations, and neurofeedback using EEG features during resting and sleep for memory enhancement and as sensitive outcome measures.

Shoulder electromyography-based indicators to assess manifestation of muscle fatigue during laboratory-simulated manual handling task

Muscle fatigue is a risk factor for developing shoulder musculoskeletal disorders. The aim of this study was to identify shoulder electromyographic indicators that are most indicative of muscle fatigue during a laboratory simulated manual handling task. Thirty-two participants were equipped with electromyographic electrodes on 10 shoulder muscles and moved boxes for 45-minutes. The modified rate of perceived exertion (mRPE) was assessed every 5-minutes and multivariate linear regressions were performed between myoelectric manifestation of fatigue (MMF) and the mRPE scores. During a manual handling task representative of industry working conditions, spectral entropy, median frequency, and mobility were the electromyographic indicators that explained the largest percentage of the mRPE. Overall, the deltoids, biceps and upper trapezius were the muscles that most often showed significant changes over time in their electromyographic indicators. The combination of these three indicators may improve the accuracy for the assessment of MMF during manual handling. Practitioner Summary: To date, muscle fatigue has primarily been assessed during tasks done to exhaustion, which are not representative of typical working conditions. During a manual handling task representative of industry working conditions, EMG-derived spectral entropy, and median frequency, both extracted from time-frequency analysis, and mobility extracted from time domain, were the best indicators of the manifestation of muscle fatigue.

Deep Transfer Learning for Parkinson’s Disease Monitoring by Image-Based Representation of Resting-State EEG Using Directional Connectivity

Parkinson’s disease (PD) is characterized by abnormal brain oscillations that can change rapidly. Tracking neural alternations with high temporal resolution electrophysiological monitoring methods such as EEG can lead to valuable information about alterations observed in PD. Concomitantly, there have been advances in the high-accuracy performance of deep neural networks (DNNs) using few-patient data. In this study, we propose a method to transform resting-state EEG data into a deep latent space to classify PD subjects from healthy cases. We first used a general orthogonalized directed coherence (gOPDC) method to compute directional connectivity (DC) between all pairwise EEG channels in four frequency bands (Theta, Alpha, Beta, and Gamma) and then converted the DC maps into 2D images. We then used the VGG-16 architecture (trained on the ImageNet dataset) as our pre-trained model, enlisted weights of convolutional layers as initial weights, and fine-tuned all layer weights with our data. After training, the classification achieved 99.62% accuracy, 100% precision, 99.17% recall, 0.9958 F1 score, and 0.9958 AUC averaged for 10 random repetitions of training/evaluating on the proposed deep transfer learning (DTL) network. Using the latent features learned by the network and employing LASSO regression, we found that latent features (as opposed to the raw DC values) were significantly correlated with five clinical indices routinely measured: left and right finger tapping, left and right tremor, and body bradykinesia. Our results demonstrate the power of transfer learning and latent space derivation for the development of oscillatory biomarkers in PD.

The diagnosis of amnestic mild cognitive impairment by combining the characteristics of brain functional network and support vector machine classifier

BACKGROUND

Amnestic mild cognitive impairment (aMCI) is an essential stage of early detection and potential intervention for Alzheimer's disease (AD). Patients with aMCI exhibit partially abnormal functional brain connectivity and it is suggested that these features may represent a new diagnostic marker of early AD.

NEW METHOD

In this paper, we constructed two brain network models, a phase synchronization index (PSI) undirected network and a directed transfer function (DTF) directed network, to evaluate the cognitive function in patients with aMCI. We then built SVM classification models using the network clustering coefficient, global efficiency and average node degree as features to distinguish between aMCI patients and controls.

RESULTS

Our results reveal a classification accuracy and AUC of 66.6 ± 1.7% and 0.7475 and 80.0 ± 2.2% and 0.7825, respectively, for the two network models (PSI and DTF). As the directed network model performed better than the undirected model, we introduced an improved graph theory feature, efficiency density, which resulted in an increased classification accuracy and AUC value 86.6 ± 2.6% and 0.8295, respectively.

COMPARISON WITH EXISTING METHODS

The analysis of network models and the directionality of information flow is suitable for analysis of nonlinear EEG signals for assessment of the functional state of the brain. Compared with traditional network features, our proposed improved features more comprehensively evaluate transmission efficiency and density of the brain.

CONCLUSION

In this study, we demonstrate that an improved efficiency density feature is helpful for enhancing classification the accuracy of aMCI. Moreover, directed brain network models exhibit better classification for aMCI diagnosis than undirected networks.

Characteristics of Resting State EEG Power in 80+-Year-Olds of Different Cognitive Status

Compared with healthy older adults, patients with Alzheimer's disease show decreased alpha and beta power as well as increased delta and theta power during resting state electroencephalography (rsEEG). Findings for mild cognitive impairment (MCI), a stage of increased risk of conversion to dementia, are less conclusive. Cognitive status of 213 non-demented high-agers (mean age, 82.5 years) was classified according to a neuropsychological screening and a cognitive test battery. RsEEG was measured with eyes closed and open, and absolute power in delta, theta, alpha, and beta bands were calculated for nine regions. Results indicate no rsEEG power differences between healthy individuals and those with MCI. There were also no differences present between groups in EEG reactivity, the change in power from eyes closed to eyes open, or the topographical pattern of each frequency band. Overall, EEG reactivity was preserved in 80+-year-olds without dementia, and topographical patterns were described for each frequency band. The application of rsEEG power as a marker for the early detection of dementia might be less conclusive for high-agers.

Robust EEG Based Biomarkers to Detect Alzheimer's Disease

Biomarkers to detect Alzheimer's disease (AD) would enable patients to gain access to appropriate services and may facilitate the development of new therapies. Given the large numbers of people affected by AD, there is a need for a low-cost, easy to use method to detect AD patients. Potentially, the electroencephalogram (EEG) can play a valuable role in this, but at present no single EEG biomarker is robust enough for use in practice. This study aims to provide a methodological framework for the development of robust EEG biomarkers to detect AD with a clinically acceptable performance by exploiting the combined strengths of key biomarkers. A large number of existing and novel EEG biomarkers associated with slowing of EEG, reduction in EEG complexity and decrease in EEG connectivity were investigated. Support vector machine and linear discriminate analysis methods were used to find the best combination of the EEG biomarkers to detect AD with significant performance. A total of 325,567 EEG biomarkers were investigated, and a panel of six biomarkers was identified and used to create a diagnostic model with high performance (≥85% for sensitivity and 100% for specificity).

Complexity of EEG Dynamics for Early Diagnosis of Alzheimer's Disease Using Permutation Entropy Neuromarker

BACKGROUND AND OBJECTIVE

Electroencephalogram (EEG) is one of the most demanded screening tools that investigates the effects of Alzheimer's Disease (AD) on human brain. Identification of AD in early stage gives rise to efficient treatment in dementia. Mild Cognitive Impairment (MCI) is considered as a conversion stage. Reducing EEG complexity can be used as a marker to detect AD. The aim of this study is to develop a 3-way diagnostic classification using EEG complexity in the detection of MCI/AD in clinical practice. This study also investigates the effects of different eyes states, i.e. eyes-open, eyes-closed on classification performance.

METHODS

EEG recordings from 85 AD, 85 MCI subjects, and 85 Healthy Controls with eyes-open and eyes- closed are analyzed. Permutation Entropy (PE) values are computed from frontal, central, parietal, temporal, and occipital regions for each EEG epoch. Distribution of PE values are visualized to observe discrimination of MCI/AD with HC. Visual investigations are combined with statistical analysis using ANOVA to determine whether groups are significant or not. Multinomial Logistic Regression model is applied to feature sets in order to classify participants individually.

RESULTS

Distribution of measured PE shows that EEG complexity is lower in AD and higher in HC group. MCI group is observed as an intermediate form due to heterogeneous values. Results from 3-way classification indicate that F1-scores and rates of sensitivity and specificity achieve the highest overall discrimination rates reaching up to 100% for at TP8 for eyes-closed condition; and C3, C4, T8, O2 electrodes for eyes-open condition. Classification of HC from both patient groups is achieved best. Eyes-open state increases discrimination of MCI and AD.

CONCLUSIONS

This nonlinear EEG methodology study contributes to literature with high discrimination rates for identification of AD. PE is recommended as a practical diagnostic neuro-marker for AD studies. Resting state EEG at eyes-open condition can be more advantageous over eyes-closed EEG recordings for diagnosis of AD.

Frontoparietal network and neuropsychological measures in typically developing children

Resting-state activity has been used to gain a broader understanding of typical and aberrant developmental changes. However, the developmental trajectory of resting-state activity in relation to cognitive performance has not been studied in detail. The present study assessed spectral characteristics of theta (5-8 Hz) and alpha (9-13 Hz) frequency bands during resting-state in a priori selected regions of the frontoparietal network (FPN). We also examined the relationship between resting-state activity and cognitive performance in typically developing children. We hypothesized that older children and children with high attentional scores would have higher parietal alpha activity and frontal theta activity while at rest compared to young children and those with lower attentional scores. MEG data were collected in 65 typically developing children, ages 9-14 years, as part of the Developmental Chronnecto-Genomics study. Resting-state data were collected during eyes open and eyes closed for 5 min. Participants completed the NIH Toolbox Flanker Inhibitory Control (FICA) and Attention Test and Dimensional Change Card Sort Test (DCCS) to assess top-down attentional control. Spectral power density was used to characterize the FPN. We found during eyes open and eyes closed, all participants had higher theta and alpha power in parietal regions relative to frontal regions. The group with high attentional scores had higher alpha power during resting-state eyes closed compared to those with low attentional scores. However, there were no significant differences between age groups, suggesting changes in the maturation of neural oscillations in theta and alpha are not evident among children in the 9-14-year age range.

Interval-based features of auditory ERPs for diagnosis of early Alzheimer's disease

INTRODUCTION

It has been demonstrated that event-related potentials (ERPs) mirror the neurodegenerative process of Alzheimer's disease (AD) and may therefore qualify as diagnostic markers. The aim of this study was to explore the potential of interval-based features as possible ERP biomarkers for early detection of AD patients.

METHODS

The current results are based on 7-channel ERP recordings of 95 healthy controls (HCs) and 75 subjects with mild AD acquired during a three-stimulus auditory oddball task. To evaluate interval-based features as diagnostic biomarkers in AD, two classifiers were applied to the selected features to distinguish AD and healthy control ERPs: RBFNN (radial basis function neural network) and MLP (multilayer perceptron).

RESULTS

Using extracted features and a radial basis function neural network, a high overall diagnostic accuracy of 98.3% was achieved.

DISCUSSION

Our findings demonstrate the great promise for scalp ERP and interval-based features as non-invasive, objective, and low-cost biomarkers for early AD detection.

A Review of Automated Techniques for Assisting the Early Detection of Alzheimer's Disease with a Focus on EEG

In this paper, we review state-of-the-art approaches that apply signal processing (SP) and machine learning (ML) to automate the detection of Alzheimer's disease (AD) and its prodromal stages. In the first part of the document, we describe the economic and social implications of the disease, traditional diagnosis techniques, and the fundaments of automated AD detection. Then, we present electroencephalography (EEG) as an appropriate alternative for the early detection of AD, owing to its reduced cost, portability, and non-invasiveness. We also describe the main time and frequency domain EEG features that are employed in AD detection. Subsequently, we examine some of the main studies of the last decade that aim to provide an automatic detection of AD and its previous stages by means of SP and ML. In these studies, brain data was acquired using multiple medical techniques such as magnetic resonance imaging, positron emission tomography, and EEG. The main aspects of each approach, namely feature extraction, classification model, validation approach, and performance metrics, are compiled and discussed. Lastly, a set of conclusions and recommendations for future research on AD automatic detection are drawn in the final section of the paper.

Past, Present, and Future of Non-invasive Brain Stimulation Approaches to Treat Cognitive Impairment in Neurodegenerative Diseases: Time for a Comprehensive Critical Review

Low birth rates and increasing life expectancy experienced by developed societies have placed an unprecedented pressure on governments and the health system to deal effectively with the human, social and financial burden associated to aging-related diseases. At present, ∼24 million people worldwide suffer from cognitive neurodegenerative diseases, a prevalence that doubles every five years. Pharmacological therapies and cognitive training/rehabilitation have generated temporary hope and, occasionally, proof of mild relief. Nonetheless, these approaches are yet to demonstrate a meaningful therapeutic impact and changes in prognosis. We here review evidence gathered for nearly a decade on non-invasive brain stimulation (NIBS), a less known therapeutic strategy aiming to limit cognitive decline associated with neurodegenerative conditions. Transcranial Magnetic Stimulation and Transcranial Direct Current Stimulation, two of the most popular NIBS technologies, use electrical fields generated non-invasively in the brain to long-lastingly enhance the excitability/activity of key brain regions contributing to relevant cognitive processes. The current comprehensive critical review presents proof-of-concept evidence and meaningful cognitive outcomes of NIBS in eight of the most prevalent neurodegenerative pathologies affecting cognition: Alzheimer's Disease, Parkinson's Disease, Dementia with Lewy Bodies, Primary Progressive Aphasias (PPA), behavioral variant of Frontotemporal Dementia, Corticobasal Syndrome, Progressive Supranuclear Palsy, and Posterior Cortical Atrophy. We analyzed a total of 70 internationally published studies: 33 focusing on Alzheimer's disease, 19 on PPA and 18 on the remaining neurodegenerative pathologies. The therapeutic benefit and clinical significance of NIBS remains inconclusive, in particular given the lack of a sufficient number of double-blind placebo-controlled randomized clinical trials using multiday stimulation regimes, the heterogeneity of the protocols, and adequate behavioral and neuroimaging response biomarkers, able to show lasting effects and an impact on prognosis. The field remains promising but, to make further progress, research efforts need to take in account the latest evidence of the anatomical and neurophysiological features underlying cognitive deficits in these patient populations. Moreover, as the development of in vivo biomarkers are ongoing, allowing for an early diagnosis of these neuro-cognitive conditions, one could consider a scenario in which NIBS treatment will be personalized and made part of a cognitive rehabilitation program, or useful as a potential adjunct to drug therapies since the earliest stages of suh diseases. Research should also integrate novel knowledge on the mechanisms and constraints guiding the impact of electrical and magnetic fields on cerebral tissues and brain activity, and incorporate the principles of information-based neurostimulation.

A new method to build multiplex networks using Canonical Correlation Analysis for the characterization of the Alzheimer's disease continuum

OBJECTIVE

The aim of this study was to solve one of the current limitations for the characterization of the brain network in the Alzheimer's disease (AD) continuum. Nowadays, frequency-dependent approaches have reached contradictory results depending on the frequency band under study, tangling the possible clinical interpretations.

APPROACH

To overcome this issue, we proposed a new method to build multiplex networks based on canonical correlation analysis (CCA). Our method determines two basis vectors using the source and electrodelevel frequency-specific network parameters for a reference group, and then project the results for the rest of the groups into these hyperplanes to make them comparable. It was applied to: (i) synthetic signals generated with a Kuramoto-based model; and (ii) a resting-state EEG database formed by recordings from 51 cognitively healthy controls, 51 mild cognitive impairment subjects, 51 mild AD patients, 50 moderate AD patients, and 50 severe AD patients.

MAIN RESULTS

Our results using synthetic signals showed that the interpretation of the proposed CCA-based multiplex parameters (multiplex average node degree, multiplex characteristic path length and multiplex clustering coefficient) can be analogous to their frequency-specific counterparts, as they displayed similar behaviors in terms of average connectivity, integration, and segregation. Findings using real EEG recordings revealed that dementia due to AD is characterized by a significant increase in average connectivity, and by a loss of integration and segregation.

SIGNIFICANCE

We can conclude that CCA can be used to build multiplex networks based from frequency-specific results, summarizing all the available information and avoiding the limitations of possible frequency-specific conflicts. Additionally, our method supposes a novel approach for the construction and analysis of multiplex networks during AD continuum.

A Novel Detection Tool for Mild Cognitive Impairment Patients Based on Eye Movement and Electroencephalogram

BACKGROUND

Detecting subtle changes in visual attention from electroencephalography (EEG) and the perspective of eye movement in mild cognitive impairment (MCI) patients can be of great significance in screening early Alzheimer's disease (AD) in a large population at primary care.

OBJECTIVE

We proposed an automatic, non-invasive, and quick MCI detection approach based on multimodal physiological signals for clinical decision-marking.

METHODS

The proposed model recruited 152 patients with MCI and 184 healthy elderly controls (HC) who underwent EEG and eye movement signal recording under a visual stimuli task, as well as other neuropsychological assessments. Forty features were extracted from EEG and eye movement signals by linear and nonlinear analysis. The features related to MCI were selected by logistic regression analysis. To evaluate the efficacy of this MCI detection approach, we applied the same procedures to achieve the Clinical model, EEG model, Eye movement model, EEG+ Clinical model, Eye movement+ Clinical model, and Combined model, and compared the classification accuracy between the MCI and HC groups with the above six models.

RESULTS

After the penalization of logistic regression analysis, five features from EEG and eye movement features exhibited significant differences (p < 0.05). In the classification experiment, the combined model resulted in the best accuracy. The average accuracy for the Clinical/EEG/Eye movement/EEG+ Clinical/Eye movement+ Clinical/Combined model was 68.69%, 61.79%, 73.13%, 69.46%, 75.61%, and 81.51%, respectively.

CONCLUSION

These results suggest that the proposed MCI detection tool has the potential to screen MCI patients from HCs and may be a powerful tool for personalized precision MCI screening in the large-scale population under primary care condition.

Alpha Power and Functional Connectivity in Cognitive Decline: A Systematic Review and Meta-Analysis

Background:

Mild cognitive impairment (MCI) is a stage between expected age-related cognitive decline and dementia. Dementias have been associated with changes in neural oscillations across the frequency spectrum, including the alpha range. Alpha is the most prominent rhythm in human EEG and is best detected during awake resting state (RS). Though several studies measured alpha power and synchronization in MCI, findings have not yet been integrated.

Objective:

To consolidate findings on power and synchronization of alpha oscillations across stages of cognitive decline.

Methods:

We included studies published until January 2020 that compared power or functional connectivity between 1) people with MCI and cognitively healthy older adults (OA) or people with a neurodegenerative dementia, and 2) people with progressive and stable MCI. Random-effects meta-analyses were performed when enough data was available.

Results:

Sixty-eight studies were included in the review. Global RS alpha power was lower in AD than in MCI (ES = –0.30; 95% CI = –0.51, –0.10; k = 6), and in MCI than in OA (ES = –1.49; 95% CI = –2.69, –0.29; k = 5). However, the latter meta-analysis should be interpreted cautiously due to high heterogeneity. The review showed lower RS alpha power in progressive than in stable MCI, and lower task-related alpha reactivity in MCI than in OA. People with MCI had both lower and higher functional connectivity than OA. Publications lacked consistency in MCI diagnosis and EEG measures.

Conclusion:

Research indicates that RS alpha power decreases with increasing impairment, and could—combined with measures from other frequency bands—become a biomarker of early cognitive decline.

Inter-band Bispectral Analysis of EEG Background Activity to Characterize Alzheimer's Disease Continuum

The aim of this study was to characterize the EEG alterations in inter-band interactions along the Alzheimer's disease (AD) continuum. For this purpose, EEG background activity from 51 healthy control subjects, 51 mild cognitive impairment patients, 50 mild AD patients, 50 moderate AD patients, and 50 severe AD patients was analyzed by means of bispectrum. Three inter-band features were extracted from bispectrum matrices: bispectral relative power (BispRP), cubic bispectral entropy (BispEn), and bispectral median frequency (BispMF). BispRP results showed an increase of delta and theta interactions with other frequency bands and the opposite behavior for alpha, beta-1, and beta-2. Delta and theta interactions, along with the rest of the spectrum, also experimented a decrease of BispEn with disease progression, suggesting these bands interact with a reduced variety of components in advanced stages of dementia. Finally, BispMF showed a consistent reduction along the AD continuum in all bands, which is reflective of an interaction of the global spectrum with lower frequency bands as the disease develops. Our results indicate a progressive decrease in inter-band interactions with the severity of the disease, especially those involving high frequency components. Since inter-band coupling oscillations are related to complex and multi-scaled brain processes, these alterations likely reflect the neurodegeneration associated with the AD continuum.

Changes in electroencephalography complexity and functional magnetic resonance imaging connectivity following robotic hand training in chronic stroke

Introduction: In recent years, robotic training has been utilized for recovery of motor control in patients with motor deficits. Along with clinical assessment, electrical patterns in the brain have emerged as a marker for studying changes in the brain associated with brain injury and rehabilitation. These changes mainly involve an imbalance between the two hemispheres. We aimed to study the effect of brain computer interface (BCI)-based robotic hand training on stroke subjects using clinical assessment, electroencephalographic (EEG) complexity analysis, and functional magnetic resonance imaging (fMRI) connectivity analysis. Method: Resting-state simultaneous EEG-fMRI was conducted on 14 stroke subjects before and after training who underwent 20 sessions robot hand training. Fractal dimension (FD) analysis was used to assess neuronal impairment and functional recovery using the EEG data, and fMRI connectivity analysis was performed to assess changes in the connectivity of brain networks. Results: FD results indicated a significant asymmetric difference between the ipsilesional and contralesional hemispheres before training, which was reduced after robotic hand training. Moreover, a positive correlation between interhemispheric asymmetry change for central brain region and change in Fugl Meyer Assessment (FMA) scores for upper limb was observed. Connectivity results showed a significant difference between pre-training interhemispheric connectivity and post-training interhemispheric connectivity. Moreover, the change in connectivity correlated with the change in FMA scores. Results also indicated a correlation between the increase in connectivity for motor regions and decrease in FD interhemispheric asymmetry for central brain region covering the motor area. Conclusion: In conclusion, robotic hand training significantly facilitated stroke motor recovery, and FD, along with connectivity analysis can detect neuroplasticity changes.

Iterative Filtering Decomposition Based Early Dementia Diagnosis Using EEG With Cognitive Tests

OBJECTIVE

There has been a constant increase in life expectancy with the advancement of modern medicine. Likewise, dementia has also increased and projected to elevate in the coming decades with the higher expenditure on healthcare. Consequently, it is essential to identify early dementia, e.g., a patient suffering from mild cognitive impairment who is highly vulnerable to developing dementia soon.

METHODS

Through this work, we brought forward an approach by fusing cognitive task and EEG signal processing. Continuous EEG of 16 dementia, 16 early dementia and 15 healthy subjects recorded under two resting states; eye open and eye closed, and two cognitive states; finger tapping test (FTT) and the continuous performance test (CPT). The present approach introduced iterative filtering (IF) as a decomposition technique for dementia diagnosis along with four significant EEG features power spectral density, variance, fractal dimension and Tsallis entropy. Multi-class classification conducted to compare the decision tree, k nearest neighbour ( k NN), support vector machine, and ensemble classifiers.

RESULTS

The proposed approach deeply checked for their capability of prediction using cognitive scores and EEG measures. The highest accuracies obtained by k NN with 10-fold cross-validation for dementia, early dementia and healthy are 92.00%, 91.67% and 91.87%, respectively.

CONCLUSION

The essential findings of this study are: 1) Experimental results indicate that k NN is superior over other classifier algorithms for dementia diagnosis. 2) CPT is the best predictor for healthy subjects. 3) FTT can be an essential test to diagnose significant dementia.

SIGNIFICANCE

IF decomposition technique enhances the diagnostic accuracy even with a limited dataset.

A New Framework for Automatic Detection of Patients With Mild Cognitive Impairment Using Resting-State EEG Signals

Mild cognitive impairment (MCI) can be an indicator representing the early stage of Alzheimier's disease (AD). AD, which is the most common form of dementia, is a major public health problem worldwide. Efficient detection of MCI is essential to identify the risks of AD and dementia. Currently Electroencephalography (EEG) is the most popular tool to investigate the presenence of MCI biomarkers. This study aims to develop a new framework that can use EEG data to automatically distinguish MCI patients from healthy control subjects. The proposed framework consists of noise removal (baseline drift and power line interference noises), segmentation, data compression, feature extraction, classification, and performance evaluation. This study introduces Piecewise Aggregate Approximation (PAA) for compressing massive volumes of EEG data for reliable analysis. Permutation entropy (PE) and auto-regressive (AR) model features are investigated to explore whether the changes in EEG signals can effectively distinguish MCI from healthy control subjects. Finally, three models are developed based on three modern machine learning techniques: Extreme Learning Machine (ELM); Support Vector Machine (SVM) and K-Nearest Neighbours (KNN) for the obtained feature sets. Our developed models are tested on a publicly available MCI EEG database and the robustness of our models is evaluated by using a 10-fold cross validation method. The results show that the proposed ELM based method achieves the highest classification accuracy (98.78%) with lower execution time (0.281 seconds) and also outperforms the existing methods. The experimental results suggest that our proposed framework could provide a robust biomarker for efficient detection of MCI patients.

Relationship between the Presence of the ApoE ε4 Allele and EEG Complexity along the Alzheimer's Disease Continuum

Alzheimer's disease (AD) is the most prevalent cause of dementia, being considered a major health problem, especially in developed countries. Late-onset AD is the most common form of the disease, with symptoms appearing after 65 years old. Genetic determinants of AD risk are vastly unknown, though, ε 4 allele of the ApoE gene has been reported as the strongest genetic risk factor for AD. The objective of this study was to analyze the relationship between brain complexity and the presence of ApoE ε 4 alleles along the AD continuum. For this purpose, resting-state electroencephalography (EEG) activity was analyzed by computing Lempel-Ziv complexity (LZC) from 46 healthy control subjects, 49 mild cognitive impairment subjects, 45 mild AD patients, 44 moderate AD patients and 33 severe AD patients, subdivided by ApoE status. Subjects with one or more ApoE ε 4 alleles were included in the carriers subgroups, whereas the ApoE ε 4 non-carriers subgroups were formed by subjects without any ε 4 allele. Our results showed that AD continuum is characterized by a progressive complexity loss. No differences were observed between AD ApoE ε 4 carriers and non-carriers. However, brain activity from healthy subjects with ApoE ε 4 allele (carriers subgroup) is more complex than from non-carriers, mainly in left temporal, frontal and posterior regions (p-values < 0.05, FDR-corrected Mann-Whitney U-test). These results suggest that the presence of ApoE ε 4 allele could modify the EEG complexity patterns in different brain regions, as the temporal lobes. These alterations might be related to anatomical changes associated to neurodegeneration, increasing the risk of suffering dementia due to AD before its clinical onset. This interesting finding might help to advance in the development of new tools for early AD diagnosis.

Feature Classification Method of Resting-State EEG Signals From Amnestic Mild Cognitive Impairment With Type 2 Diabetes Mellitus Based on Multi-View Convolutional Neural Network

The convolutional neural network (CNN) model is an active research topic in the field of EEG signals analysis. However, the classification effect of CNN on EEG signals of amnestic mild cognitive impairment (aMCI) with type 2 diabetes mellitus (T2DM) is not ideal. Even if EEG signals are transformed into multispectral images that are more closely matched with the model, the best classification performance can not be achieved. Therefore, to improve the performance of CNN toward EEG multispectral image classification, a multi-view convolutional neural network (MVCNN) classification model based on inceptionV1 is designed in this study. This model mainly improves and optimizes the convolutional layers and stochastic gradient descent (SGD) in the convolutional architecture model. Firstly, based on the discreteness of EEG multispectral image features, the multi-view convolutional layer structure was proposed. Then the learning rate change function of the SGD was optimized to increase the classification performance. The multi-view convolutional nerve was used in an EEG multispectral classification task involving 19 aMCI with T2DM and 20 normal controls. The results showed that compared with the traditional classification models, MVCNN had a better stability and accuracy. Therefore, MVCNN could be used as an effective feature classification method for aMCI with T2DM.

Resting-state EEG signal classification of amnestic mild cognitive impairment with type 2 diabetes mellitus based on multispectral image and convolutional neural network

OBJECTIVE

The purpose of this study is to judge whether this combination method of multispectral image and convolutional neural network (CNN) method can be used to distinguish amnestic mild cognitive impairment (aMCI) with Type 2 diabetes mellitus (T2DM) and normal controls (NC) with T2DM effectively.

APPROACH

In this study, the authors first combined EEG signals from aMCI patients with T2DM and NC with T2DM on five different frequency bands, including Theta, Alpha1, Alpha2, Beta1, and Beta2. Then, the authors converted these time series into a series of multispectral images. Finally, the images data were classified with the CNN method.

MAIN RESULTS

The classification effects of up to 89%, 91%, and 92% are obtained on the three combinations of frequency bands: Theta, Alpha1, and Alpha2; Alpha1, Alpha2, and Beta1; and Alpha2, Beta1, and Beta2. The spatial properties of EEG signals are highlighted, and its classification performance is found to be better than all the previous methods in the field of aMCI and T2DM diagnosis. The combination of multispectral images and CNN can be used as an effective biomarker for distinguishing the EEG signals in patients with aMCI and T2DM and in patients with NC with T2DM.

SIGNIFICANCE

The combined approach used in this paper provides a new perspective for the analysis of EEG signals in patients with aMCI and T2DM.

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

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.