Performance analysis of univariate and multivariate EEG measurements in the diagnosis of ADHD

EEG spectral power in developmental coordination disorder and attention-deficit/hyperactivity disorder: a pilot study

Developmental coordination disorder (DCD) and attention-deficit/hyperactivity disorder (ADHD) overlap in symptoms and often co-occur. Differentiation of DCD and ADHD is crucial for a better understanding of the conditions and targeted support. Measuring electrical brain activity with EEG may help to discern and better understand the conditions given that it can objectively capture changes and potential differences in brain activity related to externally measurable symptoms beneficial for targeted interventions. Therefore, a pilot study was conducted to exploratorily examine neurophysiological differences between adults with DCD and/or ADHD at rest. A total of N = 46 adults with DCD (n = 12), ADHD (n = 9), both DCD + ADHD (n = 8), or typical development (n = 17) completed 2 min of rest with eyes-closed and eyes-open while their EEG was recorded. Spectral power was calculated for frequency bands: delta (0.5-3 Hz), theta (3.5-7 Hz), alpha (7.5-12.5 Hz), beta (13-25 Hz), mu (8-13 Hz), gamma (low: 30-40 Hz; high: 40-50 Hz). Within-participants, spectral power in a majority of waveforms significantly increased from eyes-open to eyes-closed conditions. Groups differed significantly in occipital beta power during the eyes-open condition, driven by the DCD versus typically developing group comparison. However, other group comparisons reached only marginal significance, including whole brain alpha and mu power with eyes-open, and frontal beta and occipital high gamma power during eyes-closed. While no strong markers could be determined to differentiate DCD versus ADHD, we theorize that several patterns in beta activity were indicative of potential motor maintenance differences in DCD at rest. Therefore, larger studies comparing EEG spectral power may be useful to identify neurological mechanisms of DCD and continued differentiation of DCD and ADHD.

Investigating the discrimination of linear and nonlinear effective connectivity patterns of EEG signals in children with Attention-Deficit/Hyperactivity Disorder and Typically Developing children

BACKGROUND

Analysis of effective connectivity among brain regions is an important key to decipher the mechanisms underlying neural disorders such as Attention Deficit Hyperactivity Disorder (ADHD). We previously introduced a new method, called nCREANN (nonlinear Causal Relationship Estimation by Artificial Neural Network), for estimating linear and nonlinear components of effective connectivity, and provided novel findings about effective connectivity of EEG signals of children with autism. Using the nCREANN method in the present study, we assessed effective connectivity patterns of ADHD children based on their EEG signals recorded during a visual attention task, and compared them with the aged-matched Typically Developing (TD) subjects.

METHOD

In addition to the nCREANN method for estimating linear and nonlinear aspects of effective connectivity, the direct Directed Transfer Function (dDTF) was utilized to extract the spectral information of connectivity patterns.

RESULTS

The dDTF results did not suggest a specific frequency band for distinguishing between the two groups, and different patterns of effective connectivity were observed in all bands. Both nCREANN and dDTF methods showed decreased connectivity between temporal/frontal and temporal/occipital regions, and increased connection between frontal/parietal regions in ADHDs than TDs. Furthermore, the nCREANN results showed more left-lateralized connections in ADHDs compared to the symmetric bilateral inter-hemispheric interactions in TDs. In addition, by fusion of linear and nonlinear connectivity measures of nCREANN method, we achieved an accuracy of 99% in classification of the two groups.

CONCLUSION

These findings emphasize the capability of nCREANN method to investigate the brain functioning of neural disorders and its strength in preciously distinguish between healthy and disordered subjects.

Electroencephalogram aperiodic power spectral slope can be reliably measured and predicts ADHD risk in early development

The aperiodic exponent of the electroencephalogram (EEG) power spectrum has received growing attention as a physiological marker of neurodevelopmental psychopathology, including attention-deficit/hyperactivity disorder (ADHD). However, its use as a marker of ADHD risk across development, and particularly in very young children, is limited by unknown reliability, difficulty in aligning canonical band-based measures across development periods, and unclear effects of treatment in later development. Here, we investigate the internal consistency of the aperiodic EEG power spectrum slope and its association with ADHD risk in both infants (n = 69, 1-month-old) and adolescents (n = 262, ages 11-17 years). Results confirm good to excellent internal consistency in infancy and adolescence. In infancy, a larger aperiodic exponent was associated with greater family history of ADHD. In contrast, in adolescence, ADHD diagnosis was associated with a smaller aperiodic exponent, but only in children with ADHD who had not received stimulant medication treatment. Results suggest that disruptions in cortical development associated with ADHD risk may be detectable shortly after birth via this approach. Together, findings imply a dynamic developmental shift in which the developmentally normative flattening of the EEG power spectrum is exaggerated in ADHD, potentially reflecting imbalances in cortical excitation and inhibition that could contribute to long-lasting differences in brain connectivity.

Detection of ADHD From EEG Signals Using Different Entropy Measures and ANN

Attention deficit hyperactivity disorder (ADHD) is a prevalent behavioral, cognitive, neurodevelopmental pediatric disorder. Clinical evaluations, symptom surveys, and neuropsychological assessments are some of the ADHD assessment methods, which are time-consuming processes and have a certain degree of uncertainty. This research investigates an efficient computer-aided technological solution for detecting ADHD from the acquired electroencephalography (EEG) signals based on different nonlinear entropy estimators and an artificial neural network classifier. Features extracted through fuzzy entropy, log energy entropy, permutation entropy, SURE entropy, and Shannon entropy are analyzed for effective discrimination of ADHD subjects from the control group. The experimented results confirm that the proposed techniques can effectively detect and classify ADHD subjects. The permutation entropy gives the highest classification accuracy of 99.82%, sensitivity of 98.21%, and specificity of 98.82%. Also, the potency of different entropy estimators derived from the t-test reflects that the Shannon entropy has a higher P-value (>.001); therefore, it has a limited scope than other entropy estimators for ADHD diagnosis. Furthermore, the considerable variance found from potential features obtained in the frontal polar (FP) and frontal (F) lobes using different entropy estimators under the eyes-closed condition shows that the signals received in these lobes will have more significance in distinguishing ADHD from normal subjects.

Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG

BACKGROUND AND OBJECTIVE

Attention-Deficit/Hyperactivity Disorder (ADHD) is a chronic behavioral disorder in children. Children with ADHD face many difficulties in maintaining their concentration and controlling their behaviors. Early diagnosis of this disorder is one of the most important challenges in its control and treatment. No definitive expert method has been found to detect this disorder early. Our goal in this study is to develop an assistive tool for physicians to recognize ADHD children from healthy children using electroencephalography (EEG) based on a continuous mental task.

METHODS

We used EEG signals recorded from 31 ADHD children and 30 healthy children. In this study, we developed a deep learning model using a convolutional neural network that have had significant performance in image processing fields. For this purpose, we first preprocessed EEG signals to eliminate noise and artifacts. Then we segmented preprocessed samples into more samples. We extracted the theta, alpha, beta, and gamma frequency bands from each segmented sample and formed a color RGB image with three channels. Eventually, we imported the resulting images into a 13-layer convolutional neural network for feature extraction and classification.

RESULTS

The proposed model was evaluated by 5-fold cross validation for train, evaluation, and test data and achieved an average accuracy of 99.06%, 97.81%, 97.47% for segmented samples. The average accuracy for subject-based test samples was 98.48%. Also, the performance of the model was evaluated using the confusion matrix with precision, recall, and f1-score metrics. The results of these metrics also confirmed the outstanding performance of the model.

CONCLUSIONS

The accuracy, precision, recall, and f1-score of our model were better than all previous works for diagnosing ADHD in children. Based on these prominent and reliable results, this technique can be used as an assistive tool for the physicians in the early diagnosis of ADHD in children.

Investigation of Brain Functional Networks in Children Suffering from Attention Deficit Hyperactivity Disorder

ADHD defects the recognition of facial emotions. This study assesses the neurophysiological differences between children with ADHD and matched healthy controls during a face emotional recognition task. The study also explores how brain connectivity is affected by ADHD. Electroencephalogram (EEG) signals were recorded from 64 scalp electrodes. Event-related phase coherence (ERPCOH) method was applied to pre-processed signals, and functional connectivity between any pair of electrodes was computed in different frequency bands. A logistic regression (LR) classifier with elastic net regularization (ENR) was trained to classify ADHD and HC participants using the functional connectivity of frequency bands as a potential biomarker. Subsequently, the brain network is constructed using graph-theoretic techniques, and graph indices such as clustering coefficient (C) and shortest path length (L) were calculated. Significant intra-hemispheric and the inter-hemispheric discrepancy between ADHD and healthy control (HC) groups in the beta band was observed. The graph features indicate that the clustering coefficient is significantly higher in the ADHD group than that in the HC group. At the same time, the shortest path length is significantly lower in the beta band. ADHD's brain networks have a problem in transferring information among various neural regions, which can cause a deficiency in the processing of facial emotions. The beta band seems better to reflect the differences between ADHD and HC. The observed functional connectivity and graph differences could also be helpful in ADHD investigations.

Functional EEG connectivity is a neuromarker for adult attention deficit hyperactivity disorder symptoms

OBJECTIVE

Altered brain functional connectivity has been shown in youth with attention-deficit/hyperactivity disorder (ADHD). However, relatively little is known about functional connectivity in adult ADHD, and how it is linked with the heritability of ADHD.

METHODS

We measured eyes-open and eyes-closed resting electroencephalography (EEG) from 38 adults with ADHD, 45 1st degree relatives of people with ADHD and 51 healthy controls. Functional connectivity among all scalp channels was calculated using a weighted phase lag index for delta, theta, alpha, beta and gamma frequency bands. A machine learning analysis using penalized linear regression was used to identify if connectivity features (10,080 connectivity pairs) could predict ADHD symptoms. Furthermore, we examined if EEG connectivity could accurately classify participants into ADHD, 1st degree relatives and/or control groups.

RESULTS

Hyperactive symptoms were best predicted by eyes-open EEG connectivity in delta, beta and gamma bands. Inattentive symptoms were predicted by eyes-open EEG connectivity in delta, alpha and gamma bands, and eyes-closed EEG connectivity in delta and gamma bands. EEG connectivity features did not reliably classify participants into groups.

CONCLUSIONS

EEG connectivity may represent a neuromarker for ADHD symptoms.

SIGNIFICANCE

EEG connectivity may help elucidate the neural basis of adult ADHD symptoms.

EEG development in Attention Deficit Hyperactivity Disorder: From child to adult

OBJECTIVE

Attention Deficit Hyperactivity Disorder (ADHD) is one of the most common psychiatric disorders found in children. While an extensive literature has documented the EEG in this clinical population, few studies have investigated EEG throughout the lifespan in ADHD. This study aimed to investigate EEG maturational changes, in subjects with ADHD combined type, that spanned from childhood into adulthood.

METHOD

Twenty five male adults with ADHD were assessed between the ages of 8-12 years and again as adults. At both ages, an EEG was recorded during an eyes-closed resting period, and power estimates were calculated for relative delta, theta, alpha and beta.

RESULTS

At the childhood assessment, the ADHD subjects had elevated posterior delta. Relative theta was elevated, with diminished alpha activity across all sites. Significant maturational changes were observed, with reductions in the delta and theta bands, and increases in the alpha and beta bands across all electrodes. In adulthood, relative to controls, diminished frontal delta and elevated global theta activity were apparent.

CONCLUSIONS

Substantial developmental changes occurred in the EEG of these subjects. These results identify important issues when using EEG as part of the diagnosis for ADHD.

SIGNIFICANCE

This study is the first to explore EEG changes from childhood to adulthood over an 11 year period in the same subjects with ADHD.

The blessing of Dimensionality: Feature Selection outperforms functional connectivity-based feature transformation to classify ADHD subjects from EEG patterns of phase synchronisation

Functional connectivity (FC) characterizes brain activity from a multivariate set of N brain signals by means of an NxN matrix A, whose elements estimate the dependence within each possible pair of signals. Such matrix can be used as a feature vector for (un)supervised subject classification. Yet if N is large, A is highly dimensional. Little is known on the effect that different strategies to reduce its dimensionality may have on its classification ability. Here, we apply different machine learning algorithms to classify 33 children (age [6-14 years]) into two groups (healthy controls and Attention Deficit Hyperactivity Disorder patients) using EEG FC patterns obtained from two phase synchronisation indices. We found that the classification is highly successful (around 95%) if the whole matrix A is taken into account, and the relevant features are selected using machine learning methods. However, if FC algorithms are applied instead to transform A into a lower dimensionality matrix, the classification rate drops to less than 80%. We conclude that, for the purpose of pattern classification, the relevant features should be selected among the elements of A by using appropriate machine learning algorithms.

Robustness and versatility of a nonlinear interdependence method for directional coupling detection from spike trains

The detection of directional couplings between dynamics based on measured spike trains is a crucial problem in the understanding of many different systems. In particular, in neuroscience it is important to assess the connectivity between neurons. One of the approaches that can estimate directional coupling from the analysis of point processes is the nonlinear interdependence measure L. Although its efficacy has already been demonstrated, it still needs to be tested under more challenging and realistic conditions prior to an application to real data. Thus, in this paper we use the Hindmarsh-Rose model system to test the method in the presence of noise and for different spiking regimes. We also examine the influence of different parameters and spike train distances. Our results show that the measure L is versatile and robust to various types of noise, and thus suitable for application to experimental data.

Comparison of Electroencephalography (EEG) Coherence between Major Depressive Disorder (MDD) without Comorbidity and MDD Comorbid with Internet Gaming Disorder

Internet gaming disorder (IGD) has many comorbid psychiatric problems including major depressive disorder (MDD). In the present study, we compared the neurobiological differences between MDD without comorbidity (MDD-only) and MDD comorbid with IGD (MDD+IGD) by analyzing the quantitative electroencephalogram (QEEG) findings. We recruited 14 male MDD+IGD (mean age, 20.0 ± 5.9 years) and 15 male MDD-only (mean age, 20.3 ± 5.5 years) patients. The electroencephalography (EEG) coherences were measured using a 21-channel digital EEG system and computed to assess synchrony in the frequency ranges of alpha (7.5-12.5 Hz) and beta (12.5-35.0 Hz) between the following 12 electrode site pairs: inter-hemispheric (Fp1-Fp2, F7-F8, T3-T4, and P3-P4) and intra-hemispheric (F7-T3, F8-T4, C3-P3, C4-P4, T5-O1, T6-O2, P3-O1, and P4-O2) pairs. Differences in inter- and intra-hemispheric coherence values for the frequency bands between groups were analyzed using the independent t-test. Inter-hemispheric coherence value for the alpha band between Fp1-Fp2 electrodes was significantly lower in MDD+IGD than MDD-only patients. Intra-hemispheric coherence value for the alpha band between P3-O1 electrodes was higher in MDD+IGD than MDD-only patients. Intra-hemispheric coherence values for the beta band between F8-T4, T6-O2, and P4-O2 electrodes were higher in MDD+IGD than MDD-only patients. There appears to be an association between decreased inter-hemispheric connectivity in the frontal region and vulnerability to attention problems in the MDD+IGD group. Increased intra-hemisphere connectivity in the fronto-temporo-parieto-occipital areas may result from excessive online gaming.

Comparison of QEEG Findings between Adolescents with Attention Deficit Hyperactivity Disorder (ADHD) without Comorbidity and ADHD Comorbid with Internet Gaming Disorder

Internet gaming disorder (IGD) is often comorbid with attention deficit hyperactivity disorder (ADHD). In this study, we compared the neurobiological differences between ADHD comorbid with IGD (ADHD+IGD group) and ADHD without comorbidity (ADHD-only group) by analyzing quantitative electroencephalogram (QEEG) findings. We recruited 16 male ADHD+IGD, 15 male ADHD-only adolescent patients, and 15 male healthy controls (HC group). Participants were assessed using Young's Internet Addiction Scale and ADHD Rating Scale. Relative power and inter- and intra-hemispheric coherences of brain waves were measured using a digital electroencephalography (EEG) system. Compared to the ADHD-only group, the ADHD+IGD group showed lower relative delta power and greater relative beta power in temporal regions. The relative theta power in frontal regions were higher in ADHD-only group compared to HC group. Inter-hemispheric coherence values for the theta band between F3-F4 and C3-C4 electrodes were higher in ADHD-only group compared to HC group. Intra-hemispheric coherence values for the delta, theta, alpha, and beta bands between P4-O2 electrodes and intra-hemispheric coherence values for the theta band between Fz-Cz and T4-T6 electrodes were higher in ADHD+IGD group compared to ADHD-only group. Adolescents who show greater vulnerability to ADHD seem to continuously play Internet games to unconsciously enhance attentional ability. In turn, relative beta power in attention deficit in ADHD+IGD group may become similar to that in HC group. Repetitive activation of brain reward and working memory systems during continuous gaming may result in an increase in neuronal connectivity within the parieto-occipital and temporal regions for the ADHD+IGD group.

Personalized Medicine: Review and Perspectives of Promising Baseline EEG Biomarkers in Major Depressive Disorder and Attention Deficit Hyperactivity Disorder

Personalized medicine in psychiatry is in need of biomarkers that resemble central nervous system function at the level of neuronal activity. Electroencephalography (EEG) during sleep or resting-state conditions and event-related potentials (ERPs) have not only been used to discriminate patients from healthy subjects, but also for the prediction of treatment outcome in various psychiatric diseases, yielding information about tailored therapy approaches for an individual. This review focuses on baseline EEG markers for two psychiatric conditions, namely major depressive disorder and attention deficit hyperactivity disorder. It covers potential biomarkers from EEG sleep research and vigilance regulation, paroxysmal EEG patterns and epileptiform discharges, quantitative EEG features within the EEG main frequency bands, connectivity markers and ERP components that might help to identify favourable treatment outcome. Further, the various markers are discussed in the context of their potential clinical value and as research domain criteria, before giving an outline for future studies that are needed to pave the way to an electrophysiological biomarker-based personalized medicine.

MEG Analysis of Neural Interactions in Attention-Deficit/Hyperactivity Disorder

The aim of the present study was to explore the interchannel relationships of resting-state brain activity in patients with attention-deficit/hyperactivity disorder (ADHD), one of the most common mental disorders that develop in children. Magnetoencephalographic (MEG) signals were recorded using a 148-channel whole-head magnetometer in 13 patients with ADHD (range: 8–12 years) and 14 control subjects (range: 8–13 years). Three complementary measures (coherence, phase-locking value, and Euclidean distance) were calculated in the conventional MEG frequency bands: delta, theta, alpha, beta, and gamma. Our results showed that the interactions among MEG channels are higher for ADHD patients than for control subjects in all frequency bands. Statistically significant differences were observed for short-distance values within right-anterior and central regions, especially at delta, beta, and gamma-frequency bands (p < 0.05; Mann-Whitney U test with false discovery rate correction). These frequency bands also showed statistically significant differences in long-distance interactions, mainly among anterior and central regions, as well as among anterior, central, and other areas. These differences might reflect alterations during brain development in children with ADHD. Our results support the role of frontal abnormalities in ADHD pathophysiology, which may reflect a delay in cortical maturation in the frontal cortex.

Electroencephalography signatures of attention-deficit/hyperactivity disorder: clinical utility

The techniques and the most important results on the use of electroencephalography (EEG) to extract different measures are reviewed in this work, which can be clinically useful to study subjects with attention-deficit/hyperactivity disorder (ADHD). First, we discuss briefly and in simple terms the EEG analysis and processing techniques most used in the context of ADHD. We review techniques that both analyze individual EEG channels (univariate measures) and study the statistical interdependence between different EEG channels (multivariate measures), the so-called functional brain connectivity. Among the former ones, we review the classical indices of absolute and relative spectral power and estimations of the complexity of the channels, such as the approximate entropy and the Lempel-Ziv complexity. Among the latter ones, we focus on the magnitude square coherence and on different measures based on the concept of generalized synchronization and its estimation in the state space. Second, from a historical point of view, we present the most important results achieved with these techniques and their clinical utility (sensitivity, specificity, and accuracy) to diagnose ADHD. Finally, we propose future research lines based on these results.

Vestibular insights into cognition and psychiatry

The vestibular system has traditionally been thought of as a balance apparatus; however, accumulating research suggests an association between vestibular function and psychiatric and cognitive symptoms, even when balance is measurably unaffected. There are several brain regions that are implicated in both vestibular pathways and psychiatric disorders. The present review examines the anatomical associations between the vestibular system and various psychiatric disorders. Despite the lack of direct evidence for vestibular pathology in the key psychiatric disorders selected for this review, there is a substantial body of literature implicating the vestibular system in each of the selected psychiatric disorders. The second part of this review provides complimentary evidence showing the link between vestibular dysfunction and vestibular stimulation upon cognitive and psychiatric symptoms. In summary, emerging research suggests the vestibular system can be considered a potential window for exploring brain function beyond that of maintenance of balance, and into areas of cognitive, affective and psychiatric symptomology. Given the paucity of biological and diagnostic markers in psychiatry, novel avenues to explore brain function in psychiatric disorders are of particular interest and warrant further exploration.