Functional brain dynamic analysis of ADHD and control children using nonlinear dynamical features of EEG signals

Machine learning-enabled detection of attention-deficit/hyperactivity disorder with multimodal physiological data: a case-control study

BACKGROUND

Attention-Deficit/Hyperactivity Disorder (ADHD) is a multifaceted neurodevelopmental psychiatric condition that typically emerges during childhood but often persists into adulthood, significantly impacting individuals' functioning, relationships, productivity, and overall quality of life. However, the current diagnostic process exhibits limitations that can significantly affect its overall effectiveness. Notably, its face-to-face and time-consuming nature, coupled with the reliance on subjective recall of historical information and clinician subjectivity, stand out as key challenges. To address these limitations, objective measures such as neuropsychological evaluations, imaging techniques and physiological monitoring of the Autonomic Nervous System functioning, have been explored.

METHODS

The main aim of this study was to investigate whether physiological data (i.e., Electrodermal Activity, Heart Rate Variability, and Skin Temperature) can serve as meaningful indicators of ADHD, evaluating its utility in distinguishing adult ADHD patients. This observational, case-control study included a total of 76 adult participants (32 ADHD patients and 44 healthy controls) who underwent a series of Stroop tests, while their physiological data was passively collected using a multi-sensor wearable device. Univariate feature analysis was employed to identify the tests that triggered significant signal responses, while the Informative k-Nearest Neighbors (KNN) algorithm was used to filter out less informative data points. Finally, a machine-learning decision pipeline incorporating various classification algorithms, including Logistic Regression, KNN, Random Forests, and Support Vector Machines (SVM), was utilized for ADHD patient detection.

RESULTS

Results indicate that the SVM-based model yielded the optimal performance, achieving 81.6% accuracy, maintaining a balance between the experimental and control groups, with sensitivity and specificity of 81.4% and 81.9%, respectively. Additionally, integration of data from all physiological signals yielded the best results, suggesting that each modality captures unique aspects of ADHD.

CONCLUSIONS

This study underscores the potential of physiological signals as valuable diagnostic indicators of adult ADHD. For the first time, to the best of our knowledge, our findings demonstrate that multimodal physiological data collected via wearable devices can complement traditional diagnostic approaches. Further research is warranted to explore the clinical applications and long-term implications of utilizing physiological markers in ADHD diagnosis and management.

Identification of attention deficit hyperactivity disorder with deep learning model

This article explores the detection of Attention Deficit Hyperactivity Disorder, a neurobehavioral disorder, from electroencephalography signals. Due to the unstable behavior of electroencephalography signals caused by complex neuronal activity in the brain, frequency analysis methods are required to extract the hidden patterns. In this study, the feature extraction was performed with the Multitaper and Multivariate Variational Mode Decomposition methods. Then, these features were analyzed with the neighborhood component analysis and the features that contribute effectively to the classification were selected. The deep learning model including the convolution, pooling, and bidirectional long short term cell and fully connected layer was trained with the selected features. The trained model could effectively classify the subjects with Attention Deficit Hyperactivity Disorder with a deep learning model, support vector machines and linear discriminant analysis. The experiments were validated with an Attention Deficit Hyperactivity Disorder open access dataset ( https://doi.org/10.21227/rzfh-zn36 ). In validation, the deep learning model was able to classify 1210 test samples (600 subjects in the control group as Normal and 610 subjects in the ADHD group as ADHD) in 0.1 s with an accuracy of 95.54%. This accuracy rate is quite high compared to the Linear Discriminant Analysis (76.38%) and Support Vector Machines (81.69%). Experimental results showed that the proposed approach can innovatively classify Attention Deficit Hyperactivity Disorder subjects from the Control group effectively.

Electroencephalogram (EEG) based prediction of attention deficit hyperactivity disorder (ADHD) using machine learning

"Attention-Deficit Hyperactivity Disorder (ADHD)" is a neuro-developmental disorder in children under 12 years old. Learning deficits, anxiety, depression, sensory processing disorder, and oppositional defiant disorder are the most frequent comorbidities of ADHD. This research focuses on ADHD in children, considering its common occurrence and frequent coexistence with other mental disorders. The study utilizes the resting-state open-eye "Electroencephalogram" (EEG) signals of 61 children with ADHD and 60 healthy children. Morphological and "Power Spectral Density" (PSD) features associated with ADHD are analysed and "Principal Component Analysis" (PCA) is employed to reduce data dimensionality. Classification algorithms including AdaBoost, "K-Nearest Neighbour" (KNN) classifier, Naive Bayes, and random forest are utilized, with the Bernoulli Naive Bayes classifier achieving the highest accuracy of 96%. This study found some relevant characteristics for classification at the frontal (F), central (C), and parietal (P) electrode placement sites. Finally, this reveals distinct EEG patterns in children with ADHD and the study provides a potential supplementary method for ADHD diagnosis.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Brain entropy, fractal dimensions and predictability: A review of complexity measures for EEG in healthy and neuropsychiatric populations

There has been an increasing trend towards the use of complexity analysis in quantifying neural activity measured by electroencephalography (EEG) signals. On top of revealing complex neuronal processes of the brain that may not be possible with linear approaches, EEG complexity measures have also demonstrated their potential as biomarkers of psychopathology such as depression and schizophrenia. Unfortunately, the opacity of algorithms and descriptions originating from mathematical concepts have made it difficult to understand what complexity is and how to draw consistent conclusions when applied within psychology and neuropsychiatry research. In this review, we provide an overview and entry-level explanation of existing EEG complexity measures, which can be broadly categorized as measures of predictability and regularity. We then synthesize complexity findings across different areas of psychological science, namely, in consciousness research, mood and anxiety disorders, schizophrenia, neurodevelopmental and neurodegenerative disorders, as well as changes across the lifespan, while addressing some theoretical and methodological issues underlying the discrepancies in the data. Finally, we present important considerations when choosing and interpreting these metrics.

A Case Study on EEG Analysis: Embedding Entropy Estimations Indicate the Decreased Neuro-Cortical Complexity Levels Mediated by Methylphenidate Treatment in Children with ADHD

Objective: Complexity analysis is a method employed to understand the activity of the brain. The effect of methylphenidate (MPH) treatment on neuro-cortical complexity changes is still unknown. This study aimed to reveal how MPH treatment affects the brain complexity of children with attention deficit hyperactivity disorder (ADHD) using entropy-based quantitative EEG analysis. Three embedding entropy approaches were applied to short segments of both pre- and post- medication EEG series. EEG signals were recorded for 25 boys with combined type ADHD prior to the administration of MPH and at the end of the first month of the treatment. Results: In comparison to Approximate Entropy (ApEn) and Sample Entropy (SampEn), Permutation Entropy (PermEn) provided the most sensitive estimations in investigating the impact of MPH treatment. In detail, the considerable decrease in EEG complexity levels were observed at six cortical regions (F3, F4, P4, T3, T6, O2) with statistically significant level (p < .05). As well, PermEn provided the most meaningful associations at central lobes as follows: 1) The largeness of EEG complexity levels was moderately related to the severity of ADHD symptom detected at pre-treatment stage. 2) The percentage change in the severity of opposition as the symptom cluster was moderately reduced by the change in entropy. Conclusion: A significant decrease in entropy levels in the frontal region was detected in boys with combined type ADHD undergoing MPH treatment at resting-state mode. The changes in entropy correlated with pre-treatment general symptom severity of ADHD and conduct disorder symptom cluster severity.

Event-related brain dynamics during mind wandering in attention-deficit/hyperactivity disorder: An experience-sampling approach

Adults with attention-deficit/hyperactivity disorder (ADHD) report increased spontaneous mind wandering (MW) compared to control adults. Since MW is associated with ADHD severity and functional impairment, elucidating the brain mechanisms underlying MW may inform new interventions targeting MW and point to neural markers to monitor their efficacy. Population-based electroencephalographic (EEG) studies suggest that weaker event-related decreases in occipital alpha power characterise periods of MW, but no study has examined event-related brain oscillations during MW in individuals with ADHD. Using an experience-sampling method, we compared adults with ADHD (N = 23) and controls (N = 25) on event-related EEG measures of power modulations and phase consistency during two tasks with high and low demands on working memory and sustained attention, and during periods of MW and task focus. Compared to controls, individuals with ADHD showed weaker alpha power decreases during high working memory demands and across sustained attention demands, weaker theta power increases and phase consistency across working memory demands and during low sustained attention demands, and weaker beta power decreases during low working memory demands. These EEG patterns suggest broadly deficient attentional and motor response processes in ADHD. During MW episodes, adults with ADHD showed weaker alpha power decreases in the sustained attention task and lower theta phase consistency in the working memory task compared to controls. These findings suggest that atypical EEG patterns thought to reflect reduced inhibition of task-irrelevant processes and inconsistent stimulus processing underlie increased MW in adults with ADHD and may be useful for future real-time monitoring of treatment effects.

EEG Global Coherence in Scholar ADHD Children during Visual Object Processing

Among neurodevelopmental disorders, attention deficit hyperactivity disorder (ADHD) is the main cause of school failure in children. Notably, visuospatial dysfunction has also been emphasized as a leading cause of low cognitive performance in children with ADHD. Consequently, the present study aimed to identify ADHD-related changes in electroencephalography (EEG) characteristics, associated with visual object processing in school-aged children. We performed Multichannel EEG recordings in 16-year-old children undergoing Navon’s visual object processing paradigm. We mapped global coherence during the processing of local and global visual stimuli that were consistent, inconsistent, or neutral. We found that Children with ADHD showed significant differences in global weighted coherence during the processing of local and global inconsistent visual stimuli and longer response times in comparison to the control group. Delta and theta EEG bands highlighted important features for classification in both groups. Thus, we advocate EEG coherence and low-frequency EEG spectral power as prospective markers of visual processing deficit in ADHD. Our results have implications for the development of diagnostic interventions in ADHD and provide a deeper understanding of the factors leading to low performance in school-aged children.

Machine learning models effectively distinguish attention-deficit/hyperactivity disorder using event-related potentials

Accurate diagnosis of Attention-Deficit/Hyperactivity Disorder (ADHD) is a significant challenge. Misdiagnosis has significant negative medical side effects. Due to the complex nature of this disorder, there is no computational expert system for diagnosis. Recently, automatic diagnosis of ADHD by machine learning analysis of brain signals has received an increased attention. This paper aimed to achieve an accurate model to discriminate between ADHD patients and healthy controls by pattern discovery. Event-Related Potentials (ERP) data were collected from ADHD patients and healthy controls. After pre-processing, ERP signals were decomposed and features were calculated for different frequency bands. The classification was carried out based on each feature using seven machine learning algorithms. Important features were then selected and combined. To find specific patterns for each model, the classification was repeated using the proposed patterns. Results indicated that the combination of complementary features can significantly improve the performance of the predictive models. The newly developed features, defined based on band power, were able to provide the best classification using the Generalized Linear Model, Logistic Regression, and Deep Learning with the average accuracy and Receiver operating characteristic curve > %99.85 and > 0.999, respectively. High and low frequencies (Beta, Delta) performed better than the mid, frequencies in the discrimination of ADHD from control. Altogether, this study developed a machine learning expert system that minimises misdiagnosis of ADHD and is beneficial for the evaluation of treatment efficacy.

Automated classification of attention deficit hyperactivity disorder and conduct disorder using entropy features with ECG signals

BACKGROUND

The most prevalent neuropsychiatric disorder among children is attention deficit hyperactivity disorder (ADHD). ADHD presents with a high prevalence of comorbid disorders such as conduct disorder (CD). The lack of definitive confirmatory diagnostic tests for ADHD and CD make diagnosis challenging. The distinction between ADHD, ADHD + CD and CD is important as the course and treatment are different. Electrocardiography (ECG) signals may become altered in behavioral disorders due to brain-heart autonomic interactions. We have developed a software tool to categorize ADHD, ADHD + CD and CD automatically on ECG signals.

METHOD

ECG signals from participants were decomposed using empirical wavelet transform into various modes, from which entropy features were extracted. Robust ten-fold cross-validation with adaptive synthetic sampling (ADASYN) and z-score normalization were performed at each fold. Analysis of variance (ANOVA) technique was employed to determine the variability within the three classes, and obtained the most discriminatory features. Highly significant entropy features were then fed to classifiers.

RESULTS

Our model yielded the best classification results with the bagged tree classifier: 87.19%, 87.71% and 86.29% for accuracy, sensitivity and specificity, respectively.

CONCLUSION

The proposed expert system can potentially assist mental health professionals in the stratification of the three classes, for appropriate intervention using accessible ECG signals.

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.

Complexity analysis of the brain activity in Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD) due to cognitive loads/demands induced by Aristotle's type of syllogism/reasoning. A Power Spectral Density and multiscale entropy (MSE) analysis

OBJECTIVE

We aim to investigate whether EEG dynamics differ in adults with ASD (Autism Spectrum Disorders), ADHD (attention-deficit/hyperactivity disorder), compared with healthy subjects during the performance of an innovative cognitive task: Aristotle's valid and invalid syllogisms. We follow the Neuroanatomical differences type of criterion in assessing the results of our study in supporting or not the dual-process theory of Kahneman, 2011) (Systems I & II of thinking).

METHOD

We recorded EEGs from 14 scalp electrodes in 30 adults with ADHD, 30 with ASD and 24 healthy, normal subjects. The subjects were exposed in a set of innovative cognitive tasks (inducing varying cognitive loads), the Aristotle's four types of syllogism mentioned above. The multiscale entropy (MSE), a nonlinear information-theoretic measure or tool was computed to extract features that quantify the complexity of the EEG.

RESULTS

The dynamics of the curves of the grand average of MSE values of the ADHD and ASD participants was significantly in higher levels for the majority of time scales, than the healthy subjects over a number of brain regions (electrodes locations), during the performance of both valid and invalid types of syllogism. This result is seemingly not in accordance of the broadly accepted 'theory' of complexity loss in 'pathological' subjects, but actually this is not the case as explained in the text. ADHD subjects are engaged in System II of thinking, for both Valid and Invalid syllogism, ASD and Control in System I for valid and invalid syllogism, respectively. A surprising and 'provocative' result of this paper, as shown in the next sections, is that the Complexity-variability of ASD and ADHD subjects, when they face Aristotle's types of syllogisms, is higher than that of the control subjects. An explanation is suggested as described in the text. Also, in the case of invalid type of Aristotelian syllogisms, the linguistic and visuo-spatial systems are both engaged ONLY in the temporal and occipital regions of the brain, respectively, of ADHD subjects. In the case of valid type, both above systems are engaged in the temporal and occipital regions of the brain, respectively, of both ASD and ADHD subjects, while in the control subjects only the visuo-spatial type is engaged (Goel et al., 2000; Knauff, 2007).

CONCLUSION

Based on the results of the analysis described in this work, the differences in the EEG complexity between the three groups of participants lead to the conclusion that cortical information processing is changed in ASD and ADHD adults, therefore their level of cortical activation may be insufficient to meet the peculiar cognitive demand of Aristotle's reasoning.

SIGNIFICANCE

The present paper suggest that MSE, is a powerful and efficient nonlinear measure in detecting neural dysfunctions in adults with ASD and ADHD characteristics, when they are called on to perform in a very demanding as well as innovative set of cognitive tasks, that can be considered as a new diagnostic 'benchmark' in helping detecting more effectively such type of disorders. A linear measure alone, as the typical PSD, is not capable in making such a distinction. The work contributes in shedding light on the neural mechanisms of syllogism/reasoning of Aristotelian type, as well as toward understanding how humans reason logically and why 'pathological' subjects deviate from the norms of formal logic.

CEPS: An Open Access MATLAB Graphical User Interface (GUI) for the Analysis of Complexity and Entropy in Physiological Signals

BACKGROUND

We developed CEPS as an open access MATLAB^® GUI (graphical user interface) for the analysis of Complexity and Entropy in Physiological Signals (CEPS), and demonstrate its use with an example data set that shows the effects of paced breathing (PB) on variability of heart, pulse and respiration rates. CEPS is also sufficiently adaptable to be used for other time series physiological data such as EEG (electroencephalography), postural sway or temperature measurements.

METHODS

Data were collected from a convenience sample of nine healthy adults in a pilot for a larger study investigating the effects on vagal tone of breathing paced at various different rates, part of a development programme for a home training stress reduction system.

RESULTS

The current version of CEPS focuses on those complexity and entropy measures that appear most frequently in the literature, together with some recently introduced entropy measures which may have advantages over those that are more established. Ten methods of estimating data complexity are currently included, and some 28 entropy measures. The GUI also includes a section for data pre-processing and standard ancillary methods to enable parameter estimation of embedding dimension m and time delay τ ('tau') where required. The software is freely available under version 3 of the GNU Lesser General Public License (LGPLv3) for non-commercial users. CEPS can be downloaded from Bitbucket. In our illustration on PB, most complexity and entropy measures decreased significantly in response to breathing at 7 breaths per minute, differentiating more clearly than conventional linear, time- and frequency-domain measures between breathing states. In contrast, Higuchi fractal dimension increased during paced breathing.

CONCLUSIONS

We have developed CEPS software as a physiological data visualiser able to integrate state of the art techniques. The interface is designed for clinical research and has a structure designed for integrating new tools. The aim is to strengthen collaboration between clinicians and the biomedical community, as demonstrated here by using CEPS to analyse various physiological responses to paced breathing.

Automated detection of conduct disorder and attention deficit hyperactivity disorder using decomposition and nonlinear techniques with EEG signals

BACKGROUND AND OBJECTIVES

Attention deficit hyperactivity disorder (ADHD) is often presented with conduct disorder (CD). There is currently no objective laboratory test or diagnostic method to discern between ADHD and CD, and diagnosis is further made difficult as ADHD is a common neuro-developmental disorder often presenting with other co-morbid difficulties; and in particular with conduct disorder which has a high degree of associated behavioural challenges. A novel automated system (AS) is proposed as a convenient supplementary tool to support clinicians in their diagnostic decisions. To the best of our knowledge, we are the first group to develop an automated classification system to classify ADHD, CD and ADHD+CD classes using brain signals.

METHODS

The empirical mode decomposition (EMD) and discrete wavelet transform (DWT) methods were employed to decompose the electroencephalogram (EEG) signals. Autoregressive modelling coefficients and relative wavelet energy were then computed on the signals. Various nonlinear features were extracted from the decomposed coefficients. Adaptive synthetic sampling (ADASYN) was then employed to balance the dataset. The significant features were selected using sequential forward selection method. The highly discriminatory features were subsequently fed to an array of classifiers.

RESULTS

The highest accuracy of 97.88% was achieved with the K-Nearest Neighbour (KNN) classifier. The proposed system was developed using ten-fold validation strategy on EEG data from 123 children. To the best of our knowledge this is the first study to develop an AS for the classification of ADHD, CD and ADHD+CD classes using EEG signals.

POTENTIAL APPLICATION

Our AS can potentially be used as a web-based application with cloud system to aid the clinical diagnosis of ADHD and/or CD, thus supporting faster and accurate treatment for the children. It is important to note that testing with larger data is required before the AS can be employed for clinical applications.

A Study on Resting EEG Effective Connectivity Difference before and after Neurofeedback for Children with ADHD

Altered functional networks in attention deficit/hyperactivity disorder (ADHD) have been frequently reported, but effective connectivity has hardly been studied. Especially the differences of effective connectivity in children with ADHD after receiving neurofeedback (NF) training have been merely reported. Therefore, this study aimed to explore the effective networks of ADHD and the positive influence of NF on the effective networks. Electroencephalogram (EEG) data were recorded from 22 children with ADHD (including data from children pretraining and posttraining) and 15 age-matched healthy controls during an eyes-closed resting state. Phase transfer entropy (PTE) was used to construct the effective connectivity. The topological properties of networks and flow gain were measured separately in four bands (delta, theta, alpha, and beta). Results revealed the following: pretraining children with ADHD manifested a higher clustering coefficient and lower characteristic path length in the delta band than healthy controls; weakened anterior-to-posterior flow gain in the delta band, strengthened posterior-to-anterior flow gain in the alpha band and strengthened anterior-to-posterior flow gain in the beta band were observed in pretraining children with ADHD; The topological properties and flow gain in posttraining children with ADHD were close to those of healthy controls. Moreover, parent's SWAN presented significant improvements of ADHD symptoms after NF. Our findings revealed that the effective connectivity of ADHD was altered and that NF could improve the brain function of ADHD. The present study provided the first evidence that children with ADHD differed from healthy children in phase-based effective connectivity and that NF could reduce the differences.

Diagnosis of attention deficit hyperactivity disorder using non-linear analysis of the EEG signal

Attention deficit hyperactivity disorder (ADHD) is a common behavioural disorder that may be found in 5%-8% of the children. Early diagnosis of ADHD is crucial for treating the disease and reducing its harmful effects on education, employment, relationships, and life quality. On the other hand, non-linear analysis methods are widely applied in processing the electroencephalogram (EEG) signals. It has been proved that the brain neuronal activity and its related EEG signals have chaotic behaviour. Hence, chaotic indices can be employed to classify the EEG signals. In this study, a new approach is proposed based on the combination of some non-linear features to distinguish ADHD from normal children. Lyapunov exponent, fractal dimension, correlation dimension and sample, fuzzy and approximate entropies are the non-linear extracted features. For computing, the chaotic time series of obtained EEG in the brain frontal lobe (FP1, FP2, F3, F4, and Fz) need to be analysed. Experiments on a set of EEG signal obtained from 50 ADHD and 26 normal cases yielded a sensitivity, specificity, and accuracy of 98, 92.31, and 96.05%, respectively. The obtained accuracy provides a significant improvement in comparison to the other similar studies in identifying and classifying children with ADHD.

Deep Learning Based on Event-Related EEG Differentiates Children with ADHD from Healthy Controls

Attention Deficit Hyperactivity Disorder (ADHD) is one of the most prevalent neuropsychiatric disorders in childhood and adolescence and its diagnosis is based on clinical interviews, symptom questionnaires, and neuropsychological testing. Much research effort has been undertaken to evaluate the usefulness of neurophysiological (EEG) data to aid this diagnostic process. In the current study, we applied deep learning methods on event-related EEG data to examine whether it is possible to distinguish ADHD patients from healthy controls using purely neurophysiological measures. The same was done to distinguish between ADHD subtypes. The results show that the applied deep learning model (“EEGNet”) was able to distinguish between both ADHD subtypes and healthy controls with an accuracy of up to 83%. However, a significant fraction of individuals could not be classified correctly. It is shown that neurophysiological processes indicating attentional selection associated with superior parietal cortical areas were the most important for that. Using the applied deep learning method, it was not possible to distinguish ADHD subtypes from each other. This is the first study showing that deep learning methods applied to EEG data are able to dissociate between ADHD patients and healthy controls. The results show that the applied method reflects a promising means to support clinical diagnosis in ADHD. However, more work needs to be done to increase the reliability of the taken approach.

Long-range temporal correlation in Auditory Brainstem Responses to Spoken Syllable/da/

The speech auditory brainstem response (sABR) is an objective clinical tool to diagnose particular impairments along the auditory brainstem pathways. We explore the scaling behavior of the brainstem in response to synthetic /da/ stimuli using a proposed pipeline including Multifractal Detrended Moving Average Analysis (MFDMA) modified by Singular Value Decomposition. The scaling exponent confirms that all normal sABR are classified into the non-stationary process. The average Hurst exponent is H = 0:77 ± 0:12 at 68% confidence interval indicating long-range correlation which shows the first universality behavior of sABR. Our findings exhibit that fluctuations in the sABR series are dictated by a mechanism associated with long-term memory of the dynamic of the auditory system in the brainstem level. The q-dependency of h(q) demonstrates that underlying data sets have multifractal nature revealing the second universality behavior of the normal sABR samples. Comparing Hurst exponent of original sABR with the results of the corresponding shuffled and surrogate series, we conclude that its multifractality is almost due to the long-range temporal correlations which are devoted to the third universality. Finally, the presence of long-range correlation which is related to the slow timescales in the subcortical level and integration of information in the brainstem network is confirmed.