Neural Decoding of EEG Signals with Machine Learning: A Systematic Review

vEpiNet: A multimodal interictal epileptiform discharge detection method based on video and electroencephalogram data

To enhance deep learning-based automated interictal epileptiform discharge (IED) detection, this study proposes a multimodal method, vEpiNet, that leverages video and electroencephalogram (EEG) data. Datasets comprise 24 931 IED (from 484 patients) and 166 094 non-IED 4-second video-EEG segments. The video data is processed by the proposed patient detection method, with frame difference and Simple Keypoints (SKPS) capturing patients' movements. EEG data is processed with EfficientNetV2. The video and EEG features are fused via a multilayer perceptron. We developed a comparative model, termed nEpiNet, to test the effectiveness of the video feature in vEpiNet. The 10-fold cross-validation was used for testing. The 10-fold cross-validation showed high areas under the receiver operating characteristic curve (AUROC) in both models, with a slightly superior AUROC (0.9902) in vEpiNet compared to nEpiNet (0.9878). Moreover, to test the model performance in real-world scenarios, we set a prospective test dataset, containing 215 h of raw video-EEG data from 50 patients. The result shows that the vEpiNet achieves an area under the precision-recall curve (AUPRC) of 0.8623, surpassing nEpiNet's 0.8316. Incorporating video data raises precision from 70% (95% CI, 69.8%-70.2%) to 76.6% (95% CI, 74.9%-78.2%) at 80% sensitivity and reduces false positives by nearly a third, with vEpiNet processing one-hour video-EEG data in 5.7 min on average. Our findings indicate that video data can significantly improve the performance and precision of IED detection, especially in prospective real clinic testing. It suggests that vEpiNet is a clinically viable and effective tool for IED analysis in real-world applications.

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

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

Neuronal avalanches in temporal lobe epilepsy as a noninvasive diagnostic tool investigating large scale brain dynamics

The epilepsy diagnosis still represents a complex process, with misdiagnosis reaching 40%. We aimed at building an automatable workflow, helping the clinicians in the diagnosis of temporal lobe epilepsy (TLE). We hypothesized that neuronal avalanches (NA) represent a feature better encapsulating the rich brain dynamics compared to classically used functional connectivity measures (Imaginary Coherence; ImCoh). We analyzed large-scale activation bursts (NA) from source estimation of resting-state electroencephalography. Using a support vector machine, we reached a classification accuracy of TLE versus controls of 0.86 ± 0.08 (SD) and an area under the curve of 0.93 ± 0.07. The use of NA features increase by around 16% the accuracy of diagnosis prediction compared to ImCoh. Classification accuracy increased with larger signal duration, reaching a plateau at 5 min of recording. To summarize, NA represents an interpretable feature for an automated epilepsy identification, being related with intrinsic neuronal timescales of pathology-relevant regions.

Increasing accessibility to a large brain-computer interface dataset: Curation of physionet EEG motor movement/imagery dataset for decoding and classification

A reliable motor imagery (MI) brain-computer interface (BCI) requires accurate decoding, which in turn requires model calibration using electroencephalography (EEG) signals from subjects executing or imagining the execution of movements. Although the PhysioNet EEG Motor Movement/Imagery Dataset is currently the largest EEG dataset in the literature, relatively few studies have used it to decode MI trials. In the present study, we curated and cleaned this dataset to store it in an accessible format that is convenient for quick exploitation, decoding, and classification using recent integrated development environments. We dropped six subjects owing to anomalies in EEG recordings and pre-possessed the rest, resulting in 103 subjects spanning four MI and four motor execution tasks. The annotations were coded to correspond to different tasks using numerical values. The resulting dataset is stored in both MATLAB structure and CSV files to ensure ease of access and organization. We believe that improving the accessibility of this dataset will help EEG-based MI-BCI decoding and classification, enabling more reliable real-life applications. The convenience and ease of access of this dataset may therefore lead to improvements in cross-subject classification and transfer learning.

Contribution of low-level image statistics to EEG decoding of semantic content in multivariate and univariate models with feature optimization

Spatio-temporal patterns of evoked brain activity contain information that can be used to decode and categorize the semantic content of visual stimuli. However, this procedure can be biased by low-level image features independently of the semantic content present in the stimuli, prompting the need to understand the robustness of different models regarding these confounding factors. In this study, we trained machine learning models to distinguish between concepts included in the publicly available THINGS-EEG dataset using electroencephalography (EEG) data acquired during a rapid serial visual presentation paradigm. We investigated the contribution of low-level image features to decoding accuracy in a multivariate model, utilizing broadband data from all EEG channels. Additionally, we explored a univariate model obtained through data-driven feature selection applied to the spatial and frequency domains. While the univariate models exhibited better decoding accuracy, their predictions were less robust to the confounding effect of low-level image statistics. Notably, some of the models maintained their accuracy even after random replacement of the training dataset with semantically unrelated samples that presented similar low-level content. In conclusion, our findings suggest that model optimization impacts sensitivity to confounding factors, regardless of the resulting classification performance. Therefore, the choice of EEG features for semantic decoding should ideally be informed by criteria beyond classifier performance, such as the neurobiological mechanisms under study.

EEG Changes in Migraine-Can EEG Help to Monitor Attack Susceptibility?

Migraine is a highly prevalent brain condition with paroxysmal changes in brain excitability believed to contribute to the initiation of an attack. The attacks and their unpredictability have a major impact on the lives of patients. Clinical management is hampered by a lack of reliable predictors for upcoming attacks, which may help in understanding pathophysiological mechanisms to identify new treatment targets that may be positioned between the acute and preventive possibilities that are currently available. So far, a large range of studies using conventional hospital-based EEG recordings have provided contradictory results, with indications of both cortical hyper- as well as hypo-excitability. These heterogeneous findings may largely be because most studies were cross-sectional in design, providing only a snapshot in time of a patient's brain state without capturing day-to-day fluctuations. The scope of this narrative review is to (i) reflect on current knowledge on EEG changes in the context of migraine, the attack cycle, and underlying pathophysiology; (ii) consider the effects of migraine treatment on EEG features; (iii) outline challenges and opportunities in using EEG for monitoring attack susceptibility; and (iv) discuss future applications of EEG in home-based settings.

ECoG activity distribution patterns detects global cortical responses following weak tactile inputs

Many studies have suggested that the neocortex operates as a global network of functionally interconnected neurons, indicating that any sensory input could shift activity distributions across the whole brain. A tool assessing the activity distribution across cortical regions with high temporal resolution could then potentially detect subtle changes that may pass unnoticed in regionalized analyses. We used eight-channel, distributed electrocorticogram (ECoG) recordings to analyze changes in global activity distribution caused by single pulse electrical stimulations of the paw. We analyzed the temporally evolving patterns of the activity distributions using principal component analysis (PCA). We found that the localized tactile stimulation caused clearly measurable changes in global ECoG activity distribution. These changes in signal activity distribution patterns were detectable across a small number of ECoG channels, even when excluding the somatosensory cortex, suggesting that the method has high sensitivity, potentially making it applicable to human electroencephalography (EEG) for detection of pathological changes.

Reproducible machine learning research in mental workload classification using EEG

This study addresses concerns about reproducibility in scientific research, focusing on the use of electroencephalography (EEG) and machine learning to estimate mental workload. We established guidelines for reproducible machine learning research using EEG and used these to assess the current state of reproducibility in mental workload modeling. We first started by summarizing the current state of reproducibility efforts in machine learning and in EEG. Next, we performed a systematic literature review on Scopus, Web of Science, ACM Digital Library, and Pubmed databases to find studies about reproducibility in mental workload prediction using EEG. All of this previous work was used to formulate guidelines, which we structured along the widely recognized Cross-Industry Standard Process for Data Mining (CRISP-DM) framework. By using these guidelines, researchers can ensure transparency and comprehensiveness of their methodologies, therewith enhancing collaboration and knowledge-sharing within the scientific community, and enhancing the reliability, usability and significance of EEG and machine learning techniques in general. A second systematic literature review extracted machine learning studies that used EEG to estimate mental workload. We evaluated the reproducibility status of these studies using our guidelines. We highlight areas studied and overlooked and identify current challenges for reproducibility. Our main findings include limitations on reporting performance on unseen test data, open sharing of data and code, and reporting of resources essential for training and inference processes.

Exploring Aesthetic Perception in Impaired Aging: A Multimodal Brain-Computer Interface Study

In the field of neuroscience, brain-computer interfaces (BCIs) are used to connect the human brain with external devices, providing insights into the neural mechanisms underlying cognitive processes, including aesthetic perception. Non-invasive BCIs, such as EEG and fNIRS, are critical for studying central nervous system activity and understanding how individuals with cognitive deficits process and respond to aesthetic stimuli. This study assessed twenty participants who were divided into control and impaired aging (AI) groups based on MMSE scores. EEG and fNIRS were used to measure their neurophysiological responses to aesthetic stimuli that varied in pleasantness and dynamism. Significant differences were identified between the groups in P300 amplitude and late positive potential (LPP), with controls showing greater reactivity. AI subjects showed an increase in oxyhemoglobin in response to pleasurable stimuli, suggesting hemodynamic compensation. This study highlights the effectiveness of multimodal BCIs in identifying the neural basis of aesthetic appreciation and impaired aging. Despite its limitations, such as sample size and the subjective nature of aesthetic appreciation, this research lays the groundwork for cognitive rehabilitation tailored to aesthetic perception, improving the comprehension of cognitive disorders through integrated BCI methodologies.

Graph-based EEG approach for depression prediction: integrating time-frequency complexity and spatial topology

Depression has become the prevailing global mental health concern. The accuracy of traditional depression diagnosis methods faces challenges due to diverse factors, making primary identification a complex task. Thus, the imperative lies in developing a method that fulfills objectivity and effectiveness criteria for depression identification. Current research underscores notable disparities in brain activity between individuals with depression and those without. The Electroencephalogram (EEG), as a biologically reflective and easily accessible signal, is widely used to diagnose depression. This article introduces an innovative depression prediction strategy that merges time-frequency complexity and electrode spatial topology to aid in depression diagnosis. Initially, time-frequency complexity and temporal features of the EEG signal are extracted to generate node features for a graph convolutional network. Subsequently, leveraging channel correlation, the brain network adjacency matrix is employed and calculated. The final depression classification is achieved by training and validating a graph convolutional network with graph node features and a brain network adjacency matrix based on channel correlation. The proposed strategy has been validated using two publicly available EEG datasets, MODMA and PRED+CT, achieving notable accuracy rates of 98.30 and 96.51%, respectively. These outcomes affirm the reliability and utility of our proposed strategy in predicting depression using EEG signals. Additionally, the findings substantiate the effectiveness of EEG time-frequency complexity characteristics as valuable biomarkers for depression prediction.

Support-vector classification of low-dose nitrous oxide administration with multi-channel EEG power spectra

Support-vector machines (SVMs) can potentially improve patient monitoring during nitrous oxide anaesthesia. By elucidating the effects of low-dose nitrous oxide on the power spectra of multi-channel EEG recordings, we quantified the degree to which these effects generalise across participants. In this single-blind, cross-over study, 32-channel EEG was recorded from 12 healthy participants exposed to 0, 20, 30 and 40% end-tidal nitrous oxide. Features of the delta-, theta-, alpha- and beta-band power were used within a 12-fold, participant-wise cross-validation framework to train and test two SVMs: (1) binary SVM classifying EEG during 0 or 40% exposure (chance = 50%); (2) multi-class SVM classifying EEG during 0, 20, 30 or 40% exposure (chance = 25%). Both the binary (accuracy 92%) and the multi-class (accuracy 52%) SVMs classified EEG recordings at rates significantly better than chance (p < 0.001 and p = 0.01, respectively). To determine the relative importance of frequency band features for classification accuracy, we systematically removed features before re-training and re-testing the SVMs. This showed the relative importance of decreased delta power and the frontal region. SVM classification identified that the most important effects of nitrous oxide were found in the delta band in the frontal electrodes that was consistent between participants. Furthermore, support-vector classification of nitrous oxide dosage is a promising method that might be used to improve patient monitoring during nitrous oxide anaesthesia.

Exploring Convolutional Neural Network Architectures for EEG Feature Extraction

The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals.

Dyslexia, the Amsterdam Way

The current aim is to illustrate our research on dyslexia conducted at the Developmental Psychology section of the Department of Psychology, University of Amsterdam, in collaboration with the nationwide IWAL institute for learning disabilities (now RID). The collaborative efforts are institutionalized in the Rudolf Berlin Center. The first series of studies aimed at furthering the understanding of dyslexia using a gamified tool based on an artificial script. Behavioral measures were augmented with diffusion modeling in one study, and indices derived from the electroencephalogram were used in others. Next, we illustrated a series of studies aiming to assess individuals who struggle with reading and spelling using similar research strategies. In one study, we used methodology derived from the machine learning literature. The third series of studies involved intervention targeting the phonics of language. These studies included a network analysis that is now rapidly gaining prominence in the psychopathology literature. Collectively, the studies demonstrate the importance of letter-speech sound mapping and word decoding in the acquisition of reading. It was demonstrated that focusing on these abilities may inform the prediction, classification, and intervention of reading difficulties and their neural underpinnings. A final section examined dyslexia, conceived as a neurobiological disorder. This analysis converged on the conclusion that recent developments in the psychopathology literature inspired by the focus on research domain criteria and network analysis might further the field by staying away from longstanding debates in the dyslexia literature (single vs. a multiple deficit, category vs. dimension, disorder vs. lack of skill).

A novel wearable ERP-based BCI approach to explicate hunger necessity

This study aimed to design a Brain-Computer Interface system to detect people's hunger status. EEG signals were recorded in various scenarios to create a database. We extracted the time-domain and frequency-domain features from these signals and applied them to the inputs of various Machine Learning algorithms. We compared the classification performances and reached the best-performing algorithm. The highest success score of 97.62% was achieved using the Multilayer Perceptron Neural Network algorithm in Event-Related Potential analysis.

Consumer-Grade Electroencephalogram and Functional Near-Infrared Spectroscopy Neurofeedback Technologies for Mental Health and Wellbeing

Neurofeedback, utilizing an electroencephalogram (EEG) and/or a functional near-infrared spectroscopy (fNIRS) device, is a real-time measurement of brain activity directed toward controlling and optimizing brain function. This treatment has often been attributed to improvements in disorders such as ADHD, anxiety, depression, and epilepsy, among others. While there is evidence suggesting the efficacy of neurofeedback devices, the research is still inconclusive. The applicability of the measurements and parameters of consumer neurofeedback wearable devices has improved, but the literature on measurement techniques lacks rigorously controlled trials. This paper presents a survey and literary review of consumer neurofeedback devices and the direction toward clinical applications and diagnoses. Relevant devices are highlighted and compared for treatment parameters, structural composition, available software, and clinical appeal. Finally, a conclusion on future applications of these systems is discussed through the comparison of their advantages and drawbacks.

An ensemble deep-learning approach for single-trial EEG classification of vibration intensity

Objective. Single-trial electroencephalography (EEG) classification is a promising approach to evaluate the cognitive experience associated with haptic feedback. Convolutional neural networks (CNNs), which are among the most widely used deep learning techniques, have demonstrated their effectiveness in extracting EEG features for the classification of different cognitive functions, including the perception of vibration intensity that is often experienced during human-computer interaction. This paper proposes a novel CNN ensemble model to classify the vibration-intensity from a single trial EEG data that outperforms the state-of-the-art EEG models.Approach. The proposed ensemble model, named SE NexFusion, builds upon the observed complementary learning behaviors of the EEGNex and TCNet Fusion models, exhibited in learning personal as well generic neural features associated with vibration intensity. The proposed ensemble employs multi-branch feature encoders corroborated with squeeze-and-excitation units that enables rich-feature encoding while at the same time recalibrating the weightage of the obtained feature maps based on their discriminative power. The model takes in a single trial of raw EEG as an input and does not require complex EEG signal-preprocessing.Main results. The proposed model outperforms several state-of-the-art bench-marked EEG models by achieving an average accuracy of 60.7% and 61.6% under leave-one-subject-out and within-subject cross-validation (three-classes), respectively. We further validate the robustness of the model through Shapley values explainability method, where the most influential spatio-temporal features of the model are counter-checked with the neural correlates that encode vibration intensity.Significance. Results show that SE NexFusion outperforms other benchmarked EEG models in classifying the vibration intensity. Additionally, explainability analysis confirms the robustness of the model in attending to features associated with the neural correlates of vibration intensity.

EEG-based investigation of effects of mindfulness meditation training on state and trait by deep learning and traditional machine learning

Introduction

This study examines the state and trait effects of short-term mindfulness-based stress reduction (MBSR) training using convolutional neural networks (CNN) based deep learning methods and traditional machine learning methods, including shallow and deep ConvNets as well as support vector machine (SVM) with features extracted from common spatial pattern (CSP) and filter bank CSP (FBCSP).

Methods

We investigated the electroencephalogram (EEG) measurements of 11 novice MBSR practitioners (6 males, 5 females; mean age 35.7 years; 7 Asians and 4 Caucasians) during resting and meditation at early and late training stages. The classifiers are trained and evaluated using inter-subject, mix-subject, intra-subject, and subject-transfer classification strategies, each according to a specific application scenario.

Results

For MBSR state effect recognition, trait effect recognition using meditation EEG, and trait effect recognition using resting EEG, from shallow ConvNet classifier we get mix-subject/intra-subject classification accuracies superior to related previous studies for both novice and expert meditators with a variety of meditation types including yoga, Tibetan, and mindfulness, whereas from FBSCP + SVM classifier we get inter-subject classification accuracies of 68.50, 85.00, and 78.96%, respectively.

Conclusion

Deep learning is superior for state effect recognition of novice meditators and slightly inferior but still comparable for both state and trait effects recognition of expert meditators when compared to the literatures. This study supports previous findings that short-term meditation training has EEG-recognizable state and trait effects.

A neurorobotics approach to behaviour selection based on human activity recognition

Behaviour selection has been an active research topic for robotics, in particular in the field of human-robot interaction. For a robot to interact autonomously and effectively with humans, the coupling between techniques for human activity recognition and robot behaviour selection is of paramount importance. However, most approaches to date consist of deterministic associations between the recognised activities and the robot behaviours, neglecting the uncertainty inherent to sequential predictions in real-time applications. In this paper, we address this gap by presenting an initial neurorobotics model that embeds, in a simulated robot, computational models of parts of the mammalian brain that resembles neurophysiological aspects of the basal ganglia-thalamus-cortex (BG-T-C) circuit, coupled with human activity recognition techniques. A robotics simulation environment was developed for assessing the model, where a mobile robot accomplished tasks by using behaviour selection in accordance with the activity being performed by the inhabitant of an intelligent home. Initial results revealed that the initial neurorobotics model is advantageous, especially considering the coupling between the most accurate activity recognition approaches and the computational models of more complex animals.

Survey on the research direction of EEG-based signal processing

Electroencephalography (EEG) is increasingly important in Brain-Computer Interface (BCI) systems due to its portability and simplicity. In this paper, we provide a comprehensive review of research on EEG signal processing techniques since 2021, with a focus on preprocessing, feature extraction, and classification methods. We analyzed 61 research articles retrieved from academic search engines, including CNKI, PubMed, Nature, IEEE Xplore, and Science Direct. For preprocessing, we focus on innovatively proposed preprocessing methods, channel selection, and data augmentation. Data augmentation is classified into conventional methods (sliding windows, segmentation and recombination, and noise injection) and deep learning methods [Generative Adversarial Networks (GAN) and Variation AutoEncoder (VAE)]. We also pay attention to the application of deep learning, and multi-method fusion approaches, including both conventional algorithm fusion and fusion between conventional algorithms and deep learning. Our analysis identifies 35 (57.4%), 18 (29.5%), and 37 (60.7%) studies in the directions of preprocessing, feature extraction, and classification, respectively. We find that preprocessing methods have become widely used in EEG classification (96.7% of reviewed papers) and comparative experiments have been conducted in some studies to validate preprocessing. We also discussed the adoption of channel selection and data augmentation and concluded several mentionable matters about data augmentation. Furthermore, deep learning methods have shown great promise in EEG classification, with Convolutional Neural Networks (CNNs) being the main structure of deep neural networks (92.3% of deep learning papers). We summarize and analyze several innovative neural networks, including CNNs and multi-structure fusion. However, we also identified several problems and limitations of current deep learning techniques in EEG classification, including inappropriate input, low cross-subject accuracy, unbalanced between parameters and time costs, and a lack of interpretability. Finally, we highlight the emerging trend of multi-method fusion approaches (49.2% of reviewed papers) and analyze the data and some examples. We also provide insights into some challenges of multi-method fusion. Our review lays a foundation for future studies to improve EEG classification performance.

A comparative study of machine learning methods for classifying ERP scalp distribution

Objective. Machine learning (ML) methods are used in different fields for classification and regression purposes with different applications. These methods are also used with various non-invasive brain signals, including Electroencephalography (EEG) signals to detect some patterns in the brain signals. ML methods are considered critical tools for EEG analysis since could overcome some of the limitations in the traditional methods of EEG analysis such as Event-related potentials (ERPs) analysis. The goal of this paper was to apply ML classification methods on ERP scalp distribution to investigate the performance of these methods in identifying numerical information carried in different finger-numeral configurations (FNCs). FNCs in their three forms of montring, counting, and non-canonical counting are used for communication, counting, and doing arithmetic across the world between children and even adults. Studies have shown the relationship between perceptual and semantic processing of FNCs, and neural differences in visually identifying different types of FNCs.Approach.A publicly available 32-channel EEG dataset recorded for 38 participants while they were shown a picture of an FNC (i.e., three categories and four numbers of 1,2,3, and 4) was used. EEG data were pre-processed and ERP scalp distribution of different FNCs was classified across time by six ML methods, including support vector machine, linear discriminant analysis, naïve Bayes, decision tree, K-nearest neighbor, and neural network. The classification was conducted in two conditions: classifying all FNCs together (i.e., 12 classes) and classifying FNCs of each category separately (i.e., 4 classes).Results.The support vector machine had the highest classification accuracy for both conditions. For classifying all FNCs together, the K-nearest neighbor was the next in line; however, the neural network could retrieve numerical information from the FNCs for category-specific classification.Significance.The significance of this study is in exploring the application of multiple ML methods in recognizing numerical information contained in ERP scalp distribution of different finger-numeral configurations.

Machine-Learning Methods for Speech and Handwriting Detection Using Neural Signals: A Review

Brain-Computer Interfaces (BCIs) have become increasingly popular in recent years due to their potential applications in diverse fields, ranging from the medical sector (people with motor and/or communication disabilities), cognitive training, gaming, and Augmented Reality/Virtual Reality (AR/VR), among other areas. BCI which can decode and recognize neural signals involved in speech and handwriting has the potential to greatly assist individuals with severe motor impairments in their communication and interaction needs. Innovative and cutting-edge advancements in this field have the potential to develop a highly accessible and interactive communication platform for these people. The purpose of this review paper is to analyze the existing research on handwriting and speech recognition from neural signals. So that the new researchers who are interested in this field can gain thorough knowledge in this research area. The current research on neural signal-based recognition of handwriting and speech has been categorized into two main types: invasive and non-invasive studies. We have examined the latest papers on converting speech-activity-based neural signals and handwriting-activity-based neural signals into text data. The methods of extracting data from the brain have also been discussed in this review. Additionally, this review includes a brief summary of the datasets, preprocessing techniques, and methods used in these studies, which were published between 2014 and 2022. This review aims to provide a comprehensive summary of the methodologies used in the current literature on neural signal-based recognition of handwriting and speech. In essence, this article is intended to serve as a valuable resource for future researchers who wish to investigate neural signal-based machine-learning methods in their work.

Recognize enhanced temporal-spatial-spectral features with a parallel multi-branch CNN and GRU

Deep learning has been applied to the recognition of motor imagery electroencephalograms (MI-EEG) in brain-computer interface, and the performance results depend on data representation as well as neural network structure. Especially, MI-EEG is so complex with the characteristics of non-stationarity, specific rhythms, and uneven distribution; however, its multidimensional feature information is difficult to be fused and enhanced simultaneously in the existing recognition methods. In this paper, a novel channel importance (NCI) based on time-frequency analysis is proposed to develop an image sequence generation method (NCI-ISG) for enhancing the integrity of data representation and highlighting the contribution inequalities of different channels as well. Each electrode of MI-EEG is converted to a time-frequency spectrum by utilizing short-time Fourier transform; the corresponding part to 8-30 Hz is combined with random forest algorithm for computing NCI; and it is further divided into three sub-images covered by α (8-13 Hz), β₁ (13-21 Hz), and β₂ (21-30 Hz) bands; their spectral powers are further weighted by NCI and interpolated to 2-dimensional electrode coordinates, producing three main sub-band image sequences. Then, a parallel multi-branch convolutional neural network and gate recurrent unit (PMBCG) is designed to successively extract and identify the spatial-spectral and temporal features from the image sequences. Two public four-class MI-EEG datasets are adopted; the proposed classification method respectively achieves the average accuracies of 98.26% and 80.62% by 10-fold cross-validation experiment; and its statistical performance is also evaluated by multi-indexes, such as Kappa value, confusion matrix, and ROC curve. Extensive experiment results show that NCI-ISG + PMBCG can yield great performance on MI-EEG classification compared to state-of-the-art methods. The proposed NCI-ISG can enhance the feature representation of time-frequency-space domains and match well with PMBCG, which improves the recognition accuracies of MI tasks and demonstrates the preferable reliability and distinguishable ability. This paper proposes a novel channel importance (NCI) based on time-frequency analysis to develop an image sequences generation method (NCI-ISG) for enhancing the integrity of data representation and highlighting the contribution inequalities of different channels as well. Then, a parallel multi-branch convolutional neural network and gate recurrent unit (PMBCG) is designed to successively extract and identify the spatial-spectral and temporal features from the image sequences.

Prehospital Electroencephalography to Detect Traumatic Brain Injury during Helicopter Transport: A Pilot Observational Cohort Study

OBJECTIVE

Early recognition of traumatic brain injury (TBI) is important to facilitate time-sensitive care. Electroencephalography (EEG) can identify TBI, but feasibility of EEG has not been evaluated in prehospital settings. We tested the feasibility of obtaining single-channel EEG during air medical transport after trauma. We measured association between quantitative EEG features, early blood biomarkers, and abnormalities on head computerized tomography (CT).

METHODS

We performed a pilot prospective, observational study enrolling consecutive patients transported by critical care air ambulance from the scene of trauma to a Level I trauma center. During transport, prehospital clinicians placed a sensor on the patient's forehead to record EEG. We reviewed EEG waveforms and selected 90 seconds of recording for quantitative analysis. EEG data processing included fast Fourier transform to summarize component frequency power in the delta (0-4 Hz), theta (4-8 Hz), and alpha (8-13 Hz) ranges. We collected blood samples on day 1 and day 3 post-injury and measured plasma levels of two brain injury biomarkers (ubiquitin C-terminal hydrolase L1 [UCH-L1] and glial fibrillary acidic protein [GFAP]). We compared predictors between individuals with and without CT-positive TBI findings.

RESULTS

Forty subjects were enrolled, with EEG recordings successfully obtained in 34 (85%). Reasons for failure included uncharged battery (n = 5) and user error (n = 1). Data were lost in three cases. Of 31 subjects with data, interpretable EEG signal was recorded in 26 (84%). Mean age was 48 (SD 16) years, 79% were male, and 50% suffered motor vehicle crashes. Eight subjects (24%) had CT-positive TBI. Subjects with and without CT-positive TBI had similar median delta power, alpha power, and theta power. UCH-L1 and GFAP plasma levels did not differ across groups. Delta power inversely correlated with UCH-L1 day 1 plasma concentration (r = -0.60, p = 0.03).

CONCLUSIONS

Prehospital EEG acquisition is feasible during air transport after trauma.

An Analysis of Deep Learning Models in SSVEP-Based BCI: A Survey

The brain–computer interface (BCI), which provides a new way for humans to directly communicate with robots without the involvement of the peripheral nervous system, has recently attracted much attention. Among all the BCI paradigms, BCIs based on steady-state visual evoked potentials (SSVEPs) have the highest information transfer rate (ITR) and the shortest training time. Meanwhile, deep learning has provided an effective and feasible solution for solving complex classification problems in many fields, and many researchers have started to apply deep learning to classify SSVEP signals. However, the designs of deep learning models vary drastically. There are many hyper-parameters that influence the performance of the model in an unpredictable way. This study surveyed 31 deep learning models (2011–2023) that were used to classify SSVEP signals and analyzed their design aspects including model input, model structure, performance measure, etc. Most of the studies that were surveyed in this paper were published in 2021 and 2022. This survey is an up-to-date design guide for researchers who are interested in using deep learning models to classify SSVEP signals.

Statistics and contrasts of order patterns in univariate time series

Order patterns apply well to many fields, because of minimal stationarity assumptions. Here, we fix the methodology of patterns of length 3 by introducing an orthogonal system of four pattern contrasts, that is, weighted differences of pattern frequencies. These contrasts are statistically independent and turn up as eigenvectors of a covariance matrix both in the independence model and the random walk model. The most important contrast is the turning rate. It can be used to evaluate sleep depth directly from EEG (electroencephalographic brain data). The paper discusses fluctuations of permutation entropy, statistical tests, and the need of new models for noises like EEG.

Application of EEG in migraine

Migraine is a common disease of the nervous system that seriously affects the quality of life of patients and constitutes a growing global health crisis. However, many limitations and challenges exist in migraine research, including the unclear etiology and the lack of specific biomarkers for diagnosis and treatment. Electroencephalography (EEG) is a neurophysiological technique for measuring brain activity. With the updating of data processing and analysis methods in recent years, EEG offers the possibility to explore altered brain functional patterns and brain network characteristics of migraines in depth. In this paper, we provide an overview of the methodology that can be applied to EEG data processing and analysis and a narrative review of EEG-based migraine-related research. To better understand the neural changes of migraine or to provide a new idea for the clinical diagnosis and treatment of migraine in the future, we discussed the study of EEG and evoked potential in migraine, compared the relevant research methods, and put forwards suggestions for future migraine EEG studies.

Energy-Efficient EEG-Based Scheme for Autism Spectrum Disorder Detection Using Wearable Sensors

The deployment of wearable wireless systems that collect physiological indicators to aid in diagnosing neurological disorders represents a potential solution for the new generation of e-health systems. Electroencephalography (EEG), a recording of the brain's electrical activity, is a promising physiological test for the diagnosis of autism spectrum disorders. It can identify the abnormalities of the neural system that are associated with autism spectrum disorders. However, streaming EEG samples remotely for classification can reduce the wireless sensor's lifespan and creates doubt regarding the application's feasibility. Therefore, decreasing data transmission may conserve sensor energy and extend the lifespan of wireless sensor networks. This paper suggests the development of a sensor-based scheme for early age autism detection. The proposed scheme implements an energy-efficient method for signal transformation allowing relevant feature extraction for accurate classification using machine learning algorithms. The experimental results indicate an accuracy of 96%, a sensitivity of 100%, and around 95% of F1 score for all used machine learning models. The results also show that our scheme energy consumption is 97% lower than streaming the raw EEG samples.

Impulsivity Classification Using EEG Power and Explainable Machine Learning

Impulsivity is a multidimensional construct often associated with unfavorable outcomes. Previous studies have implicated several electroencephalography (EEG) indices to impulsiveness, but results are heterogeneous and inconsistent. Using a data-driven approach, we identified EEG power features for the prediction of self-reported impulsiveness. To this end, EEG signals of 56 individuals (18 low impulsive, 20 intermediate impulsive, 18 high impulsive) were recorded during a risk-taking task. Extracted EEG power features from 62 electrodes were fed into various machine learning classifiers to identify the most relevant band. Robustness of the classifier was varied by stratified [Formula: see text]-fold cross validation. Alpha and beta band power showed best performance in the classification of impulsiveness (accuracy = 95.18% and 95.11%, respectively) using a random forest classifier. Subsequently, a sequential bidirectional feature selection algorithm was used to estimate the most relevant electrode sites. Results show that as little as 10 electrodes are sufficient to reliably classify impulsiveness using alpha band power ([Formula: see text]-measure = 94.50%). Finally, the Shapley Additive exPlanations (SHAP) analysis approach was employed to reveal the individual EEG features that contributed most to the model's output. Results indicate that frontal as well as posterior midline alpha power seems to be of most importance for the classification of impulsiveness.

On the Influence of Aging on Classification Performance in the Visual EEG Oddball Paradigm Using Statistical and Temporal Features

The utilization of a non-invasive electroencephalogram (EEG) as an input sensor is a common approach in the field of the brain-computer interfaces (BCI). However, the collected EEG data pose many challenges, one of which may be the age-related variability of event-related potentials (ERPs), which are often used as primary EEG BCI signal features. To assess the potential effects of aging, a sample of 27 young and 43 older healthy individuals participated in a visual oddball study, in which they passively viewed frequent stimuli among randomly occurring rare stimuli while being recorded with a 32-channel EEG set. Two types of EEG datasets were created to train the classifiers, one consisting of amplitude and spectral features in time and another with extracted time-independent statistical ERP features. Among the nine classifiers tested, linear classifiers performed best. Furthermore, we show that classification performance differs between dataset types. When temporal features were used, maximum individuals' performance scores were higher, had lower variance, and were less affected overall by within-class differences such as age. Finally, we found that the effect of aging on classification performance depends on the classifier and its internal feature ranking. Accordingly, performance will differ if the model favors features with large within-class differences. With this in mind, care must be taken in feature extraction and selection to find the correct features and consequently avoid potential age-related performance degradation in practice.

Integrating Statistical and Machine Learning Approaches for Neural Classification

Neurons can code for multiple variables simultaneously and neuroscientists are often interested in classifying neurons based on their receptive field properties. Statistical models provide powerful tools for determining the factors influencing neural spiking activity and classifying individual neurons. However, as neural recording technologies have advanced to produce simultaneous spiking data from massive populations, classical statistical methods often lack the computational efficiency required to handle such data. Machine learning (ML) approaches are known for enabling efficient large scale data analyses; however, they typically require massive training sets with balanced data, along with accurate labels to fit well. Additionally, model assessment and interpretation are often more challenging for ML than for classical statistical methods. To address these challenges, we develop an integrated framework, combining statistical modeling and machine learning approaches to identify the coding properties of neurons from large populations. In order to demonstrate this framework, we apply these methods to data from a population of neurons recorded from rat hippocampus to characterize the distribution of spatial receptive fields in this region.

Non-invasive brain-spine interface: Continuous control of trans-spinal magnetic stimulation using EEG

Brain-controlled neuromodulation has emerged as a promising tool to promote functional recovery in patients with motor disorders. Brain-machine interfaces exploit this neuromodulatory strategy and could be used for restoring voluntary control of lower limbs. In this work, we propose a non-invasive brain-spine interface (BSI) that processes electroencephalographic (EEG) activity to volitionally control trans-spinal magnetic stimulation (ts-MS), as an approach for lower-limb neurorehabilitation. This novel platform allows to contingently connect motor cortical activation during leg motor imagery with the activation of leg muscles via ts-MS. We tested this closed-loop system in 10 healthy participants using different stimulation conditions. This BSI efficiently removed stimulation artifacts from EEG regardless of ts-MS intensity used, allowing continuous monitoring of cortical activity and real-time closed-loop control of ts-MS. Our BSI induced afferent and efferent evoked responses, being this activation ts-MS intensity-dependent. We demonstrated the feasibility, safety and usability of this non-invasive BSI. The presented system represents a novel non-invasive means of brain-controlled neuromodulation and opens the door towards its integration as a therapeutic tool for lower-limb rehabilitation.

Classification of Contrasting Discrete Emotional States Indicated by EEG Based Graph Theoretical Network Measures

The present study shows new findings that reveal the high association between emotional arousal and neuro-functional brain connectivity measures. For this purpose, contrasting discrete emotional states (happiness vs sadness, amusement vs disgust, calmness vs excitement, calmness vs anger, fear vs anger) are classified by using Support Vector Machines (SVMs) driven by Graph Theoretical segregation (clustering coefficients, transitivity, modularity) and integration (global efficiency, local efficiency) measures of the brain network. Emotional EEG data mediated by short duration video film clips is downloaded from publicly available database called DREAMER. Pearson Correlation (PC) and Spearman Correlation have been examined to estimate statistical dependencies between relatively shorter (6 sec) and longer (12 sec) non-overlapped EEG segments across the cortex. Then the corresponding brain connectivity encoded as a graph is transformed into binary numbers with respect to two different thresholds (60%max and mean). Statistical differences between contrasting emotions are obtained by using both one-way Anova tests and step-wise logistic regression modelling in accordance with variables (dependency estimation, segment length, threshold, network measure). Combined integration measures provided the highest classification accuracies (CAs) (75.00% 80.65%) when PC is applied to longer segments in accordance with particular threshold as the mean. The segregation measures also provided useful CAs (74.13% 80.00%), while the combination of both measures did not. The results reveal that discrete emotional states are characterized by balanced network measures even if both segregation and integration measures vary depending on arousal scores of audio-visual stimuli due to neurotransmitter release during video watching.

Single-channel EEG signal extraction based on DWT, CEEMDAN, and ICA method

In special application scenarios, such as portable anesthesia depth monitoring, portable emotional state recognition and portable sleep monitoring, electroencephalogram (EEG) signal acquisition equipment is required to be convenient and easy to use. It is difficult to remove electrooculogram (EOG) artifacts when the number of EEG acquisition channels is small, especially when the number of observed signals is less than that of the source signals, and the overcomplete problem will arise. The independent component analysis (ICA) algorithm commonly used for artifact removal requires the number of basis vectors to be smaller than the dimension of the input data due to a set of standard orthonormal bases learned during the convergence process, so it cannot be used to solve the overcomplete problem. The empirical mode decomposition method decomposes the signal into several independent intrinsic mode functions so that the number of observed signals is more than that of the source signals, solving the overcomplete problem. However, when using this method to solve overcompleteness, the modal aliasing problem will arise, which is caused by abnormal events such as sharp signals, impulse interference, and noise. Aiming at the above problems, we propose a novel EEG artifact removal method based on discrete wavelet transform, complete empirical mode decomposition for adaptive noise (CEEMDAN) and ICA in this paper. First, the input signals are transformed by discrete wavelet (DWT), and then CEEMDAN is used to solve the overcomplete and mode aliasing problems, meeting the a priori conditions of the ICA algorithm. Finally, the components belonging to EOG artifacts are removed according to the sample entropy value of each independent component. Experiments show that this method can effectively remove EOG artifacts while solving the overcomplete and modal aliasing problems.

Side-Aware Meta-Learning for Cross-Dataset Listener Diagnosis With Subjective Tinnitus

With the development of digital technology, machine learning has paved the way for the next generation of tinnitus diagnoses. Although machine learning has been widely applied in EEG-based tinnitus analysis, most current models are dataset-specific. Each dataset may be limited to a specific range of symptoms, overall disease severity, and demographic attributes; further, dataset formats may differ, impacting model performance. This paper proposes a side-aware meta-learning for cross-dataset tinnitus diagnosis, which can effectively classify tinnitus in subjects of divergent ages and genders from different data collection processes. Owing to the superiority of meta-learning, our method does not rely on large-scale datasets like conventional deep learning models. Moreover, we design a subject-specific training process to assist the model in fitting the data pattern of different patients or healthy people. Our method achieves a high accuracy of 73.8% in the cross-dataset classification. We conduct an extensive analysis to show the effectiveness of side information of ears in enhancing model performance and side-aware meta-learning in improving the quality of the learned features.

The convolutional neural network as a tool to classify electroencephalography data resulting from the consumption of juice sweetened with caloric or non-caloric sweeteners

Sweetener type can influence sensory properties and consumer's acceptance and preference for low-calorie products. An ideal sweetener does not exist, and each sweetener must be used in situations to which it is best suited. Aspartame and sucralose can be good substitutes for sucrose in passion fruit juice. Despite the interest in artificial sweeteners, little is known about how artificial sweeteners are processed in the human brain. Here, we applied the convolutional neural network (CNN) to evaluate brain signals of 11 healthy subjects when they tasted passion fruit juice equivalently sweetened with sucrose (9.4 g/100 g), sucralose (0.01593 g/100 g), or aspartame (0.05477 g/100 g). Electroencephalograms were recorded for two sites in the gustatory cortex (i.e., C3 and C4). Data with artifacts were disregarded, and the artifact-free data were used to feed a Deep Neural Network with tree branches that applied a Convolutions and pooling for different feature filtering and selection. The CNN received raw signal as input for multiclass classification and with supervised training was able to extract underling features and patterns from the signal with better performance than handcrafted filters like FFT. Our results indicated that CNN is an useful tool for electroencephalography (EEG) analyses and classification of perceptually similar tastes.

Evaluation of Machine Learning Algorithms for Classification of EEG Signals

In brain–computer interfaces (BCIs), it is crucial to process brain signals to improve the accuracy of the classification of motor movements. Machine learning (ML) algorithms such as artificial neural networks (ANNs), linear discriminant analysis (LDA), decision tree (D.T.), K-nearest neighbor (KNN), naive Bayes (N.B.), and support vector machine (SVM) have made significant progress in classification issues. This paper aims to present a signal processing analysis of electroencephalographic (EEG) signals among different feature extraction techniques to train selected classification algorithms to classify signals related to motor movements. The motor movements considered are related to the left hand, right hand, both fists, feet, and relaxation, making this a multiclass problem. In this study, nine ML algorithms were trained with a dataset created by the feature extraction of EEG signals.The EEG signals of 30 Physionet subjects were used to create a dataset related to movement. We used electrodes C3, C1, CZ, C2, and C4 according to the standard 10-10 placement. Then, we extracted the epochs of the EEG signals and applied tone, amplitude levels, and statistical techniques to obtain the set of features. LabVIEW™2015 version custom applications were used for reading the EEG signals; for channel selection, noise filtering, band selection, and feature extraction operations; and for creating the dataset. MATLAB 2021a was used for training, testing, and evaluating the performance metrics of the ML algorithms. In this study, the model of Medium-ANN achieved the best performance, with an AUC average of 0.9998, Cohen’s Kappa coefficient of 0.9552, a Matthews correlation coefficient of 0.9819, and a loss of 0.0147. These findings suggest the applicability of our approach to different scenarios, such as implementing robotic prostheses, where the use of superficial features is an acceptable option when resources are limited, as in embedded systems or edge computing devices.

A Depression Diagnosis Method Based on the Hybrid Neural Network and Attention Mechanism

Depression is a common but easily misdiagnosed disease when using a self-assessment scale. Electroencephalograms (EEGs) provide an important reference and objective basis for the identification and diagnosis of depression. In order to improve the accuracy of the diagnosis of depression by using mainstream algorithms, a high-performance hybrid neural network depression detection method is proposed in this paper combined with deep learning technology. Firstly, a concatenating one-dimensional convolutional neural network (1D-CNN) and gated recurrent unit (GRU) are employed to extract the local features and to determine the global features of the EEG signal. Secondly, the attention mechanism is introduced to form the hybrid neural network. The attention mechanism assigns different weights to the multi-dimensional features extracted by the network, so as to screen out more representative features, which can reduce the computational complexity of the network and save the training time of the model while ensuring high precision. Moreover, dropout is applied to accelerate network training and address the over-fitting problem. Experiments reveal that the 1D-CNN-GRU-ATTN model has more effectiveness and a better generalization ability compared with traditional algorithms. The accuracy of the proposed method in this paper reaches 99.33% in a public dataset and 97.98% in a private dataset, respectively.

Resting-state electroencephalography (EEG) biomarkers of chronic neuropathic pain. A systematic review

Diagnosis and management of chronic neuropathic pain are challenging, leading to current efforts to characterize 'objective' biomarkers of pain using imaging or neurophysiological techniques, such as electroencephalography (EEG). A systematic literature review was conducted in PubMed-Medline and Web-of-Science until October 2021 to identify EEG biomarkers of chronic neuropathic pain in humans. The risk of bias was assessed by the Newcastle-Ottawa-Scale. Experimental, provoked, or chronic non-neuropathic pain studies were excluded. We identified 14 studies, in which resting-state EEG spectral analysis was compared between patients with pain related to a neurological disease and patients with the same disease but without pain or healthy controls. From these heterogeneous exploratory studies, some conclusions can be drawn, even if they must be weighted by the fact that confounding factors, such as medication and association with anxio-depressive disorders, are generally not taken into account. Overall, EEG signal power was increased in the θ band (4-7Hz) and possibly in the high-β band (20-30Hz), but decreased in the high-α-low-β band (10-20Hz) in the presence of ongoing neuropathic pain, while increased γ band oscillations were not evidenced, unlike in experimental pain. Consequently, the dominant peak frequency was decreased in the θ-α band and increased in the whole-β band in neuropathic pain patients. Disappointingly, pain intensity correlated with various EEG changes across studies, with no consistent trend. This review also discusses the location of regional pain-related EEG changes in the pain connectome, as the perspectives offered by advanced techniques of EEG signal analysis (source location, connectivity, or classification methods based on artificial intelligence). The biomarkers provided by resting-state EEG are of particular interest for optimizing the treatment of chronic neuropathic pain by neuromodulation techniques, such as transcranial alternating current stimulation or neurofeedback procedures.

A solution to supervised motor imagery task in the BCI Controlled Robot Contest in World Robot Contest

Background:

One of the most prestigious competitions in the world is the World Robot Conference. This paper presents the winning solution to the supervised motor imagery (MI) task in the BCI Controlled Robot Contest in World Robot Contest 2021.

Methods:

Data augmentation, preprocessing, feature extraction, and model training are the main components of the solution. The model is based on EEGNet, a popular convolutional neural networks model for classifying electroencephalography data.

Results:

Despite the model’s lack of stability, this solution was the most successful in the task. The channels closest to the vertex were the most helpful in feature extraction.

Conclusion:

This solution is suitable for supervised MI tasks not only in this competition but also in future scenarios.

A Depression Prediction Algorithm Based on Spatiotemporal Feature of EEG Signal

Depression has gradually become the most common mental disorder in the world. The accuracy of its diagnosis may be affected by many factors, while the primary diagnosis seems to be difficult to define. Finding a way to identify depression by satisfying both objective and effective conditions is an urgent issue. In this paper, a strategy for predicting depression based on spatiotemporal features is proposed, and is expected to be used in the auxiliary diagnosis of depression. Firstly, electroencephalogram (EEG) signals were denoised through the filter to obtain the power spectra of the three corresponding frequency ranges, Theta, Alpha and Beta. Using orthogonal projection, the spatial positions of the electrodes were mapped to the brainpower spectrum, thereby obtaining three brain maps with spatial information. Then, the three brain maps were superimposed on a new brain map with frequency domain and spatial characteristics. A Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) were applied to extract the sequential feature. The proposed strategy was validated with a public EEG dataset, achieving an accuracy of 89.63% and an accuracy of 88.56% with the private dataset. The network had less complexity with only six layers. The results show that our strategy is credible, less complex and useful in predicting depression using EEG signals.

EEG monitoring during anesthesia in children aged 0 to 18 months: amplitude-integrated EEG and age effects

Background

The amplitude-integrated EEG (aEEG) is a widely used monitoring tool in neonatology / pediatric intensive care. It takes into account the amplitudes, but not the frequency composition, of the EEG. Advantages of the aEEG are clear criteria for interpretation and time compression. During the first year of life, the electroencephalogram (EEG) during sedation / anesthesia changes from a low-differentiated to a differentiated EEG; higher-frequency waves develop increasingly. There are few studies on the use of aEEG during pediatric anesthesia. A systematic evaluation of the aEEG in defined EEG stages during anesthesia / sedation is not yet available. Parameters of pediatric EEGs (power, median frequency, spectral edge frequency) recorded during anesthesia and of the corresponding aEEGs (upper and lower value of the aEEG trace) should be examined for age-related changes. Furthermore, it should be examined whether the aEEG can distinguish EEG stages of sedation / anesthesia in differentiated EEGs.

Methods

In a secondary analysis of a prospective observational study EEGs and aEEGs (1-channel recordings, electrode positions on forehead) of 50 children (age: 0–18 months) were evaluated. EEG stages: A (awake), Slow EEG, E2, F0, and F1 in low-differentiated EEGs and A (awake), B0–2, C0–2, D0–2, E0–2, F0–1 in differentiated EEGs.

Results

Median and spectral edge frequency increased significantly with age (p < 0.001 each). In low-differentiated EEGs, the power of the Slow EEG increased significantly with age (p < 0.001). In differentiated EEGs, the power increased significantly with age in each of the EEG stages B1 to E1 (p = 0.04, or less), and the upper and lower values of the aEEG trace increased with age (p < 0.001). A discriminant analysis using the upper and lower values of the aEEG showed that EEG epochs from the stages B1 to E1 were assigned to the original EEG stage in only 19.3% of the cases. When age was added as the third variable, the rate of correct reclassifications was 28.5%.

Conclusions

The aEEG was not suitable for distinguishing EEG stages above the burst suppression range. For this purpose, the frequency composition of the EEG should be taken into account.