Investigation of attention deficit hyperactivity disorder (ADHD) sub-types in children via EEG frequency domain analysis

Aperiodic and periodic components of oscillatory brain activity in relation to cognition and symptoms in pediatric ADHD

Children with attention-deficit/hyperactivity disorder show deficits in processing speed, as well as aberrant neural oscillations, including both periodic (oscillatory) and aperiodic (1/f-like) activity, reflecting the pattern of power across frequencies. Both components were suggested as underlying neural mechanisms of cognitive dysfunctions in attention-deficit/hyperactivity disorder. Here, we examined differences in processing speed and resting-state-Electroencephalogram neural oscillations and their associations between 6- and 12-year-old children with (n = 33) and without (n = 33) attention-deficit/hyperactivity disorder. Spectral analyses of the resting-state EEG signal using fast Fourier transform revealed increased power in fronto-central theta and beta oscillations for the attention-deficit/hyperactivity disorder group, but no differences in the theta/beta ratio. Using the parameterization method, we found a higher aperiodic exponent, which has been suggested to reflect lower neuronal excitation-inhibition, in the attention-deficit/hyperactivity disorder group. While fast Fourier transform-based theta power correlated with clinical symptoms for the attention-deficit/hyperactivity disorder group only, the aperiodic exponent was negatively correlated with processing speed across the entire sample. Finally, the aperiodic exponent was correlated with fast Fourier transform-based beta power. These results highlight the different and complementary contribution of periodic and aperiodic components of the neural spectrum as metrics for evaluation of processing speed in attention-deficit/hyperactivity disorder. Future studies should further clarify the roles of periodic and aperiodic components in additional cognitive functions and in relation to clinical status.

An explainable and interpretable model for attention deficit hyperactivity disorder in children using EEG signals

BACKGROUND

Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder that affects a person's sleep, mood, anxiety, and learning. Early diagnosis and timely medication can help individuals with ADHD perform daily tasks without difficulty. Electroencephalogram (EEG) signals can help neurologists to detect ADHD by examining the changes occurring in it. The EEG signals are complex, non-linear, and non-stationary. It is difficult to find the subtle differences between ADHD and healthy control EEG signals visually. Also, making decisions from existing machine learning (ML) models do not guarantee similar performance (unreliable).

METHOD

The paper explores a combination of variational mode decomposition (VMD), and Hilbert transform (HT) called VMD-HT to extract hidden information from EEG signals. Forty-one statistical parameters extracted from the absolute value of analytical mode functions (AMF) have been classified using the explainable boosted machine (EBM) model. The interpretability of the model is tested using statistical analysis and performance measurement. The importance of the features, channels and brain regions has been identified using the glass-box and black-box approach. The model's local and global explainability has been visualized using Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), Partial Dependence Plot (PDP), and Morris sensitivity. To the best of our knowledge, this is the first work that explores the explainability of the model prediction in ADHD detection, particularly for children.

RESULTS

Our results show that the explainable model has provided an accuracy of 99.81%, a sensitivity of 99.78%, 99.84% specificity, an F-1 measure of 99.83%, the precision of 99.87%, a false detection rate of 0.13%, and Mathew's correlation coefficient, negative predicted value, and critical success index of 99.61%, 99.73%, and 99.66%, respectively in detecting the ADHD automatically with ten-fold cross-validation. The model has provided an area under the curve of 100% while the detection rate of 99.87% and 99.73% has been obtained for ADHD and HC, respectively.

CONCLUSIONS

The model show that the interpretability and explainability of frontal region is highest compared to pre-frontal, central, parietal, occipital, and temporal regions. Our findings has provided important insight into the developed model which is highly reliable, robust, interpretable, and explainable for the clinicians to detect ADHD in children. Early and rapid ADHD diagnosis using robust explainable technologies may reduce the cost of treatment and lessen the number of patients undergoing lengthy diagnosis procedures.

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.

Characteristics of sleep spindles in school-aged children with attention-deficit/hyperactivity disorder

OBJECTIVE

Attention deficit/hyperactivity disorder (ADHD) is a complex disorder, characterized by different presentations with distinct cognitive and neurobiological characterizations. Here we aimed to investigate whether sleep spindle activity, which has been associated with brain maturation, may be a potential biomarker able to differentiate ADHD presentations in school-aged children (7-11 years).

METHOD

Spindle characteristics were extracted from overnight polysomnography in 74 children (27 ADHD-Inattentive [IQ = 96.04], 25 ADHD-hyperactive/impulsive [IQ = 98.9], and 22 ADHD-combined [IQ = 96.1]). We obtained data of the frontal (Fz) and parietal (Pz) derivations using a validated spindle detection algorithm.

RESULTS

Children with ADHD showed a higher number and density of slow compared to fast spindles which were more frequent in frontal area. No differences were observed among ADHD presentations for any spindle characteristics. Spindle frequency and density increased with age, indicating an age-dependent maturation of different sleep spindles. However, no associations between IQ and spindle characteristics were observed.

CONCLUSIONS

In children with ADHD the spindle characteristics evolve with age but sleep spindle activity does not seem to be a valid biomarker of ADHD phenotypes or general cognitive ability.

High-gamma oscillations as neurocorrelates of ADHD: A MEG crossover placebo-controlled study

Attention Deficit Hyperactive Disorder (ADHD) is a common neurobehavioral disorder with a significant and pervasive impact on patients' lives. Identifying neurophysiological correlates of ADHD is important for understanding its underlying mechanisms, as well as for improving clinical accuracy beyond cognitive and emotional factors. The present study focuses on finding a diagnostic stable neural correlate based on evaluating MEG resting state frequency bands. Twenty-two ADHD patients and 23 controls adults were blindly randomized to two methylphenidate/placebo evaluation days. On each evaluation day state anxiety was assessed, a 2N-back executive function task was performed, and resting state MEG brain activity was recorded at three timepoints. A frequency-based cluster analysis yielded higher high-gamma power for ADHD over posterior sensors and lower high-gamma power for ADHD over frontal-central sensors. These results were shown to be stable over three measurements, unaffected by methylphenidate treatment, and linked to cognitive accuracy and state anxiety. Furthermore, the differential high-gamma activity evidenced substantial ADHD diagnostic efficacy, comparable to the cognitive and emotional factors. These results indicate that resting state high-gamma activity is a promising, stable, valid and diagnostically-relevant neurocorrelate of ADHD. Due to the evolving understanding both in the cellular and network level of high-gamma oscillations, focusing future studies on this frequency band bears the potential for a better understanding of ADHD, thus advancing the specificity of the evaluation of the disorder and developing new tools for therapy.

The dynamics of theta-related pro-active control and response inhibition processes in AD(H)D

Impulsivity and deficits in response inhibition are hallmarks of attention-deficit(-hyperactivity) disorder (AD(H)D), can cause severe problems in daily functioning, and are thus of high clinical relevance. Traditionally, research to elucidate associated neural correlates has intensively, but also quite selectively examined mechanisms during response inhibition in various tasks. Doing so, in-between trial periods or periods prior to the response inhibition process, where no information relevant to inhibitory control is presented, have been neglected. Yet, these periods may nevertheless reveal relevant information. In the present study, using a case-control cross-sectional design, we take a more holistic approach, examining the inter-relation of pre-trial and within-trial periods in a Go/Nogo task with a focus on EEG theta band activity. Applying EEG beamforming methods, we show that the dynamics between pre-trial (pro-active) and within-trial (inhibition-related) control processes significantly differ between AD(H)D subtypes. We show that response inhibition, and differences between AD(H)D subtypes, exhibit distinct patterns of (at least) three factors: (i) strength of pre-trial (pro-active control) theta-band activity, (ii) the inter-relation of pro-active control and inhibition-relation theta band activity and (iii) the functional neuroanatomical region active during theta-related pro-active control processes. This multi-factorial pattern is captured by AD(H)D subtype clinical symptom clusters. The study provides a first hint that novel cognitive-neurophysiological facets of AD(H)D may be relevant to distinguish AD(H)D subtypes.

The Relationship between Carotid Doppler Ultrasound and EEG Metrics in Healthy Preschoolers and Adults

Despite widespread using electroencephalography (EEG) and Doppler ultrasound in pediatric neurology clinical practice, there are still no well-known correlations between these methods that could contribute to a better understanding of brain processes and development of neurological pathology. This study aims to reveal relationship between EEG and Doppler ultrasound methods. We compared two cohorts of adults and preschool children with no history of neurological or mental diseases. The data analysis included investigation of EEG and carotid blood flow indexes, which are significant in neurological diagnosis, as well as calculation of linear and non-linear EEG parameters and ratios between the systolic peak velocities of carotid arteries and carotid blood asymmetry. We have found age-dependent correlations between EEG and power Doppler ultrasound imaging (PDUI) data. Carotid blood flow asymmetry correlated with delta-rhythm power spectral density only in preschoolers. The ratios of blood flow velocities in the internal carotid arteries to those in the common carotid arteries correlated with higher peak alpha frequency and lower fractal dimension; moreover, they were associated with lower Epworth sleepiness scale scores. The study revealed significant correlations between EEG and PDUI imaging indexes, which are different for healthy children and adults. Despite the fact that the correlations were associated with non-clinical states such as overwork or stress, we assumed that the investigated parameters could be applicable for clinical trials.

The relationship between alpha asymmetry and ADHD depends on negative affect level and parenting practices

Atypical frontal alpha asymmetry is associated with the approach/withdrawal and affective processes implicated in many psychiatric disorders. Rightward alpha asymmetry, associated with high approach, is a putative endophenotype for attention deficit/hyperactivity disorder (ADHD). However, findings are inconsistent, likely because of a failure to consider emotional heterogeneity within the ADHD population. In addition, how this putative risk marker interacts with environmental factors known to increase symptom severity, such as parenting practices, has not been examined. The current study examined patterns of alpha asymmetry in a large sample of adolescents with and without ADHD, including the moderating role of negative affect and inconsistent discipline. Resting-state EEG was recorded from 169 well-characterized adolescents (nADHD = 79). Semi-structured clinical interviews and well-validated rating scales were used to create composites for negative affect and inconsistent discipline. The relationship between alpha asymmetry and ADHD diagnosis was moderated by negative affect. Right asymmetry was present only for those with ADHD and low levels of negative affect. In addition, greater right alpha asymmetry predicted severity of ADHD symptoms for those with the disorder, but only in the context of inconsistent parenting practices. Results confirm right alpha asymmetry is a possible endophenotype in ADHD but highlight the need to consider emotional heterogeneity and how biological risk interacts with child environment in order to fully characterize its relationship to disorder liability and severity.

Measuring Treatment Response in Pharmacological and Lifestyle Interventions Using Electroencephalography in ADHD: A Review

Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by inattention, hyperactivity, and/or impulsivity with associations to short- and long-term aversive life events. The exact etiology of the disorder is still unknown. ADHD is heterogeneous in symptomology and a single consistent, reliable biomarker has not been found. Quantitative electroencephalography (EEG) has been proposed as a potential way to differentiate those with ADHD from typically developing controls; however, the data on the diagnostic utility of this approach have been variable. Quantitative EEG has been employed in prognostic ways to assess differences in baseline spectral power profiles and pharmacological and nonpharmacological treatment effects on electrocortical activity within the ADHD population. The aim of this review is to summarize the literature investigating the degree of normalization of resting-state EEG profiles in individuals with ADHD through various interventions, including stimulant and nonstimulant medication, exercise, and diet.

Comparison between Concentration and Immersion Based on EEG Analysis

Concentration and immersion belong to a similar mental state in which a person is preoccupied with a particular task. In this study, we investigated a possibility of diagnosing two mental states with a subtle difference. Concentration and immersion states were induced to analyze the electroencephalography (EEG) changes during these states. Thirty-two college students in their 20s participated in the study. For concentration, subjects were asked to focus on a red dot at the center of a white screen, and for immersion they were asked to focus on playing a computer game. Relative to rest, Alpha waves decreased during concentration and immersion. Relative to rest, Theta waves decreased at almost all channels during concentration and, on the other hand, increased at all channels during immersion. Beta waves increased during concentration and immersion in the frontal and occipital lobes, with a higher increase in immersion. In the temporal lobe, Beta waves decreased during concentration and increased during immersion. In the central region, Beta waves decreased during concentration and immersion, and the decrease during immersion was larger. Such evident differences between the EEG results for concentration and immersion can imply diagnostic capabilities of various other mental states.