Systematic Review on Resting-State EEG for Alzheimer's Disease Diagnosis and Progression Assessment

Chronic effects of tobacco smoking on electrical brain activity: A systematic review on electroencephalography studies

Despite significant strides in reducing smoking prevalence globally, tobacco use remains a leading contributor to ill health and premature death worldwide. While the detrimental impacts of smoking on various organs are well-established, its specific effects on nervous system function remain an area of ongoing investigation. This systematic review delves into the neurobiological effects of smoking, particularly through the lens of resting-state electroencephalography (EEG). A systematic search was conducted in May 2024 in PubMed, Embase, and Web of Science databases, and all available evidence comparing resting-state EEG findings between smokers and non-smokers was assessed. The 13 included studies investigated a total of 684 participants, with a median female percentage of of 25 % (range: 0-100), and the age of participants ranged from 18 to approximately 73 years. Alterations in the alpha band were the most prevalent findings observed in the EEG of smokers compared to non-smokers, observed in 8 studies, suggesting changes in the attention and cognitive functions of smokers. However, findings regarding the specific direction and location of changes were not consistent. Additionally, changes in delta, theta, and beta bands were identified on a less frequent basis. There was evidence suggesting that the observed neural oscillation changes are influenced by various factors, including the number of cigarettes used, pack years of smoking, age of smoking initiation, and smoking cessation status. These findings underscore the multifaceted nature of the impact of smoking on brain activity, especially on cognition and the attentional system.

Intra- and Inter-Regional Complexity in Multi-Channel Awake EEG Through Multivariate Multiscale Dispersion Entropy for Assessing Sleep Quality and Aging

Aging and poor sleep quality are associated with altered brain dynamics, yet current electroencephalography (EEG) analyses often overlook regional complexity. This study addresses this gap by introducing a novel integration of intra- and inter-regional complexity analysis using multivariate multiscale dispersion entropy (mvMDE) from awake resting-state EEG for the first time. Moreover, assessing both intra- and inter-regional complexity provides a comprehensive perspective on the dynamic interplay between localized neural activity and its coordination across brain regions, which is essential for understanding the neural substrates of aging and sleep quality. Data from 58 participants-24 young adults (mean age = 24.7 ± 3.4) and 34 older adults (mean age = 72.9 ± 4.2)-were analyzed, with each age group further divided based on Pittsburgh Sleep Quality Index (PSQI) scores. To capture inter-regional complexity, mvMDE was applied to the most informative group of sensors, with one sensor selected from each brain region using four methods: highest average correlation, highest entropy, highest mutual information, and highest principal component loading. This targeted approach reduced computational cost and enhanced the effect sizes (ESs), particularly at large scale factors (e.g., 25) linked to delta-band activity, with the PCA-based method achieving the highest ESs (1.043 for sleep quality in older adults). Overall, we expect that both inter- and intra-regional complexity will play a pivotal role in elucidating neural mechanisms as captured by various physiological data modalities-such as EEG, magnetoencephalography, and magnetic resonance imaging-thereby offering promising insights for a range of biomedical applications.

Exploring the neuromagnetic signatures of cognitive decline from mild cognitive impairment to Alzheimer's disease dementia

BACKGROUND

Developing non-invasive and affordable biomarkers to detect Alzheimer's disease (AD) at a prodromal stage is essential, particularly in the context of new disease-modifying therapies. Mild cognitive impairment (MCI) is a critical stage preceding dementia, but not all patients with MCI will progress to AD. This study explores the potential of magnetoencephalography (MEG) to predict cognitive decline from MCI to AD dementia.

METHODS

We analysed resting-state MEG data from the BioFIND dataset including 117 patients with MCI among whom 64 developed AD dementia (AD progression), while 53 remained cognitively stable (stable MCI), using spectral analysis. Logistic regression models estimated the additive explanation of selected clinical, MEG, and MRI variables for AD progression risk. We then built a high-dimensional classification model to combine all modalities and variables of interest.

FINDINGS

MEG 16-38Hz spectral power, particularly over parieto-occipital magnetometers, was significantly reduced in the AD progression group. In logistic regression models, decreased MEG 16-38Hz spectral power and reduced hippocampal volume/total grey matter ratio on MRI were independently linked to higher AD progression risk. The data-driven classification model confirmed, among other factors, the complementary information of MEG covariance (AUC = 0.74, SD = 0.13) and MRI cortical volumes (AUC = 0.77, SD = 0.14) to predict AD progression. Combining all inputs led to markedly improved classification scores (AUC = 0.81, SD = 0.12).

INTERPRETATION

These findings highlight the potential of spectral power and covariance as robust non-invasive electrophysiological biomarkers to predict AD progression, complementing other diagnostic measures, including cognitive scores and MRI.

FUNDING

This work was supported by: Fondation pour la Recherche Médicale (grant FDM202106013579).

Modulated theta band frequency with binaural beat stimulation correlates with improved cognitive scores in Alzheimer's patients

Introduction

Alzheimer's disease (AD) affects 50 million individuals worldwide, a number projected to triple by 2050. Due to discomfort through electrical and magnetic neuromodulation technologies, this is the first study to propose the potential of auditory binaural beat (BB) stimulation at an alpha frequency (10 Hz) for enhancing cognitive and neurological outcomes in AD patients.

Methods

Twenty-five patients were divided into the experimental-Group (n = 15) and control-Group (n = 10). Psychometric and neurological assessments were conducted Pre-Treatment (Day 1) and Post-Treatment (Day 14) following consecutive days of binaural beats (BB) or auditory tone stimulation administered from Day 2 to Day 13.

Results

A two-way ANOVA revealed a significant main effect of group (F = 6.087, p = 0.016) and session (F = 3.859, p = 0.024) on MMSE scores, with the experimental group showing significant improvement in MMSE scores (t = 7.33, p = 0.00000012) compared to the control group (p = 0.2306). Paired t-tests revealed a significant reduction in depression scores (DASS-21, t = 1.701, p = 0.0253) in the experimental group, while no significant improvements were noted in the control group. EEG recordings revealed significant changes in α-band, β-band, and γ-band power (p < 0.05). Moreover, The correlation between EEG bands and MMSE subparts showed that increased θ-band power in the experimental group was positively correlated (p < 0.05) with the frontal region during language tasks and in the frontal and central regions during registration and orientation tasks, indicating potential neurocognitive benefits.

Discussion

The results of this research imply that BB stimulation has untapped potential as a non-invasive therapy for patients with AD, hence there is the need for further studies to manage the dementia epidemic.

Functional and effective EEG connectivity patterns in Alzheimer's disease and mild cognitive impairment: a systematic review

Background

Alzheimer's disease (AD) might be best conceptualized as a disconnection syndrome, such that symptoms may be largely attributable to disrupted communication between brain regions, rather than to deterioration within discrete systems. EEG is uniquely capable of directly and non-invasively measuring neural activity with precise temporal resolution; connectivity quantifies the relationships between such signals in different brain regions. EEG research on connectivity in AD and mild cognitive impairment (MCI), often considered a prodromal phase of AD, has produced mixed results and has yet to be synthesized for comprehensive review. Thus, we performed a systematic review of EEG connectivity in MCI and AD participants compared with cognitively healthy older adult controls.

Methods

We searched PsycINFO, PubMed, and Web of Science for peer-reviewed studies in English on EEG, connectivity, and MCI/AD relative to controls. Of 1,344 initial matches, 124 articles were ultimately included in the systematic review.

Results

The included studies primarily analyzed coherence, phase-locked, and graph theory metrics. The influence of factors such as demographics, design, and approach was integrated and discussed. An overarching pattern emerged of lower connectivity in both MCI and AD compared to healthy controls, which was most prominent in the alpha band, and most consistent in AD. In the minority of studies reporting greater connectivity, theta band was most commonly implicated in both AD and MCI, followed by alpha. The overall prevalence of alpha effects may indicate its potential to provide insight into nuanced changes associated with AD-related networks, with the caveat that most studies were during the resting state where alpha is the dominant frequency. When greater connectivity was reported in MCI, it was primarily during task engagement, suggesting compensatory resources may be employed. In AD, greater connectivity was most common during rest, suggesting compensatory resources during task engagement may already be exhausted.

Conclusion

The review highlighted EEG connectivity as a powerful tool to advance understanding of AD-related changes in brain communication. We address the need for including demographic and methodological details, using source space connectivity, and extending this work to cognitively healthy older adults with AD risk toward advancing early AD detection and intervention.

Relationship between regional relative theta power and amyloid deposition in mild cognitive impairment: an exploratory study

Introduction

Electroencephalographic (EEG) abnormalities, such as increased theta power, have been proposed as biomarkers for neurocognitive disorders. Advancements in amyloid positron emission tomography (PET) imaging have enhanced our understanding of the pathology of neurocognitive disorders, such as amyloid deposition. However, much remains unknown regarding the relationship between regional amyloid deposition and EEG abnormalities. This study aimed to explore the relationship between regional EEG abnormalities and amyloid deposition in patients with mild cognitive impairment (MCI).

Methods

We recruited 24 older adults with MCI from a community center for dementia prevention, and 21 participants were included in the final analysis. EEG was recorded using a 64-channel system, and amyloid deposition was measured using amyloid PET imaging. Magnetic resonance imaging (MRI) data were used to create individualized brain models for EEG source localization. Correlations between relative theta power and standardized uptake value ratios (SUVRs) in 12 brain regions were analyzed using Spearman's correlation coefficient.

Results

Significant positive correlations between relative theta power and SUVR values were found in several brain regions in the individualized brain model during the resting eyes-closed condition, including right temporal lobe (r = 0.581, p = 0.006), left hippocampus (r = 0.438, p = 0.047), left parietal lobe (r = 0.471, p = 0.031), right parietal lobe (r = 0.509, p = 0.018), left occipital lobe (r = 0.597, p = 0.004), and right occipital lobe (r = 0.590, p = 0.005). During the visual working memory condition, significant correlations were found in both cingulate lobes (left: r = 0.483, p = 0.027; right: r = 0.449, p = 0.041), left parietal lobe (r = 0.530, p = 0.010), right parietal lobe (r = 0.606, p = 0.004), left occipital lobe (r = 0.648, p = 0.001), and right occipital lobe (r = 0.657, p = 0.001).

Conclusion

The result suggests that regional increases in relative theta power are associated with regional amyloid deposition in patients with MCI. These findings highlight the potential of EEG in detecting amyloid deposition. Future large-scale studies are needed to validate these preliminary findings and explore their clinical applications.

Resting-State EEG Oscillations in Amyotrophic Lateral Sclerosis (ALS): Toward Mechanistic Insights and Clinical Markers

Introduction: Amyotrophic lateral sclerosis (ALS) is a complex, progressive neurodegenerative disorder characterized by the degeneration of motor neurons in the brain, brainstem, and spinal cord. Several neuroimaging techniques can help reveal the pathophysiology of ALS. One of these is the electroencephalogram (EEG), a noninvasive and relatively inexpensive tool for examining electrical activity of the brain with excellent temporal precision. Methods: This mechanistic review examines the pattern of resting-state EEG activity. With a focus on publications published between January 1995 and October 2024, we carried out a comprehensive search in October 2024 across a number of databases, including PubMed/Medline, Research Gate, Google Scholar, and Cochrane. Results: The literature search yielded 17 studies included in this review. The studies varied significantly in their methodology and patient characteristics. Despite this, a common biomarker typical of ALS was found-reduced alpha power. Regarding other oscillations, the findings are less consistent and sometimes contradictory. As this is a mechanistic review, three possible explanations for this biomarker are provided. The main and most important one is increased cortical excitability. In addition, due to the limitations of the studies, recommendations for future research on this topic are outlined to enable a further and better understanding of EEG patterns in ALS. Conclusions: Most studies included in this review showed alpha power deficits in ALS patients, reflecting pathological hyperexcitability of the cerebral cortex. Future studies should address the methodological limitations identified in this review, including small sample sizes, inconsistent frequency-band definitions, and insufficient functional outcome measures, to solidify and extend current findings.

A Novel CNN-Based Framework for Alzheimer's Disease Detection Using EEG Spectrogram Representations

Background: Alzheimer's disease (AD) is a progressive neurodegenerative disorder that poses critical challenges in global healthcare due to its increasing prevalence and severity. Diagnosing AD and other dementias, such as frontotemporal dementia (FTD), is slow and resource-intensive, underscoring the need for automated approaches. Methods: To address this gap, this study proposes a novel deep learning methodology for EEG classification of AD, FTD, and control (CN) signals. The approach incorporates advanced preprocessing techniques and CNN classification of FFT-based spectrograms and is evaluated using the leave-N-subjects-out validation, ensuring robust cross-subject generalizability. Results: The results indicate that the proposed methodology outperforms state-of-the-art machine learning and EEG-specific neural network models, achieving an accuracy of 79.45% for AD/CN classification and 80.69% for AD+FTD/CN classification. Conclusions: These results highlight the potential of EEG-based deep learning models for early dementia screening, enabling more efficient, scalable, and accessible diagnostic tools.

Novel AIRTrode-based wearable electrode supports long-term, online brain-computer interface operations

Objective.Non-invasive electroencephalograms (EEG)-based brain-computer interfaces (BCIs) play a crucial role in a diverse range of applications, including motor rehabilitation, assistive and communication technologies, holding potential promise to benefit users across various clinical spectrums. Effective integration of these applications into daily life requires systems that provide stable and reliable BCI control for extended periods. Our prior research introduced the AIRTrode, a self-adhesive (A), injectable (I), and room-temperature (RT) spontaneously-crosslinked hydrogel electrode (AIRTrode). The AIRTrode has shown lower skin-contact impedance and greater stability than dry electrodes and, unlike wet gel electrodes, does not dry out after just a few hours, enhancing its suitability for long-term application. This study aims to demonstrate the efficacy of AIRTrodes in facilitating reliable, stable and long-term online EEG-based BCI operations.Approach.In this study, four healthy participants utilized AIRTrodes in two BCI control tasks-continuous and discrete-across two sessions separated by six hours. Throughout this duration, the AIRTrodes remained attached to the participants' heads. In the continuous task, participants controlled the BCI through decoding of upper-limb motor imagery (MI). In the discrete task, the control was based on decoding of error-related potentials (ErrPs).Main Results.Using AIRTrodes, participants demonstrated consistently reliable online BCI performance across both sessions and tasks. The physiological signals captured during MI and ErrPs tasks were valid and remained stable over sessions. Lastly, both the BCI performances and physiological signals captured were comparable with those from freshly applied, research-grade wet gel electrodes, the latter requiring inconvenient re-application at the start of the second session.Significance.AIRTrodes show great potential promise for integrating non-invasive BCIs into everyday settings due to their ability to support consistent BCI performances over extended periods. This technology could significantly enhance the usability of BCIs in real-world applications, facilitating continuous, all-day functionality that was previously challenging with existing electrode technologies.

Leveraging deep learning for robust EEG analysis in mental health monitoring

Introduction

Mental health monitoring utilizing EEG analysis has garnered notable interest due to the non-invasive characteristics and rich temporal information encoded in EEG signals, which are indicative of cognitive and emotional conditions. Conventional methods for EEG-based mental health evaluation often depend on manually crafted features or basic machine learning approaches, like support vector classifiers or superficial neural networks. Despite the potential of these approaches, they often fall short in capturing the intricate spatiotemporal relationships within EEG data, leading to lower classification accuracy and poor adaptability across various populations and mental health scenarios.

Methods

To overcome these limitations, we introduce the EEG Mind-Transformer, an innovative deep learning architecture composed of a Dynamic Temporal Graph Attention Mechanism (DT-GAM), a Hierarchical Graph Representation and Analysis (HGRA) module, and a Spatial-Temporal Fusion Module (STFM). The DT-GAM is designed to dynamically extract temporal dependencies within EEG data, while the HGRA models the brain's hierarchical structure to capture both localized and global interactions among different brain regions. The STFM synthesizes spatial and temporal elements, generating a comprehensive representation of EEG signals.

Results and discussion

Our empirical results confirm that the EEG Mind-Transformer significantly surpasses conventional approaches, achieving an accuracy of 92.5%, a recall of 91.3%, an F1-score of 90.8%, and an AUC of 94.2% across several datasets. These findings underline the model's robustness and its generalizability to diverse mental health conditions. Moreover, the EEG Mind-Transformer not only pushes the boundaries of state-of-the-art EEG-based mental health monitoring but also offers meaningful insights into the underlying brain functions associated with mental disorders, solidifying its value for both research and clinical settings.

Optimizing electrode configurations for EEG mild cognitive impairment detection

The Optimal electrode configuration of Electroencephalograms (EEG) systems for mild cognitive impairment (MCI) detection and monitoring in non-clinical settings, i.e. number of electrodes and the positions of the electrodes, remains to be explored. In the current study, we explored the optimization of electrode configuration for MCI detection. We used a 32-channel EEG device to record the data of 21 MCI patients and 20 cognitively normal elderly (NC) undergoing working memory (WM) tasks. Based on the differential value (MCI group vs. NC group) from the Power Spectral Density (PSD) value of each electrode in θ and α frequency band during WM coding stage, six different electrode configurations were obtained: (1) four electrodes in the occipital lobe (OCL4); (2) three electrodes in the prefrontal lobe (PRL3); (3) four electrodes in the parietal lobe (PLL4), (4) eight electrodes in occipital combined parietal lobe (OPL8), (5) seven electrodes in occipital combined prefrontal lobe (OPL7); and (6) seven electrodes in parietal combined prefrontal lobe (PPL7). A multi-parameter combination-assisted binary logistic regression model was established to distinguish two groups. Receiver operating characteristic (ROC) curves were used to evaluate the MCI diagnostic power of each electrode configuration. The area under curve (AUC) of the ROC of electrode configurations OCL4, PRL3, PLL4, OPL8, OPL7 and PPL7 were 0.765, 0.683, 0.729, 0.83, 0.788, and 0.769, respectively. And the sensitivity of six electrode configurations were 0.962, 0.794, 0.873, 0.943, 0.859, and 0.938, respectively. Among these six configurations, OCL4, i.e. PO3, PO4, PO8, and PO7, had the highest sensitivity 96.2%, which meant that relying solely on these four electrodes of the occipital lobe had the potential to serve as an objective tool for preliminary screening of MCI. The abnormal brain rhythm characteristics of the frontal, parietal, and occipital lobes in the memory encoding stage of MCI provide a new perspective for MCI-WM impairment, which has the potential to be a novel biomarker for the early detection of pathological age-related cognitive decline. Further, a potential four-electrode configuration may be used for a novel detecting and monitoring EEG system of MCI in non-clinical settings.

Graph neural networks for electroencephalogram analysis: Alzheimer's disease and epilepsy use cases

Electroencephalography (EEG) is widely used as a non-invasive technique for the diagnosis of several brain disorders, including Alzheimer's disease and epilepsy. Until recently, diseases have been identified over EEG readings by human experts, which may not only be specific and difficult to find, but are also subject to human error. Despite the recent emergence of machine learning methods for the interpretation of EEGs, most approaches are not capable of capturing the underlying arbitrary non-Euclidean relations between signals in the different regions of the human brain. In this context, Graph Neural Networks (GNNs) have gained attention for their ability to effectively analyze complex relationships within different types of graph-structured data. This includes EEGs, a use case still relatively unexplored. In this paper, we aim to bridge this gap by presenting a study that applies GNNs for the EEG-based detection of Alzheimer's disease and discrimination of two different types of seizures. To this end, we demonstrate the value of GNNs by showing that a single GNN architecture can achieve state-of-the-art performance in both use cases. Through design space explorations and explainability analysis, we develop a graph-based transformer that achieves cross-validated accuracies over 89% and 96% in the ternary classification variants of Alzheimer's disease and epilepsy use cases, respectively, matching the intuitions drawn by expert neurologists. We also argue about the computational efficiency, generalizability and potential for real-time operation of GNNs for EEGs, positioning them as a valuable tool for classifying various neurological pathologies and opening up new prospects for research and clinical practice.

Exploring Task-Related EEG for Cross-Subject Early Alzheimer's Disease Susceptibility Prediction in Middle-Aged Adults Using Multitaper Spectral Analysis

The early prediction of Alzheimer's disease (AD) risk in healthy individuals remains a significant challenge. This study investigates the feasibility of task-state EEG signals for improving detection accuracy. Electroencephalogram (EEG) data were collected from the Multi-Source Interference Task (MSIT) and Sternberg Memory Task (STMT). Time-frequency features were extracted using the Multitaper method, followed by multidimensional reduction techniques. Subspace features (F24 and F216) were selected via t-tests and False Discovery Rate (FDR) multiple comparisons correction, and subsequently analyzed in the Time-Frequency Area Average Test (TFAAT) and Prefrontal Beta Time Series Test (PBTST). The experimental results reveal that the MSIT task achieves optimal cross-subject classification performance using the Support Vector Machine (SVM) approach with the TFAAT feature set, yielding a Receiver Operating Characteristic Area Under the Curve (ROC AUC) of 58%. Similarly, the Sternberg Memory Task demonstrates classification ability with the logistic regression model applied to the PBTST feature set, emphasizing the beta band power spectrum in the prefrontal cortex as a potential marker of AD risk. These findings confirm that task-state EEG provides stronger classification potential compared to resting-state EEG, offering valuable insights for advancing early AD prediction research.

Alzheimer's disease: A case study involving EEG-based fE/I ratio and pTau-181 protein analysis through nasal administration of Saraswata Ghrita

Background

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that impairs memory, language, and cognitive functions and currently has no definitive cure. Saraswata Ghrita (SG), a traditional Ayurvedic remedy administered nasally, offers a holistic approach and is believed to directly affect brain functions through its unique delivery route.

Objective

This study aimed to evaluate the effectiveness of SG in improving cognitive function and neurochemical biomarkers in a patient with AD. Key outcomes included electroencephalography-based excitation/inhibition (fE/I) ratio, and levels of phosphorylated Tau-181 (pTau-181), serotonin, dopamine, acetylcholine, and dehydroepiandrosterone (DHEA).

Methods

A 90-day proof-of-concept clinical trial was conducted with one AD patient. Nasal administration of SG was performed twice daily. Measurements included EEG spectral power analysis across 1-48 Hz, cognitive function assessed by Alzheimer's Disease Assessment Scale-Cognitive Subscale (ADAS-Cog), Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), and Quality of Life in Alzheimer's Disease (QoL-AD) scales, and biochemical analyses of pTau-181, serotonin, dopamine, acetylcholine, and DHEA.

Results

Notable improvements were observed: ADAS-Cog score decreased from 40 to 36, QoL-AD score increased from 23 to 31, MMSE score improved from 13 to 18, and MoCA score increased from 8 to 13. Biochemical markers showed a decrease in pTau-181 (12.50 pg/ml to 6.28 pg/ml), an increase in acetylcholine (13.73 pg/ml to 31.83 pg/ml), while serotonin and DHEA levels rose, and dopamine levels decreased (39.14 pg/ml to 36.21 pg/ml).

Conclusions

SG demonstrated potential in enhancing cognitive functions and neurochemical markers in AD, with the nasal route proving safe and effective. These findings suggest the value of traditional Ayurvedic treatments in contemporary AD management.

An objective and sensitive electrophysiological marker of word semantic categorization impairment in Alzheimer's disease

OBJECTIVE

Combining electroencephalographic (EEG) recording and fast periodic visual stimulation (FPVS) to provide an implicit, objective and sensitive electrophysiological measure of semantic word categorization impairment in Alzheimer's Disease (AD).

METHODS

Twenty-five AD patients and 25 matched elderly healthy controls were tested with a validated FPVS-EEG paradigm in which different written words of the same semantic category (cities) appear at a fixed frequency of 4 words per second (4 Hz) for 70 seconds. Words from a different semantic category (animal) appear every 4 stimuli (i.e., 1 Hz).

RESULTS

Frequency domain EEG analysis showed a robust response objectively identified at specific 1 Hz harmonics over the left occipito-temporal cortex for healthy controls, indexing automatic semantic categorization. However, only a negligible response, less than 25 % of healthy controls', was found in AD patients, this response being inversely correlated with the amount of Tau protein in the cerebrospinal fluid. The significant group difference was maximal when including an additional left central region, with only 2.5 min of testing providing a significant group difference.

CONCLUSION

A reduced semantic word categorisation EEG amplitude rapidly differentiates AD patients from healthy controls.

SIGNIFICANCE

FPVS-EEG provides a valuable electrophysiological index of semantic categorization impairment in AD.

Different oscillatory mechanisms of dementia-related diseases with cognitive impairment in closed-eye state

The escalating global trend of aging has intensified the focus on health concerns prevalent among the elderly. Notably, Dementia related diseases, including Alzheimer's disease (AD) and frontotemporal dementia (FTD), significantly impair the quality of life for both affected seniors and their caregivers. However, the underlying neural mechanisms of these diseases remain incompletely understood, especially in terms of neural oscillations. In this study, we leveraged an open dataset containing 36 CE, 23 FTD, and 29 healthy controls (HC) to investigate these mechanisms. We accurately and clearly identified three stable oscillation targets (theta, ∼5 Hz, alpha, ∼10 Hz, and beta, ∼18 Hz) that facilitate differentiation between AD, FTD, and HC both statistically and through classification using machine learning algorithms. Overall, the differences between AD and HC were the most pronounced, with FTD exhibiting intermediate characteristics. The differences in the theta and alpha bands showed a global pattern, whereas the differences in the beta band were localized to the central-temporal region. Moreover, our analysis revealed that the relative theta power was significantly and negatively correlated with the Mini Mental State Examination (MMSE) scores, while the relative alpha and beta power showed a significant positive correlation. This study is the first to pinpoint multiple robust and effective neural oscillation targets to distinguish AD, offering a simple and convenient method that holds promise for future applications in the early screening of large-scale dementia-related diseases.

Time-Frequency functional connectivity alterations in Alzheimer's disease and frontotemporal dementia: An EEG analysis using machine learning

OBJECTIVE

Alzheimer's disease (AD) and frontotemporal dementia (FTD) are prevalent neurodegenerative diseases characterized by altered brain functional connectivity (FC), affecting over 100 million people worldwide. This study aims to identify distinct FC patterns as potential biomarkers for differential diagnosis.

METHODS

Resting-state EEG data from 36 AD patients, 23 FTD patients, and 29 healthy controls were analyzed using time-frequency and bandpass filtering FC metrics. These metrics were estimated through Pearson's correlations, mutual information, and phase lag index, and served as input features in a support vector machine (SVM) with Leave-One-Out Cross-Validation for group classification.

RESULTS

Both AD and FTD exhibited significantly decreased FC in the theta band within the frontal lobe and increased FC in the beta band in the posterior regions. Additionally, a decreased FC in central regions at theta band was observed uniquely in AD, but not in FTD. SVM classification accuracies reached 95% for AD and 86% for FTD.

CONCLUSIONS

High classification accuracies underscore the potential of these FC alterations as reliable biomarkers for AD and FTD.

SIGNIFICANCE

This is the first study to integrate time-frequency and bandpass filtering FC metrics to reveal brain network alterations in AD and FTD, providing new insights for diagnostics and neurodegenerative pathologies.

Contribution of Scalp Regions to Machine Learning-Based Classification of Dementia Utilizing Resting-State qEEG Signals

Purpose

This study aims to investigate using eyes-open (EO) and eyes-closed (EC) resting-state EEG data to diagnose cognitive impairment using machine learning methods, enhancing timely intervention and cost-effectiveness in dementia research.

Participants and Methods

A total of 890 participants aged 40-90 were included in the study, comprising 269 healthy controls (HC), 356 individuals with mild cognitive impairment (MCI), and 265 with Alzheimer's disease (AD) from a cohort study. Resting-state EEG (rEEG) signals were recorded and transformed into relative power spectral density (PSD) data for analysis. The processed PSD data, representing 19 scalp regions, were then input into a Random Forest (RF) machine learning classifier to identify distinctive EEG patterns across the groups. Statistical comparisons between the groups were conducted using one-way ANOVA, applied to the relative PSD features extracted from the EEG data, to assess significant differences in EEG activity across the diagnostic categories.

Results

The study found that rEEG-based categorization effectively differentiates between cognitively impaired individuals and healthy individuals. The EO rEEG achieved the highest performance metrics across various models. For HC vs MCI (combined hemisphere), the accuracy, sensitivity, specificity, and AUC were 92%, 99%, 83%, and 96%, respectively. For HC vs AD (parietal, temporal, occipital), these metrics were 95%, 96%, 94%, and 99%. The HC vs CASE (MCI + AD) (combined hemisphere) results were 90%, 99%, 73%, and 92%. The metrics for HC vs MCI vs AD (frontal, parietal, temporal) were 89%, 88%, 94%, and 96%.

Conclusion

The study demonstrates that EO rEEG can effectively distinguish between cognitive impairment and healthy states, leading to early diagnosis, cost-effective treatment, and better clinical outcomes for dementia patients. EO and EC rEEG models trained with relative PSD, particularly from parietal, temporal, occipital, and central scalp regions, can significantly assist clinicians in practice.

Electroencephalogram criticality in cognitive impairment: a monitoring biomarker?

Critical states present scale-free dynamics, optimizing neuronal complexity and serving as a potential biomarker in cognitively impaired patients. We explored electroencephalogram (EEG) criticality in amnesic Mild Cognitive Impairment patients with clinical improvement in working memory, verbal memory, verbal fluency and overall executive functions after the completion of a 6-month prospective memory training. We compared "before" and "after" stationary resting-state EEG records of right-handed MCI patients (n = 17; 11 females), using the method of critical fluctuations and Haar wavelet analysis. Improvement of criticality indices was observed in most electrodes, with mean values being higher after prospective memory training. Significant criticality enhancement was found in the subgroup analysis of frontotemporal electrodes [mean dif: 0.10; Z = 7, p = 0.019]. In the isolated electrode signal analysis, significant post-intervention improvement was noted in pooled criticality indices of electrodes T6 [mean dif: 0.204; t(10) = -2.3, p = 0.044] and F4 [mean dif: 0.0194; t(10) = -2.82; p = 0.018]. EEG criticality agreed with clinical improvement, consisting a possible quantifiable and easy-to-obtain biomarker in MCI and Alzheimer's disease (AD), especially in patients under cognitive training/rehabilitation. We highlight the role of EEG in prognostication, monitoring and potentially early treatment optimization in MCI or AD patients. Further standardization of the methodology in larger patient cohorts could be valuable for AD theragnostics in patients receiving disease-modifying treatments by providing insights regarding synaptic brain plasticity.

Graphical Abstract

Critical states' scale-free dynamics optimize neuronal complexity, emerging as biomarkers in cognitive neuroscience. Applying the method of critical fluctuations and Haar wavelet analysis in stationary EEG time-series, we demonstrate criticality enhancement in the frontotemporal electroencephalographic (EEG) recordings of mild cognitive impairment (MCI) patients after a 6-month prospective memory training, suggesting EEG criticality as a possible monitoring biomarker in MCI and Alzheimer's disease.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-024-10155-4.

Light-based gamma entrainment with novel invisible spectral flicker stimuli

Light-based gamma entrainment using sensory stimuli (GENUS) shows considerable potential for the treatment of Alzheimer's disease (AD) in both animal and human models. While the clinical efficacy of GENUS for AD is paramount, its effectiveness will eventually also rely on the barrier to treatment adherence imposed by the discomfort of gazing at luminance flickering (LF) light. Currently, there have been few attempts to improve the comfort of GENUS. Here we investigate if Invisible spectral flicker (ISF), a novel type of light-based 40 Hz GENUS for which the flicker is almost imperceptible, can be used as a more comfortable option. We found that whereas ISF, LF, and chromatic flicker (CF) all produce a 40 Hz steady-state visually evoked potential (SSVEP), ISF scores significantly better on measures of comfort and perceived flicker. We also demonstrate that, while there is a trend towards a lower SSVEP response, reducing the stimulation brightness has no significant effect on the 40 Hz SSVEP or perceived flicker, though it significantly improves comfort. Finally, there is a slight decrease in the 40 Hz SSVEP response when stimulating with ISF from increasingly peripheral angles. This may ease the discomfort of GENUS treatment by freeing patients from gazing directly at the light.

Machine learning based on event-related oscillations of working memory differentiates between preclinical Alzheimer's disease and normal aging

OBJECTIVE

To apply machine learning approaches on EEG event-related oscillations (ERO) to discriminate preclinical Alzheimer's disease (AD) from age- and sex-matched controls.

METHODS

Twenty-two cognitively normal preclinical AD participants with elevated amyloid and 21 cognitively normal controls without elevated amyloid completed n-back working memory tasks (n = 0, 1, 2). The absolute and relative power of ERO was extracted using the discrete wavelet transform in the delta, theta, alpha, and beta bands. Four machine learning methods were employed, and classification performance was assessed using three metrics.

RESULTS

The low-frequency bands produced higher discriminative performances compared to high-frequency bands. The 2-back task yielded the best classification capability among the three tasks. The highest area under the curve value (0.86) was achieved in the 2-back delta band nontarget condition data. The highest accuracy (80.47%) was obtained in the 2-back delta and theta bands nontarget data. The highest F1 score (0.82) was in the 2-back theta band nontarget data. The support vector machine achieved the highest performance among tested classifiers.

CONCLUSION

This study demonstrates the promise of using machine learning on EEG ERO from working memory tasks to detect preclinical AD.

SIGNIFICANCE

EEG ERO may reveal pathophysiological differences in the earliest stage of AD when no cognitive impairments are apparent.

Beta-to-Theta Entropy Ratio of EEG in Aging, Frontotemporal Dementia, and Alzheimer's Dementia

BACKGROUND

Aging, frontotemporal dementia (FTD), and Alzheimer's dementia (AD) manifest electroencephalography (EEG) alterations, particularly in the beta-to-theta power ratio derived from linear power spectral density (PSD). Given the brain's nonlinear nature, the EEG nonlinear features could provide valuable physiological indicators of aging and cognitive impairment. Multiscale dispersion entropy (MDE) serves as a sensitive nonlinear metric for assessing the information content in EEGs across biologically relevant time scales.

OBJECTIVE

To compare the MDE-derived beta-to-theta entropy ratio with its PSD-based counterpart to detect differences between healthy young and elderly individuals and between different dementia subtypes.

METHODS

Scalp EEG recordings were obtained from two datasets: 1) Aging dataset: 133 healthy young and 65 healthy older adult individuals; and 2) Dementia dataset: 29 age-matched healthy controls (HC), 23 FTD, and 36 AD participants. The beta-to-theta ratios based on MDE vs. PSD were analyzed for both datasets. Finally, the relationships between cognitive performance and the beta-to-theta ratios were explored in HC, FTD, and AD.

RESULTS

In the Aging dataset, older adults had significantly higher beta-to-theta entropy ratios than young individuals. In the Dementia dataset, this ratio outperformed the beta-to-theta PSD approach in distinguishing between HC, FTD, and AD. The AD participants had a significantly lower beta-to-theta entropy ratio than FTD, especially in the temporal region, unlike its corresponding PSD-based ratio. The beta-to-theta entropy ratio correlated significantly with cognitive performance.

CONCLUSION

Our study introduces the beta-to-theta entropy ratio using nonlinear MDE for EEG analysis, highlighting its potential as a sensitive biomarker for aging and cognitive impairment.

Prediction of rTMS Efficacy in Patients With Essential Tremor: Biomarkers From Individual Resting-State EEG Network

The pathogenesis of essential tremor (ET) remains unclear, and the efficacy of related drug treatment is inadequate for proper tremor control. Hence, in the current study, consecutive low-frequency repetitive transcranial magnetic stimulation (rTMS) modulation on cerebellum was accomplished in a population of ET patients, along with pre- and post-treatment resting-state electroencephalogram (EEG) networks being constructed. The results primarily clarified the decreasing of resting-state network interactions occurring in ET, especially the weaker frontal-parietal connectivity, compared to healthy individuals. While after the rTMS stimulation, promotions in both network connectivity and properties, as well as clinical scales, were identified. Furthermore, significant correlations between network characteristics and clinical scale scores enabled the development of predictive models for assessing rTMS intervention efficacy. Using a multivariable linear model, clinical scales after one-month rTMS treatment were accurately predicted, underscoring the potential of brain networks in evaluating rTMS effectiveness for ET. The findings consistently demonstrated that repetitive low-frequency rTMS neuromodulation on cerebellum can significantly improve the manifestations of ET, and individual networks will be reliable tools for evaluating the rTMS efficacy, thereby guiding personalized treatment strategies for ET patients.

SpectroCVT-Net: A convolutional vision transformer architecture and channel attention for classifying Alzheimer's disease using spectrograms

Dementia arises from various brain-affecting diseases and injuries, with Alzheimer's disease being the most prevalent, impacting around 55 million people globally. Current clinical diagnosis often relies on biomarkers indicative of Alzheimer's distinctive features. Electroencephalography (EEG) serves as a cost-effective, user-friendly, and safe biomarker for early Alzheimer's detection. This study utilizes EEG signals processed with Short-Time Fourier Transform (STFT) to generate spectrograms, facilitating visualization of EEG signal properties. Leveraging the Brainlat database, we propose SpectroCVT-Net, a novel convolutional vision transformer architecture incorporating channel attention mechanisms. SpectroCVT-Net integrates convolutional and attention mechanisms to capture local and global dependencies within spectrograms. Comprising feature extraction and classification stages, the model enhances Alzheimer's disease classification accuracy compared to transfer learning methods, achieving 92.59 ± 2.3% accuracy across Alzheimer's, healthy controls, and behavioral variant frontotemporal dementia (bvFTD). This article introduces a new architecture and evaluates its efficacy with unconventional data for Alzheimer's diagnosis, contributing: SpectroCVT-Net, tailored for EEG spectrogram classification without reliance on transfer learning; a convolutional vision transformer (CVT) module in the classification stage, integrating local feature extraction with attention heads for global context analysis; Grad-CAM analysis for network decision insight, identifying critical layers, frequencies, and electrodes influencing classification; and enhanced interpretability through spectrograms, illuminating key brain wave contributions to Alzheimer's, frontotemporal dementia, and healthy control classifications, potentially aiding clinical diagnosis and management.

Controlling Alzheimer's disease by deep brain stimulation based on a data-driven cortical network model

This work aims to explore the control effect of DBS on Alzheimer's disease (AD) from a neurocomputational perspective. Firstly, a data-driven cortical network model is constructed using the Diffusion Tensor Imaging data. Then, a typical electrophysiological feature of EEG slowing in AD is reproduced by reducing the synaptic connectivity parameters. The corresponding changes in kinetic behavior mainly include an oscillation decrease in the amplitude and frequency of the pyramidal neuron population. Subsequently, DBS current with specific parameters is introduced into three potential targets of the hippocampus, the nucleus accumbens and the olfactory tubercle, respectively. The results indicate that applying DBS to simulated mild AD patients induces an increase in relative alpha power, a decrease in relative theta power, and a significant rightward shift of the dominant frequency. This is consistent with the EEG reversal in pharmacological treatments for AD. Further, the optimal stimulation strategy of DBS is investigated through spectral and statistical analyses. Specifically, the pathological symptoms of AD could be alleviated by adjusting the critical parameters of DBS, and the control effect of DBS on various targets is that the hippocampus is superior to the olfactory tubercle and nucleus accumbens. Finally, using correlation analysis between the power increments and the nodal degrees, it is concluded that the control effect of DBS is related to the importance of the nodes in the brain network. This study provides a theoretical guidance for determining DBS targets and parameters, which may have a substantial impact on the development of DBS treatment for AD.

Lattice 123 pattern for automated Alzheimer's detection using EEG signal

This paper presents an innovative feature engineering framework based on lattice structures for the automated identification of Alzheimer's disease (AD) using electroencephalogram (EEG) signals. Inspired by the Shannon information entropy theorem, we apply a probabilistic function to create the novel Lattice123 pattern, generating two directed graphs with minimum and maximum distance-based kernels. Using these graphs and three kernel functions (signum, upper ternary, and lower ternary), we generate six feature vectors for each input signal block to extract textural features. Multilevel discrete wavelet transform (MDWT) was used to generate low-level wavelet subbands. Our proposed model mirrors deep learning approaches, facilitating feature extraction in frequency and spatial domains at various levels. We used iterative neighborhood component analysis to select the most discriminative features from the extracted vectors. An iterative hard majority voting and a greedy algorithm were used to generate voted vectors to select the optimal channel-wise and overall results. Our proposed model yielded a classification accuracy of more than 98% and a geometric mean of more than 96%. Our proposed Lattice123 pattern, dynamic graph generation, and MDWT-based multilevel feature extraction can detect AD accurately as the proposed pattern can extract subtle changes from the EEG signal accurately. Our prototype is ready to be validated using a large and diverse database.

Classification of Alzheimer's Disease and Frontotemporal Dementia Using Electroencephalography to Quantify Communication between Electrode Pairs

Accurate diagnosis of dementia subtypes is crucial for optimizing treatment planning and enhancing caregiving strategies. To date, the accuracy of classifying Alzheimer's disease (AD) and frontotemporal dementia (FTD) using electroencephalogram (EEG) data has been lower than that of distinguishing individuals with these diseases from healthy elderly controls (HCs). This limitation has impeded the feasibility of a cost-effective differential diagnosis for the two subtypes in clinical settings. This study addressed this issue by quantifying communication between electrode pairs in EEG data, along with demographic information, as features to train machine learning (support vector machine) models. Our focus was on refining the feature set specifically for AD-FTD classification. Using our initial feature set, we achieved classification accuracies of 76.9% for AD-HC, 90.4% for FTD-HC, and 91.5% for AD-FTD. Notably, feature importance analyses revealed that the features influencing AD-HC classification are unnecessary for distinguishing between AD and FTD. Eliminating these unnecessary features improved the classification accuracy of AD-FTD to 96.6%. We concluded that communication between electrode pairs specifically involved in the neurological pathology of FTD, but not AD, enables highly accurate EEG-based AD-FTD classification.

Resting-state EEG data before and after cognitive activity across the adult lifespan and a 5-year follow-up

This dataset consists of 64-channels resting-state EEG recordings of 608 participants aged between 20 and 70 years, 61.8% female, as well as follow-up measurements after approximately 5 years of 208 participants, starting 2021. The EEG was measured for three minutes with eyes open and eyes closed before and after a 2-hour block of cognitive experimental tasks. The data set is part of the Dortmund Vital Study, a prospective study on the determinants of healthy cognitive aging. The dataset can be used for (1) analyzing cross-sectional resting-state EEG of healthy individuals across the adult life span; (2) generating normalization data sets for comparison of resting-state EEG data of patients with clinically relevant disorders; (3) studying effects of performing cognitive tasks on resting-state EEG and age; (4) exploring intra-individual changes in resting-state EEG and effects of task performance over a time period of about 5 years. The data are provided in Brain Imaging Data Structure (BIDS) format and are available on OpenNeuro.

Dementia rhythms: Unveiling the EEG dynamics for MCI detection through spectral and synchrony neuromarkers

BACKGROUND

Neurological disorders arise primarily from the dysfunction of brain cells, leading to various impairments. Electroencephalography (EEG) stands out as the most popular method in the discovery of neuromarkers indicating neurological disorders. The proposed study investigates the effectiveness of spectral and synchrony neuromarkers derived from resting state EEG in the detection of Mild Cognitive Impairment (MCI) with controls.

NEW METHODS

The dataset is composed of 10 MCI and 10 HC groups. Spectral features and synchrony measures are utilized to detect slowing patterns in MCI. Efficient neuro-markers are classified by 25 classification algorithm. Independent samples t-test and Pearson's Correlation Coefficients are applied to reveal group differences for spectral markers, and repeated measures ANOVA is tested for wPLI-based markers.

RESULTS

Lower peak amplitudes are prominent in MCI participants for high frequencies indicating slower physiological behavior of the demented EEG. The MCI and HC groups are correctly classified with 95 % acc. using peak amplitudes of beta band with LGBM classifier. Higher wPLI values are calculated for HC participants in high frequencies. The alpha wPLI values achieve a classification accuracy of 99 % using the LGBM algorithm for MCI detection.

COMPARISON WITH EXISTING METHODS

The neuro-markers including peak amplitudes, frequencies, and wPLIs with advanced machine learning techniques showcases the innovative nature of this research.

CONCLUSION

The findings suggest that peak amplitudes and wPLI in high frequency bands derived from resting state EEG are effective neuromarkers for detection of MCI. Spectral and synchrony neuro-markers hold great promise for accurate MCI detection.

The influence of mental calculations on brain regions and heart rates

Performing mathematical calculations is a cognitive activity that can affect biological signals. This study aims to examine the changes in electroencephalogram (EEG) and electrocardiogram (ECG) signals of 36 healthy subjects during the performance of arithmetic tasks. To process EEG signals in different frequency bands, the energy and entropy of entropy (EoE) were extracted from the power spectrum and phase spectrum, respectively. Statistical analysis was conducted to determine meaningful features. These features were sent into support vector machine (SVM) and multi-layer perception (MLP) classifiers to assess their capability in separating math and rest classes. Results indicated the highest classification accuracy of 98.4% for classifying good counters in math and rest state using the MLP method. Based on the majority of features selected for each EEG channel, discriminative brain areas were identified. Analyzing EEG signals proved that math calculation may have multiple influences on various parts of the brain. By comparing good counters' brain activities to those in a resting state, prominent changes were observed in the F4, C4, T4, T5, P3, and O2 areas. However, O1 and O2 channels showed significant changes in the brain of bad counters compared to the resting state. Considering ECG signals also demonstrated that during math calculation the number of heart rates per minute surpasses the rest state. These alterations can occur due to cognitive abilities or emotional processes which were observed to be prominent in subjects who performed more accurate calculations.

EEG and ERP biosignatures of mild cognitive impairment for longitudinal monitoring of early cognitive decline in Alzheimer's disease

Cognitive decline in Alzheimer's disease is associated with electroencephalographic (EEG) biosignatures even at early stages of mild cognitive impairment (MCI). The aim of this work is to provide a unified measure of cognitive decline by aggregating biosignatures from multiple EEG modalities and to evaluate repeatability of the composite measure at an individual level. These modalities included resting state EEG (eyes-closed) and two event-related potential (ERP) tasks on visual memory and attention. We compared individuals with MCI (n = 38) to age-matched healthy controls HC (n = 44). In resting state EEG, the MCI group exhibited higher power in Theta (3-7Hz) and lower power in Beta (13-20Hz) frequency bands. In both ERP tasks, the MCI group exhibited reduced ERP late positive potential (LPP), delayed ERP early component latency, slower reaction time, and decreased response accuracy. Cluster-based permutation analysis revealed significant clusters of difference between the MCI and HC groups in the frequency-channel and time-channel spaces. Cluster-based measures and performance measures (12 biosignatures in total) were selected as predictors of MCI. We trained a support vector machine (SVM) classifier achieving AUC = 0.89, accuracy = 77% in cross-validation using all data. Split-data validation resulted in (AUC = 0.87, accuracy = 76%) and (AUC = 0.75, accuracy = 70%) on testing data at baseline and follow-up visits, respectively. Classification scores at baseline and follow-up visits were correlated (r = 0.72, p<0.001, ICC = 0.84), supporting test-retest reliability of EEG biosignature. These results support the utility of EEG/ERP for prognostic testing, repeated assessments, and tracking potential treatment outcomes in the limited duration of clinical trials.

Complexity measures reveal age-dependent changes in electroencephalogram during working memory task

The alterations in electroencephalogram (EEG) signals are the complex outputs of functional factors, such as normal physiological aging, pathological process, which results in further cognitive decline. It is not clear that when brain aging initiates, but elderly people are vulnerable to be incipient of neurodegenerative diseases such as Alzheimer's disease. The EEG signals were recorded from 20 healthy middle age and 20 healthy elderly subjects while performing a working memory task. Higuchi's fractal dimension (HFD), Katz's fractal dimension (KFD), sample entropy and three Hjorth parameters were extracted to analyse the complexity of EEG signals. Four machine learning classifiers, multilayer perceptron (MLP), support vector machine (SVM), K-nearest neighbour (KNN), and logistic model tree (LMT) were employed to distinguish the EEG signals of middle age and elderly age groups. HFD, KFD and Hjorth complexity were found significantly correlated with age. MLP achieved the highest overall accuracy of 93.75%. For posterior region, the maximum accuracy of 92.50% was achieved using MLP. Since fractal dimension associated with the complexity of EEG signals, HFD, KFD and Hjorth complexity demonstrated the decreased complexity from middle age to elderly groups. The complexity features appear to be more appropriate indicators of monitoring EEG signal complexity in healthy aging.

EEG-Based Detection of Mild Cognitive Impairment Using DWT-Based Features and Optimization Methods

In recent years, electroencephalography (EEG) has been investigated for identifying brain disorders. This technique involves placing multiple electrodes (channels) on the scalp to measure the brain's activities. This study focuses on accurately detecting mild cognitive impairment (MCI) from the recorded EEG signals. To achieve this, this study first introduced discrete wavelet transform (DWT)-based approaches to generate reliable biomarkers for MCI. These approaches decompose each channel's signal using DWT into a set of distinct frequency band signals, then extract features using a non-linear measure such as band power, energy, or entropy. Various machine learning approaches then classify the generated features. We investigated these methods on EEGs recorded using 19 channels from 29 MCI patients and 32 healthy subjects. In the second step, the study explored the possibility of decreasing the number of EEG channels while preserving, or even enhancing, classification accuracy. We employed multi-objective optimization techniques, such as the non-dominated sorting genetic algorithm (NSGA) and particle swarm optimization (PSO), to achieve this. The results show that the generated DWT-based features resulted in high full-channel classification accuracy scores. Furthermore, selecting fewer channels carefully leads to better accuracy scores. For instance, with a DWT-based approach, the full-channel accuracy achieved was 99.84%. With only four channels selected by NSGA-II, NSGA-III, or PSO, the accuracy increased to 99.97%. Furthermore, NSGA-II selects five channels, achieving an accuracy of 100%. The results show that the suggested DWT-based approaches are promising to detect MCI, and picking the most useful EEG channels makes the accuracy even higher. The use of a small number of electrodes paves the way for EEG-based diagnosis in clinical practice.

From Gut Microbiota to Brain Waves: The Potential of the Microbiome and EEG as Biomarkers for Cognitive Impairment

Alzheimer's disease (AD) is a prevalent neurodegenerative disorder and a leading cause of dementia. Aging is a significant risk factor for AD, emphasizing the importance of early detection since symptoms cannot be reversed once the advanced stage is reached. Currently, there is no established method for early AD diagnosis. However, emerging evidence suggests that the microbiome has an impact on cognitive function. The gut microbiome and the brain communicate bidirectionally through the gut-brain axis, with systemic inflammation identified as a key connection that may contribute to AD. Gut dysbiosis is more prevalent in individuals with AD compared to their cognitively healthy counterparts, leading to increased gut permeability and subsequent systemic inflammation, potentially causing neuroinflammation. Detecting brain activity traditionally involves invasive and expensive methods, but electroencephalography (EEG) poses as a non-invasive alternative. EEG measures brain activity and multiple studies indicate distinct patterns in individuals with AD. Furthermore, EEG patterns in individuals with mild cognitive impairment differ from those in the advanced stage of AD, suggesting its potential as a method for early indication of AD. This review aims to consolidate existing knowledge on the microbiome and EEG as potential biomarkers for early-stage AD, highlighting the current state of research and suggesting avenues for further investigation.

The phase coherence of the neurovascular unit is reduced in Huntington's disease

Huntington's disease is a neurodegenerative disorder in which neuronal death leads to chorea and cognitive decline. Individuals with ≥40 cytosine-adenine-guanine repeats on the interesting transcript 15 gene develop Huntington's disease due to a mutated huntingtin protein. While the associated structural and molecular changes are well characterized, the alterations in neurovascular function that lead to the symptoms are not yet fully understood. Recently, the neurovascular unit has gained attention as a key player in neurodegenerative diseases. The mutant huntingtin protein is known to be present in the major parts of the neurovascular unit in individuals with Huntington's disease. However, a non-invasive assessment of neurovascular unit function in Huntington's disease has not yet been performed. Here, we investigate neurovascular interactions in presymptomatic (N = 13) and symptomatic (N = 15) Huntington's disease participants compared to healthy controls (N = 36). To assess the dynamics of oxygen transport to the brain, functional near-infrared spectroscopy, ECG and respiration effort were recorded. Simultaneously, neuronal activity was assessed using EEG. The resultant time series were analysed using methods for discerning time-resolved multiscale dynamics, such as wavelet transform power and wavelet phase coherence. Neurovascular phase coherence in the interval around 0.1 Hz is significantly reduced in both Huntington's disease groups. The presymptomatic Huntington's disease group has a lower power of oxygenation oscillations compared to controls. The spatial coherence of the oxygenation oscillations is lower in the symptomatic Huntington's disease group compared to the controls. The EEG phase coherence, especially in the α band, is reduced in both Huntington's disease groups and, to a significantly greater extent, in the symptomatic group. Our results show a reduced efficiency of the neurovascular unit in Huntington's disease both in the presymptomatic and symptomatic stages of the disease. The vasculature is already significantly impaired in the presymptomatic stage of the disease, resulting in reduced cerebral blood flow control. The results indicate vascular remodelling, which is most likely a compensatory mechanism. In contrast, the declines in α and γ coherence indicate a gradual deterioration of neuronal activity. The results raise the question of whether functional changes in the vasculature precede the functional changes in neuronal activity, which requires further investigation. The observation of altered dynamics paves the way for a simple method to monitor the progression of Huntington's disease non-invasively and evaluate the efficacy of treatments.

Associations of Plasma Glutamatergic Metabolites with Alpha Desynchronization during Cognitive Interference and Working Memory Tasks in Asymptomatic Alzheimer's Disease

Electroencephalogram (EEG) studies have suggested compensatory brain overactivation in cognitively healthy (CH) older adults with pathological beta-amyloid(Aβ42)/tau ratios during working memory and interference processing. However, the association between glutamatergic metabolites and brain activation proxied by EEG signals has not been thoroughly investigated. We aim to determine the involvement of these metabolites in EEG signaling. We focused on CH older adults classified under (1) normal CSF Aβ42/tau ratios (CH-NATs) and (2) pathological Aβ42/tau ratios (CH-PATs). We measured plasma glutamine, glutamate, pyroglutamate, and γ-aminobutyric acid concentrations using tandem mass spectrometry and conducted a correlational analysis with alpha frequency event-related desynchronization (ERD). Under the N-back working memory paradigm, CH-NATs presented negative correlations (r = ~-0.74--0.96, p = 0.0001-0.0414) between pyroglutamate and alpha ERD but positive correlations (r = ~0.82-0.95, p = 0.0003-0.0119) between glutamine and alpha ERD. Under Stroop interference testing, CH-NATs generated negative correlations between glutamine and left temporal alpha ERD (r = -0.96, p = 0.037 and r = -0.97, p = 0.027). Our study demonstrated that glutamine and pyroglutamate levels were associated with EEG activity only in CH-NATs. These results suggest cognitively healthy adults with amyloid/tau pathology experience subtle metabolic dysfunction that may influence EEG signaling during cognitive challenge. A longitudinal follow-up study with a larger sample size is needed to validate these pilot studies.

Small World derived index to distinguish Alzheimer's type dementia and healthy subjects

BACKGROUND

This article introduces a novel index aimed at uncovering specific brain connectivity patterns associated with Alzheimer's disease (AD), defined according to neuropsychological patterns.

METHODS

Electroencephalographic (EEG) recordings of 370 people, including 170 healthy subjects and 200 mild-AD patients, were acquired in different clinical centres using different acquisition equipment by harmonising acquisition settings. The study employed a new derived Small World (SW) index, SWcomb, that serves as a comprehensive metric designed to integrate the seven SW parameters, computed across the typical EEG frequency bands. The objective is to create a unified index that effectively distinguishes individuals with a neuropsychological pattern compatible with AD from healthy ones.

RESULTS

Results showed that the healthy group exhibited the lowest SWcomb values, while the AD group displayed the highest SWcomb ones.

CONCLUSIONS

These findings suggest that SWcomb index represents an easy-to-perform, low-cost, widely available and non-invasive biomarker for distinguishing between healthy individuals and AD patients.

Understanding the Role of Self-Attention in a Transformer Model for the Discrimination of SCD From MCI Using Resting-State EEG

The identification of EEG biomarkers to discriminate Subjective Cognitive Decline (SCD) from Mild Cognitive Impairment (MCI) conditions is a complex task which requires great clinical effort and expertise. We exploit the self-attention component of the Transformer architecture to obtain physiological explanations of the model's decisions in the discrimination of 56 SCD and 45 MCI patients using resting-state EEG. Specifically, an interpretability workflow leveraging attention scores and time-frequency analysis of EEG epochs through Continuous Wavelet Transform is proposed. In the classification framework, models are trained and validated with 5-fold cross-validation and evaluated on a test set obtained by selecting 20% of the total subjects. Ablation studies and hyperparameter tuning tests are conducted to identify the optimal model configuration. Results show that the best performing model, which achieves acceptable results both on epochs' and patients' classification, is capable of finding specific EEG patterns that highlight changes in the brain activity between the two conditions. We demonstrate the potential of attention weights as tools to guide experts in understanding which disease-relevant EEG features could be discriminative of SCD and MCI.

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.

Beyond Frequency Bands: Complementary-Ensemble-Empirical-Mode-Decomposition-Enhanced Microstate Sequence Non-Randomness Analysis for Aiding Diagnosis and Cognitive Prediction of Dementia

Exploring the spatiotemporal dynamic patterns of multi-channel electroencephalography (EEG) is crucial for interpreting dementia and related cognitive decline. Spatiotemporal patterns of EEG can be described through microstate analysis, which provides a discrete approximation of the continuous electric field patterns generated by the brain cortex. Here, we propose a novel microstate spatiotemporal dynamic indicator, termed the microstate sequence non-randomness index (MSNRI). The essence of the method lies in initially generating a sequence of microstate transition patterns through state space compression of EEG data using microstate analysis. Following this, we assess the non-randomness of these microstate patterns using information-based similarity analysis. The results suggest that this MSNRI metric is a potential marker for distinguishing between health control (HC) and frontotemporal dementia (FTD) (HC vs. FTD: 6.958 vs. 5.756, p < 0.01), as well as between HC and populations with Alzheimer's disease (AD) (HC vs. AD: 6.958 vs. 5.462, p < 0.001). Healthy individuals exhibit more complex macroscopic structures and non-random spatiotemporal patterns of microstates, whereas dementia disorders lead to more random spatiotemporal patterns. Additionally, we extend the proposed method by integrating the Complementary Ensemble Empirical Mode Decomposition (CEEMD) method to explore spatiotemporal dynamic patterns of microstates at specific frequency scales. Moreover, we assessed the effectiveness of this innovative method in predicting cognitive scores. The results demonstrate that the incorporation of CEEMD-enhanced microstate dynamic indicators significantly improved the prediction accuracy of Mini-Mental State Examination (MMSE) scores (R2 = 0.940). The CEEMD-enhanced MSNRI method not only aids in the exploration of large-scale neural changes in populations with dementia but also offers a robust tool for characterizing the dynamics of EEG microstate transitions and their impact on cognitive function.

Data leakage in deep learning studies of translational EEG

A growing number of studies apply deep neural networks (DNNs) to recordings of human electroencephalography (EEG) to identify a range of disorders. In many studies, EEG recordings are split into segments, and each segment is randomly assigned to the training or test set. As a consequence, data from individual subjects appears in both the training and the test set. Could high test-set accuracy reflect data leakage from subject-specific patterns in the data, rather than patterns that identify a disease? We address this question by testing the performance of DNN classifiers using segment-based holdout (in which segments from one subject can appear in both the training and test set), and comparing this to their performance using subject-based holdout (where all segments from one subject appear exclusively in either the training set or the test set). In two datasets (one classifying Alzheimer's disease, and the other classifying epileptic seizures), we find that performance on previously-unseen subjects is strongly overestimated when models are trained using segment-based holdout. Finally, we survey the literature and find that the majority of translational DNN-EEG studies use segment-based holdout. Most published DNN-EEG studies may dramatically overestimate their classification performance on new subjects.

Septohippocampal cholinergic system at the intersection of stress and cognition: Current trends and translational implications

Deficits in hippocampus-dependent memory processes are common across psychiatric and neurodegenerative disorders such as depression, anxiety and Alzheimer's disease. Moreover, stress is a major environmental risk factor for these pathologies and it exerts detrimental effects on hippocampal functioning via the activation of hypothalamic-pituitary-adrenal (HPA) axis. The medial septum cholinergic neurons extensively innervate the hippocampus. Although, the cholinergic septohippocampal pathway (SHP) has long been implicated in learning and memory, its involvement in mediating the adaptive and maladaptive impact of stress on mnemonic processes remains less clear. Here, we discuss current research highlighting the contributions of cholinergic SHP in modulating memory encoding, consolidation and retrieval. Then, we present evidence supporting the view that neurobiological interactions between HPA axis stress response and cholinergic signalling impact hippocampal computations. Finally, we critically discuss potential challenges and opportunities to target cholinergic SHP as a therapeutic strategy to improve cognitive impairments in stress-related disorders. We argue that such efforts should consider recent conceptualisations on the dynamic nature of cholinergic signalling in modulating distinct subcomponents of memory and its interactions with cellular substrates that regulate the adaptive stress response.

Classification of Sleep Quality and Aging as a Function of Brain Complexity: A Multiband Non-Linear EEG Analysis

Understanding and classifying brain states as a function of sleep quality and age has important implications for developing lifestyle-based interventions involving sleep hygiene. Current studies use an algorithm that captures non-linear features of brain complexity to differentiate awake electroencephalography (EEG) states, as a function of age and sleep quality. Fifty-eight participants were assessed using the Pittsburgh Sleep Quality Inventory (PSQI) and awake resting state EEG. Groups were formed based on age and sleep quality (younger adults n = 24, mean age = 24.7 years, SD = 3.43, good sleepers n = 11; older adults n = 34, mean age = 72.87; SD = 4.18, good sleepers n = 9). Ten non-linear features were extracted from multiband EEG analysis to feed several classifiers followed by a leave-one-out cross-validation. Brain state complexity accurately predicted (i) age in good sleepers, with 75% mean accuracy (across all channels) for lower frequencies (alpha, theta, and delta) and 95% accuracy at specific channels (temporal, parietal); and (ii) sleep quality in older groups with moderate accuracy (70 and 72%) across sub-bands with some regions showing greater differences. It also differentiated younger good sleepers from older poor sleepers with 85% mean accuracy across all sub-bands, and 92% at specific channels. Lower accuracy levels (<50%) were achieved in predicting sleep quality in younger adults. The algorithm discriminated older vs. younger groups excellently and could be used to explore intragroup differences in older adults to predict sleep intervention efficiency depending on their brain complexity.

Slowing of Parameterized Resting-State Electroencephalography After Mild Traumatic Brain Injury

Reported changes in electroencephalography (EEG)-derived spectral power after mild traumatic brain injury (mTBI) remains inconsistent across existing literature. However, this may be a result of previous analyses depending solely on observing spectral power within traditional canonical frequency bands rather than accounting for the aperiodic activity within the collected neural signal. Therefore, the aim of this study was to test for differences in rhythmic and arrhythmic time series across the brain, and in the cognitively relevant frontoparietal (FP) network, and observe whether those differences were associated with cognitive recovery post-mTBI. Resting-state electroencephalography (rs-EEG) was collected from 88 participants (56 mTBI and 32 age- and sex-matched healthy controls) within 14 days of injury for the mTBI participants. A battery of executive function (EF) tests was collected at the first session with follow-up metrics collected approximately 2 and 4 months after the initial visit. After spectral parameterization, a significant between-group difference in aperiodic-adjusted alpha center peak frequency within the FP network was observed, where a slowing of alpha peak frequency was found in the mTBI group in comparison to the healthy controls. This slowing of week 2 (collected within 2 weeks of injury) aperiodic-adjusted alpha center peak frequency within the FP network was associated with increased EF over time (evaluated using executive composite scores) post-mTBI. These findings suggest alpha center peak frequency within the FP network as a candidate prognostic marker of EF recovery and may inform clinical rehabilitative methods post-mTBI.

Classification of cognitive impairment using electroencephalography for clinical inspection

Impairment in cognitive skill though set-in due to various diseases, its progress is based on neuronal degeneration. In general, cognitive impairment (CI) is divided into three stages: mild, moderate and severe. Quantification of CI is important for deciding/changing therapy. Attempted in this work is to quantify electroencephalograph (EEG) signal and group it into four classes (controls and three stages of CI). After acquiring resting state EEG signal from the participants, non-local and local synchrony measures are derived from phase amplitude coupling and phase locking value. This totals to 160 features per individual for each task. Two types of classification networks are constructed. The first one is an artificial neural network (ANN) that takes derived features and gives a maximum accuracy of 85.11%. The second network is convolutional neural network (CNN) for which topographical images constructed from EEG features becomes the input dataset. The network is trained with 60% of data and then tested with remaining 40% of data. This process is performed in 5-fold technique, which yields an average accuracy of 94.75% with only 30 numbers of inputs for every individual. The result of the study shows that CNN outperforms ANN with a relatively lesser number of inputs. From this it can be concluded that this method proposes a simple task for acquiring EEG (which can be done by CI subjects) and quantifies CI stages with no overlapping between control and test group, thus making it possible for identifying early symptoms of CI.

Cognitive and Neuropathophysiological Outcomes of Gamma-tACS in Dementia: A Systematic Review

Despite the numerous pharmacological interventions targeting dementia, no disease-modifying therapy is available, and the prognosis remains unfavorable. A promising perspective involves tackling high-frequency gamma-band (> 30 Hz) oscillations involved in hippocampal-mediated memory processes, which are impaired from the early stages of typical Alzheimer's Disease (AD). Particularly, the positive effects of gamma-band entrainment on mouse models of AD have prompted researchers to translate such findings into humans using transcranial alternating current stimulation (tACS), a methodology that allows the entrainment of endogenous cortical oscillations in a frequency-specific manner. This systematic review examines the state-of-the-art on the use of gamma-tACS in Mild Cognitive Impairment (MCI) and dementia patients to shed light on its feasibility, therapeutic impact, and clinical effectiveness. A systematic search from two databases yielded 499 records resulting in 10 included studies and a total of 273 patients. The results were arranged in single-session and multi-session protocols. Most of the studies demonstrated cognitive improvement following gamma-tACS, and some studies showed promising effects of gamma-tACS on neuropathological markers, suggesting the feasibility of gamma-tACS in these patients anyhow far from the strong evidence available for mouse models. Nonetheless, the small number of studies and their wide variability in terms of aims, parameters, and measures, make it difficult to draw firm conclusions. We discuss results and methodological limitations of the studies, proposing possible solutions and future avenues to improve research on the effects of gamma-tACS on dementia.

Executive function measures of participants with mild cognitive impairment: Systematic review and meta-analysis of event-related potential studies

OBJECTIVE

Objective measurements of executive functions using event-related potential (ERP) may be used as markers for differentiating healthy controls (HC) from patients with mild cognitive impairment (MCI). ERP is non-invasive, cost-effective, and affordable. Older adults with MCI demonstrate deteriorated executive function, serving as a potentially valid neurophysiological marker for identifying MCI. We aimed to review published ERP studies on executive function in older adults with MCI and summarize the performance differences by component between healthy older adults and older adults with MCI.

METHODS

Eight electronic databases (Web of Science, PubMed, ScienceDirect, American Psychological Association PsycNet, Cochrane Library, Scopus, Embase, and Ovid) were searched for the study. Articles published from January 1 to December 31, 2022, were considered for this review. A random-effects meta-analysis and between-study heterogeneity analysis were conducted using Comprehensive Meta-Analysis V3.0 software.

RESULTS

We identified 7829 articles of which 28 met the full inclusion criteria and were included in the systematic review and analyses. Our pooled analysis suggested that participants with MCI can be differentiated from HC by significant P200, P300, and N200 latencies. The P100 and P300 amplitudes were significantly smaller in participants with MCI when compared with those in the HCs, and the patients with MCI showed increased N200 amplitudes. Our findings provide new insights into potential electrophysiological biomarkers for diagnosing MCI.

The effects of different acetylcholinesterase inhibitors on EEG patterns in patients with Alzheimer's disease: A systematic review

OBJECTIVE

Alzheimer's disease (AD) is a progressive neurodegenerative disorder and the most common type of dementia. The early diagnosis of AD is an important factor for the control of AD progression. Electroencephalography (EEG) can be used for early diagnosis of AD. Acetylcholinesterase inhibitors (AChEIs) are also used for the amelioration of AD symptoms. In this systematic review, we reviewed the effect of different AChEIs including donepezil, rivastigmine, tacrine, physostigmine, and galantamine on EEG patterns in patients with AD.

METHODS

PubMed electronic database was searched and 122 articles were found. After removal of unrelated articles, 24 articles were selected for the present study.

RESULTS

AChEIs can decrease beta, theta, and delta frequency bands in patients with AD. However, conflicting results were found for alpha band. Some studies have shown increased alpha frequency, while others have shown decreased alpha frequency following treatment with AChEIs. The only difference was the type of drug.

CONCLUSIONS

We found that studies reporting the decreased alpha frequency used donepezil and galantamine, while studies reporting the increased alpha frequency used rivastigmine and tacrine. It was suggested that future studies should focus on the effect of different AChEIs on EEG bands, especially alpha frequency in patients with AD, to compare their effects and find the reason for their different influence on EEG patterns. Also, differences between the effects of AChEIs on oligodendrocyte differentiation and myelination may be another important factor. This is the first article investigating the effect of different AChEIs on EEG patterns in patients with AD.

Quantitative EEG Spectral and Connectivity Analysis for Cognitive Decline in Amnestic Mild Cognitive Impairment

BACKGROUND

Mild cognitive impairment (MCI) is considered to be the borderline of cognitive changes associated with aging and very early dementia. Cognitive functions in MCI can improve, remain stable or progress to clinically probable AD. Quantitative electroencephalography (qEEG) can become a useful tool for using the analytical techniques to quantify EEG patterns indicating cognitive impairment.

OBJECTIVE

The aim of our study was to assess spectral and connectivity analysis of the EEG resting state activity in amnestic MCI (aMCI) patients in comparison with healthy control group (CogN).

METHODS

30 aMCI patients and 23 CogN group, matched by age and education, underwent equal neuropsychological assessment and EEG recording, according to the same protocol.

RESULTS

qEEG spectral analysis revealed decrease of global relative beta band power and increase of global relative theta and delta power in aMCI patients. Whereas, decreased coherence in centroparietal right area considered to be an early qEEG biomarker of functional disconnection of the brain network in aMCI patients. In conclusion, the demonstrated changes in qEEG, especially, the coherence patterns are specific biomarkers of cognitive impairment in aMCI.

CONCLUSIONS

Therefore, qEEG measurements appears to be a useful tool that complements neuropsychological diagnostics, assessing the risk of progression and provides a basis for possible interventions designed to improve cognitive functions or even inhibit the progression of the disease.

Neural Computation-Based Methods for the Early Diagnosis and Prognosis of Alzheimer's Disease Not Using Neuroimaging Biomarkers: A Systematic Review

Background

The growing number of older adults in recent decades has led to more prevalent geriatric diseases, such as strokes and dementia. Therefore, Alzheimer's disease (AD), as the most common type of dementia, has become more frequent too.

Background

Objective: The goals of this work are to present state-of-the-art studies focused on the automatic diagnosis and prognosis of AD and its early stages, mainly mild cognitive impairment, and predicting how the research on this topic may change in the future.

Methods

Articles found in the existing literature needed to fulfill several selection criteria. Among others, their classification methods were based on artificial neural networks (ANNs), including deep learning, and data not from brain signals or neuroimaging techniques were used. Considering our selection criteria, 42 articles published in the last decade were finally selected.

Results

The most medically significant results are shown. Similar quantities of articles based on shallow and deep ANNs were found. Recurrent neural networks and transformers were common with speech or in longitudinal studies. Convolutional neural networks (CNNs) were popular with gait or combined with others in modular approaches. Above one third of the cross-sectional studies utilized multimodal data. Non-public datasets were frequently used in cross-sectional studies, whereas the opposite in longitudinal ones. The most popular databases were indicated, which will be helpful for future researchers in this field.

Conclusions

The introduction of CNNs in the last decade and their superb results with neuroimaging data did not negatively affect the usage of other modalities. In fact, new ones emerged.