Distinct EEG Research Articles

Ictal scalp EEG patterns are shaped by seizure etiology in temporal lobe epilepsy.

To investigate how etiology and seizure localization influence ictal scalp electroencephalographic (EEG) patterns in temporal lobe epilepsy (TLE). We retrospectively analyzed ictal EEG features from 504 focal seizures recorded in 189 TLE patients with various etiologies who underwent resective surgery. For seizure onset patterns (SOPs), α/β onset was more common in the low-grade tumor group (38.4%) than in the hippocampal sclerosis (HS) group (14.1%, p < 0.001). The ictal EEG duration was shorter in the tumor group compared to the focal cortical dysplasia (FCD), HS, and non-specific groups (p < 0.05). Among mesial TLE patients, SOPs varied depending on the etiology. Within both the tumor and non-specific groups, SOPs and the spreading time to the contralateral hemisphere differed between mesial and neocortical origins. Ictal pattern (87.7%) and ictal theta activity (83.9%) correctly lateralized the seizure in most cases. The ictal scalp pattern in TLE is influenced by both etiology and seizure localization. TLE associated with low-grade tumors exhibits distinct ictal EEG characteristics. Furthermore, ictal pattern and ictal theta activity are equally effective in lateralizing seizures, regardless of etiology. This research examined how brain activity during seizures in people with temporal lobe epilepsy can be different based on what caused the epilepsy and where in the brain the seizure starts. We found that seizures caused by brain tumors have unique patterns in the brain's electrical activity. Additionally, we discovered that specific patterns and types of brain waves can help determine which side of the brain the seizure is occurring on, regardless of its cause.

Characterizing PTSD Using Electrophysiology: Towards A Precision Medicine Approach

Objective. Resting-state EEG measures have shown potential in distinguishing individuals with PTSD from healthy controls. ERP components such as N2, P3, and late positive potential have been consistently linked to cognitive abnormalities in PTSD, especially in tasks involving emotional or trauma-related stimuli. However, meta-analyses have reported inconsistent findings. The understanding of biomarkers that can classify the varied symptoms of PTSD remains limited. This study aimed to develop a concise set of electrophysiological biomarkers, using neutral cognitive tasks, that could be applied across psychiatric conditions, and to identify biomarkers associated with the anxiety and depression dimensions of PTSD. Approach. Continuous simultaneous recordings of EEG and electrocardiogram (ECG) were obtained in veterans with PTSD (n = 29) and healthy controls (n = 62) during computerized tasks. EEG, ERP, and heart rate measures were evaluated in terms of their ability to discriminate between the groups or correlate with psychological measures. Results. The PTSD cohort exhibited faster alpha oscillations, reduced alpha power, and a flatter power spectrum. Furthermore, stronger reduction in alpha power was associated with higher trait anxiety, while a flatter slope was related to more severe depression symptoms in individuals with PTSD. In ERP tasks of visual memory and sustained attention, the PTSD cohort demonstrated delayed and exaggerated early components, along with attenuated LPP amplitudes. The three tasks revealed distinct and complementary EEG signatures PTSD. Significance. Multimodal individualized biomarkers based on EEG, cognitive ERPs, and ECG show promise as objective tools for assessing mood and anxiety disturbances within the PTSD spectrum.

Unraveling EEG correlates of unimanual finger movements: insights from non-repetitive flexion and extension tasks

BackgroundThe loss of finger control in individuals with neuromuscular disorders significantly impacts their quality of life. Electroencephalography (EEG)-based brain-computer interfaces that actuate neuroprostheses directly via decoded motor intentions can help restore lost finger mobility. However, the extent to which finger movements exhibit distinct and decodable EEG correlates remains unresolved. This study aims to investigate the EEG correlates of unimanual, non-repetitive finger flexion and extension.MethodsSixteen healthy, right-handed participants completed multiple sessions of right-hand finger movement experiments. These included five individual (Thumb, Index, Middle, Ring, and Pinky) and four coordinated (Pinch, Point, ThumbsUp, and Fist) finger flexions and extensions, along with a rest condition (None). High-density EEG and finger trajectories were simultaneously recorded and analyzed. We examined low-frequency (0.3–3 Hz) time series and movement-related cortical potentials (MRCPs), and event-related desynchronization/synchronization (ERD/S) in the alpha- (8–13 Hz) and beta (13–30 Hz) bands. A clustering approach based on Riemannian distances was used to chart similarities between the broadband EEG responses (0.3–70 Hz) to the different finger scenarios. The contribution of different state-of-the-art features was identified across sub-bands, from low-frequency to low gamma (30–70 Hz), and an ensemble approach was used to pairwise classify single-trial finger movements and rest.ResultsA significant decrease in EEG amplitude in the low-frequency time series was observed in the contralateral frontal-central regions during finger flexion and extension. Distinct MRCP patterns were found in the pre-, ongoing-, and post-movement stages. Additionally, strong ERD was detected in the contralateral central brain regions in both alpha and beta bands during finger flexion and extension, with the beta band showing a stronger rebound (ERS) post-movement. Within the finger movement repertoire, the Thumb was most distinctive, followed by the Fist. Decoding results indicated that low-frequency time-domain amplitude better differentiates finger movements, while alpha and beta band power and Riemannian features better detect movement versus rest. Combining these features yielded over 80% finger movement detection accuracy, while pairwise classification accuracy exceeded 60% for the Thumb versus the other fingers.ConclusionOur findings confirm that non-repetitive finger movements, whether individual or coordinated, can be precisely detected from EEG. However, differentiating between specific movements is challenging due to highly overlapping neural correlates in time, spectral, and spatial domains. Nonetheless, certain finger movements, such as those involving the Thumb, exhibit distinct EEG responses, making them prime candidates for dexterous finger neuroprostheses.

The neural basis of self-ambivalence: an ERP study

The primary objective of this study was to investigate the neural basis of self-ambivalence, a phenomenon firmly established by behavioral research but whose underlying brain mechanisms have been less explored. Employing EEG methods and a modified self-reference paradigm, we analyzed event-related potentials using a linear mixed model to determine whether self-ambivalence processing exhibits a distinct neural representation. The results indicated that self-ambivalence processing primarily affected the late components (N2, N450, and P3), with N450 activation in the midline brain regions showing a significant positive correlation with scores on the Dialectical Self Scale. This finding suggests that individuals with higher levels of self-ambivalence may engage in more extensive processing of self-ambivalent information. The current study confirms the importance of the cortical midline in self-ambivalence and provides the first evidence of a distinct EEG representation of self-ambivalence processing. These findings contribute to our understanding of the neural mechanisms underlying self-ambivalence and highlight the potential role of individual differences in shaping the neural processing of self-ambivalent information.

Exploring the link between cognitive load and brain activity during calculus learning through electroencephalogram (EEG): Insights from visualization and cluster analysis

Understanding the relationship between cognitive load and brain activity is essential for enhancing learning outcomes, particularly in complex subjects such as calculus. Despite its significance, empirical research examining the manifestation of cognitive load in brain activity patterns remains sparse, indicating a notable gap in the literature. This study aims to investigate the correlation between brain activity and cognitive load in a cohort of 30 mathematics education students enrolled in a calculus course, utilizing electroencephalogram (EEG) recordings. A quantitative descriptive research design was employed, integrating cluster analysis and data visualization techniques to facilitate an in-depth examination. EEG recordings of theta, alpha, and beta wave activity were collected during calculus sessions, followed by the administration of a cognitive load questionnaire. Descriptive statistics were utilized to analyze the distribution of cognitive load and brain activity, while correlation analysis was conducted to explore the relationships between cognitive load and EEG parameters across the different brainwave bands. The results revealed that higher cognitive load was positively correlated with increased frequency and amplitude in the alpha and beta bands, while a negative correlation was observed with theta frequency. Furthermore, cluster analysis effectively categorized participants based on distinct EEG signal patterns associated with varying levels of cognitive load. These findings offer valuable insights for the development of personalized learning interventions tailored to individual brain activity profiles, providing a foundation for future research on adaptive learning environments.

Comparative EEG biosignatures in Alzheimer’s disease and frontotemporal dementia: A pilot study

AbstractBackgroundAlzheimer's disease (AD) and frontotemporal dementia (FTD) are common causes of dementia, but differentiating between them can be challenging due to overlapping symptoms [1]. Quantitative electroencephalography (EEG) is emerging as a promising tool to identify potential biosignatures that can distinguish AD and FTD [2]–[5]. Prior EEG research has revealed slowing of the posterior dominant rhythm (PDR) in both AD and FTD patients compared to controls, reflecting underlying neurodegeneration. Our study aimed to compare quantitative EEG measures during resting‐state and attention tasks between bvFTD, PPAFTD, AD patients, and controls to determine if distinctive EEG/ERP profiles exist that can aid differential diagnosis.MethodsParticipants included individuals with behavioral‐variant Fronto‐temporal dementia (bvFTD, n=8, ages 42‐78), Primary Progressive Aphasia Frontotemporal dementia (PPAFTD, n=6, ages 53‐75), Alzheimer’s dementia (AD, n=20, ages 58‐79), and controls with normal cognition (HC, n=14, ages 47‐78). Twenty‐channel resting‐state EEG with eyes‐closed was collected during 5‐minutes of wakefulness (STAT X24). A subset of participants also completed a 3‐Choice‐vigilance‐task (3CVT) ERP attention task. Power spectral densities (PSD) during resting‐state and ERP waveforms elicited by the ERP task were computed and compared between groups.ResultsbvFTD on average exhibited a slowing of the posterior‐dominant rhythm (PDR) similar to the slowing observed in the AD group. However, unlike the AD group that showed a significant reduction in the power of the PDR (alpha power), both FTD groups had alpha power similar to HC. In the ERP attention task, FTD groups exhibited a delayed and reduced late positive potential (LPP) compared to controls.ConclusionsWe identified distinctive EEG biosignatures associated with Frontotemporal Dementia (FTD) and Alzheimer's Disease (AD). Quantitative analysis of the posterior dominant rhythm (PDR) revealed that both AD and FTD patients exhibited slowing of the PDR frequency. However, the power of PDR was significantly reduced in the AD while relatively preserved in FTD. FTD subtypes may also demonstrate distinct EEG abnormalities such as more pronounced PDR slowing in bvFTD/ more delayed event‐related potential (ERP) components in PPAFTD. Additional research is still needed to validate the reliability and specificity of these EEG biosignatures in differentiating FTD subtypes from each other and from AD.

Interest paradigm for early identification of autism spectrum disorder: an analysis from electroencephalography combined with eye tracking.

Early identification of Autism Spectrum Disorder (ASD) is critical for effective intervention. Restricted interests (RIs), a subset of repetitive behaviors, are a prominent but underutilized domain for early ASD diagnosis. This study aimed to identify objective biomarkers for ASD by integrating electroencephalography (EEG) and eye-tracking (ET) to analyze toddlers' visual attention and cortical responses to RI versus neutral interest (NI) objects. The study involved 59 toddlers aged 2-4 years, including 32 with ASD and 27 non-ASD controls. Participants underwent a 24-object passive viewing paradigm, featuring RI (e.g., transportation items) and NI objects (e.g., balloons). ET metrics (fixation time and pupil size) and EEG time-frequency (TF) power in theta (4-8 Hz) and alpha (8-13 Hz) bands were analyzed. Statistical methods included logistic regression models to assess the predictive potential of combined EEG and ET biomarkers. Toddlers with ASD exhibited significantly increased fixation times and pupil sizes for RI objects compared to NI objects, alongside distinct EEG patterns with elevated theta and reduced alpha power in occipital regions during RI stimuli. The multimodal logistic regression model, incorporating EEG and ET metrics, achieved an area under the curve (AUC) of 0.75, demonstrating robust predictive capability for ASD. This novel integration of ET and EEG metrics highlights the potential of RIs as diagnostic markers for ASD. The observed neural and attentional distinctions underscore the utility of multimodal biomarkers for early diagnosis and personalized intervention strategies. Future work should validate findings across broader age ranges and diverse populations.

ChMinMaxPat: Investigations on Violence and Stress Detection Using EEG Signals.

Electroencephalography (EEG) signals, often termed the letters of the brain, are one of the most cost-effective methods for gathering valuable information about brain activity. This study presents a new explainable feature engineering (XFE) model designed to classify EEG data for violence detection. The primary objective is to assess the classification capability of the proposed XFE model, which uses a next-generation feature extractor, and to obtain interpretable findings for EEG-based violence and stress detection. In this research, two distinct EEG signal datasets were used to obtain classification and explainable results. The recommended XFE model utilizes a channel-based minimum and maximum pattern (ChMinMaxPat) feature extraction function, which generates 15 distinct feature vectors from EEG data. Cumulative weight-based neighborhood component analysis (CWNCA) is employed to select the most informative features from these vectors. Classification is performed by applying an iterative and ensemble t-algorithm-based k-nearest neighbors (tkNN) classifier to each feature vector. Information fusion is achieved through iterative majority voting (IMV), which consolidates the 15 tkNN classification results. Finally, the Directed Lobish (DLob) symbolic language generates interpretable outputs by leveraging the identities of the selected features. Together, the tkNN classifier, IMV-based information fusion, and DLob-based explainable feature extraction transform the model into a self-organizing explainable feature engineering (SOXFE) framework. The ChMinMaxPat-based model achieved over 70% accuracy on both datasets with leave-one-record-out (LORO) cross-validation (CV) and over 90% accuracy with 10-fold CV. For each dataset, 15 DLob strings were generated, providing explainable outputs based on these symbolic representations. The ChMinMaxPat-based SOXFE model demonstrates high classification accuracy and interpretability in detecting violence and stress from EEG signals. This model contributes to both feature engineering and neuroscience by enabling explainable EEG classification, underscoring the potential importance of EEG analysis in clinical and forensic applications.

Patterns of ictal surface EEG in occipital seizures: A simultaneous scalp and intracerebral recording study

ObjectiveTo describe the ictal scalp EEG patterns of occipital seizures (OS) and their spatiotemporal correlations with intracerebral occipital ictal discharges derived from simultaneous SEEG-EEG recordings. MethodsPatients with SEEG confirmed OS (14 OS from 8 patients) were selected from an epilepsy surgery center and were monitored 3–10 days using simultaneous scalp EEG and SEEG recordings. ResultsOn scalp EEG, the most common onset patterns were background activity suppression (28.6 %) and high amplitude slow wave corresponding to intracerebral DC-shift (28.6 %) and occurred with a median delay of 0 s after intra-cerebral onset. The initial discharge involved occipital electrodes in only 50 % of the seizures (7/14) with additional basal temporal (8/14) or parietal electrodes (5/14). The onset was ipsilateral to the intra-cerebral onset zone in 71.4 % of seizures and bilateral in the remaining (28.6 %). The most common propagation pattern was either unilateral (50 %) or bilateral (50 %) and a rhythmic slow activity (66.7 %). Different OS subtypes display distinct scalp EEG patterns. ConclusionScalp EEG accurately determines intra-cerebral seizure onset time in OS and has good lateralizing value. However, initial scalp modification does not always involves occipital electrodes and the second modification is well lateralizing in only 50 % of seizures. SignificanceThis study describes will help clinicians to better identify OS during video EEG and better plan intra-cerebral explorations for epilepsy surgery.

Quantitative EEG Spectral Features Differentiate Genetic Epilepsies and Predict Neurologic Outcomes.

EEG plays an integral part in the diagnosis and management of children with genetic epilepsies. Nevertheless, how quantitative EEG features differ between genetic epilepsies and neurological outcomes remains largely unknown. Here, we aimed to identify quantitative EEG biomarkers in children with epilepsy and a genetic diagnosis in STXBP1 , SCN1A , or SYNGAP1 , and to assess how quantitative EEG features associate with neurological outcomes in genetic epilepsies more broadly. We analyzed individuals with pathogenic variants in STXBP1 (95 EEGs, n =20), SCN1A (154 EEGs, n =68), and SYNGAP1 (46 EEGs, n =21) and a control cohort of individuals without epilepsy or known cerebral disease (847 EEGs, n =806). After removing artifacts and epochs with excess noise or altered state from EEGs, we extracted spectral features. We validated our preprocessing pipeline by comparing automatically-detected posterior dominant rhythm (PDR) to annotations from clinical EEG reports. Next, as a coarse measure of pathological slowing, we compared the alpha-delta bandpower ratio between controls and the different genetic epilepsies. We then trained random forest models to predict a diagnosis of STXBP1 , SCN1A , and SYNGAP1 . Finally, to understand how EEG features vary with neurological outcomes, we trained random forest models to predict seizure frequency and motor function. There was strong agreement between the automatically-calculated PDR and clinical EEG reports ( R 2 =0.75). Individuals with STXBP1 -related epilepsy have a significantly lower alpha-delta ratio than controls ( P< 0.001) across all age groups. Additionally, individuals with a missense variant in STXBP1 have a significantly lower alpha-delta ratio than those with a protein-truncating variant in toddlers ( P< 0.001), children ( P =0.02), and adults ( P< 0.001). Models accurately predicted a diagnosis of STXBP1 (AUC=0.91), SYNGAP1 (AUC=0.82), and SCN1A (AUC=0.86) against controls and from each other in a three-class model (accuracy=0.74). From these models, we isolated highly correlated biomarkers for these respective genetic disorders, including alpha-theta ratio in frontal, occipital, and parietal electrodes with STXBP1 , SYNGAP1 , and SCN1A , respectively. Models were unable to predict seizure frequency (AUC=0.53). Random forest models predicted motor scores significantly better than age-based null models ( P< 0.001), suggesting spectral features contain information pertinent to gross motor function. In summary, we demonstrate that STXBP1 -, SYNGAP1- , and SCN1A -related epilepsies have distinct quantitative EEG signatures. Furthermore, EEG spectral features are predictive of some functional outcome measures in patients with genetic epilepsies. Large-scale retrospective quantitative analysis of clinical EEG has the potential to discover novel biomarkers and to quantify and track individuals' disease progression across development.

Accurate Machine Learning-based Monitoring of Anesthesia Depth with EEG Recording.

General anesthesia, pivotal for surgical procedures, requires precise depth monitoring to mitigate risks ranging from intraoperative awareness to postoperative cognitive impairments. Traditional assessment methods, relying on physiological indicators or behavioral responses, fall short of accurately capturing the nuanced states of unconsciousness. This study introduces a machine learning-based approach to decode anesthesia depth, leveraging EEG data across different anesthesia states induced by propofol and esketamine in rats. Our findings demonstrate the model's robust predictive accuracy, underscored by a novel intra-subject dataset partitioning and a 5-fold cross-validation method. The research diverges from conventional monitoring by utilizing anesthetic infusion rates as objective indicators of anesthesia states, highlighting distinct EEG patterns and enhancing prediction accuracy. Moreover, the model's ability to generalize across individuals suggests its potential for broad clinical application, distinguishing between anesthetic agents and their depths. Despite relying on rat EEG data, which poses questions about real-world applicability, our approach marks a significant advance in anesthesia monitoring.

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

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

Electroencephalogram and phenotype patterns in neuronopathic Gaucher disease patients – ten years of experience in a single center

BackgroundThis study aimed to investigate the unique electroencephalography (EEG) patterns in neuronopathic Gaucher disease (GD) patients and explore the correlations between EEG findings and neurological phenotypes so as to optimize clinical outcomes.MethodsA retrospective analysis was conducted on 74 EEG recordings from 50 GD patients between January 2012 and July 2022.ResultsTwenty-three patients exhibited abnormal EEG recordings, including 11 of the GD1 type (the transitional type) and 12 with neuronopathic GD. Of the 12 neuronopathic GD patients, 9 patients with epilepsy were analysed specifically in terms of the clinical course. The primary waveform observed in the neuronopathic EEG recordings was the spike-and-wave complex (SWC) during both awake and sleep states. This was significantly different from sharp waves observed only during sleep in the patients of the transitional type (P = 0.0230). The abnormal discharges in the neuronopathic patients were most commonly located in the bilateral Rolandic areas, while the transitional type commonly involved the bilateral frontal regions. Three patients with an epileptic EEG pattern reported their initial seizures years later. Seizures in the neuronopathic patients were effectively controlled with anti-seizure medications (ASMs), despite the ongoing presence of abnormal EEG patterns. The EEG patterns during ocular symptoms were characterized by sporadic or continuous unilateral SWC during sleep.ConclusionsPatients with neuronopathic GD exhibit distinct EEG patterns that can help differentiate them from GD1 patients. Early treatment with ASMs can effectively control seizures. EEG plays a crucial role in monitoring seizures and can facilitate prompt intervention for GD patients.

Resting-state EEG predicts cognitive decline in a neuropathologically diagnosed longitudinal community autopsied cohort

ObjectiveTo assess correlative strengths of quantitative electroencephalography (qEEG) and visual rating scale EEG features on cognitive outcomes in only autopsied cases from the Arizona Study of Neurodegenerative Disorders (AZSAND). We hypothesized that autopsy proven Parkinson Disease will show distinct EEG features from Alzheimer's Disease prior to dementia (mild cognitive impairment). BackgroundCognitive decline is debilitating across neurodegenerative diseases. Resting-state EEG analysis, including spectral power across frequency bins (qEEG), has shown significant associations with neurodegenerative disease classification and cognitive status, with autopsy confirmed diagnosis relatively lacking. MethodsBiannual EEG was analyzed from autopsied cases in AZSAND who had at least one rsEEG (>1 min eyes closed±eyes open). Analysis included global relative spectral power and a previously described visual rating scale (VRS). Linear mixed regression was performed for neuropsychological assessment and testing within 2 years of death (n = 236, 594 EEG exams) in a mixed linear regression model. ResultsThe cohort included cases with final clinicopathologic diagnoses of Parkinson's disease (n = 73), Alzheimer disease (n = 65), and tauopathy not otherwise specified (n = 56). A VRS score of 3 diffuse or frequent generalized slowing) over the study duration was associated with an increase in consensus diagnosis cognitive worsening at 4.9 (3.1) years (HR 2.02, CI 1.05–3.87). Increases in global theta power% and VRS were the most consistently associated with large regression coefficients inversely with cognitive performance measures. ConclusionResting-state EEG analysis was meaningfully related to cognitive performance measures in a community-based autopsy cohort. EEG deserves further study and use as a cognitive biomarker.

Emotion recognition of EEG signals based on contrastive learning graph convolutional model.

Electroencephalogram (EEG) signals offer invaluable insights into the complexities of emotion generation within the brain. Yet, the variability in EEG signals across individuals presents a formidable obstacle for empirical implementations. Our research addresses these challenges innovatively, focusing on the commonalities within distinct subjects' EEG data.We introduce a novel approach named Contrastive Learning Graph Convolutional Network (CLGCN). This method captures the distinctive features and crucial channel nodes related to individuals' emotional states. Specifically, CLGCN merges the dual benefits of Contrastive Learning's synchronous multisubject data learning and the Graph Convolutional Network's proficiency in deciphering brain connectivity matrices.Understanding multifaceted brain functions and their information interchange processes is realized as CLGCN generates a standardized brain network learning matrix during a dataset's learning process. Our model significantly streamlines the retraining process for new subjects, requiring only 5% of the initial sample size for fine-tuning to attain a remarkable 92.8% accuracy rate. Additionally, our model has undergone extensive testing on the DEAP and SEED datasets, demonstrating the effectiveness of our model.&#xD.

Generalizability of electroencephalographic interpretation using artificial intelligence: An external validation study.

The automated interpretation of clinical electroencephalograms (EEGs) using artificial intelligence (AI) holds the potential to bridge the treatment gap in resource-limited settings and reduce the workload at specialized centers. However, to facilitate broad clinical implementation, it is essential to establish generalizability across diverse patient populations and equipment. We assessed whether SCORE-AI demonstrates diagnostic accuracy comparable to that of experts when applied to a geographically different patient population, recorded with distinct EEG equipment and technical settings. We assessed the diagnostic accuracy of a "fixed-and-frozen" AI model, using an independent dataset and external gold standard, and benchmarked it against three experts blinded to all other data. The dataset comprised 50% normal and 50% abnormal routine EEGs, equally distributed among the four major classes of EEG abnormalities (focal epileptiform, generalized epileptiform, focal nonepileptiform, and diffuse nonepileptiform). To assess diagnostic accuracy, we computed sensitivity, specificity, and accuracy of the AI model and the experts against the external gold standard. We analyzed EEGs from 104 patients (64 females, median age = 38.6 [range = 16-91] years). SCORE-AI performed equally well compared to the experts, with an overall accuracy of 92% (95% confidence interval [CI] = 90%-94%) versus 94% (95% CI = 92%-96%). There was no significant difference between SCORE-AI and the experts for any metric or category. SCORE-AI performed well independently of the vigilance state (false classification during awake: 5/41 [12.2%], false classification during sleep: 2/11 [18.2%]; p = .63) and normal variants (false classification in presence of normal variants: 4/14 [28.6%], false classification in absence of normal variants: 3/38 [7.9%]; p = .07). SCORE-AI achieved diagnostic performance equal to human experts in an EEG dataset independent of the development dataset, in a geographically distinct patient population, recorded with different equipment and technical settings than the development dataset.

Sleep stages and brain oscillations: An in-depth analysis using quantitative and mathematical models

This study explores the intricate relationship between sleep stages and brain oscillations, utilizing quantitative EEG analysis and mathematical models. We examine the distinct EEG characteristics of light sleep, deep sleep, and REM sleep, focusing on power spectral density (PSD), coherence, and phase synchronization analyses. The Ising model and Kuramoto model provide frameworks for understanding the synchronization dynamics and phase relationships of neuronal populations across sleep stages. Our findings highlight significant variations in oscillatory activity, coherence, and phase synchronization, offering insights into the neural mechanisms underlying sleep regulation. Additionally, we discuss the implications of these findings for sleep disorders such as insomnia, sleep apnea, and narcolepsy, demonstrating how mathematical models can predict therapeutic outcomes and guide targeted interventions. This comprehensive analysis contributes to the understanding of sleep architecture and the development of novel treatments for sleep disorders.

Contributions of brain regions to machine learning-based classifications of attention deficit hyperactivity disorder (ADHD) utilizing EEG signals

Objective The study presented focuses on the creation of a machine learning (ML) model that uses electrophysiological (EEG) data to identify kids with attention deficit hyperactivity disorder (ADHD) from healthy controls. The EEG signals are acquired during cognitive tasks to distinguish children with ADHD from their counterparts. Methodology The EEG data recorded in cognitive exercises was filtered using low pass Bessel filter and notch filters to remove artifacts, by the data set owners. To identify unique EEG patterns, we used many well-known classifiers, including Naïve Bayes (NB), Random Forest, Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), AdaBoost and Linear Discriminant Analysis (LDA), to identify distinct EEG patterns. Input features comprised EEG data from nineteen channels, individually and in combination. Findings Study indicates that EEG-based categorization can differentiate between individuals with ADHD and healthy individuals with accuracy of 84%. The RF classifier achieved a maximum accuracy of 0.84 when particular region combinations were used. Evaluation of classification performance utilizing hemisphere-specific EEG data yielded promising outcomes, particularly in the right hemisphere channels. Novelty The study goes beyond traditional methodologies by investigating the effect of regional data on categorization results. The contributions of various brain regions to these classifications are being extensively researched. Understanding the role of different brain regions in ADHD can lead to better diagnosis and treatment options for individuals with ADHD. The study of categorization ability, utilizing EEG data specific to each hemisphere, particularly channels in the right hemisphere region, provides further granularity to the findings.

Characterization of Vagus Nerve Stimulation (VNS) Dose-Dependent Effects on EEG Power Spectrum and Synchronization.

This study investigates the dose-dependent EEG effects of Vagus Nerve Stimulation (VNS) in patients with drug-resistant epilepsy. This research examines how varying VNS intensities impacts EEG power spectrum and synchronization in a cohort of 28 patients. Patients were categorized into responders, partial-responders, and non-responders based on seizure frequency reduction. The methods involved EEG recordings at incremental VNS intensities, followed by spectral and synchronization analysis. The results reveal significant changes in EEG power, particularly in the delta and beta bands across different intensities. Notably, responders exhibited distinct EEG changes compared to non-responders. Our study has found that VNS intensity significantly influences EEG power topographic allocation and brain desynchronization, suggesting the potential use of acute dose-dependent effects to personalized VNS therapy in the treatment of epilepsy. The findings underscore the importance of individualized VNS dosing for optimizing therapeutic outcomes and highlight the use of EEG metrics as an effective tool for monitoring and adjusting VNS parameters. These insights offer a new avenue for developing individualized VNS therapy strategies, enhancing treatment efficacy in epilepsy.

Single-channel qEEG characteristics distinguish delirium from no delirium, but not postoperative from non-postoperative delirium

ObjectiveThis exploratory study examined quantitative electroencephalography (qEEG) changes in delirium and the use of qEEG features to distinguish postoperative from non-postoperative delirium. MethodsThis project was part of the DeltaStudy, a cross-sectional,multicenterstudy in Intensive Care Units (ICUs) and non-ICU wards. Single-channel (Fp2-Pz) four-minutes resting-state EEG was analyzed in 456 patients. After calculating 98 qEEG features per epoch, random forest (RF) classification was used to analyze qEEG changes in delirium and to test whether postoperative and non-postoperative delirium could be distinguished. ResultsAn area under the receiver operatingcharacteristic curve (AUC) of 0.76 (95% Confidence Interval (CI) 0.71–0.80) was found when classifying delirium with a sensitivity of 0.77 and a specificity of 0.63 at the optimal operating point. The classification of postoperative versus non-postoperative delirium resulted in an AUC of 0.50 (95%CI 0.38–0.61). ConclusionsRF classification was able to discriminate delirium from no delirium with reasonable accuracy, while also identifying new delirium qEEG markers like autocorrelation and theta peak frequency. RF classification could not distinguish postoperative from non-postoperative delirium. SignificanceSingle-channel EEG differentiates between delirium and no delirium with reasonable accuracy. We found no distinct EEG profile for postoperative delirium, which may suggest that delirium is one entity, whether it develops postoperatively or not.