EEG Processing Research Articles

The impact of the type of playful massage movements on the perception of tactile stimulation in children: EEG study

Tactile play and playful massage are a normal interaction between adults and children in many cultures. Experimental data show that activation of the C-tactile system during such playful touches contributes to children’s socialization and the establishment of psychoemotional bonds in the parent-child dyad. However, comprehensive studies of the effects of different types of touch on perception of tactile stimulation in children have not been conducted before. Twenty-three children participated in the present study: 10 in the preschool age group and 13 in the elementary school age group. Children in both groups received play massage containing different types of touch with simultaneous recording of electroencephalogram (EEG) and heart rate. EEG processing included determination of spectral power, alpha rhythm peak frequency and fractal dimension. Analysis of the results showed that the relaxing effect of the procedure was more pronounced in children of primary school age, which can be explained both by the greater maturity of the CNS and the greater need for tactile contact, which is not realized in the school environment.

O-CLEAN: a novel multi-stage algorithm for the ocular artifacts' correction from EEG data in out-of-the-lab applications.

In the context of electroencephalographic (EEG) signal processing, artifacts generated by ocular movements, such as blinks, are significant confounding factors. These artifacts overwhelm informative EEG features and may occur too frequently to simply remove affected epochs without losing valuable data. Correcting these artifacts remains a challenge, particularly in out-of-lab and online applications using wearable EEG systems (i.e. with low number of EEG channels, without any additional channels to track EOG).Objective.The main objective of the present work consisted in validating a novel ocular blinks artefacts correction method, named multi-stage OCuLar artEfActs deNoising algorithm (o-CLEAN), suitable for online processing with minimal EEG channels.Approach.The research was conducted considering one EEG dataset collected in highly controlled environment, and a second one collected in real environment. The analysis was performed by comparing the o-CLEAN method with previously validated state-of-art techniques, and by evaluating its performance along two dimensions: (a) the ocular artefacts correction performance (IN-Blink), and (b) the EEG signal preservation when the method was applied without any ocular artefacts occurrence (OUT-Blink).Main results.Results highlighted that (i) o-CLEAN algorithm resulted to be, at least, significantly reliable as the most validated approaches identified in scientific literature in terms of ocular blink artifacts correction, (ii) o-CLEAN showed the best performances in terms of EEG signal preservation especially with a low number of EEG channels.Significance.The testing and validation of the o-CLEAN addresses a relevant open issue in bioengineering EEG processing, especially within out-of-the-lab application. In fact, the method offers an effective solution for correcting ocular artifacts in EEG signals with a low number of available channels, for online processing, and without any specific template of the EOG. It was demonstrated to be particularly effective for EEG data gathered in real environments using wearable systems, a rapidly expanding area within applied neuroscience.

Adaptive channel-weight dual-constrained semi-supervised EEG clustering

When processing Electroencephalography(EEG) for applications such as brain disease diagnosis, rehabilitation, and brain–computer interfaces, we encounter challenges related to missing labels or incorrect annotations. These challenges may arise from subjective factors, technical limitations, or data quality issues. In traditional EEG processing, unsupervised clustering algorithms are commonly used; however, due to the lack of labels, these methods may struggle to fully leverage latent information, resulting in uncertainty and instability in clustering outcomes. To address this issue, we propose a semi-supervised clustering method tailored for partially labeled EEG signals, named Adaptive Channel-weight Dual-constrained Semi-supervised EEG Clustering (ACDSEEGc). This method incorporates dual constraints: a connectivity constraint for the interconnections between EEG points and a neighborhood constraint for the spatial neighborhood relationships among EEG data points. Additionally, it integrates channel weights to emphasize information from important channels. The objective function of ACDSEEGc integrates cross-entropy evaluation, channel weight learning, pseudo-label learning, connectivity constraint, and least squares error minimization. Our aim is to maximize the use of limited prior knowledge to achieve better EEG clustering results. Experimental validation demonstrates that ACDSEEGc effectively produces superior clustering outcomes compared to state-of-the-art standard unsupervised and semi-supervised EEG/time-series clustering algorithms. Furthermore, we conducted sensitivity experiments and ablation studies to verify the performance of ACDSEEGc under different settings.

METHODS OF MATHEMATICAL ANALYSIS AND PROCESSING OF EEG SIGNALS: OVERVIEW OF THE CURRENT STATE AND LATEST TRENDS

Aim. With the help of retrospective analysis, establish the current level of achievements in the field of applying methods of mathematical analysis and processing of biomedical signals, in particular EEG, and characterize the main trends. Materials and methods. The research was conducted using theoretical methods, by studying and analyzing freely available literature, publications, materials of working groups of domestic and foreign scientists over the past few years. Results. The analysis of scientific works devoted to the development and development of EEG showed that over the past five years there has been a deepening of the tendency to separate the methods of improving the hardware and software parts of electroencephalographic complexes. The last of them, in turn, can be divided into several main directions. The first direction is the improvement of real-time EEG analysis methods, including automatic processing included in the software of EEG complexes. The second direction combines mathematical methods of signal analysis to detect existing pathologies and predict the onset of pathological conditions, such as statistical, spectral-correlation analysis, building mathematical models. The next direction brings together the application of mathematical methods for EEG signal processing and further use in deep learning, the use of convolutional neural networks to detect epileptic seizures, sleep disorders, differentiation of neuropsychiatric disorders, etc. The direction of using EEG in prosthetics deserves special attention. Methods of mathematical processing of the EEG signal are widely implemented in the development of bionic prostheses. The main achievements in these directions are considered in detail in the work. Conclusions. While the improvement of the material and technical part of the EEG is focused on the issues of improving the methods of recording biological signals, finding optimal methods of suppressing noise without losing the useful signal and does not currently have breakthrough results, the methods of analysis and processing of the already received signal have developed rapidly. The use of EEG to detect pathological conditions, the study of the neurophysiological basis of cognitive processes, etc., has always attracted the interest of scientists, but the use of neural networks for EEG processing and analysis and their implementation in robotics developments has given this direction a new impetus.

Evaluation of features and channels of electroencephalographic signals for biometric systems

Biometric systems are essential tools in modern society where most of our personal information lives in digital form. Although there is a significant variety of biometrics, electroencephalogram (EEG) signals are a useful technique to guarantee that the person is alive, they are universal, and not falsifiable. Nevertheless, EEG processing needs to address some challenges to become a viable technique to build production-ready biometric systems. These challenges include the adequate selection of features and channels that maximize the quality of the results and optimize resources. This work provides an analysis of which are the most important features and channels for the correct operation of a biometric system. The experimental analysis worked with two datasets and evaluated 19 features belonging to three groups, wavelet-based, spectral, and complexity. Five classifiers were trained: multilayer perceptron, AdaBoost, random forest, support vector machine, and K-nearest neighbors. The results found that the best feature for developing a biometric system is the standard deviation extracted from the coefficients of a three-level discrete wavelet transform. Additionally, the experimental results with the two datasets showed that the proposed method for channel selection can reduce the necessary number of channels while maintaining its performance. Our results, from one of the datasets, showed a reduction of 21 channels (from 32 to 11) and indicated that the best channels to develop biometric systems seem to be those located on the central area of the scalp.

Detection of epileptiform discharges by patient state index and density spectral array during anesthetic emergence after resection of hemispheric brain tumor. Case report

Background: Processed electroencephalogram (EEGp) plays a crucial role in anesthesia as a quantitative and automated method for assessing anesthetic depth. It utilizes mathematical algorithms to furnish objective measures, offering an intuitive interface for anesthesiologists lacking specialized neurophysiology training. Among the array of visual graphical analyses, the Density Spectral Array (DSA) stands out as particularly promising. DSA furnishes a comprehensive and visual depiction of the patient's brain activity, aiding anesthesiologists in maintaining optimal anesthetic depth during surgical procedures Conclusion: This report underscores the potential of analyzing Case report: A 51-year-old male with a medical history of neurofibromatosis type 2 and a frontal hemispheric brain tumor underwent resection in the operating room under total intravenous anesthesia. Anesthetic depth was monitored utilizing SedLine® Patient Status Index (PSi). The resection proceeded uneventfully; however, upon extubation, EEG processing revealed epileptiform discharges concurrent with tonic-clonic movement of the right hand electroencephalogram waveforms alongside the latest SedLine-derived Density Spectral Array to confirm the presence of partial epileptic seizures during the immediate post-extubation and postoperative phases following brain tumor resection. Employing advanced monitoring techniques like Density Spectral Array aids in early detection of neurological complications, facilitating timely intervention and potentially enhancing patient outcomes during the critical postoperative period.

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.

MEP and TEP features variability: is it just the brain-state?

Objective. The literature investigating the effects of alpha oscillations on corticospinal excitability is divergent. We believe inconsistency in the findings may arise, among others, from the electroencephalography (EEG) processing for brain-state determination. Here, we provide further insights in the effects of the brain-state on cortical and corticospinal excitability and quantify the impact of different EEG processing. Approach. Corticospinal excitability was measured using motor evoked potential (MEP) peak-to-peak amplitudes elicited with transcranial magnetic stimulation (TMS); cortical responses were studied through TMS-evoked potentials’ TEPs features. A TMS-EEG-electromyography (EMG) dataset of 18 young healthy subjects who received 180 single-pulse (SP) and 180 paired pulses (PP) to determine short-intracortical inhibition (SICI) was investigated. To study the effect of different EEG processing, we compared the brain-state estimation deriving from three published methods. The influence of presence of neural oscillations was also investigated. To evaluate the effect of the brain-state on MEP and TEP features variability, we defined the brain-state based on specific EEG phase and power combinations, only in trials where neural oscillations were present. The relationship between TEPs and MEPs was further evaluated. Main results. The presence of neural oscillations resulted in more consistent results regardless of the EEG processing approach. Nonetheless, the latter still critically affected the outcomes, making conclusive claims complex. With our approach, the MEP amplitude was positively modulated by the alpha power and phase, with stronger responses during the trough phase and high power. Power and phase also affected TEP features. Importantly, similar effects were observed in both TMS conditions. Significance. These findings support the view that the brain state of alpha oscillations is associated with the variability observed in cortical and corticospinal responses to TMS, with a tight correlation between the two. The results further highlight the importance of closed-loop stimulation approaches while underlining that care is needed in designing experiments and choosing the analytical approaches, which should be based on knowledge from offline studies to control for the heterogeneity originating from different EEG processing strategies.

Finding neural correlates of depersonalisation/derealisation disorder via explainable CNN-based analysis guided by clinical assessment scores

Mental health disorders are typically diagnosed based on subjective reports (e.g., through questionnaires) followed by clinical interviews to evaluate the self-reported symptoms. Therefore, considering the interconnected nature of psychiatric disorders, their accurate diagnosis is a real challenge without indicators of underlying physiological dysfunction. Depersonalisation/derealisation disorder (DPD) is an example of dissociative disorder affecting 1–2 % of the population. DPD is characterised mainly by persistent disembodiment, detachment from surroundings, and feelings of emotional numbness, which can significantly impact patients' quality of life. The underlying neural correlates of DPD have been investigated for years to understand and help with a more accurate and in-time diagnosis of the disorder. However, in terms of EEG studies, which hold great importance due to their convenient and inexpensive nature, the literature has often been based on hypotheses proposed by experts in the field, which require prior knowledge of the disorder. In addition, participants' labelling in research experiments is often derived from the outcome of the Cambridge Depersonalisation Scale (CDS), a subjective assessment to quantify the level of depersonalisation/derealisation, the threshold and reliability of which might be challenged. As a result, we aimed to propose a novel end-to-end EEG processing pipeline based on deep neural networks for DPD biomarker discovery, which requires no prior handcrafted labelled data. Alternatively, it can assimilate knowledge from clinical outcomes like CDS as well as data-driven patterns that differentiate individual brain responses. In addition, the structure of the proposed model targets the uncertainty in CDS scores by using them as prior information only to guide the unsupervised learning task in a multi-task learning scenario. A comprehensive evaluation has been done to confirm the significance of the proposed deep structure, including new ways of network visualisation to investigate spectral, spatial, and temporal information derived in the learning process. We argued that the proposed EEG analytics could also be applied to investigate other psychological and mental disorders currently indicated on the basis of clinical assessment scores. The code to reproduce the results presented in this paper is openly accessible at https://github.com/AbbasSalami/DPD_Analysis.

GAPses: Versatile smart glasses for comfortable and fully-dry acquisition and parallel ultra-low-power processing of EEG and EOG.

Recent advancements in head-mounted wearable technology are revolutionizing the field of biopotential measurement, but the integration of these technologies into practical, user-friendly devices remains challenging due to issues with design intrusiveness, comfort, reliability, and data privacy. To address these challenges, this paper presents GAPSES, a novel smart glasses platform designed for unobtrusive, comfortable, and secure acquisition and processing of electroencephalography (EEG) and electrooculography (EOG) signals.We introduce a direct electrode-electronics interface within a sleek frame design, with custom fully dry soft electrodes to enhance comfort for long wear. The fully assembled glasses, including electronics, weigh 40 g and have a compact size of 160 mm × 145 mm. An integrated parallel ultra-low-power RISC-V processor (GAP9, Greenwaves Technologies) processes data at the edge, thereby eliminating the need for continuous data streaming through a wireless link, enhancing privacy, and increasing system reliability in adverse channel conditions. We demonstrate the broad applicability of the designed prototype through validation in a number of EEG-based interaction tasks, including alpha waves, steady-state visual evoked potential analysis, and motor movement classification. Furthermore, we demonstrate an EEG-based biometric subject recognition task, where we reach a sensitivity and specificity of 98.87% and 99.86% respectively, with only 8 EEG channels and an energy consumption per inference on the edge as low as 121 μJ. Moreover, in an EOG-based eye movement classification task, we reach an accuracy of 96.68% on 11 classes, resulting in an information transfer rate of 94.78 bit/min, which can be further increased to 161.43 bit/min by reducing the accuracy to 81.43%. The deployed implementation has an energy consumption of 40 μJ per inference and a total system power of only 12.4 mW, of which only 1.61% is used for classification, allowing for continuous operation of more than 22 h with a small 75 mAh battery.

Mindspeak: Empowering Communication with Brain Keyboard

Brain-Computer Interface (BCI) technology stands as a groundbreaking innovation, revolutionizing the way individuals with severe motor disabilities interact with the world. The integration of Electroencephalogram (EEG) sensors within applications like the Brain Keyboard marks a pivotal stride forward. By capturing and interpreting brain signals triggered by simple actions such as eye blinking, these sensors empower users to control a virtual keyboard, transcending the limitations imposed by traditional motor pathways. This direct channel between the human brain and external devices offers an unprecedented avenue for communication, particularly invaluable for those grappling with conditions like paralysis or locked-in syndrome. The profound impact of BCIs extends far beyond facilitating textual communication; they represent a lifeline, a bridge toward autonomy and engagement for individuals facing profound physical challenges. Through these interfaces, users can articulate thoughts, express emotions, and actively participate in social interactions, fundamentally enhancing their quality of life. This technological marvel not only breaks down communication barriers but also holds promise in broader applications. As BCIs evolve, their potential encompasses enabling control over robotic prosthetics, granting users the ability to accomplish tasks once deemed impossible. Moreover, the implications of BCIs stretch into the realm of neuroscience, offering a unique window into understanding cognitive processes and neurological disorders. The ability to decode and interpret brain activity not only aids in facilitating communication but also paves the way for groundbreaking research and potential therapies. Challenges persist, such as enhancing signal accuracy and streamlining usability, yet the remarkable benefits that BCIs offer to individuals with motor disabilities continue to fuel ongoing innovation in this dynamic field. Ultimately, the fusion of EEG sensors, processing units, and user interfaces in BCIs heralds a new era of inclusivity and empowerment, where individuals previously marginalized by physical limitations find newfound avenues for expression, interaction, and independence. This transformative technology not only unlocks communication but also holds the key to reshaping our understanding of the human brain and its intricate workings, promising a f uture where disabilities no longer confine one's ability to engage with the world.

Changes In Objective Characteristics In Brain Electrical Activity In Newborns As A Function Of Birth Weight

The aim of the present study was to detect characteristic features of oscillatory electrical activity of the brain in the first day of postnatal life depending on the weight of newborns. Material — Eighteen neonates of conditionally normal gestational age (37.7±1.5 weeks) weighing 2500±720 g were included in the study. All neonates were children of first births of mothers aged 18-35 years, all pregnancies were physiologic, conventionally normal, without significant complications. The height of the newborns was 47±4.643 cm and head circumference was33.0±2.908 cm. The Apgar score at delivery was 7-9 points. All newborns were divided among groups 1 (weight: 2850-4000 gr), 2 (weight: 2000-2800 gr) and 3 (1200-2000 gr). Each newborn underwent EEG monitoring (EEG, monopolar recording, channels C3 and C4) for 40 minutes during the first 12 hours after birth. Methods — Automatic processing of EEG was performed without separating the monitoring records into sleep and wakefulness stages. Oscillatory patterns were calculated for each EEG channel based on the continuous wavelet transform method. Statistical estimations of the number and duration of oscillatory patterns developing in different EEG frequency ranges were performed. Results — A strong correlation was found between neonatal birth weight and integral characteristics of the number \ duration of oscillatory patterns in the low-frequency band [4; 6] Hz (r=-0.878\0.920). Practically healthy newborns with different birth weights show statistically different EEG characteristics in the [4; 6] Hz band in the first 12 hours after birth (p-value≤0.005). Conclusion — Electrical activity of the brain varies significantly depending on the weight of newborns immediately after birth. Monitoring of EEG signals according to the proposed algorithm may become the basis for the development of additional tools for early detection of possible disorders of neurological development of the newborn.

Spectral representation of EEG data using learned graphs with application to motor imagery decoding

Electroencephalography (EEG) data entail a complex spatiotemporal structure that reflects ongoing organization of brain activity. Characterization of the spatial patterns is an indispensable step in numerous EEG processing pipelines. We present a novel method for transforming EEG data into a spectral representation. First, we learn subject-specific graphs from each subject’s EEG data. Second, by eigendecomposition of the normalized Laplacian matrix of each subject’s graph, an orthonormal basis is obtained using which any given EEG map of the subject can be decomposed, providing a spectral representation of the data. We show that energy of EEG maps is strongly associated with low frequency components of the learned basis, reflecting the smooth topography of EEG maps. As a proof-of-concept for this alternative view of EEG data, we consider the task of decoding two-class motor imagery (MI) data. To this aim, the spectral representations are first mapped into a discriminative subspace for differentiating two-class data using a projection matrix obtained by the Fukunaga–Koontz transform (FKT). An SVM classifier is then trained and tested on the resulting features to differentiate MI classes. The method is benchmarked against features extracted from a subject-specific functional connectivity matrix as well as four alternative MI-decoding methods on Dataset IVa of BCI Competition III. Experimental results show the superiority of the proposed method over alternative approaches in differentiating MI classes, reflecting the added benefit of (i) decomposing EEG data using data-driven, subject-specific harmonic bases, and (ii) accounting for class-specific temporal variations in spectral profiles.

Decoding Algorithm of Motor Imagery Electroencephalogram Signal Based on CLRNet Network Model.

EEG decoding based on motor imagery is an important part of brain-computer interface technology and is an important indicator that determines the overall performance of the brain-computer interface. Due to the complexity of motor imagery EEG feature analysis, traditional classification models rely heavily on the signal preprocessing and feature design stages. End-to-end neural networks in deep learning have been applied to the classification task processing of motor imagery EEG and have shown good results. This study uses a combination of a convolutional neural network (CNN) and a long short-term memory (LSTM) network to obtain spatial information and temporal correlation from EEG signals. The use of cross-layer connectivity reduces the network gradient dispersion problem and enhances the overall network model stability. The effectiveness of this network model is demonstrated on the BCI Competition IV dataset 2a by integrating CNN, BiLSTM and ResNet (called CLRNet in this study) to decode motor imagery EEG. The network model combining CNN and BiLSTM achieved 87.0% accuracy in classifying motor imagery patterns in four classes. The network stability is enhanced by adding ResNet for cross-layer connectivity, which further improved the accuracy by 2.0% to achieve 89.0% classification accuracy. The experimental results show that CLRNet has good performance in decoding the motor imagery EEG dataset. This study provides a better solution for motor imagery EEG decoding in brain-computer interface technology research.

NeuXus open-source tool for real-time artifact reduction in simultaneous EEG-fMRI

The simultaneous acquisition of electroencephalography and functional magnetic resonance imaging (EEG-fMRI) allows the complementary study of the brain's electrophysiology and hemodynamics with high temporal and spatial resolution. One application with great potential is neurofeedback training of targeted brain activity, based on the real-time analysis of the EEG and/or fMRI signals. This depends on the ability to reduce in real time the severe artifacts affecting the EEG signal acquired with fMRI, mainly the gradient and pulse artifacts. A few methods have been proposed for this purpose, but they are either slow, hardware-dependent, publicly unavailable, or proprietary software. Here, we present a fully open-source and publicly available tool for real-time EEG artifact reduction in simultaneous EEG-fMRI recordings that is fast and applicable to any hardware. Our tool is integrated in the Python toolbox NeuXus for real-time EEG processing and adapts to a real-time scenario well-established artifact average subtraction methods combined with a long short-term memory network for R peak detection. We benchmarked NeuXus on three different datasets, in terms of artifact power reduction and background signal preservation in resting state, alpha-band power reactivity to eyes closure, and event-related desynchronization during motor imagery. We showed that NeuXus performed at least as well as the only available real-time tool for conventional hardware setups (BrainVision's RecView) and a well-established offline tool (EEGLAB's FMRIB plugin). We also demonstrated NeuXus’ real-time ability by reporting execution times under 250 ms. In conclusion, we present and validate the first fully open-source and hardware-independent solution for real-time artifact reduction in simultaneous EEG-fMRI studies.

Machine-learning for the prediction of one-year seizure recurrence based on routine electroencephalography

Predicting seizure recurrence risk is critical to the diagnosis and management of epilepsy. Routine electroencephalography (EEG) is a cornerstone of the estimation of seizure recurrence risk. However, EEG interpretation relies on the visual identification of interictal epileptiform discharges (IEDs) by neurologists, with limited sensitivity. Automated processing of EEG could increase its diagnostic yield and accessibility. The main objective was to develop a prediction model based on automated EEG processing to predict one-year seizure recurrence in patients undergoing routine EEG. We retrospectively selected a consecutive cohort of 517 patients undergoing routine EEG at our institution (training set) and a separate, temporally shifted cohort of 261 patients (testing set). We developed an automated processing pipeline to extract linear and non-linear features from the EEGs. We trained machine learning algorithms on multichannel EEG segments to predict one-year seizure recurrence. We evaluated the impact of IEDs and clinical confounders on performances and validated the performances on the testing set. The receiver operating characteristic area-under-the-curve for seizure recurrence after EEG in the testing set was 0.63 (95% CI 0.55–0.71). Predictions were still significantly above chance in EEGs with no IEDs. Our findings suggest that there are changes other than IEDs in the EEG signal embodying seizure propensity.

Overview of mathematical EEG analysis. Quantitative EEG

The purpose of this article is to familiarize medical specialists involved in registration and analysis of electroencephalographic (EEG) studies using methods of mathematical processing and analysis for recorded EEG data. Understanding the principles of how quantitative EEG analysis tools work should help medical personnel to properly use their capabilities and ultimately improve quality of medical care. Here, we discuss basic and innovative mathematical tools for EEG processing and analysis.

Machine learning polysomnographically-derived electroencephalography biomarkers predictive of epworth sleepiness scale

Excessive daytime sleepiness (EDS) causes difficulty in concentrating and continuous fatigue during the day. In the clinical setting, the assessment and diagnosis of EDS rely mostly on subjective questionnaires and verbal reports, which compromises the reliability of clinical diagnosis and the ability to robustly discern candidacy for available therapies and track treatment response. In this study, we used a computational pipeline for the automated, rapid, high-throughput, and objective analysis of previously collected encephalography (EEG) data to identify surrogate biomarkers for EDS, thereby defining the quantitative EEG changes in individuals with high Epworth Sleepiness Scale (ESS) (n = 31), compared to a group of individuals with low ESS (n = 41) at the Cleveland Clinic. The epochs of EEG analyzed were extracted from a large overnight polysomnogram registry during the most proximate period of wakefulness. Signal processing of EEG showed significantly different EEG features in the low ESS group compared to high ESS, including enhanced power in the alpha and beta bands and attenuation in the delta and theta bands. Our machine learning (ML) algorithms trained on the binary classification of high vs. low ESS reached an accuracy of 80.2%, precision of 79.2%, recall of 73.8% and specificity of 85.3%. Moreover, we ruled out the effects of confounding clinical variables by evaluating the statistical contribution of these variables on our ML models. These results indicate that EEG data contain information in the form of rhythmic activity that could be leveraged for the quantitative assessment of EDS using ML.

A bidirectional interaction-based hybrid network architecture for EEG cognitive recognition

Background and objective: Extracting cognitive representation and computational representation information simultaneously from electroencephalography (EEG) data and constructing corresponding information interaction models can effectively improve the recognition capability of brain cognitive status. However, due to the huge gap in the interaction between the two types of information, existing studies have yet to consider the advantages of the interaction of both.Methods: This paper introduces a novel architecture named the bidirectional interaction-based hybrid network (BIHN) for EEG cognitive recognition. BIHN consists of two networks: a cognitive-based network named CogN (e.g., graph convolution network, GCN; capsule network, CapsNet) and a computing-based network named ComN (e.g., EEGNet). CogN is responsible for extracting cognitive representation features from EEG data, while ComN is responsible for extracting computational representation features. Additionally, a bidirectional distillation-based coadaptation (BDC) algorithm is proposed to facilitate information interaction between CogN and ComN to realize the coadaptation of the two networks through bidirectional closed-loop feedback.Results: Cross-subject cognitive recognition experiments were performed on the Fatigue-Awake EEG dataset (FAAD, 2-class classification) and SEED dataset (3-class classification), and hybrid network pairs of GCN + EEGNet and CapsNet + EEGNet were verified. The proposed method achieved average accuracies of 78.76% (GCN + EEGNet) and 77.58% (CapsNet + EEGNet) on FAAD and 55.38% (GCN + EEGNet) and 55.10% (CapsNet + EEGNet) on SEED, outperforming the hybrid networks without the bidirectional interaction strategy.Conclusions: Experimental results show that BIHN can achieve superior performance on two EEG datasets and enhance the ability of both CogN and ComN in EEG processing as well as cognitive recognition. We also validated its effectiveness with different hybrid network pairs. The proposed method could greatly promote the development of brain-computer collaborative intelligence.

Predicting Seizure Freedom through Computational Processing of Routine EEG (S30.002)

Predicting Seizure Freedom through Computational Processing of Routine EEG (S30.002)