EEG microstate in first-episode drug-naive adolescents with depression

Sex differences of signal complexity at resting-state functional magnetic resonance imaging and their associations with the estrogen-signaling pathway in the brain

Sex differences in the brain have been widely reported and may hold the key to elucidating sex differences in many medical conditions and drug response. However, the molecular correlates of these sex differences in structural and functional brain measures in the human brain remain unclear. Herein, we used sample entropy (SampEn) to quantify the signal complexity of resting-state functional magnetic resonance imaging (rsfMRI) in a large neuroimaging cohort (N = 1,642). The frontoparietal control network and the cingulo-opercular network had high signal complexity while the cerebellar and sensory motor networks had low signal complexity in both men and women. Compared with those in male brains, we found greater signal complexity in all functional brain networks in female brains with the default mode network exhibiting the largest sex difference. Using the gene expression data in brain tissues, we identified genes that were significantly associated with sex differences in brain signal complexity. The significant genes were enriched in the gene sets that were differentially expressed between the brain cortex and other tissues, the estrogen-signaling pathway, and the biological function of neural plasticity. In particular, the G-protein-coupled estrogen receptor 1 gene in the estrogen-signaling pathway was expressed more in brain regions with greater sex differences in SampEn. In conclusion, greater complexity in female brains may reflect the interactions between sex hormone fluctuations and neuromodulation of estrogen in women.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-023-09954-y.

The Role of EEG microstates in predicting oxcarbazepine treatment outcomes in patients with newly-diagnosed focal epilepsy

PURPOSE

Microstates represent the global and topographical distribution of electrical brain activity from scalp-recorded EEG. This study aims to explore EEG microstates of patients with focal epilepsy prior to medication, and employ extracted microstate metrics for predicting treatment outcomes with Oxcarbazepine monotherapy.

METHODS

This study involved 25 newly-diagnosed focal epilepsy patients (13 females), aged 12 to 68, with various etiologies. Patients were categorized into Non-Seizure-Free (NSF) and Seizure-Free (SF) groups according to their first follow-up outcomes. From pre-medication EEGs, four representative microstates were identified by using clustering. The temporal parameters and transition probabilities of microstates were extracted and analyzed to discern group differences. With generating sample method, Support Vector Machine (SVM), Logistic Regression (LR), and Naïve Bayes (NB) classifiers were employed for predicting treatment outcomes.

RESULTS

In the NSF group, Microstate 1 (MS1) exhibited a significantly higher duration (mean±std. = 0.092±0.008 vs. 0.085±0.008, p = 0.047), occurrence (mean±std. = 2.587±0.334 vs. 2.260±0.278, p = 0.014), and coverage (mean±std. = 0.240±0.046 vs. 0.194±0.040, p = 0.014) compared to the SF group. Additionally, the transition probabilities from Microstate 2 (MS2) and Microstate 3 (MS3) to MS1 were increased. In MS2, the NSF group displayed a stronger correlation (mean±std. = 0.618±0.025 vs. 0.571±0.034, p < 0.001) and a higher global explained variance (mean±std. = 0.083±0.035 vs. 0.055±0.023, p = 0.027) than the SF group. Conversely, Microstate 4 (MS4) in the SF group demonstrated significantly greater coverage (mean±std. = 0.388±0.074 vs. 0.334±0.052, p = 0.046) and more frequent transitions from MS2 to MS4, indicating a distinct pattern. Temporal parameters contribute major predictive role in predicting treatment outcomes of Oxcarbazepine, with area under curves (AUCs) of 0.95, 0.70, and 0.86, achieved by LR, NB and SVM, respectively.

CONCLUSION

This study underscores the potential of EEG microstates as predictive biomarkers for Oxcarbazepine treatment responses in newly-diagnosed focal epilepsy patients.

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.

A gender recognition method based on EEG microstates

BACKGROUND

Gender carries important information related to male and female characteristics, and a large number of studies have attempted to use physiological measurement methods for gender classification. Although previous studies have shown that there exist statistical differences in some Electroencephalographic (EEG) microstate parameters between males and females, it is still unknown that whether these microstate parameters can be used as potential biomarkers for gender classification based on machine learning.

METHODS

We used two independent resting-state EEG datasets: the first dataset included 74 females and matched 74 males, and the second one included 42 males and matched 42 females. EEG microstate analysis based on modified k-means clustering method was applied, and temporal parameter and nonlinear characteristics (sample entropy and Lempel-Ziv complexity) of EEG microstate sequences were extracted to compare between males and females. More importantly, these microstate temporal parameters and complexity were tried to train six machine learning methods for gender classification.

RESULTS

We obtained five common microstates for each dataset and each group. Compared with the male group, the female group has significantly higher temporal parameters of microstate B, C, E and lower temporal parameters of microstate A and D, and higher complexity of microstate sequence. When using combination of microstate temporal parameters and complexity or only microstate temporal parameters as classification features in an independent test set (the second dataset), we achieved 95.2% classification accuracy.

CONCLUSION

Our research findings indicate that the dynamics of microstate have considerable Gender-specific alteration. EEG microstates can be used as neurophysiological biomarkers for gender classification.

Construction of machine learning models for recognizing comorbid anxiety in epilepsy patients based on their clinical and quantitative EEG features

BACKGROUND

This study aimed to construct prediction models for the recognizing of anxiety disorders (AD) in patients with epilepsy (PWEs) by combining clinical features with quantitative electroencephalogram (qEEG) features and using machine learning (ML).

METHODS

Nineteen clinical features and 20-min resting-state EEG were collected from 71 PWEs comorbid with AD and another 60 PWEs without AD who met the inclusion-exclusion criteria of this study. The EEG were preprocessed and 684 Phase Locking Value (PLV) and 76 Lempel-Ziv Complexity (LZC) features on four bands were extracted. The Fisher score method was used to rank all the derived features. We constructed four models for recognizing AD in PWEs, whether PWEs based on different combinations of features using eXtreme gradient boosting (XGboost) and evaluated these models using the five-fold cross-validation method.

RESULTS

The prediction model constructed by combining the clinical, PLV, and LZC features showed the best performance, with an accuracy of 96.18%, precision of 94.29%, sensitivity of 98.33%, F1-score of 96.06%, and Area Under the Curve (AUC) of 0.96. The Fisher score ranking results displayed that the top ten features were depression, educational attainment, α_P3LZC, α_T6-PzPLV, α_F7LZC, β_Fp2-O1PLV, θ_T4-CzPLV, θ_F7-PzPLV, α_Fp2LZC, and θ_T4-PzPLV.

CONCLUSIONS

The model, constructed by combining the clinical and qEEG features PLV and LZC, efficiently identified the presence of AD comorbidity in PWEs and might have the potential to complement the clinical diagnosis. Our findings suggest that LZC features in the α band and PLV features in Fp2-O1 may be potential biomarkers for diagnosing AD in PWEs.

Normative Temporal Dynamics of Resting EEG Microstates

The large-scale electrophysiological events known as electroencephalographic microstates provide an important window into the intrinsic activity of whole-brain neuronal networks. The spontaneous activity of coordinated brain networks, including the ongoing temporal dynamics expressed by microstates, are thought to reflect individuals' neurocognitive functioning, and predict development, disease progression, and psychological differences among varied populations. A comprehensive understanding of human brain function therefore requires characterizing typical and atypical patterns in the temporal dynamics of microstates. But population-level estimates of normative microstate temporal dynamics are still unknown. To address this gap, I conducted a systematic search of the literature and accompanying meta-analysis of the average dynamics of microstates obtained from studies investigating spontaneous brain activity in individuals during periods of eyes-closed and eyes-open rest. Meta-analyses provided estimates of the average temporal dynamics of microstates across 93 studies totaling 6583 unique individual participants drawn from diverse populations. Results quantified the expected range of plausible estimates of average microstate dynamics across study samples, as well as characterized heterogeneity resulting from sampling variability and systematic differences in development, clinical diagnoses, or other study methodological factors. Specifically, microstate dynamics significantly differed for samples with specific developmental differences or clinical diagnoses, relative to healthy, typically developing samples. This research supports the notion that microstates and their dynamics reflect functionally relevant properties of large-scale brain networks, encoding typical and atypical neurocognitive functioning.

Disrupted properties of functional brain networks in major depressive disorder during emotional face recognition: an EEG study via graph theory analysis

Previous neuroimaging studies have revealed abnormal brain networks in patients with major depressive disorder (MDD) in emotional processing. While any cognitive task consists of a series of stages, little is yet known about the topology of functional brain networks in MDD for these stages during emotional face recognition. To address this problem, electroencephalography (EEG)-based functional brain networks of MDD patients at different stages of facial information processing were investigated in this study. First, EEG signals were collected from 16 patients with MDD and 18 age-, gender-, and education-matched normal subjects when performing an emotional face recognition task. Second, the global field power (GFP) method was employed to divide group-averaged event-related potentials into different stages. Third, using the phase transfer entropy (PTE) approach, the brain networks of MDD patients and normal individuals were constructed for each stage in negative and positive face processing, respectively. Finally, we compared the topological properties of brain networks of each stage between the two groups using graph theory approaches. The results showed that the analyzed three stages of emotional face processing corresponded to specific neurophysiological phases, namely, visual perception, face recognition, and emotional decision-making. It was also demonstrated that depressed patients showed abnormally decreased characteristic path length at the visual perception stage of negative face recognition and normalized characteristic path length in the stage of emotional decision-making during positive face processing compared to healthy subjects. Furthermore, while both the MDD and normal groups' brain networks were found to exhibit small-world network characteristics, the brain network of patients with depression tended to be randomized. Moreover, for patients with MDD, the centro-parietal region may lose its status as a hub in the process of facial expression identification. Together, our findings suggested that altered emotional function in MDD patients might be associated with disruptions in the topological organization of functional brain networks during emotional face recognition, which further deepened our understanding of the emotion processing dysfunction underlying MDD.

A model for the diagnosis of anxiety in patients with epilepsy based on phase locking value and Lempel-Ziv complexity features of the electroencephalogram

OBJECTIVE

Anxiety disorders (AD) are critical factors that significantly (about one-fifth) impact the quality of life (QoL) in patients with epilepsy (PWE). Objective diagnostic methods have contributed to the identification of PWE susceptible to AD. This study aimed to identify AD in PWE by constructing a diagnostic model based on the phase locking value (PLV) and Lempel-Ziv Complexity (LZC) features of the electroencephalogram (EEG).

METHODS

EEG data from 131 patients with epilepsy (PWE) were enrolled in this study. Patients were divided into two groups, anxiety disorder (AD, n = 61) and non-anxiety disorder (NAD, n = 70), according to the Hamilton Rating Scale for Anxiety (HAM-A). Support vector machine (SVM) and K-Nearest-Neighbor(KNN) algorithms were used to construct three models - the PLVEEG, LZCEEG, and PLVEEG + LZCEEG feature models. Finally, the area under the receiver operating characteristic curve (AUC) and statistical analyses were performed to evaluate the model performance.

RESULTS

The efficiency of the KNN-based PLCEEG + LZCEEG feature model was the best, and the accuracy, precision, recall, F1-score, and AUC of the model after five-fold cross-validations scores were 87.89 %, 82.27 %, 98.33 %, 88.95 %, and 0.89, respectively. When the model efficiency was optimal, 29 EEG features were suggested. Further analysis of these features indicated 22 EEG features that were significantly different between the two groups, including 50 % features of the alpha (α)-band.

CONCLUSIONS

The PLVEEG + LZCEEG model features can identify AD in PWE. The PLVEEG and LZCEEG characteristics of the α-band may further be explored as potential biomarkers for AD in PWE.

EEG microstate analysis reveals large-scale brain network alterations in depressed adolescents with suicidal ideation

BACKGROUND

Accumulating evidence showed abnormalities in brain network connectivity in depressive individuals with suicidal ideation (SI). We aimed to investigate the large-scale brain network dynamics in adolescents with SI and major depressive disorder (MDD).

METHODS

We recruited 47 first-episode drug-naïve adolescents with MDD and SI, 26 depressed adolescents without SI (noSI), and 26 age-matched healthy controls (HC). The Columbia Suicidal Ideation Severity Scale (C-SSRS) was utilized to assess suicide ideation. We acquired 64-channel resting-state EEG recordings from all subjects and used microstate analysis to investigate the large-scale brain network dynamics.

RESULTS

We observed a significant reduction in the occurrence and coverage of microstate B within the SI group when contrasted with the noSI group. Conversely, there was a significant increase in the occurrence and coverage of microstate A in the SI group as compared to the HC group. Additionally, we observed heightened transition probabilities from microstates D and C to microstate A in the SI group; meanwhile, transitions from microstate D to B were more prevalent in the noSI group. Furthermore, the noSI group exhibited a significant decline in the transition probabilities from microstate D to microstate C.

LIMITATIONS

The cross-sectional nature limits the capacity to determine whether microstate dynamics have prognostic significance for SI.

CONCLUSION

We provided evidence that depressed adolescents with SI have a distinct pattern in microstate dynamics compared to those without SI. These findings suggest that microstate dynamics might serve as a potential neurobiomarker for identifying SI in depressed adolescents.

Electroencephalography microstates as novel functional biomarkers for insomnia disorder

Background

Insomnia disorder (ID) is one of the most common mental disorders. Research on ID focuses on exploring its mechanism of disease, novel treatments and treatment outcome prediction. An emerging technique in this field is the use of electroencephalography (EEG) microstates, which offer a new method of EEG feature extraction that incorporates information from both temporal and spatial dimensions.

Aims

To explore the electrophysiological mechanisms of repetitive transcranial magnetic stimulation (rTMS) for ID treatment and use baseline microstate metrics for the prediction of its efficacy.

Methods

This study included 60 patients with ID and 40 age-matched and gender-matched good sleep controls (GSC). Their resting-state EEG microstates were analysed, and the Pittsburgh Sleep Quality Index (PSQI) and polysomnography (PSG) were collected to assess sleep quality. The 60 patients with ID were equally divided into active and sham groups to receive rTMS for 20 days to test whether rTMS had a moderating effect on abnormal microstates in patients with ID. Furthermore, in an independent group of 90 patients with ID who received rTMS treatment, patients were divided into optimal and suboptimal groups based on their median PSQI reduction rate. Baseline EEG microstates were used to build a machine-learning predictive model for the effects of rTMS treatment.

Results

The class D microstate was less frequent and contribute in patients with ID, and these abnormalities were associated with sleep onset latency as measured by PSG. Additionally, the abnormalities were partially reversed to the levels observed in the GSC group following rTMS treatment. The baseline microstate characteristics could predict the therapeutic effect of ID after 20 days of rTMS, with an accuracy of 80.13%.

Conclusions

Our study highlights the value of EEG microstates as functional biomarkers of ID and provides a new perspective for studying the neurophysiological mechanisms of ID. In addition, we predicted the therapeutic effect of rTMS on ID based on the baseline microstates of patients with ID. This finding carries great practical significance for the selection of therapeutic options for patients with ID.

AMGCN-L: an adaptive multi-time-window graph convolutional network with long-short-term memory for depression detection

Objective.Depression is a common chronic mental disorder characterized by high rates of prevalence, recurrence, suicide, and disability as well as heavy disease burden. An accurate diagnosis of depression is a prerequisite for treatment. However, existing questionnaire-based diagnostic methods are limited by the innate subjectivity of medical practitioners and subjects. In the search for a more objective diagnostic methods for depression, researchers have recently started to use deep learning approaches.Approach.In this work, a deep-learning network, named adaptively multi-time-window graph convolutional network (GCN) with long-short-term memory (LSTM) (i.e. AMGCN-L), is proposed. This network can automatically categorize depressed and non-depressed people by testing for the existence of inherent brain functional connectivity and spatiotemporal features contained in electroencephalogram (EEG) signals. AMGCN-L is mainly composed of two sub-networks: the first sub-network is an adaptive multi-time-window graph generation block with which adjacency matrices that contain brain functional connectivity on different time periods are adaptively designed. The second sub-network consists of GCN and LSTM, which are used to fully extract the innate spatial and temporal features of EEG signals, respectively.Main results.Two public datasets, namely the patient repository for EEG data and computational tools, and the multi-modal open dataset for mental-disorder analysis, were used to test the performance of the proposed network; the depression recognition accuracies achieved in both datasets (using tenfold cross-validation) were 90.38% and 90.57%, respectively.Significance.This work demonstrates that GCN and LSTM have eminent effects on spatial and temporal feature extraction, respectively, suggesting that the exploration of brain connectivity and the exploitation of spatiotemporal features benefit the detection of depression. Moreover, the proposed method provides effective support and supplement for the detection of clinical depression and later treatment procedures.

Resting-state EEG microstates as electrophysiological biomarkers in post-stroke disorder of consciousness

Introduction

Ischemic stroke patients commonly experience disorder of consciousness (DOC), leading to poorer discharge outcomes and higher mortality risks. Therefore, the identification of applicable electrophysiological biomarkers is crucial for the rapid diagnosis and evaluation of post-stroke disorder of consciousness (PS-DOC), while providing supportive evidence for cerebral neurology.

Methods

In our study, we conduct microstate analysis on resting-state electroencephalography (EEG) of 28 post-stroke patients with awake consciousness and 28 patients with PS-DOC, calculating the temporal features of microstates. Furthermore, we extract the Lempel-Ziv complexity of microstate sequences and the delta/alpha power ratio of EEG on spectral. Statistical analysis is performed to examine the distinctions in features between the two groups, followed by inputting the distinctive features into a support vector machine for the classification of PS-DOC.

Results

Both groups obtain four optimal topographies of EEG microstates, but notable distinctions are observed in microstate C. Within the PS-DOC group, there is a significant increase in the mean duration and coverage of microstates B and C, whereas microstate D displays a contrasting trend. Additionally, noteworthy variations are found in the delta/alpha ratio and Lempel-Ziv complexity between the two groups. The integration of the delta/alpha ratio with microstates' temporal and Lempel-Ziv complexity features demonstrates the highest performance in the classifier (Accuracy = 91.07%).

Discussion

Our results suggest that EEG microstates can provide insights into the abnormal brain network dynamics in DOC patients post-stroke. Integrating the temporal and Lempel-Ziv complexity microstate features with spectral features offers a deeper understanding of the neuro mechanisms underlying brain damage in patients with DOC, holding promise as effective electrophysiological biomarkers for diagnosing PS-DOC.

Neurophysiological biomarkers for depression classification: Utilizing microstate k-mers and a bag-of-words model

Microstates are analogous to characters in a language, and short fragments consisting of several microstates (k-mers) are analogous to words. We aimed to investigate whether microstate k-mers could be used as neurophysiological biomarkers to differentiate between depressed patients and normal controls. We utilized a bag-of-words model to process microstate sequences, using k-mers with a k range of 1-10 as terms, and the term frequency (TF) with or without inverse-document-frequency (IDF) as features. We performed nested cross-validation on Dataset 1 (27 patients and 26 controls) and Dataset 2 (34 patients and 30 controls) separately and then trained on one dataset and tested on the other. The best area under the curve (AUC) of 81.5% was achieved for the model with L1 regularization using the TF of 4-mers as features in Dataset 1, and the best AUC of 88.9% was achieved for the model with L1 regularization using the TF of 9-mers as features in Dataset 2. When Dataset 1 was used as the training set, the best AUC of predicting Dataset 2 was 74.1% for the model with L2 regularization using the TF-IDF of 9-mers as features, while the best AUC of predicting Dataset 1 was 70.2% for the model with L1 regularization using the TF of 8-mers as features. Our study provided novel insights into the potential of microstate k-mers as neurophysiological biomarkers for individual-level classification of depression. These may facilitate further exploration of microstate sequences using natural language processing techniques.

Degradation of EEG microstates patterns in subjective cognitive decline and mild cognitive impairment: Early biomarkers along the Alzheimer's Disease continuum?

Alzheimer's disease (AD) pathological changes may begin up to decades earlier than the appearance of the first symptoms of cognitive decline. Subjective cognitive decline (SCD) could be the first pre-clinical sign of possible AD, which might be followed by mild cognitive impairment (MCI), the initial stage of clinical cognitive decline. However, the neural correlates of these prodromic stages are not completely clear yet. Recent studies suggest that EEG analysis tools characterizing the cortical activity as a whole, such as microstates and cortical regions connectivity, might support a characterization of SCD and MCI conditions. Here we test this approach by performing a broad set of analyses to identify the prominent EEG markers differentiating SCD (n = 57), MCI (n = 46) and healthy control subjects (HC, n = 19). We found that the salient differences were in the temporal structure of the microstates patterns, with MCI being associated with less complex sequences due to the altered transition probability, frequency and duration of canonic microstate C. Spectral content of EEG, network connectivity, and spatial arrangement of microstates were instead largely similar in the three groups. Interestingly, comparing properties of EEG microstates in different cerebrospinal fluid (CSF) biomarkers profiles, we found that canonic microstate C displayed significant differences in topography in AD-like profile. These results show that the progression of dementia might be associated with a degradation of the cortical organization captured by microstates analysis, and that this leads to altered transitions between cortical states. Overall, our approach paves the way for the use of non-invasive EEG recordings in the identification of possible biomarkers of progression to AD from its prodromal states.