Improved empirical mode decomposition bagging RCSP combined with Fisher discriminant method for EEG feature extraction and classification.

Background: Traditional Common Spatial Pattern (CSP) algorithms for Electroencephalogram (EEG) signal classification are sensitive to noise and can produce low accuracy in small sample datasets. New method: To solve the problem, an improved Empirical Mode Decomposition (EMD) Bagging Regularized CSP (RCSP) algorithm is proposed. It filters EEG signals through improved EMD, inhibits high-frequency noise, retains effective information in the characteristic frequency band, and uses Bagging algorithm for data reconstruction. Feature extraction is performed with regularization of spatial patterns and Fisher linear discriminant analysis for feature classification. T-test is used for classification. Results: The improved EMD Bagging RCSP algorithm has improved accuracy and robustness compared to CSP and its derivatives. The average classification rate is increased by about 6%, demonstrating the effectiveness and correctness of the proposed algorithm.Comparison with existing methods: The proposed algorithm outperforms CSP and its derivatives by retaining effective information and inhibiting high-frequency noise in small sample EEG datasets. Conclusions: The proposed EMD Bagging RCSP algorithm provides a reliable and effective method for EEG signal classification and can be used in various applications, including brain-computer interfaces and clinical EEG diagnosis.

Artifact removal and motor imagery classification in EEG using advanced algorithms and modified DNN.

This paper presents an advanced approach for EEG artifact removal and motor imagery classification using a combination of Four Class Iterative Filtering and Filter Bank Common Spatial Pattern Algorithm with a Modified Deep Neural Network (DNN) classifier. The research aims to enhance the accuracy and reliability of BCI systems by addressing the challenges posed by EEG artifacts and complex motor imagery tasks. The methodology begins by introducing FCIF, a novel technique for ocular artifact removal, utilizing iterative filtering and filter banks. FCIF's mathematical formulation allows for effective artifact mitigation, thereby improving the quality of EEG data. In tandem, the FC-FBCSP algorithm is introduced, extending the Filter Bank Common Spatial Pattern approach to handle four-class motor imagery classification. The Modified DNN classifier enhances the discriminatory power of the FC-FBCSP features, optimizing the classification process. The paper showcases a comprehensive experimental setup, featuring the utilization of BCI Competition IV Dataset 2a & 2b. Detailed preprocessing steps, including filtering and feature extraction, are presented with mathematical rigor. Results demonstrate the remarkable artifact removal capabilities of FCIF and the classification prowess of FC-FBCSP combined with the Modified DNN classifier. Comparative analysis highlights the superiority of the proposed approach over baseline methods and the method achieves the mean accuracy of 98.575%.

EEG and EMG-based human-machine interface for navigation of mobility-related assistive wheelchair (MRA-W).

The control of human-machine interfaces (HMIs), such as motorized wheelchairs, has been widely investigated using biopotentials produced by electrochemical processes in the human body. However, many studies in this field sometimes overlook crucial factors like special users' needs, who often have inadequate muscle mass and strength, and paresis needed to operate a wheelchair. This study proposes a novel solution: an economical, universally compatible, and user-centric manual-to-powered wheelchair conversion kit. The powered wheelchair is operated using a hybrid control system integrating electroencephalogram (EEG) and electromyography (EMG), utilizing an LSTM network. It uses a low-cost electroencephalogram (EEG) headset and a wearable electromyography (EMG) electrode armband to solve these constraints. The proposed system comprised three crucial objectives: the development of an EEG-based user attentive detection system, an EMG-based navigation system, and a transform conventional wheelchair into a powered wheelchair. Human test subjects were utilized to evaluate the proposed system, and the study complied with accepted ethical guidelines. We selected four EEG features (p < 0.023) for the attentive detection system and six EMG features (p < 0.037) to detect navigation intentions. User attentive detection was achieved at 83.33 (±0.34) %, while the navigation intention system produced 86.67 (±0.52) % accuracy. The overall system was successful in reaching an accuracy rate of 85.0 (±0.19) % and a weighted average precision of 0.89. After the dataset was trained using an LSTM network, the overall accuracy produced was 97.3 (±0.5) %, higher than the accuracy produced by the Quadratic SVM classifier. By giving older and disabled people a more convenient way to use powered wheelchairs, this research helps to build ergonomic and cost-effective biopotential-based HMIs, enhancing their quality of life.

Influencing factors of corticomuscular coherence in stroke patients.

Stroke, also known as cerebrovascular accident, is an acute cerebrovascular disease with a high incidence, disability rate, and mortality. It can disrupt the interaction between the cerebral cortex and external muscles. Corticomuscular coherence (CMC) is a common and useful method for studying how the cerebral cortex controls muscle activity. CMC can expose functional connections between the cortex and muscle, reflecting the information flow in the motor system. Afferent feedback related to CMC can reveal these functional connections. This paper aims to investigate the factors influencing CMC in stroke patients and provide a comprehensive summary and analysis of the current research in this area. This paper begins by discussing the impact of stroke and the significance of CMC in stroke patients. It then proceeds to elaborate on the mechanism of CMC and its defining formula. Next, the impacts of various factors on CMC in stroke patients were discussed individually. Lastly, this paper addresses current challenges and future prospects for CMC.

Elevating understanding: Linking high-altitude hypoxia to brain aging through EEG functional connectivity and spectral analyses.

High-altitude hypoxia triggers brain function changes reminiscent of those in healthy aging and Alzheimer's disease, compromising cognition and executive functions. Our study sought to validate high-altitude hypoxia as a model for assessing brain activity disruptions akin to aging. We collected EEG data from 16 healthy volunteers during acute high-altitude hypoxia (at 4,000 masl) and at sea level, focusing on relative changes in power and aperiodic slope of the EEG spectrum due to hypoxia. Additionally, we examined functional connectivity using wPLI, and functional segregation and integration using graph theory tools. High altitude led to slower brain oscillations, that is, increased δ and reduced α power, and flattened the 1/f aperiodic slope, indicating higher electrophysiological noise, akin to healthy aging. Notably, functional integration strengthened in the θ band, exhibiting unique topographical patterns at the subnetwork level, including increased frontocentral and reduced occipitoparietal integration. Moreover, we discovered significant correlations between subjects' age, 1/f slope, θ band integration, and observed robust effects of hypoxia after adjusting for age. Our findings shed light on how reduced oxygen levels at high altitudes influence brain activity patterns resembling those in neurodegenerative disorders and aging, making high-altitude hypoxia a promising model for comprehending the brain in health and disease.

Exposure to high-altitude hypoxia, with reduced oxygen levels, can replicate brain function changes akin to aging and Alzheimer's disease. In our work, we propose high-altitude hypoxia as a possible reversible model of human brain aging. We gathered EEG data at high altitude and sea level, investigating the impact of hypoxia on brainwave patterns and connectivity. Our findings revealed that high-altitude exposure led to slower and noisier brain oscillations and produced altered brain connectivity, resembling some remarkable changes seen in the aging process. Intriguingly, these changes were linked to age, even when hypoxia's effects were considered. Our research unveils how high-altitude conditions emulate brain patterns associated with aging and neurodegenerative conditions, providing valuable insights into the understanding of both normal and impaired brain function.

Reconstructing brain functional networks through identifiability and deep learning.

We propose a novel approach for the reconstruction of functional networks representing brain dynamics based on the idea that the coparticipation of two brain regions in a common cognitive task should result in a drop in their identifiability, or in the uniqueness of their dynamics. This identifiability is estimated through the score obtained by deep learning models in supervised classification tasks and therefore requires no a priori assumptions about the nature of such coparticipation. The method is tested on EEG recordings obtained from Alzheimer's and Parkinson's disease patients, and matched healthy volunteers, for eyes-open and eyes-closed resting-state conditions, and the resulting functional networks are analysed through standard topological metrics. Both groups of patients are characterised by a reduction in the identifiability of the corresponding EEG signals, and by differences in the patterns that support such identifiability. Resulting functional networks are similar, but not identical to those reconstructed by using a correlation metric. Differences between control subjects and patients can be observed in network metrics like the clustering coefficient and the assortativity in different frequency bands. Differences are also observed between eyes open and closed conditions, especially for Parkinson's disease patients.

Spectral exponent assessment and neurofilament light chain: a comprehensive approach to describe recovery patterns in stroke.

Introduction: Understanding the residual recovery potential in stroke patients is crucial for tailoring effective neurorehabilitation programs. We propose using EEG and plasmatic Neurofilament light chain (NfL) levels as a model to depict longitudinal patterns of stroke recovery. Methods: We enrolled 13 patients (4 female, mean age 74.7 ± 8.8) who underwent stroke in the previous month and were hospitalized for 2-months rehabilitation. Patients underwent blood withdrawal, clinical evaluation and high-definition EEG at T1 (first week of rehabilitation) and at T2 (53 ± 10 days after). We assessed the levels of NfL and we analyzed the EEG signal extracting Spectral Exponent (SE) values. We compared our variables between the two timepoint and between cortical and non-cortical strokes. Results: We found a significant difference in the symmetry of SE values between cortical and non-cortical stroke at both T1 (p = 0.005) and T2 (p = 0.01). SE in the affected hemisphere showed significantly steeper values at T1 when compared with T2 (p = 0.001). EEG measures were consistently related to clinical scores, while NfL at T1 was related to the volume of ischemic lesions (r = 0.75; p = 0.003). Additionally, the combined use of NfL and SE indicated varying trends in longitudinal clinical recovery. Conclusion: We present proof of concept of a promising approach for the characterization of different recovery patterns in stroke patients.

Corrigendum: The effect of acupuncture at the Taiyang acupoint on visual function and EEG microstates in myopia.

[This corrects the article DOI: 10.3389/fnint.2023.1234471.].

Relationship between preinduction electroencephalogram patterns and propofol sensitivity in adult patients.

PURPOSE: To determine the precise induction dose, an objective assessment of individual propofol sensitivity is necessary. This study aimed to investigate whether preinduction electroencephalogram (EEG) data are useful in determining the optimal propofol dose for the induction of general anesthesia in healthy adult patients. METHODS: Seventy healthy adult patients underwent total intravenous anesthesia (TIVA), and the effect-site target concentration of propofol was observed to measure each individual's propofol requirements for loss of responsiveness. We analyzed preinduction EEG data to assess its relationship with propofol requirements and conducted multiple regression analyses considering various patient-related factors. RESULTS: Patients with higher relative delta power (ρ = 0.47, p < 0.01) and higher absolute delta power (ρ = 0.34, p = 0.01) required a greater amount of propofol for anesthesia induction. In contrast, patients with higher relative beta power (ρ = -0.33, p < 0.01) required less propofol to achieve unresponsiveness. Multiple regression analysis revealed an independent association between relative delta power and propofol requirements. CONCLUSION: Preinduction EEG, particularly relative delta power, is associated with propofol requirements during the induction of general anesthesia. The utilization of preinduction EEG data may improve the precision of induction dose selection for individuals.

Does Self-View Mode Generate More Videoconferencing Fatigue in Women than Men? An Experiment Using EEG Signals.

The ability to see or hide one's own image is a typical feature of videoconferencing platforms. Previous research, informed primarily by self-reported data, has suggested that enabling self-view mode is associated with videoconferencing fatigue, particularly for women. Our goal in this study is to test this assumption by gathering neurophysiological evidence. We conducted an experiment using electroencephalography (EEG) with 32 volunteers (16 men and 16 women), who each participated in a live video meeting with the self-view mode both on and off. Our findings confirm the effects of self-view on fatigue, with significantly greater alpha activity when self-view was on than when it was off. Alpha activity did not change significantly across a 20-minute session, and was not significantly different for men or women. Thus, our study does not replicate previous findings that women experience greater videoconferencing fatigue because of the increased self-awareness generated when viewing themselves on a screen. We discuss why our EEG findings may diverge from prior self-reported studies.

Alterations in gamma frequency oscillations correlate with cortical tau deposition in Alzheimer's disease.

We assessed the relationship of gamma oscillations with tau deposition in Alzheimer's disease (AD) and other cognitive diseases, as both are altered during the disease course and relate to neurodegeneration. We retrospectively analyzed data from 7 AD, tau positive patients and 9 tau negative patients, who underwent cerebral amyloid PET and tau PET, and EEG within 12 months. Relative gamma power was higher in tau positive (AD) patients than in tau negative patients (p < .05). In tau positive AD patients, tau burden was associated with a linear increase in gamma power (p < .05), while no association was present in the tau negative group nor with amyloid-ß burden in either group. Thus, increase in the gamma power might represent a novel biomarker for tau driven neurodegeneration.

Case report: Insulinoma masquerades as epilepsy - quantitative EEG analysis.

Insulinomas are rare gastrointestinal tumors with an incidence of 1-3 per million inhabitants annually. These tumors result in excessive insulin production, culminating in hypoglycemia. Such hypoglycemia triggers various central nervous system (CNS) manifestations, including headache, confusion, abnormal behavior, and epileptic seizures, which can lead to misdiagnosis as epilepsy. This case report documents a 46-year-old male who presented seizure-like episodes. Episodes occurred mainly during the night, lasting several minutes to hours. Initial seizures were characterized by bizarre behavior and altered responsiveness. Over time, seizure frequency, complexity, and severity escalated. We managed to record two episodes during long-term EEG and report, as the first ones, the detailed quantitative EEG analysis of these hypoglycemia-related events. EEG changes preceded the development of clear-cut pathological motor activity in tens of minutes and were present in all investigated frequency bands. The development of profound motor activity was associated with other increases in EEG power spectra in all frequencies except for delta. The most pronounced changes were found over the left temporal region, which can be the most susceptible to hypoglycemia. In our patient, the seizure-like episodes completely disappeared after the insulinoma removal, which demonstrates their relationship to hypoglycemia.

Prevalence of Electrographic Seizures in Hospitalized Patients With Altered Mental Status With No Significant Seizure Risk Factors Who Underwent Continuous EEG Monitoring: A Retrospective Study.

OBJECTIVES: The objective of this study is to evaluate the prevalence of electrographic seizures in hospitalized patients with altered mental status and no significant risk factors for seizures. METHODS: We retrospectively reviewed over a six-year period (2013-2019) the medical records of all adults admitted at Ohio State University Wexner Medical Center (OSUWMC), who underwent continuous electroencephalography (cEEG) monitoring for > 48 hours. Our primary objective was to identify the prevalence of electrographic seizures in patients with altered mental status and no significant acute or remote risk factors for seizures. RESULTS: A total of 1966 patients were screened for the study, 1892 were excluded (96.2%) and 74 patients met inclusion criteria. Electrographic seizures were identified in seven of 74 patients (9.45%). We found a significant correlation between electrographic seizures and a history of hepatic cirrhosis, n= 4 (57%), (p=0.035), acute chronic hepatic failure during admission, 71% (n=5), (p=0.027), and hyperammonemia (p =0.009). CONCLUSION: In this retrospective study of patients with altered mental status and no significant acute or remote risk factors for seizures who underwent cEEG monitoring for > 48 hours, electrographic seizures were identified in 9.45%. Electrographic seizures were associated with hepatic dysfunction and hyperammonemia. Based on our results, cEEG monitoring should be considered in patients with altered mental status and hepatic dysfunction even in the absence of other seizure risk factors.

Exploring the Potential of Pretrained CNNs and Time-Frequency Methods for Accurate Epileptic EEG Classification: A Comparative Study.

Prompt diagnosis of epilepsy relies on accurate classification of automated electroencephalogram (EEG) signals. Several approaches have been developed to characterize epileptic EEG data; however, none of them have exploited time-frequency data to evaluate the effect of tweaking parameters in pretrained frameworks for EEG data classification. This study compares the performance of several pretrained convolutional neural networks (CNNs) namely, AlexNet, GoogLeNet, MobileNetV2, ResNet-18 and SqueezeNet for the localization of epilepsy EEG data using various time-frequency data representation algorithms. Continuous wavelet transform (CWT), empirical Fourier decomposition (EFD), empirical mode decomposition (EMD), empirical wavelet transform (EWT), and variational mode decomposition (VMD) were exploited for the acquisition of 2D scalograms from 1D data. The research evaluates the effect of multiple factors, including noisy versus denoised scalograms, different optimizers, learning rates, single versus dual channels, model size, and computational time consumption. The benchmark Bern Barcelona EEG dataset is used for testing purpose. Results obtained show that the combination of MobileNetV2, Continuous Wavelet Transform (CWT) and Adam optimizer at a learning rate of 10^-4, coupled with dual-data channels, provides the best performance metrics. Specifically, these parameters result in optimal sensitivity, specificity, f1-score, and classification accuracy, with respective values of 96.06%, 96.15%, 96.08%, and 96.10%. To further corroborate the efficacy of opted pretrained models on exploited Signal Decomposition (SD) algorithms, the classifiers are also being simulated on Temple University database at pinnacle modeling composition. A similar pattern in the outcome readily validate the findings of our study and robustness of deep learning models on epilepsy EEG scalograms.The conclusions drawn emphasize the potential of pretrained CNN-based models to create a robust, automated system for diagnosing epileptiform. Furthermore, the study offers insights into the effectiveness of varying time-frequency techniques and classifier parameters for classifying epileptic EEG data.

Altered neural oscillations in classical galactosaemia during sentence production.

Classical galactosaemia (CG) is a hereditary disease in galactose metabolism that despite dietary treatment is characterized by a wide range of cognitive deficits, among which is language production. CG brain functioning has been studied with several neuroimaging techniques, which revealed both structural and functional atypicalities. In the present study, for the first time, we compared the oscillatory dynamics, especially the power spectrum and time-frequency representations (TFR), in the electroencephalography (EEG) of CG patients and healthy controls while they were performing a language production task. Twenty-one CG patients and 19 healthy controls described animated scenes, either in full sentences or in words, indicating two levels of complexity in syntactic planning. Based on previous work on the P300 event related potential (ERP) and its relation with theta frequency, we hypothesized that the oscillatory activity of patients and controls would differ in theta power and TFR. With regard to behavior, reaction times showed that patients are slower, reflecting the language deficit. In the power spectrum, we observed significant higher power in patients in delta (1-3 Hz), theta (4-7 Hz), beta (15-30 Hz) and gamma (30-70 Hz) frequencies, but not in alpha (8-12 Hz), suggesting an atypical oscillatory profile. The time-frequency analysis revealed significantly weaker event-related theta synchronization (ERS) and alpha desynchronization (ERD) in patients in the sentence condition. The data support the hypothesis that CG language difficulties relate to theta-alpha brain oscillations.

Orthogonal extended infomax algorithm.

Objective.The extended infomax algorithm for independent component analysis (ICA) can separate sub- and super-Gaussian signals but converges slowly as it uses stochastic gradient optimization. In this paper, an improved extended infomax algorithm is presented that converges much faster.Approach.Accelerated convergence is achieved by replacing the natural gradient learning rule of extended infomax by a fully-multiplicative orthogonal-group based update scheme of the ICA unmixing matrix, leading to an orthogonal extended infomax algorithm (OgExtInf). The computational performance of OgExtInf was compared with original extended infomax and with two fast ICA algorithms: the popular FastICA and Picard, a preconditioned limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm belonging to the family of quasi-Newton methods.Main results.OgExtInf converges much faster than original extended infomax. For small-size electroencephalogram (EEG) data segments, as used for example in online EEG processing, OgExtInf is also faster than FastICA and Picard.Significance.OgExtInf may be useful for fast and reliable ICA, e.g. in online systems for epileptic spike and seizure detection or brain-computer interfaces.

Postictal psychiatric symptoms: A neurophysiological study.

OBJECTIVE: Postictal psychiatric symptoms (PPS) are a relatively common but understudied phenomenon in epilepsy. The mechanisms by which seizures contribute to worsening in psychiatric symptoms are unclear. We aimed to identify PPS prospectively during and after admission to the epilepsy monitoring unit (EMU) in order to characterize the postictal physiologic changes leading to PPS. METHODS: We prospectively enrolled patients admitted to the EMU and administered repeat psychometric questionnaires during and after their hospital stay in order to assess for postictal exacerbations in four symptom complexes: anger/hostility, anxiety, depression, and paranoia. Electroclinical and electrographic seizures were identified from the EEG recordings, and seizure durations were measured. The severity of postictal slowing was calculated as the proportion of postictal theta/delta activity in the postictal EEG relative to the preictal EEG using the Hilbert transform. RESULTS: Among 33 participants, 8 demonstrated significant increases in at least one of the four symptoms (the PPS+ group) within three days following the first seizure. The most common PPS was anger/hostility, experienced by 7/8 participants with PPS. Among the 8 PPS+ participants, four experienced more than one PPS. As compared to those without PPS (the PPS- group), the PPS+ group demonstrated a greater degree of postictal EEG slowing at 10 min (p = 0.022) and 20 min (p = 0.05) following seizure termination. They also experienced significantly more seizures during the study period (p = 0.005). There was no difference in seizure duration between groups. SIGNIFICANCE: Postictal psychiatric symptoms including anger/hostility, anxiety, depression, and paranoia may be more common than recognized. In particular, postictal increases in anger and irritability may be particularly common. We provide physiological evidence of a biological mechanism as well as a demonstration of the use of quantitative electroencephalography toward a better understanding of postictal neurophysiology.

Decomposing neurophysiological underpinnings of age-related decline in visual working memory.

Exploring the neural basis of age-related decline in working memory is vital in our aging society. Previous electroencephalographic studies suggested that the contralateral delay activity (CDA) may be insensitive to age-related decline in lateralized visual working memory (VWM) performance. Instead, recent evidence indicated that task-induced alpha power lateralization decreases in older age. However, the relationship between alpha power lateralization and age-related decline of VWM performance remains unknown, and recent studies have questioned the validity of these findings due to confounding factors of the aperiodic signal. Using a sample of 134 participants, we replicated the age-related decrease of alpha power lateralization after adjusting for the aperiodic signal. Critically, the link between task performance and alpha power lateralization was found only when correcting for aperiodic signal biases. Functionally, these findings suggest that age-related declines in VWM performance may be related to the decreased ability to prioritize relevant over irrelevant information. Conversely, CDA amplitudes were stable across age groups, suggesting a distinct neural mechanism possibly related to preserved VWM encoding or early maintenance.