Motor Imagery EEG Signal Classification Using Distinctive Feature Fusion with Adaptive Structural LASSO.

A motor imagery brain-computer interface connects the human brain and computers via electroencephalography (EEG). However, individual differences in the frequency ranges of brain activity during motor imagery tasks pose a challenge, limiting the manual feature extraction for motor imagery classification. To extract features that match specific subjects, we proposed a novel motor imagery classification model using distinctive feature fusion with adaptive structural LASSO. Specifically, we extracted spatial domain features from overlapping and multi-scale sub-bands of EEG signals and mined discriminative features by fusing the task relevance of features with spatial information into the adaptive LASSO-based feature selection. We evaluated the proposed model on public motor imagery EEG datasets, demonstrating that the model has excellent performance. Meanwhile, ablation studies and feature selection visualization of the proposed model further verified the great potential of EEG analysis.

Synchronization of Neurophysiological and Biomechanical Data in a Real-Time Virtual Gait Analysis System (GRAIL): A Proof-of-Principle Study.

The investigation of gait and its neuronal correlates under more ecologically valid conditions as well as real-time feedback visualization is becoming increasingly important in neuro-motor rehabilitation research. The Gait Real-time Analysis Interactive Lab (GRAIL) offers advanced opportunities for gait and gait-related research by creating more naturalistic yet controlled environments through immersive virtual reality. Investigating the neuronal aspects of gait requires parallel recording of brain activity, such as through mobile electroencephalography (EEG) and/or mobile functional near-infrared spectroscopy (fNIRS), which must be synchronized with the kinetic and /or kinematic data recorded while walking. This proof-of-concept study outlines the required setup by use of the lab streaming layer (LSL) ecosystem for real-time, simultaneous data collection of two independently operating multi-channel EEG and fNIRS measurement devices and gait kinetics. In this context, a customized approach using a photodiode to synchronize the systems is described. This study demonstrates the achievable temporal accuracy of synchronous data acquisition of neurophysiological and kinematic and kinetic data collection in the GRAIL. By using event-related cerebral hemodynamic activity and visually evoked potentials during a start-to-go task and a checkerboard test, we were able to confirm that our measurement system can replicate known physiological phenomena with latencies in the millisecond range and relate neurophysiological and kinetic data to each other with sufficient accuracy.

An Innovative EEG-Based Pain Identification and Quantification: A Pilot Study.

OBJECTIVE: The present pilot study aimed to propose an innovative scale-independent measure based on electroencephalographic (EEG) signals for the identification and quantification of the magnitude of chronic pain. METHODS: EEG data were collected from three groups of participants at rest: seven healthy participants with pain, 15 healthy participants submitted to thermal pain, and 66 participants living with chronic pain. Every 30 s, the pain intensity score felt by the participant was also recorded. Electrodes positioned in the contralateral motor region were of interest. After EEG preprocessing, a complex analytical signal was obtained using Hilbert transform, and the upper envelope of the EEG signal was extracted. The average coefficient of variation of the upper envelope of the signal was then calculated for the beta (13-30 Hz) band and proposed as a new EEG-based indicator, namely Piqß, to identify and quantify pain. MAIN RESULTS: The main results are as follows: (1) A Piqß threshold at 10%, that is, Piqß ≥ 10%, indicates the presence of pain, and (2) the higher the Piqß (%), the higher the extent of pain. CONCLUSIONS: This finding indicates that Piqß can objectively identify and quantify pain in a population living with chronic pain. This new EEG-based indicator can be used for objective pain assessment based on the neurophysiological body response to pain. SIGNIFICANCE: Objective pain assessment is a valuable decision-making aid and an important contribution to pain management and monitoring.

Individual Variability in Brain Connectivity Patterns and Driving-Fatigue Dynamics.

Mental fatigue during driving poses significant risks to road safety, necessitating accurate assessment methods to mitigate potential hazards. This study explores the impact of individual variability in brain networks on driving fatigue assessment, hypothesizing that subject-specific connectivity patterns play a pivotal role in understanding fatigue dynamics. By conducting a linear regression analysis of subject-specific brain networks in different frequency bands, this research aims to elucidate the relationships between frequency-specific connectivity patterns and driving fatigue. As such, an EEG sustained driving simulation experiment was carried out, estimating individuals' brain networks using the Phase Lag Index (PLI) to capture shared connectivity patterns. The results unveiled notable variability in connectivity patterns across frequency bands, with the alpha band exhibiting heightened sensitivity to driving fatigue. Individualized connectivity analysis underscored the complexity of fatigue assessment and the potential for personalized approaches. These findings emphasize the importance of subject-specific brain networks in comprehending fatigue dynamics, while providing sensor space minimization, advocating for the development of efficient mobile sensor applications for real-time fatigue detection in driving scenarios.

Classification of Visually Induced Motion Sickness Based on Phase-Locked Value Functional Connectivity Matrix and CNN-LSTM.

To effectively detect motion sickness induced by virtual reality environments, we developed a classification model specifically designed for visually induced motion sickness, employing a phase-locked value (PLV) functional connectivity matrix and a CNN-LSTM architecture. This model addresses the shortcomings of traditional machine learning algorithms, particularly their limited capability in handling nonlinear data. We constructed PLV-based functional connectivity matrices and network topology maps across six different frequency bands using EEG data from 25 participants. Our analysis indicated that visually induced motion sickness significantly alters the synchronization patterns in the EEG, especially affecting the frontal and temporal lobes. The functional connectivity matrix served as the input for our CNN-LSTM model, which was used to classify states of visually induced motion sickness. The model demonstrated superior performance over other methods, achieving the highest classification accuracy in the gamma frequency band. Specifically, it reached a maximum average accuracy of 99.56% in binary classification and 86.94% in ternary classification. These results underscore the model's enhanced classification effectiveness and stability, making it a valuable tool for aiding in the diagnosis of motion sickness.

Multiclass Classification of Visual Electroencephalogram Based on Channel Selection, Minimum Norm Estimation Algorithm, and Deep Network Architectures.

This work addresses the challenge of classifying multiclass visual EEG signals into 40 classes for brain-computer interface applications using deep learning architectures. The visual multiclass classification approach offers BCI applications a significant advantage since it allows the supervision of more than one BCI interaction, considering that each class label supervises a BCI task. However, because of the nonlinearity and nonstationarity of EEG signals, using multiclass classification based on EEG features remains a significant challenge for BCI systems. In the present work, mutual information-based discriminant channel selection and minimum-norm estimate algorithms were implemented to select discriminant channels and enhance the EEG data. Hence, deep EEGNet and convolutional recurrent neural networks were separately implemented to classify the EEG data for image visualization into 40 labels. Using the k-fold cross-validation approach, average classification accuracies of 94.8% and 89.8% were obtained by implementing the aforementioned network architectures. The satisfactory results obtained with this method offer a new implementation opportunity for multitask embedded BCI applications utilizing a reduced number of both channels (<50%) and network parameters (<110 K).

Evaluating the Electroencephalographic Signal Quality of an In-Ear Wearable Device.

Wearable in-ear electroencephalographic (EEG) devices hold significant promise for advancing brain monitoring technologies into everyday applications. However, despite the current availability of several in-ear EEG devices in the market, there remains a critical need for robust validation against established clinical-grade systems. In this study, we carried out a detailed examination of the signal performance of a mobile in-ear EEG device from Naox Technologies. Our investigation had two main goals: firstly, evaluating the hardware circuit's reliability through simulated EEG signal experiments and, secondly, conducting a thorough comparison between the in-ear EEG device and gold-standard EEG monitoring equipment. This comparison assesses correlation coefficients with recognized physiological patterns during wakefulness and sleep, including alpha rhythms, eye artifacts, slow waves, spindles, and sleep stages. Our findings support the feasibility of using this in-ear EEG device for brain activity monitoring, particularly in scenarios requiring enhanced comfort and user-friendliness in various clinical and research settings.

The Voyage of SEEG.

SUMMARY: It took 50 years for stereoelectroencephalography (SEEG) to cross the Atlantic. Conceived and designed before the advent of computers and modern technology, this method turned out to be perfectly suited to brain imaging and modern video and electrophysiological tools. It eventually benefited from robotics and signal processing. However, a critical step remains accurate electrode implantation, which is based on individual patients' noninvasive phase I data. A limiting factor, especially in MRI-negative cases, is a thorough perictal and postictal clinical testing for ensuring meaningful electroclinical correlations. Adapted epilepsy monitoring units' architecture and specific technicians and nurses training are required to improve the granularity of information needed to generate valid hypotheses on localization. SEEG interpretation is based on a knowledge base in neural networks, cognitive/behavioral neuroscience, and electrophysiology quite distinct from electroencephalography. Tailored to the needs of focal epilepsy complexity exploration, SEEG does not fit well with simplification. Specific teaching and development of clinical research inside the epilepsy monitoring units will help to flatten the team learning curve and to build knowledge base from shared clinical experience.

Stereoelectroencephalography of the Deep Brain: Basal Ganglia and Thalami.

SUMMARY: Stereoelectroencephalography (SEEG) has emerged as a transformative tool in epilepsy surgery, shedding light on the complex network dynamics involved in focal epilepsy. This review explores the role of SEEG in elucidating the role of deep brain structures, namely the basal ganglia and thalamus, in epilepsy. SEEG advances understanding of their contribution to seizure generation, propagation, and control by permitting precise and minimally invasive sampling of these brain regions. The basal ganglia, comprising the subthalamic nucleus, globus pallidus, substantia nigra, and striatum, have gained recognition for their involvement in both focal and generalized epilepsy. Electrophysiological recordings reveal hyperexcitability and increased synchrony within these structures, reinforcing their role as critical nodes within the epileptic network. Furthermore, low-frequency and high-frequency stimulation of the basal ganglia have demonstrated potential in modulating epileptogenic networks. Concurrently, the thalamus, a key relay center, has garnered prominence in epilepsy research. Disrupted thalamocortical connectivity in focal epilepsy underscores its significance in seizure maintenance. The thalamic subnuclei, including the anterior nucleus, centromedian, and medial pulvinar, present promising neuromodulatory targets, suggesting pathways for personalized epilepsy therapies. The prospect of multithalamic SEEG and thalamic SEEG stimulation trials has the potential to revolutionize epilepsy management, offering tailored solutions for challenging cases. SEEG's ability to unveil the dynamics of deep brain structures in epilepsy promises enhanced and personalized epilepsy care in our new era of precision medicine. Until deep brain SEEG is accepted as a standard of care, a rigorous informed consent process remains paramount for patients for whom such an exploration is proposed.

In Search of a Common Language: The Standardized Electrode Nomenclature for Stereoelectroencephalography Applications.

PURPOSE: Stereoelectroencephalography (SEEG) is widely performed on individuals with medically refractory epilepsy for whom invasive seizure localization is desired. Despite increasing adoption in many centers across the world, no standardized electrode naming convention exists, generating confusion among both clinical and research teams. METHODS: We have developed a novel nomenclature, named the Standardized Electrode Nomenclature for SEEG Applications system. Concise, unique, informative, and unambiguous labels provide information about entry point, deep targets, and relationships between electrodes. Inter-rater agreement was evaluated by comparing original electrode names from 10 randomly sampled cases (including 136 electrodes) with those prospectively assigned by four additional blinded raters. RESULTS: The Standardized Electrode Nomenclature for SEEG Application system was prospectively implemented in 40 consecutive patients undergoing SEEG monitoring at our institution, creating unique electrode names in all cases, and facilitating implantation design, SEEG recording and mapping interpretation, and treatment planning among neurosurgeons, neurologists, and neurophysiologists. The inter-rater percent agreement for electrode names among two neurosurgeons, two epilepsy neurologists, and one neurosurgical fellow was 97.5%. CONCLUSIONS: This standardized naming convention, Standardized Electrode Nomenclature for SEEG Application, provides a simple, concise, reproducible, and informative method for specifying the target(s) and relative position of each SEEG electrode in each patient, allowing for successful sharing of information in both the clinical and research settings. General adoption of this nomenclature could pave the way for improved communication and collaboration between institutions.

Clinical Utility of Sleep Recordings During Presurgical Epilepsy Evaluation With Stereo-Electroencephalography: A Systematic Review.

SUMMARY: Although the role of sleep in modulating epileptic activity is well established, many epileptologists overlook the significance of considering sleep during presurgical epilepsy evaluations in cases of drug-resistant epilepsy. Here, we conducted a comprehensive literature review from January 2000 to May 2023 using the PubMed electronic database and compiled evidence to highlight the need to revise the current clinical approach. All articles were assessed for eligibility by two independent reviewers. Our aim was to shed light on the clinical value of incorporating sleep monitoring into presurgical evaluations with stereo-electroencephalography. We present the latest developments on the important bidirectional interactions between sleep and various forms of epileptic activity observed in stereo-electroencephalography recordings. Specifically, epileptic activity is modulated by different sleep stages, peaking in non-rapid eye movement sleep, while being suppressed in rapid eye movement sleep. However, this modulation can vary across different brain regions, underlining the need to account for sleep to accurately pinpoint the epileptogenic zone during presurgical assessments. Finally, we offer practical solutions, such as automated sleep scoring algorithms using stereo-electroencephalography data alone, to seamlessly integrate sleep monitoring into routine clinical practice. It is hoped that this review will provide clinicians with a readily accessible roadmap to the latest evidence concerning the clinical utility of sleep monitoring in the context of stereo-electroencephalography and aid the development of therapeutic and diagnostic strategies to improve patient surgical outcomes.

Escaping the Procrustean Bed: A Perspective on Pediatric Stereoelectroencephalography.

SUMMARY: Stereoelectroencephalography is an established, hypothesis-driven method for investigating refractory epilepsy. There are special considerations and some limitations that apply to children who undergo stereoelectroencephalography. A key principle in stereoelectroencephalography is taking an individualized approach to investigating refractory epilepsy. A crucial factor for success in a personalized pediatric epilepsy surgery is understanding some of the fundamental and unique aspects of it, including, but not limited to, diverse etiology, epilepsy syndromes, maturation, and age-related characteristics as well as neural plasticity. Such features are reflected in the ontogeny of semiology and electrophysiology. In addition, special considerations are taken into account during cortical stimulation in children. Stereoelectroencephalography can guide a tailored surgical intervention where it is sufficient to render the patient seizure-free but it also lessens collateral damage with a minimum or no functional deficit. Epilepsy surgery outcomes remain stagnant despite advances in noninvasive testing modalities. A stereoelectroencephalography "way of thinking" and guided mentorship may influence outcomes positively.

Beyond Stereo-EEG: Is It Worth Combining Stereo-EEG With Other Diagnostic Methods?

SUMMARY: Stereo-EEG is a widely used method to improve the diagnostic precision of presurgical workup in patients with refractory epilepsy. Its ability to detect epileptic activity and identify epileptic networks largely depends on the chosen implantation strategy. Even in an ideal situation, electrodes record activity generated in <10% of the brain and contacts only record from brain tissue in their immediate proximity. In this article, the authors discuss how recording stereo-EEG simultaneously with other diagnostic methods can improve its diagnostic value in clinical and research settings. It can help overcome the limited spatial coverage of intracranial recording and better understand the sources of epileptic activity. Simultaneous scalp EEG is the most widely available method, often used to understand large epileptic networks, seizure propagation, and EEG activity occurring on the contralateral hemisphere. Simultaneous magnetoencephalography allows for more precise source localization and identification of deep sources outside the stereo-EEG coverage. Finally, simultaneous functional MRI can highlight metabolic changes following epileptic activity and help understand the widespread network changes associated with interictal activity. This overview highlights advantages and methodological challenges for all these methods. Clinical use and research applications are presented for each approach.

Prediction of Robotic Anastomosis Competency Evaluation (RACE) metrics during vesico-urethral anastomosis using electroencephalography, eye-tracking, and machine learning.

Residents learn the vesico-urethral anastomosis (VUA), a key step in robot-assisted radical prostatectomy (RARP), early in their training. VUA assessment and training significantly impact patient outcomes and have high educational value. This study aimed to develop objective prediction models for the Robotic Anastomosis Competency Evaluation (RACE) metrics using electroencephalogram (EEG) and eye-tracking data. Data were recorded from 23 participants performing robot-assisted VUA (henceforth 'anastomosis') on plastic models and animal tissue using the da Vinci surgical robot. EEG and eye-tracking features were extracted, and participants' anastomosis subtask performance was assessed by three raters using the RACE tool and operative videos. Random forest regression (RFR) and gradient boosting regression (GBR) models were developed to predict RACE scores using extracted features, while linear mixed models (LMM) identified associations between features and RACE scores. Overall performance scores significantly differed among inexperienced, competent, and experienced skill levels (P value < 0.0001). For plastic anastomoses, R2 values for predicting unseen test scores were: needle positioning (0.79), needle entry (0.74), needle driving and tissue trauma (0.80), suture placement (0.75), and tissue approximation (0.70). For tissue anastomoses, the values were 0.62, 0.76, 0.65, 0.68, and 0.62, respectively. The models could enhance RARP anastomosis training by offering objective performance feedback to trainees.

The Effect of Caffeine on Movement-Related Cortical Potential Morphology and Detection.

Movement-related cortical potential (MRCP) is observed in EEG recordings prior to a voluntary movement. It has been used for e.g., quantifying motor learning and for brain-computer interfacing (BCIs). The MRCP amplitude is affected by various factors, but the effect of caffeine is underexplored. The aim of this study was to investigate if a cup of coffee with 85 mg caffeine modulated the MRCP amplitude and the classification of MRCPs versus idle activity, which estimates BCI performance. Twenty-six healthy participants performed 2 × 100 ankle dorsiflexion separated by a 10-min break before a cup of coffee was consumed, followed by another 100 movements. EEG was recorded during the movements and divided into epochs, which were averaged to extract three average MRCPs that were compared. Also, idle activity epochs were extracted. Features were extracted from the epochs and classified using random forest analysis. The MRCP amplitude did not change after consuming caffeine. There was a slight increase of two percentage points in the classification accuracy after consuming caffeine. In conclusion, a cup of coffee with 85 mg caffeine does not affect the MRCP amplitude, and improves MRCP-based BCI performance slightly. The findings suggest that drinking coffee is only a minor confounder in MRCP-related studies.

A Cascade xDAWN EEGNet Structure for Unified Visual-Evoked Related Potential Detection.

Visual-based brain-computer interface (BCI) enables people to communicate with others by spelling words from the brain and helps professionals recognize targets in large numbers of images. P300 signals evoked by different types of stimuli, such as words or images, may vary significantly in terms of both amplitude and latency. A unified approach is required to detect variable P300 signals, which facilitates BCI applications, as well as deepens the understanding of the P300 generation mechanism. In this study, our proposed approach involves a cascade network structure that combines xDAWN and classical EEGNet techniques. This network is designed to classify target and non-target stimuli in both P300 speller and rapid serial visual presentation (RSVP) paradigms. The proposed approach is capable of recognizing more symbols with fewer repetitions (up to 5 rounds) compared to other models while possessing a better information transfer rate (ITR) as demonstrated on Dataset II (17.22 bits/min in the second repetition round) of BCI Competition III. Additionally, our approach has the highest unweighted average recall (UAR) performance for both 5 Hz ( 0.8134±0.0259 ) and 20 Hz ( 0.6527±0.0321 ) RSVP. The results show that the cascade network structure has better performance between both the P300 Speller and RSVP paradigms, manifesting that such a cascade structure is robust enough for dealing with P300-related signals (source code is available at https://github.com/embneural/Cascade-xDAWN-EEGNet-for-ERP-Detection).

Seizure onset zone (SOZ) identification using effective brain connectivity of epileptogenic networks.

Objective. To demonstrate the capability of utilizing graph feature-based supervised machine learning (ML) algorithm on intracranial electroencephalogram recordings for the identification of seizure onset zones (SOZs) in individuals with drug-resistant epilepsy.Approach. Utilizing three model-free measures of effective connectivity (EC)-directed information, mutual information-guided Granger causality index (MI-GCI), and frequency-domain convergent cross-mapping (FD-CCM) - directed graphs are generated. Graph centrality measures at different sparsity are used as the classifier's features.Main results. The centrality features achieve high accuracies exceeding 90% in distinguishing SOZ electrodes from non-SOZ electrodes. Notably, a sparse graph representation with just ten features and simple ML models effectively achieves such performance. The study identifies FD-CCM centrality measures as particularly significant, with a mean AUC of 0.93, outperforming prior literature. The FD-CCM-based graph modeling also highlights elevated centrality measures among SOZ electrodes, emphasizing heightened activity relative to non-SOZ electrodes during ictogenesis.Significance. This research not only underscores the efficacy of automated SOZ identification but also illuminates the potential of specific EC measures in enhancing discriminative power within the context of epilepsy research.

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

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

The Potential Neurological Impact of Intraoperative Hyponatremia Using Histidine-Tryptophan-Ketoglutarate Cardioplegia Infusion in Adult Cardiac Surgery.

Background and Objectives: The relationship between histidine-tryptophan-ketoglutarate (HTK)-induced hyponatremia and brain injury in adult cardiac surgery patients is unclear. This study analyzed postoperative neurological outcomes after intraoperative HTK cardioplegia infusion. Materials and Methods: A prospective cohort study was conducted on 60 adult patients who underwent cardiac surgery with cardiopulmonary bypass. Of these patients, 13 and 47 received HTK infusion and conventional hyperkalemic cardioplegia, respectively. The patients' baseline characteristics, intraoperative data, brain injury markers, Mini-Mental State Examination (MMSE) scores, and quantitative electroencephalography (qEEG) data were collected. Electrolyte changes during cardiopulmonary bypass, the degree of hyponatremia, and any associated brain insults were evaluated. Results: The HTK group presented with acute hyponatremia during cardiopulmonary bypass, which was intraoperatively corrected through ultrafiltration and normal saline administration. Postoperative sodium levels were higher in the HTK group than in the conventional cardioplegia group. The change in neuron-specific enolase levels after cardiopulmonary bypass was significantly higher in the HTK group (p = 0.043). The changes showed no significant differences using case-control matching. qEEG analysis revealed a significant increase in relative delta power in the HTK group on postoperative day (POD) 7 (p = 0.018); however, no significant changes were noted on POD 60. The MMSE scores were not significantly different between the two groups on POD 7 and POD 60. Conclusions: HTK-induced acute hyponatremia and rapid correction with normal saline during adult cardiac surgeries were associated with a potential short-term but not long-term neurological impact. Further studies are required to determine the necessity of correction for HTK-induced hyponatremia.

Speech decoding from stereo-electroencephalography (sEEG) signals using advanced deep learning methods.

Objective.Brain-computer interfaces (BCIs) are technologies that bypass damaged or disrupted neural pathways and directly decode brain signals to perform intended actions. BCIs for speech have the potential to restore communication by decoding the intended speech directly. Many studies have demonstrated promising results using invasive micro-electrode arrays and electrocorticography. However, the use of stereo-electroencephalography (sEEG) for speech decoding has not been fully recognized.Approach.In this research, recently released sEEG data were used to decode Dutch words spoken by epileptic participants. We decoded speech waveforms from sEEG data using advanced deep-learning methods. Three methods were implemented: a linear regression method, an recurrent neural network (RNN)-based sequence-to-sequence model (RNN), and a transformer model.Main results.Our RNN and transformer models outperformed the linear regression significantly, while no significant difference was found between the two deep-learning methods. Further investigation on individual electrodes showed that the same decoding result can be obtained using only a few of the electrodes.Significance.This study demonstrated that decoding speech from sEEG signals is possible, and the location of the electrodes is critical to the decoding performance.