Electroencephalography Data Research Articles

Does theta synchronicity of sensory information enhance associative memory? Replicating the theta-induced memory effect.

The binding of information from different sensory or neural sources is critical for associative memory. Previous research in animals suggested that the timing of theta oscillations in the hippocampus is critical for long-term potentiation, which underlies associative and episodic memory. Studies with human participants showed correlations between theta oscillations in medial temporal lobe and episodic memory. Clouter et al. directly investigated this link by modulating the intensity of the luminance and the sound of the video clips so that they 'flickered' at certain frequencies and with varying synchronicity between the visual and auditory streams. Across several experiments, better memory was found for stimuli that flickered synchronously at theta frequency compared with no-flicker, asynchronous theta, or synchronous alpha and delta frequencies. This effect - which they called the theta-induced memory effect - is consistent with the importance of theta synchronicity for long-term potentiation. In addition, electroencephalography data showed entrainment of cortical regions to the visual and auditory flicker, and that synchronicity was achieved in neuronal oscillations (with a fixed delay between visual and auditory streams). The theoretical importance, large effect size, and potential application to enhance real-world memory mean that a replication of theta-induced memory effect would be highly valuable. The present study aimed to replicate the key differences among synchronous theta, asynchronous theta, synchronous delta, and no-flicker conditions, but within a single experiment. The results do not show evidence of improved memory for theta synchronicity in any of the comparisons. We suggest a reinterpretation of theta-induced memory effect to accommodate this non-replication.

EEG data based human attention recognition using various machine learning techniques: a review

ABSTRACT Attention is a cognitive process that is essential for human performance. Human development frequently depends on attention; however, this topic still requires additional research. Recently, EEG brain waves have been utilised to identify a person’s attention states. This work aims to review numerous machine learning algorithms to analyse the Electroencephalographic (EEG) data to recognise human attention. Various machine learning approaches for the analysis of emotional states with EEG data were reviewed. Moreover, the analysis includes the performance achieved in various works; their benefits and disadvantages are reviewed. An EEG data processing pipeline and a review of human attention recognition are developed to evaluate the performance of various machine learning techniques. According to the analysis, the neural network framework achieves 99.81% accuracy. The results serve as a design framework for future systems using EEG data on brain activity to monitor people’s health.

Прогнозування ризику розвитку розладів аутистичного спектра в дітей з епілептичними енцефалопатіями

Predicting the risk of developing autism spectrum disorders (ASD) in children with epileptic encephalopathies (EE) is an important task, which makes it possible to identify the most significant risk factors and develop ways of their modification. Purpose - to develop a model for predicting the risk of developing ASD in young children with EE. Materials and methods. 75 children aged 0-3 years with the onset of epileptic seizures in the first year of life, clinical manifestations of EE were examined. The most informative clinical, neurophysiological, and neuroimaging indicators for predicting the risk of clinical manifestations of ASD were determined: age of onset of epileptic seizures, index of spike-wave activity during NREM sleep, frequency and amplitude of alpha rhythm, frequency and amplitude of epileptiform activity, fractional anisotropy and mean diffusion coefficient in the Broca’s center, fractional anisotropy in the Wernicke center and knee of the corpus callosum. The multiple linear regression method was used to predict the risk of developing ASD symptoms. Results. A model for predicting the risk of developing clinical manifestations of ASD in children with EE has been developed. It was established that the risk of developing clinical manifestations of ASD increases with a decrease in the age of onset of epileptic seizures, decrease in the frequency and amplitude of the alpha rhythm according to electroencephalography (EEG) data, increase of the index of spike-wave activity, frequency and amplitude of epileptiform activity, increase in the index of fractional anisotropy in the anterior part of the arcuate tract, decrease in the average diffusion coefficient in the area of the Broca’s center, fractional anisotropy in the Wernicke center and the knee of the corpus callosum according to magnetic resonance tractography. Conclusions. A regression model for predicting the risk of clinical manifestations of ASD in children with EE was developed with an average error of approximation of 13.2% and a coefficient of determination of 0.74, which is recommended for use in clinical practice in order to form groups of children at high risk of ASD. Such children require further dynamic monitoring and early intervention by specialists of a multidisciplinary team for timely identification and correction of ASD symptoms The research was carried out in accordance with the principles of the Helsinki Declaration. The study protocol was approved by the Local Ethics Committee of the participating institution. The informed consent of the patient was obtained for conducting the studies. No conflict of interests was declared by the author.

The accuracy of different mismatch negativity amplitude representations in predicting the levels of consciousness in patients with disorders of consciousness.

The mismatch negativity (MMN) index has been used to evaluate consciousness levels in patients with disorders of consciousness (DoC). Indeed, MMN has been validated for the diagnosis of vegetative state/unresponsive wakefulness syndrome (VS/UWS) and minimally conscious state (MCS). In this study, we evaluated the accuracy of different MMN amplitude representations in predicting levels of consciousness. Task-state electroencephalography (EEG) data were obtained from 67 patients with DoC (35 VS and 32 MCS). We performed a microstate analysis of the task-state EEG and used four different representations (the peak amplitude of MMN at electrode Fz (Peak), the average amplitude within a time window -25- 25 ms entered on the latency of peak MMN component (Avg for peak ± 25 ms), the average amplitude of averaged difference wave for 100-250 ms (Avg for 100-250 ms), and the average amplitude difference between the standard stimulus ("S") and the deviant stimulus ("D") at the time corresponding to Microstate 1 (MS1) (Avg for MS1) of the MMN amplitude to predict the levels of consciousness. The results showed that among the four microstates clustered, MS1 showed statistical significance in terms of time proportion during the 100-250 ms period. Our results confirmed the activation patterns of MMN through functional connectivity analysis. Among the four MMN amplitude representations, the microstate-based representation showed the highest accuracy in distinguishing different levels of consciousness in patients with DoC (AUC = 0.89). We discovered a prediction model based on microstate calculation of MMN amplitude can accurately distinguish between MCS and VS states. And the functional connection of the MS1 is consistent with the activation mode of MMN.

Epilepsy Detection by Different Modalities with the Use of AI-Assisted Models

Epilepsy is characterized by recurrent seizures originating from any four brain lobes. It includes focal seizures with symptoms of alterations in consciousness and cognitive impairments, including memory and language difficulties. It must be radiologically identified by proper diagnosis and course of therapy. However, a visual inspection of images may not always yield an accurate interpretation from radiologists, necessitating AI-assisted methods. The computer-vision-based radiological methods are used to enhance the treatment of epilepsy by image bio-markers and deep learning algorithms. These methods are used to predict disease progression and treatment. It specifies the focus of the research on epilepsy detection using new U-transfer reinforced Gaussian network (U-TRGN) classification models. These models used for lateralization and localization of brain activity in this process. This study gives the idea of preoperative findings of different imaging modalities and postoperative findings of Electroencephalography (EEG) data analysis. The data have been pre-processed through normalization, smoothing, and noise removal techniques. The data are then classified using U-TRGN, after feature selection by kernel convolutional analysis. The performance metrics are evaluated through the training accuracy, validation accuracy, precision, dice coefficient, and area under a region of the convergence curve. The proposed technique attained an accuracy of 97.04%, precision of 94.12%, dice coefficient of 2.96%, and AUC of 99.56%, which is better than the existing methods, and it will be a baseline for upcoming studies.

A new approach to spatial localization of EEG-based electrical activity

Background. Accuracy and reliability of methods for spatial localization of brain activity based on electroencephalography (EEG) data do not lose relevance. Existing localization methods are coupled to specific difficulties due to ambiguity of the resulting solution.Ojective: verification of a new method for localizing brain activity using EEG data «Virtually Implanted Electrode» and demonstratoin of its capabilities.Material and methods. The new method was verified using deep brain stimulation (DBS) data. There were used the data from scalp electrical activity induced solely by potentials from two electrodes implanted into deep areas of human brain. It was achieved by filtering EEG signals at the stimulation frequency and excluding signals from other brain areas. A clinical case of applying the new method for EEG analysis of patient paroxysmal activity is presented as well.Results. «Virtually Implanted Electrode» method allowed to quite accurately determine the localization of DBS current sources. The effectiveness of using the method for analyzing the mechanisms of paroxysmal activity was demonstrated: based on change in potentials calculated in 33 sites of the brain (brain areas), three groups of areas were identified specifically contributing to development of paroxysmal activity. For comparison, the same artificial DBS sources were localized using other verified methods: the BrainLoc (Russia) and sLORETA (Switzerland) software providing substantially worse data.Conclusion. Identifying spatial localization of electrical potentials recorded on the scalp surface by using the new approach with the «Virtually Implanted Electrode» method shows high efficiency and reliability, demonstrating a clear advantage over other known localization methods.

Temporal segmentation of EEG based on functional connectivity network structure

In the study of brain functional connectivity networks, it is assumed that a network is built from a data window in which activity is stationary. However, brain activity is non-stationary over sufficiently large time periods. Addressing the analysis electroencephalograph (EEG) data, we propose a data segmentation method based on functional connectivity network structure. The goal of segmentation is to ensure that within a window of analysis, there is similar network structure. We designed an intuitive and flexible graph distance measure to quantify the difference in network structure between two analysis windows. This measure is modular: a variety of node importance indices can be plugged into it. We use a reference window versus sliding window comparison approach to detect changes, as indicated by outliers in the distribution of graph distance values. Performance of our segmentation method was tested in simulated EEG data and real EEG data from a drone piloting experiment (using correlation or phase-locking value as the functional connectivity strength metric). We compared our method under various node importance measures and against matrix-based dissimilarity metrics that use singular value decomposition on the connectivity matrix. The results show the graph distance approach worked better than matrix-based approaches; graph distance based on partial node centrality was most sensitive to network structural changes, especially when connectivity matrix values change little. The proposed method provides EEG data segmentation tailored for detecting changes in terms of functional connectivity networks. Our study provides a new perspective on EEG segmentation, one that is based on functional connectivity network structure differences.

Innovative and Effective Machine Learning-Based Method to Analyze Alcoholic Brain Activity with Nonlinear Dynamics and Electroencephalography Data

Innovative and Effective Machine Learning-Based Method to Analyze Alcoholic Brain Activity with Nonlinear Dynamics and Electroencephalography Data

A data assimilation method to track excitation-inhibition balance change using scalp EEG

Recent neuroscience studies have suggested that controlling the excitation and inhibition (E/I) balance is essential for maintaining normal brain function. However, while control of time-varying E/I balance is considered essential for perceptual and motor learning, an efficient method for estimating E/I balance changes has yet to be established. To tackle this issue, we propose a method to estimate E/I balance changes by applying neural-mass model-based tracking of the brain state using the Ensemble Kalman Filter. In this method, the parameters of synaptic E/I gains in the model are estimated from observed electroencephalography signals. Moreover, the index of E/I balance was defined by calculating the ratio between synaptic E/I gains based on estimated parameters. The method was validated by showing that it could estimate E/I balance changes from human electroencephalography data at the sub-second scale, indicating that it has the potential to quantify how time-varying changes in E/I balance influence changes in perceptual and motor learning. Furthermore, this method could be used to develop an E/I balance-based neurofeedback training method for clinical use.

Topological data analysis suggests human brain network reconfiguration during the transition from resting state to cognitive load

BACKGROUND: Neural networks of the brain continually adapt to changing environmental demands. The network approach in neuroscience, which focuses on the analysis of structural and functional network characteristics related to cognitive functions, is a highly promising avenue for understanding the psychophysiological mechanisms underlying the adaptive dynamics of cognitive processes. AIM: We aimed to explore how the topological features of functional connectomes in the human brain are linked to different cognitive demands. The focus was on understanding the dynamic changes in brain networks during working memory tasks to identify network characteristics inherent to working memory. METHODS: We examined the topological characteristics of functional brain networks in the resting state and cognitive load provided by the execution of the Sternberg Item Recognition Paradigm based on electroencephalographic data. Electroencephalogram traces from 67 healthy adults were processed to estimate functional connectivity using the coherence method. We propose that the topological properties of functional networks in the human brain are distinct between cognitive load and resting state, with higher integration in the networks during cognitive load. RESULTS: The topological features of functional connectomes depend on the current state of cognitive processing and change with task-induced cognitive load variation. Moreover, functional connectivity during working memory tasks showed a faster emergence of homology group generators, supporting the idea of a relationship between the initial stages of working memory execution and an increase in faster network integration, with connector hubs playing a crucial role. CONCLUSION: Collected evidence suggest that cognitive states, particularly those related to working memory, are associated with distinct topological properties of functional brain networks, highlighting the importance of network dynamics in cognitive processing.

Machine-learning applications for differentiation across states/stages of creative thinking based on time-series and time-frequency features of EEG/ERP signals

BACKGROUND: The study presents machine-learning (ML) classification approaches for the state/stage differentiation of creative tasks using the “test-control” approach. The control tasks were considered as the initial stages of the creative activity. Time-series and time-frequency electroencephalography (EEG) data analyses were employed in three divergent thinking tasks: 1) creating endings to well-known proverbs (“PROVERBS”, event-related potential [ERP] paradigm); 2) creating stories (“STORIES”, continuous EEG); 3) free creative painting (“viART”, continuous EEG). AIM: To compare and select effective ML classification approaches for EEG signal separation at different stages or states of creative task performance. METHODS: In this study, 22 individuals participated in the “PROVERBS” (ERP paradigm), 15 in the “STORIES”, and 1 (a longitudinal case study) in the “viART” tasks. Linear and convolutional neural network (CNN) classifiers were used. EEG data were previous artifacts corrected and converted to current source density (CSD). Continuous EEGs were divided into 4-s intervals and 1500 ms after stimulus presentation, were used in ERPs. The EEG/ERP time-frequency maps (Morlet wavelet transformation) for 3–30 Hz were generated for 4-s intervals with 100 ms shift (continuous EEGs in “STORIES” and “viART”) or for 1500 ms after stimulus presentation (ERPs in “PROVERBS”) and consisted of combined images (224×224 px) for frontal (Fz) and parietal (Pz) brain zones. Image classification was carried out using the modified CNN (ResNet50, ResNet18 architectures). RESULTS: The offline classification accuracy of the four-class system (description of a picture, inventing a story plot, continuation of story’s plot, and background with open eyes) in the “STORY” creation task was up to 96.4% [±8.3 SD] with ResNet architectures (ResNet50 and ResNet18). The accuracy of the three states discrimination of the artists’ creative painting (resting state with open eyes, painting on canvas, and viewing the painting) was 86.94% for kernel naive bayes and 98.2% for CNN. For the trained and tested samples given for the CNN in consecutive order (neurointerface mode), the accuracy diminished to 70.0% [11% SD] on average. In the ERP paradigm “PROVERBS”, the classification accuracy of the three-class system (creation of “new” ending, naming of semantic synonym, and remembering of the known ending) was 80.5% [±8.7 SD] for the common spatial pattern, followed by rSVM (radial kernel basis support vector machine), compared with 43.2% [±8.8 SD] for CNN. CONCLUSION: The use of CNNs allowed better classifying of “continuous” long-term states of creative activity. In fast “transient processes” such as ERP, time-series classifiers with spatial filtering proved to be more efficient.

HNN-core: A Python software for cellular and circuit-level interpretation of human MEG/EEG.

HNN-core is a library for circuit and cellular level interpretation of non-invasive human magneto-/electro-encephalography (MEG/EEG) data. It is based on the Human Neocortical Neurosolver (HNN) software (Neymotin et al., 2020), a modeling tool designed to simulate multiscale neural mechanisms generating current dipoles in a localized patch of neocortex. HNN's foundation is a biophysically detailed neural network representing a canonical neocortical column containing populations of pyramidal and inhibitory neurons together with layer-specific exogenous synaptic drive (Figure 1 left). In addition to simulating network-level interactions, HNN produces the intracellular currents in the long apical dendrites of pyramidal cells across the cortical layers known to be responsible for macroscopic current dipole generation.

Time-resolved dynamic computational modeling of human EEG recordings reveals gradients of generative mechanisms for the MMN response.

Despite attempts to unify the different theoretical accounts of the mismatch negativity (MMN), there is still an ongoing debate on the neurophysiological mechanisms underlying this complex brain response. On one hand, neuronal adaptation to recurrent stimuli is able to explain many of the observed properties of the MMN, such as its sensitivity to controlled experimental parameters. On the other hand, several modeling studies reported evidence in favor of Bayesian learning models for explaining the trial-to-trial dynamics of the human MMN. However, direct comparisons of these two main hypotheses are scarce, and previous modeling studies suffered from methodological limitations. Based on reports indicating spatial and temporal dissociation of physiological mechanisms within the timecourse of mismatch responses in animals, we hypothesized that different computational models would best fit different temporal phases of the human MMN. Using electroencephalographic data from two independent studies of a simple auditory oddball task (n = 82), we compared adaptation and Bayesian learning models' ability to explain the sequential dynamics of auditory deviance detection in a time-resolved fashion. We first ran simulations to evaluate the capacity of our design to dissociate the tested models and found that they were sufficiently distinguishable above a certain level of signal-to-noise ratio (SNR). In subjects with a sufficient SNR, our time-resolved approach revealed a temporal dissociation between the two model families, with high evidence for adaptation during the early MMN window (from 90 to 150-190 ms post-stimulus depending on the dataset) and for Bayesian learning later in time (170-180 ms or 200-220ms). In addition, Bayesian model averaging of fixed-parameter models within the adaptation family revealed a gradient of adaptation rates, resembling the anatomical gradient in the auditory cortical hierarchy reported in animal studies.

Quantitative Electroencephalography Markers for an Accurate Diagnosis of Frontotemporal Dementia: A Spectral Power Ratio Approach.

Background and Objectives: Frontotemporal dementia (FTD) is the second most common form of presenile dementia; however, its diagnosis has been poorly investigated. Previous attempts to diagnose FTD using quantitative electroencephalography (qEEG) have yielded inconsistent results in both spectral and functional connectivity analyses. This study aimed to introduce an accurate qEEG marker that could be used to diagnose FTD and other neurological abnormalities. Materials and Methods: We used open-access electroencephalography data from OpenNeuro to investigate the power ratio between the frontal and temporal lobes in the resting state of 23 patients with FTD and 29 healthy controls. Spectral data were extracted using a fast Fourier transform in the delta (0.5 ≤ 4 Hz), theta (4 ≤ 8 Hz), alpha (8-13 Hz), beta (>13-30 Hz), and gamma (>30-45 Hz) bands. Results: We found that the spectral power ratio between the frontal and temporal lobes is a promising qEEG marker of FTD. Frontal (F)-theta/temporal (T)-alpha, F-alpha/T-theta, F-theta/F-alpha, and T-beta/T-gamma showed a consistently high discrimination score for the diagnosis of FTD for different parameters and referencing methods. Conclusions: The study findings can serve as reference for future research focused on diagnosing FTD and other neurological anomalies.

The effect of hair type and texture on electroencephalography and event-related potential data quality.

Research utilizing event-related potential (ERP) methods is generally biased with regard to sample representativeness. Among the myriad of factors that contribute to sample bias are researchers' assumptions about the extent to which racial differences in hair texture, volume, and style impact electrode placement, and subsequently, study eligibility. The current study examines these impacts using data collected from n = 213 individuals ages 17-19 years, and offers guidance on collection of ERP data across the full spectrum of hair types. Individual differences were quantified for hair texture using a visual scale, and for hair volume by measuring the amount of gel used in cap preparation. Electroencephalography data quality was assessed with multiple metrics at the preprocessing, post-processing, and variable generation stages. Results indicate that hair volume is associated with small, but systematic differences in signal quality and signal amplitude. Such differences are highly problematic as they could be misattributed to cognitive differences among groups. However, inclusion of gel volume as a covariate to account for individual differences in hair volume significantly reduced, and in most cases eliminated, group differences. We discuss strategies for overcoming real and perceived technical barriers for researchers seeking to achieve greater inclusivity and representativeness in ERP research.

Effective Detection of Epileptic Seizures through EEG Signals Using Deep Learning Approaches

Epileptic seizures are a prevalent neurological condition that impacts a considerable portion of the global population. Timely and precise identification can result in as many as 70% of individuals achieving freedom from seizures. To achieve this, there is a pressing need for smart, automated systems to assist medical professionals in identifying neurological disorders correctly. Previous efforts have utilized raw electroencephalography (EEG) data and machine learning techniques to classify behaviors in patients with epilepsy. However, these studies required expertise in clinical domains like radiology and clinical procedures for feature extraction. Traditional machine learning for classification relied on manual feature engineering, limiting performance. Deep learning excels at automated feature learning directly from raw data sans human effort. For example, deep neural networks now show promise in analyzing raw EEG data to detect seizures, eliminating intensive clinical or engineering needs. Though still emerging, initial studies demonstrate practical applications across medical domains. In this work, we introduce a novel deep residual model called ResNet-BiGRU-ECA, analyzing brain activity through EEG data to accurately identify epileptic seizures. To evaluate our proposed deep learning model’s efficacy, we used a publicly available benchmark dataset on epilepsy. The results of our experiments demonstrated that our suggested model surpassed both the basic model and cutting-edge deep learning models, achieving an outstanding accuracy rate of 0.998 and the top F1-score of 0.998.

Women are expected to smile: Preliminary evidence for the role of gender in the neurophysiological processing of adult emotional faces in 3-year-old children.

Children form stereotyped expectations about the appropriateness of certain emotions for men versus women during the preschool years, based on cues from their social environments. Although ample research has examined the development of gender stereotypes in children, little is known about the neural responses that underlie the processing of gender-stereotyped emotions in children. Therefore, the current study examined whether 3-year-olds differ in the neural processing of emotional stimuli that violate gender stereotypes (i.e., male faces with fearful or happy expressions) or confirm gender stereotypes (i.e., female faces with fearful or happy expressions), and whether boys and girls differ in their neural processing of the violation and confirmation of gender stereotypes. Data from 72 3-year-olds (±6 months, 43% boy) were obtained from the YOUth Cohort Study. Electroencephalography data were obtained when children passively viewed male and female faces displaying neutral, happy, or fearful facial expressions. This study provided first indications that happy male faces elicited larger P1 amplitudes than happy female faces in preschool children, which might reflect increased attentional processing of stimuli that violate gender stereotypes. Moreover, there was preliminary evidence that girls had larger negative central (Nc) responses, associated with salience processing, toward female happy faces than male happy faces, whereas boys had larger Nc responses toward male happy faces than female happy faces. No gender differences were found in the processing of neutral and fearful facial expressions. Our results indicate that electroencephalography measurements can provide insights into preschoolers' gender-stereotype knowledge about emotions, potentially by looking at the early occipital and late fronto-central responses.

Uncovering a stability signature of brain dynamics associated with meditation experience using massive time-series feature extraction

Previous research has examined resting electroencephalographic (EEG) data to explore brain activity related to meditation. However, previous research has mostly examined power in different frequency bands. The practical objective of this study was to comprehensively test whether other types of time-series analysis methods are better suited to characterize brain activity related to meditation. To achieve this, we compared >7000 time-series features of the EEG signal to comprehensively characterize brain activity differences in meditators, using many measures that are novel in meditation research. Eyes-closed resting-state EEG data from 49 meditators and 46 non-meditators was decomposed into the top eight principal components (PCs). We extracted 7381 time-series features from each PC and each participant and used them to train classification algorithms to identify meditators. Highly differentiating individual features from successful classifiers were analysed in detail. Only the third PC (which had a central-parietal maximum) showed above-chance classification accuracy (67 %, pFDR = 0.007), for which 405 features significantly distinguished meditators (all pFDR < 0.05). Top-performing features indicated that meditators exhibited more consistent statistical properties across shorter subsegments of their EEG time-series (higher stationarity) and displayed an altered distributional shape of values about the mean. By contrast, classifiers trained with traditional band-power measures did not distinguish the groups (pFDR > 0.05). Our novel analysis approach suggests the key signatures of meditators’ brain activity are higher temporal stability and a distribution of time-series values suggestive of longer, larger, or more frequent non-outlying voltage deviations from the mean within the third PC of their EEG data. The higher temporal stability observed in this EEG component might underpin the higher attentional stability associated with meditation. The novel time-series properties identified here have considerable potential for future exploration in meditation research and the analysis of neural dynamics more broadly.

A deep learning model for the detection of various dementia and MCI pathologies based on resting-state electroencephalography data: A retrospective multicentre study

Dementia and mild cognitive impairment (MCI) represent significant health challenges in an aging population. As the search for noninvasive, precise and accessible diagnostic methods continues, the efficacy of electroencephalography (EEG) combined with deep convolutional neural networks (DCNNs) in varied clinical settings remains unverified, particularly for pathologies underlying MCI such as Alzheimer's disease (AD), dementia with Lewy bodies (DLB) and idiopathic normal-pressure hydrocephalus (iNPH). Addressing this gap, our study evaluates the generalizability of a DCNN trained on EEG data from a single hospital (Hospital #1). For data from Hospital #1, the DCNN achieved a balanced accuracy (bACC) of 0.927 in classifying individuals as healthy (n = 69) or as having AD, DLB, or iNPH (n = 188). The model demonstrated robustness across institutions, maintaining bACCs of 0.805 for data from Hospital #2 (n = 73) and 0.920 at Hospital #3 (n = 139). Additionally, the model could differentiate AD, DLB, and iNPH cases with bACCs of 0.572 for data from Hospital #1 (n = 188), 0.619 for Hospital #2 (n = 70), and 0.508 for Hospital #3 (n = 139). Notably, it also identified MCI pathologies with a bACC of 0.715 for Hospital #1 (n = 83), despite being trained on overt dementia cases instead of MCI cases. These outcomes confirm the DCNN's adaptability and scalability, representing a significant stride toward its clinical application. Additionally, our findings suggest a potential for identifying shared EEG signatures between MCI and dementia, contributing to the field's understanding of their common pathophysiological mechanisms.

The impact of electrode selection for ocular correction on the reward positivity and late positive potential components in adolescents.

Electroencephalography (EEG) data processing to derive event-related potentials (ERPs) follows a standard set of procedures to maximize signal-to-noise ratio. This often includes ocular correction, which corrects for artifacts introduced by eye movements, typically measured by electrooculogram (EOG) using facial electrodes near the eyes. Yet, attaching electrodes to the face may be uncomfortable for some populations, best to avoid in some situations, and contribute to data loss. Eye movements can also be measured using electrodes in a standard 10-20 EEG cap. An examination of the impact of electrode selection on ERPs is needed to inform best practices. The present study examined data quality when using different electrodes to measure eye movements for ocular correction (i.e., facial electrodes, cap electrodes, and no ocular correction) for two well-established and widely studied ERP components (i.e., reward positivity, RewP; and late positive potential, LPP) elicited in adolescents (N = 34). Results revealed comparable split-half reliability and standardized measurement error (SME) between facial and cap electrode approaches, with lower SME for the RewP with facial or cap electrodes compared to no ocular correction. Few significant differences in mean amplitude of ERPs were observed, but the LPP to positive images differed when using facial compared to cap electrodes. Findings provide preliminary evidence of the ability to collect high-quality ERP data without facial electrodes. However, when using cap electrodes for EOG measurement and ocular correction, it is recommended to use consistent procedures across the sample or statistically examine the impact of ocular correction procedures on results.