Electroencephalogram Features Research Articles

Machine learning for forecasting initial seizure onset in neonatal hypoxic-ischemic encephalopathy.

This study was undertaken to develop a machine learning (ML) model to forecast initial seizure onset in neonatal hypoxic-ischemic encephalopathy (HIE) utilizing clinical and quantitative electroencephalogram (QEEG) features. We developed a gradient boosting ML model (Neo-GB) that utilizes clinical features and QEEG to forecast time-dependent seizure risk. Clinical variables included cord blood gas values, Apgar scores, gestational age at birth, postmenstrual age (PMA), postnatal age, and birth weight. QEEG features included statistical moments, spectral power, and recurrence quantification analysis (RQA) features. We trained and evaluated Neo-GB on a University of California, San Francisco (UCSF) neonatal HIE dataset, augmenting training with publicly available neonatal electroencephalogram (EEG) datasets from Cork University and Helsinki University Hospitals. We assessed the performance of Neo-GB at providing dynamic and static forecasts with diagnostic performance metrics and incident/dynamic area under the receiver operating characteristic curve (iAUC) analyses. Model explanations were performed to assess contributions of QEEG features and channels to model predictions. The UCSF dataset included 60 neonates with HIE (30 with seizures). In subject-level static forecasting at 30 min after EEG initiation, baseline Neo-GB without time-dependent features had an area under the receiver operating characteristic curve (AUROC) of .76 and Neo-GB with time-dependent features had an AUROC of .89. In time-dependent evaluation of the initial seizure onset within a 24-h seizure occurrence period, dynamic forecast with Neo-GB demonstrated median iAUC = .79 (interquartile range [IQR] .75-.82) and concordance index (C-index) = .82, whereas baseline static forecast at 30 min demonstrated median iAUC = .75 (IQR .72-.76) and C-index = .69. Model explanation analysis revealed that spectral power, PMA, RQA, and cord blood gas values made the strongest contributions in driving Neo-GB predictions. Within the most influential EEG channels, as the preictal period advanced toward eventual seizure, there was an upward trend in broadband spectral power. This study demonstrates an ML model that combines QEEG with clinical features to forecast time-dependent risk of initial seizure onset in neonatal HIE. Spectral power evolution is an early EEG marker of seizure risk in neonatal HIE.

Multi-modal EEG NEO-FFI with Trained Attention Layer (MENTAL) for mental disorder prediction.

Early detection and accurate diagnosis of mental disorders is difficult due to the complexity of the diagnostic process, resulting in conditions being left undiagnosed or misdiagnosed. Previous studies have demonstrated that features of Electroencephalogram (EEG) data, such as Power Spectral Density (PSD), are useful biomarkers for indicating the onset of various mental disorders. Existing models using EEG data are typically trained to distinguish between healthy and afflicted individuals, and they are unable to distinguish between individuals with different disorders. We propose MENTAL (Multi-modal EEG NEO-FFI with Trained Attention Layer) to predict an individual's mental state using both EEG and Neo-Five Factor Inventory (NEO-FFI) personality data. We include an attention layer that captures the interactions between personality traits and PSD features, and emphasizes the important PSD features. MENTAL features a Recurrent Neural Network (RNN) to model the temporal nature of EEG data. We train our model with the Two Decades Brainclinics Research Archive for Insights in Neuroscience (TDBRAIN) dataset, which consists of 1274 healthy and psychiatric individuals including over 30 different diagnoses. MENTAL is able to achieve 93.3% accuracy when trained to classify between healthy individuals and those with ADHD. When trained to identify individuals with ADHD from among 33 disorder classes, MENTAL improves accuracy from 70.5 to 81.7%. MENTAL also demonstrates over 20% improvement in predictive accuracy when trained for MDD prediction. For the multi-class classification task of three classes, MENTAL improves accuracy by 4%, and for five classes, by nearly 8%. MENTAL is the first multi-modal model that utilizes both EEG and NEO-FFI data for the task of mental disorder prediction. We are one of the first groups to utilize TDBRAIN for automated disorder classification. MENTAL is accessible and cost-effective, as EEG is more affordable than other neuroimaging methods such as MRI, and the NEO-FFI is a self- reported survey. Our model can lead to acceptance and support for individuals living with mental health challenges and improve quality of life in our society.

Analysis of Quantitative Electroencephalogram Characteristics in Patients with Persistent Posture-Perceived Dizziness

Analysis of Quantitative Electroencephalogram Characteristics in Patients with Persistent Posture-Perceived Dizziness

Clinical Features and Electroencephalogram Analysis ofBrain Network Functional Connectivityin Anti-Leucine-RichGlioma-Inactivated1Antibody Encephalitis.

To summarize the clinical manifestations, laboratory findings, and magnetic resonance imaging (MRI) characteristics of anti-leucine-rich glioma-inactivated 1 (LGI1) antibody encephalitis (anti-LGI1 antibody encephalitis) and explore the electroencephalogram (EEG) features. We retrospectively analyzed the medical history of 16 patients diagnosed with anti-LGI1 antibody encephalitis at the First Hospital of Hebei Medical University from 2021 to 2023. EEGs of patients with anti-LGI1 antibody encephalitis and healthy individuals were analyzed. Based on Video-EEG signal analysis of EEG δ, θ, α, β frequency bands, weighted phase lag index values were calculated to form brain network matrices, studying differences in coherence between brain regions of patients with anti-LGI1 antibody encephalitis and healthy individuals. Patients with anti-LGI1 antibody encephalitis often presented with subacute onset seizures and cognitive decline. Routine test of cerebrospinal fluid was mostly normal. Serum testing revealed hyponatremia in 62.50% of patients, along with positive serum antinuclear antibodies, decreased vitamin B12, and abnormal cytokines such as interleukin-6. Head MRI revealed abnormal lesions related to the disease in seven cases (43.75%), mainly located in the unilateral or bilateral frontal and temporal lobes of the hippocampus. The EEG mainly showed generalized and focal slow waves, sometimes with focal discharges. Brain network functional connectivity analysis found a significant weakening of functional connections in the frontal-temporal lobe in the δ and β frequency bands. Intravenous pulse corticosteroids and intravenous immunoglobulin are first-line immunotherapies for anti-LGI1 antibody-related encephalitis. The disease recovery and cognitive decline improved in most patients. Anti-LGI1 antibody encephalitis is characterized by seizures and cognitive dysfunction. Serum may show abnormalities in immune indicators such as cytokines. Head MRI mainly reveals abnormal signals in the frontal-temporal lobes and the hippocampus. EEG brain network connectivity analysis reveals characteristic weakening of functional connections in the frontal-temporal lobe in the δ and β frequency bands.

Comparison of Brain Activity between Patients with Parkinson Disease Dementia and Patients Affected by Dementia with Lewy Body through EEG Analysis

Objective: Parkinson's disease dementia (PDD) and Dementia with Lewy bodies (DLB) are two syndromes categorized under synucleinopathy, sharing comparable symptoms. The identification of biomarkers would offer an accurate approach for improved diagnosis, treatment, and monitoring of treatment efficacy for these distinct forms of dementia. Method: This study utilized spectral analysis and nonlinear dynamic analysis to compare electroencephalogram (EEG) characteristics between PDD and DLB patients. EEG data was collected from 30 PDD patients, 36 DLB patients, and 36 healthy subjects at rest. Following a conditioning phase to minimize noise and eliminate artifacts, we derived spectral and complexity features using Welch's method and sample entropy. Analysis of variance with repeated measures was performed to compare spectral features and nonlinear dynamics of brain activity between the groups. Results: Post hoc comparison showed that in the control group, the power of delta and theta bands was lower and the power of alpha and beta bands was higher than in patients with PDD and DLB. (P < 0.05). In the theta and alpha bands, the PDD group showed greater power than the DLB group (P < 0.05). Furthermore, there was a significant main effect of diagnosis (F = 4.67, P = 0.007), and also the diagnosis by region interaction for complexity values (F = 4.58, P = 0.009). Post hoc analysis showed that the EEG complexity of the control group was significantly higher than that of the PDD and DLB groups in the frontal, central, temporal and parietal regions (P < 0.05). Moreover, the EEG complexity of the PDD group was significantly higher than that of the DLB group in the central, temporal and parietal regions (P < 0.05). Conclusion: Although both PDD and DLB had almost similar patterns compared to the control group, they showed differences in the EEG power spectrum and its nonlinear dynamics. Our findings indicated marked diffuse slowing and lower cortical complexity or activity in DLB patients compared to PDD in all regions, especially in the central, temporal and parietal areas.

Individuals with high autism traits show top-down attention bias towards threatening stimuli

Individuals with autistic traits (AT) are widely distributed in the general population. Strengthening understanding of AT can provide a broader perspective for autism research as well as more accurate diagnosis and personalized treatment plans for clinical practice. Previous studies on attention bias among high-AT individuals have yielded inconsistent results, which may relate to different stages of attention. In this study, we selected two groups with high and low level AT from the general population, and then adopted the odd-one-out search task, combined with Event-related potential (ERP) technique, conducted both attention orientation and attention dissociation tasks, to explore attention bias and electroencephalogram (EEG) characteristics towards threatening emotional faces in these groups. The behavioral data showed no accelerated attention orientation to angry faces and neutral faces; however, there was attention dissociation difficulty for angry faces. Compared with low-AT individuals, the EEG results showed that high-AT individuals have acceleration of attention orientation and attention dissociation difficulty for threatening emotional faces. From the perspective of top-down concept-driven processing, these findings suggest that high-AT individuals have attention bias for cognitive processing of threatening stimuli, which is mainly due to acceleration of attention orientation and attention dissociation difficulties for threatening information.

Unconscious classification of quantitative electroencephalogram features from propofol versus propofol combined with etomidate anesthesia using one-dimensional convolutional neural network.

Establishing a convolutional neural network model for the recognition of characteristic raw electroencephalogram (EEG) signals is crucial for monitoring consciousness levels and guiding anesthetic drug administration. This trial was conducted from December 2023 to March 2024. A total of 40 surgery patients were randomly divided into either a propofol group (1% propofol injection, 10 mL: 100 mg) (P group) or a propofol-etomidate combination group (1% propofol injection, 10 mL: 100 mg, and 0.2% etomidate injection, 10 mL: 20 mg, mixed at a 2:1 volume ratio) (EP group). In the P group, target-controlled infusion (TCI) was employed for sedation induction, with an initial effect site concentration set at 5-6 μg/mL. The EP group received an intravenous push with a dosage of 0.2 mL/kg. Six consciousness-related EEG features were extracted from both groups and analyzed using four prediction models: support vector machine (SVM), Gaussian Naive Bayes (GNB), artificial neural network (ANN), and one-dimensional convolutional neural network (1D CNN). The performance of the models was evaluated based on accuracy, precision, recall, and F1-score. The power spectral density (94%) and alpha/beta ratio (72%) demonstrated higher accuracy as indicators for assessing consciousness. The classification accuracy of the 1D CNN model for anesthesia-induced unconsciousness (97%) surpassed that of the SVM (83%), GNB (81%), and ANN (83%) models, with a significance level of p < 0.05. Furthermore, the mean and mean difference ± standard error of the primary power values for the EP and P groups during the induced period were as follows: delta (23.85 and 16.79, 7.055 ± 0.817, p < 0.001), theta (10.74 and 8.743, 1.995 ± 0.7045, p < 0.02), and total power (24.31 and 19.72, 4.588 ± 0.7107, p < 0.001). Large slow-wave oscillations, power spectral density, and the alpha/beta ratio are effective indicators of changes in consciousness during intravenous anesthesia with a propofol-etomidate combination. These indicators can aid anesthesiologists in evaluating the depth of anesthesia and adjusting dosages accordingly. The 1D CNN model, which incorporates consciousness-related EEG features, represents a promising tool for assessing the depth of anesthesia. https://www.chictr.org.cn/index.html.

Research on Assessment Method for Cognitive Influence Factors of Nuclear Power Plant Operators Based on Fuzzy Analytic Hierarchy Process and Deep Learning of Electroencephalogram Signals

This study explores the factors influencing the cognitive processes of operators in digital nuclear power plants, with a focus on the correlation between these factors and electroencephalogram (EEG) features. Initially, based on expert consultations, seven factors were considered: stress, time, fatigue, procedural complexity, user interface experience, procedural clarity, and efficiency. From these, four were identified as the most crucial for each stage of the cognitive process, highlighting their significant roles in influencing cognitive performance and potentially correlating with distinct EEG characteristics. These were assessed using the fuzzy analytic hierarchy process (FAHP) to determine the weightings of influences across the cognitive stages of monitoring, decision making, and execution. Employing a simulated scenario of a steam generator tube rupture, subjective questionnaires were utilized to gauge participant perceptions of influencer impacts at each stage, calculating human factors fuzzy synthetic values. Concurrently, EEG signals were segmented by operational steps, extracting around 114 features across the time, frequency, and time-frequency domains, which were then dimensionally reduced to 17 principal components via adaptive principal components analysis (APCA). A correlation analysis was performed between the human factors fuzzy synthetic values and the APCA-reduced EEG features of participants. Subsequently, the EEG feature columns of the eight selected participants were used as inputs to construct a transformer-based self-attention network model to evaluate the participants’ human factors fuzzy comprehensive values. The findings confirm the transformer model’s efficacy in assessing these values, evidencing a significant correlation between the EEG features and human factors fuzzy synthetic values. Integrating FAHP with machine learning methodologies, this model proficiently estimated operators’ cognitive states during various cognitive processes, significantly enhancing human-machine interface design and the operational safety and efficiency at nuclear power plants.

Effect of sleep-disordered breathing on stable electroencephalographic characteristics during night sleep in patients with arterial hypertension

Introduction. Obstructive sleep apnea (OSA) is the most common sleep-disordered breathing condition. A significant number of OSA patients often present with cardiovascular comorbidities, particularly arterial hypertension. OSA is associated with changes in bioelectrical activity of the brain, such as slowing of electroencephalographic activity in the cortex and reduced interhemispheric synchronization. These changes can become pathophysiological markers of sleep-disordered breathing.Aim. To investigate the effect of sleep-disordered breathing on a range of quantitative electroencephalogram (EEG) characteristics during nighttime sleep in patients with arterial hypertension and clinically significant OSA.Materials and methods. The material for this retrospective study consisted of 84 polysomnographic records of patients predominantly diagnosed with arterial hypertension. Patients were divided into three groups based on the apneahypopnea index (AHI). Polysomnographic records were used to assess the synchronization measure of brain electrical activity between occipital EEG leads. The synchronization measure was evaluated using a method based on wavelet bicoherence calculation.Results. Statistically significant differences were observed in the low-frequency ranges Δf1-Δf4: 0.2-1.0 Hz, 0.8-1.6 Hz, 1.0-2.0 Hz, 1.0-4.0 Hz. In these frequencies, the interhemispheric synchronization measure significantly decreased with increasing severity of apnea.Conclusion. To determine the severity of obstructive sleep apnea, a parameter based on the synchronization measure evaluated from symmetrical occipital EEG signals in the frequency ranges 0.2-1.0 Hz, 0.8-1.6 Hz, 1.0-2.0 Hz, and 1.0-4.0 Hz can be considered. This may serve as the basis for developing and implementing new diagnostic tools for assessing the severity of sleep-disordered breathing in practice.

SleepGCN: A transition rule learning model based on Graph Convolutional Network for sleep staging

Background and Objective:Automatic sleep staging is essential for assessing and diagnosing sleep disorders, serving millions of people who suffer from them. Numerous sleep staging models have been proposed recently, but most of them have not fully explored the sleep transition rules that are essential for sleep experts to identify sleep stages. Therefore, one objective of this paper is to develop an automatic sleep staging model to capture the transition rules between sleep stages. Methods:In this paper, we propose a novel sleep staging model named SleepGCN. It utilizes the deep features of electroencephalogram (EEG) and electrooculogram (EOG) signals extracted by the sleep representation learning (SRL) module, in conjunction with the transition rules learned by the sleep transition rule learning (STRL) module to identify sleep stages. Specifically, the SRL module utilizes the residual network (ResNet) and Long Short Term Memory (LSTM) structure to capture the deep time-invariant features and temporal information of each sleep stage from the two-channel EEG-EOG, and then applies a feature enhancement block to obtain the refined features. The STRL module employs a Graph Convolutional Network (GCN) and a transition rule matrix to capture transition rules between sleep stages based on the sequence labels of the input signals. Results:We evaluate SleepGCN on five public datasets: SleepEDF-20, SleepEDF-78, SHHS, DOD-H and DOD-O. Overall, SleepGCN achieves an accuracy of 89.70%, 87.70%, 86.16%, 82.07%, and 81.20%, alongside a macro-average F1-score of 85.20%, 82.70%, 77.69%, 72.44%, and 72.93% across these datasets, respectively. Conclusions:The results achieved by our proposed model are much better than those of all other compared models. The ablation study validates the contributions of the SRL and STRL modules proposed in SleepGCN to the sleep staging tasks. Additionally, it shows that the sleep staging model using two-channel EEG-EOG outperforms the model using single-channel EEG or EOG. Overall, SleepGCN is an effective solution for sleep staging using two-channel EEG-EOG.

Neurofeedback Training in Children with ADHD: A Systematic Review of Personalization and Methodological Features Facilitating Training Conditions.

Objective. Current research on the effectiveness of neurofeedback (NFB) in children with attention-deficit/hyperactivity disorder (ADHD) is divided. Personalized NFB (pNFB), using pre-recorded individual electroencephalogram (EEG) features, is hypothesized to provide more reliable results. Our paper reviews available evidence on pNFB effectiveness and its methodological quality. Additionally, it explores whether other methodological features implying personalization are related to successful NFB. Methods. We conducted a systematic literature review on PubMed, PSYNDEX, PsycInfo and PsycArticles until November, 30, 2023. Studies that focused on pNFB in children with ADHD were selected, deviant studies excluded. Quality ratings by independent raters using Loney's1 criteria were conducted. Pooled effect sizes for NFB effects and methodological features were calculated. Results. Three of 109 studies included personalization and were reviewed in the full-text. In two studies, theta/beta-NFB was personalized using individual alpha peak frequencies (iAPF), whereas in one study, individual beta rhythms were trained. All three studies demonstrated significant short- and long-term improvements in ADHD symptoms, as assessed by questionnaires and objective performance tests, when compared to standard protocols (SP), sham-NFB, and control conditions. Twelve of 111 studies reported methodological features consistently related to NFB effectiveness. These features, including self-control instructions, feedback animations, timing of feedback presentation, behavioral performance, pre-recorded individual ERP-components and stimulant medication dosage, can be used to personalize NFB and enhance training success. Conclusion. Personalizing NFB with iAPF appears promising based on the existing -albeit small- body of research. Future NFB studies should include iAPF and other personalized features facilitating implementation consistently associated with treatment success.

A review of graph theory-based diagnosis of neurological disorders based on EEG and MRI

Graph theory analysis, as a mathematical tool, has been widely employed in studying the connectivity of the brain to explore the structural organization. Through the computation of graph theory metrics, it can effectively reveal the nonlinear and complex behavioral features of neuroimaging data, e.g., Electroencephalogram (EEG) and Magnetic Resonance Imaging (MRI), which are often challenging to interpret using simple linear methods. Graph neural networks (GNNs), employing deep learning, offer a more flexible approach to handling large-scale, high-dimensional brain network data. This review aims to investigate the applications of graph theory and Graph Neural Networks in the diagnosis of neurological disorders. The complexity and multi-level features of neurological disorders pose challenges for traditional methods in addressing such issues. The paper begins by introducing the fundamental principles of graph theory and GNNs, elucidates the mechanisms behind diagnosis process using these methods, and then provides a comprehensive overview of their specific applications. Finally, it discusses and summarizes the current challenges in this research field, proposing future directions for development. In conclusion, this review provides a thorough theoretical foundation and methodological insight for exploring the potential applications of graph theory and GNNs in the diagnosis of neurological disorders.

A novel temporal-frequency combination pattern optimization approach based on information fusion for motor imagery BCIs

Motor imagery (MI) stands as a powerful paradigm within Brain-Computer Interface (BCI) research due to its ability to induce changes in brain rhythms detectable through common spatial patterns (CSP). However, the raw feature sets captured often contain redundant and invalid information, potentially hindering CSP performance. Methodology-wise, we propose the Information Fusion for Optimizing Temporal-Frequency Combination Pattern (IFTFCP) algorithm to enhance raw feature optimization. Initially, preprocessed data undergoes simultaneous processing in both time and frequency domains via sliding overlapping time windows and filter banks. Subsequently, we introduce the Pearson-Fisher combinational method along with Discriminant Correlation Analysis (DCA) for joint feature selection and fusion. These steps aim to refine raw electroencephalogram (EEG) features. For precise classification of binary MI problems, an Radial Basis Function (RBF)-kernel Support Vector Machine classifier is trained. To validate the efficacy of IFTFCP and evaluate it against other techniques, we conducted experimental investigations using two EEG datasets. Results indicate a notably superior classification performance, boasting an average accuracy of 78.14% and 85.98% on dataset 1 and dataset 2, which is better than other methods outlined in this article. The study’s findings suggest potential benefits for the advancement of MI-based BCI strategies, particularly in the domain of feature fusion.

Recognition of regions of stroke injury using multi-modal frequency features of electroencephalogram.

Nowadays, increasingly studies are attempting to analyze strokes in advance. The identification of brain damage areas is essential for stroke rehabilitation. We proposed Electroencephalogram (EEG) multi-modal frequency features to classify the regions of stroke injury. The EEG signals were obtained from stroke patients and healthy subjects, who were divided into right-sided brain injury group, left-sided brain injury group, bilateral brain injury group, and healthy controls. First, the wavelet packet transform was used to perform a time-frequency analysis of the EEG signal and extracted a set of features (denoted as WPT features). Then, to explore the nonlinear phase coupling information of the EEG signal, phase-locked values (PLV) and partial directed correlations (PDC) were extracted from the brain network, and the brain network produced a second set of features noted as functional connectivity (FC) features. Furthermore, we fused the extracted multiple features and used the resnet50 convolutional neural network to classify the fused multi-modal (WPT + FC) features. The classification accuracy of our proposed methods was up to 99.75%. The proposed multi-modal frequency features can be used as a potential indicator to distinguish regions of brain injury in stroke patients, and are potentially useful for the optimization of decoding algorithms for brain-computer interfaces.

Exploring the influence of subjective thermal perception on electroencephalogram characteristics based on prior thermal experience

Achieving thermal comfort for occupants in a dynamic environment that reflects their previous thermal experiences is essential for enhancing satisfaction. Current models do not fully consider these dynamic elements, thus limiting advancements in occupants' thermal comfort. This study aims to delineate the characteristics of electroencephalogram (EEG) responses aligned with subjective thermal perception in various thermal environment scenarios, inclusive of past thermal experiences. It focuses on identifying EEG indices, brain regions, and temporal markers that can distinguish between different thermal perceptions. The study involves sixteen male participants who undergo three thermal experience scenarios: predicted mean vote (PMV) 0 → PMV +2, PMV +2 → PMV –2, and PMV -2 → PMV +2. Our results highlight the sensitivity of the F3 channel in the left frontal lobe to thermal environments. The study identifies a pivotal time frame of 6 min after the experiment's start as significant for differentiating thermal perception groups. Additionally, it reveals that the EEG indices reacting to thermal changes vary depending on the participants' previous thermal experiences. These findings indicate that physiological signals, particularly EEG responses, can serve as effective biomarkers for distinguishing thermal perceptions in diverse thermal experience scenarios. This research emphasizes the need to integrate a variety of thermal environment scenarios, considering previous thermal experiences, into personal comfort models for more effective and tailored thermal comfort solutions.

Combining EEG Features and Convolutional Autoencoder for Neonatal Seizure Detection.

Neonatal epilepsy is a common emergency phenomenon in neonatal intensive care units (NICUs), which requires timely attention, early identification, and treatment. Traditional detection methods mostly use supervised learning with enormous labeled data. Hence, this study offers a semi-supervised hybrid architecture for detecting seizures, which combines the extracted electroencephalogram (EEG) feature dataset and convolutional autoencoder, called Fd-CAE. First, various features in the time domain and entropy domain are extracted to characterize the EEG signal, which helps distinguish epileptic seizures subsequently. Then, the unlabeled EEG features are fed into the convolutional autoencoder (CAE) for training, which effectively represents EEG features by optimizing the loss between the input and output features. This unsupervised feature learning process can better combine and optimize EEG features from unlabeled data. After that, the pre-trained encoder part of the model is used for further feature learning of labeled data to obtain its low-dimensional feature representation and achieve classification. This model is performed on the neonatal EEG dataset collected at the University of Helsinki Hospital, which has a high discriminative ability to detect seizures, with an accuracy of 92.34%, precision of 93.61%, recall rate of 98.74%, and F1-score of 95.77%, respectively. The results show that unsupervised learning by CAE is beneficial to the characterization of EEG signals, and the proposed Fd-CAE method significantly improves classification performance.

$\beta$ -wave-based exploration of sensitive EEG features and classification of situation awareness

AbstractThe purpose of this study was to explore the electroencephalogram (EEG) features sensitive to situation awareness (SA) and then classify SA levels. Forty-eight participants were recruited to complete an SA standard test based on the multi-attribute task battery (MATB) II, and the corresponding EEG data and situation awareness global assessment technology (SAGAT) scores were recorded. The population with the top 25% of SAGAT scores was selected as the high-SA level (HSL) group, and the bottom 25% was the low-SA level (LSL) group. The results showed that (1) for the relative power of $\beta$ 1 (16–20Hz), $\beta$ 2 (20–24Hz) and $\beta$ 3 (24–30Hz), repeated measures analysis of variance (ANOVA) in three brain regions (Central Central-Parietal, and Parietal) × three brain lateralities (left, midline, and right) × two SA groups (HSL and LSL) showed a significant main effect for SA groups; post hoc comparisons revealed that compared with LSL, the above features of HSL were higher. (2) for most ratio features associated with $\beta$ 1 ∼ $\beta$ 3, ANOVA also revealed a main effect for SA groups. (3) EEG features sensitive to SA were selected to classify SA levels with small-sample data based on the general supervised machine learning classifiers. Five-fold cross-validation results showed that among the models with easy interpretability, logistic regression (LR) and decision tree (DT) presented the highest accuracy (both 92%), while among the models with hard interpretability, the accuracy of random forest (RF) was 88.8%, followed by an artificial neural network (ANN) of 84%. The above results suggested that (1) the relative power of $\beta$ 1 ∼ $\beta$ 3 and their associated ratios were sensitive to changes in SA levels; (2) the general supervised machine learning models all exhibited good accuracy (greater than 75%); and (3) furthermore, LR and DT are recommended by combining the interpretability and accuracy of the models.

Research on the pathogenesis of Alzheimer's disease based on thalamocortical computational model.

Alpha rhythm slowing is an important electroencephalogram(EEG) feature associated with (AD). This study aims to understand the correlation between alpha band deceleration and molecular changes from the perspective of neural computing. Considering the effect of Aβ amyloid deposition on the inhibitory changes in the thalamic, a thalamic cortical model coupled with Aβ amyloid is established. The results show that Aβ amyloid deposition may induce neurotoxicity in thalamic reticular nucleus neurons, which results in inhibitory changes in the thalamus and slows the alpha rhythm of EEG output from the thalamus. In order to understand the pathogenesis more intuitively, some numerical simulations are provided to illustrate the obtained theories. This research is helpful to understand the pathogenesis of AD, so as to provide theoretical basis for the intervention and control of the disease.

Efficient Feature Learning Model of Motor Imagery EEG Signals with L1-Norm and Weighted Fusion.

Brain-computer interface (BCI) for motor imagery is an advanced technology used in the field of medical rehabilitation. However, due to the poor accuracy of electroencephalogram feature classification, BCI systems often misrecognize user commands. Although many state-of-the-art feature selection methods aim to enhance classification accuracy, they usually overlook the interrelationships between individual features, indirectly impacting the accuracy of feature classification. To overcome this issue, we propose an adaptive feature learning model that employs a Riemannian geometric approach to generate a feature matrix from electroencephalogram signals, serving as the model's input. By integrating the enhanced adaptive L1 penalty and weighted fusion penalty into the sparse learning model, we select the most informative features from the matrix. Specifically, we measure the importance of features using mutual information and introduce an adaptive weight construction strategy to penalize regression coefficients corresponding to each variable adaptively. Moreover, the weighted fusion penalty balances weight differences among correlated variables, reducing the model's overreliance on specific variables and enhancing accuracy. The performance of the proposed method was validated on BCI Competition IV datasets IIa and IIb using the support vector machine. Experimental results demonstrate the effectiveness and superiority of the proposed model compared to the existing models.

The incidence and predictors of antibiotic-associated encephalopathy: a multicenter hospital-based study

This study aimed to evaluate the incidence and likelihood of antibiotic-associated encephalopathy (AAE), comparing rates among the classes of antibiotics in monotherapy or in combination therapy. We also investigated the associations between the incidence of AAE and the glomerular filtration rate (GFR) and electroencephalogram features. Consecutive admissions that used any kind of antibiotics to treat infectious diseases were identified from six hospitals. We classified antibiotics according to three distinct pathophysiologic mechanisms and clinical subtypes. We searched for the incidence of AAE as the primary outcome. A total of 97,433 admission cases among 56,038 patients was identified. Cases that received type 1 antibiotics had significantly more frequent AAE compared to those that received type 2 antibiotics (adjusted odds ratio [OR], 2.62; 95% confidence interval [CI] 1.15–5.95; P = 0.021). Combined use of type 1 + 2 antibiotics was associated with a significantly higher incidence of AAE compared to the use of type 2 antibiotics alone (adjusted OR, 3.44; 95% CI 1.49–7.93; P = 0.004). Groups with GFR < 60 mL/min/1.73 m2 had significantly higher incidence rates of AAE compared to those with GFRs ≥ 90 mL/min/1.73 m2 among cases that received type 1 + 2 antibiotics. Detection of spike-and-wave or sharp-and-wave patterns on electroencephalogram was significantly more common in the combination therapy group. Combination use of antibiotics was associated with a higher incidence of AAE compared to monotherapy. The incidence of AAE significantly increased as renal function decreased, and epileptiform discharges were more likely to be detected in cases receiving combined antibiotics.