No evidence of associations between ADHD and event-related brain potentials from a continuous performance task in a population-based sample of adolescent twins

Longitudinal investigation in children and adolescents with ADHD and healthy controls: A 2-year ERP study

Cross-sectional group comparisons have shown altered neurocognitive and neurophysiological profiles in individuals with attention-deficit/hyperactivity disorder (ADHD). We report a two-year longitudinal observational study of ADHD children and adolescents (N = 239) regarding ADHD symptoms, behavioral metrics, and event-related potentials (ERP) and compared them to healthy controls (N = 91). The participants were assessed up to five times with a cued Go/NoGo task while ERPs were recorded. We fitted the trajectories of our variables of interest with univariate and bivariate latent growth curve models. At baseline, the ADHD group had increased reaction time variability, higher number of omission and commission errors, and attenuated CNV and P3d amplitudes compared to controls. The task performance in terms of behavioral metrics improved in both groups over two years; however, with differential patterns: the decrease in reaction time and omission errors were stronger in the control group, and the reduction of commission errors was more substantial in the ADHD group. The cueP3, CNV, and N2d amplitudes changed slightly over two years, with negligible differences between both groups. Furthermore, the parent-rated symptom burden in the ADHD group decreased by 22 % (DSM-5-based questionnaire). We did not identify any associations between the changes in symptoms and the changes in the behavioral or neurophysiological metrics. The lack of association between the changes in symptoms and the behavioral or ERP metrics supports the trait liability hypothesis, which claims that the neurocognitive deficits are independent of symptom alleviation. Furthermore, the change in symptom burden was substantial, questioning the stability of the reported ADHD symptoms.

Longitudinal Analysis of Self-Reported Symptoms, Behavioral Measures, and Event-Related Potential Components of a Cued Go/NoGo Task in Adults With Attention-Deficit/Hyperactivity Disorder and Controls

This study characterizes a large sample of adults with attention-deficit/hyperactivity disorder (ADHD) and healthy controls regarding their task performance and neurophysiology; cross-sectionally and longitudinally. Self-reported symptoms, behavioral measures, and event-related potentials from a classical cued Go/NoGo task were used to outline the symptom burden, executive function deficits and neurophysiological features, and the associations between these domains. The study participants (N = 210 ADHD, N = 158 controls, age: 18–62 years) were assessed five (ADHD) or three (controls) times over two years. We describe cross-sectional and longitudinal group differences, and associations between symptom burden, and behavioral and event-related potential (ERP) components variables by latent growth curve models, including random slopes and intercepts. The ADHD group showed increased reaction time variability, increased commission and omission errors, and attenuated cueP3, CNV, N2d, and P3d amplitudes. We observed a decrease in self-reported symptoms in the ADHD group over the two years. The behavioral measures (reaction time variability, number of omission, and commission errors) did not change over time, whereas the cueP3, P3d, and N2d amplitude attenuated in both groups. There was no evidence for a robust association between symptom burden and behavioral or ERP measures. The changes in the ERP components with stable task performance, potentially indicate more efficient neuronal processing over the two years. Whether the lack of association between symptom burden and behavioral or ERP measures might be due to the low reliability of the ADHD assessment criteria, or the inappropriateness of the objective measures cannot be inferred.

Decoding of cognitive processes involved in the continuous performance task

Decoding of electroencephalogram brain representations is a powerful data driven technique to assess the stream of cognitive information processing. It could promote a more thorough understanding of cognitive control networks. For many years, the continuous performance task has been utilized to investigate impaired proactive and reactive cognitive functions. So far, mainly task performance and univariate electroencephalogram were involved in such investigations. In this study, we benefit from multi-variate pattern analysis of continuous performance task variations to provide a more complete spatio-temporal outline of information processing flow involved in sustained and transient attention and response preparation. Besides effects that are well in line with previous EEG research but could be described in more spatial and temporal detail by the used methods, our results could suggest the presence of a higher order feedback control system when expectations are violated. Such a feedback control is related to modulations of behavior both intra- and inter-individually.

Biomarker support for ADHD diagnosis based on Event Related Potentials and scores from an attention test

ADHD is a heterogeneous neurodevelopmental disorder associated with dysfunctions in several brain systems. Objective markers of brain dysfunction for clinical assessment are lacking. Many studies applying electroencephalography (EEG) and neuropsychological tests find significant differences between ADHD and controls, but the effect sizes (ES) are often too small for diagnostic purposes. This study aimed to compute a diagnostic index for ADHD by combining behavioral test scores from a cued visual go/no-go task and Event Related Potentials (ERPs). Sixty-one children (age 9-12 years) diagnosed with ADHD and 69 age- and gender-matched typically developing children (TDC) underwent EEG-recording while tested on a go/no-go task. Based on comparisons of ERP group-means and task-performance, variables that differed significantly between the groups with at least moderate ES were converted to a five points percentile scale and multiplied by the ES of the variable. The sum-scores of the variables constituted the diagnostic index. The index discriminated significantly between patients and TDC with a large ES. This index was applied to an independent sample (20 ADHD, 21 TDC), distinguishing the groups with an even larger ES. The diagnostic index described has the potential to support assessment. Further research establishing diagnostic indexes for differential diagnoses is needed.

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.

In Quest of Pathognomonic/Endophenotypic Markers of Attention Deficit Hyperactivity Disorder (ADHD): Potential of EEG-Based Frequency Analysis and ERPs to Better Detect, Prevent and Manage ADHD

Attention deficit hyperactivity disorder (ADHD) is a chronic heritable developmental delay psychiatric disorder requiring chronic management, characterized by inattention, hyperactivity, hyperkinectivity and impulsivity. Subjective clinical evaluation still remains crucial in its diagnosis. Discussed are two key aspects in the “characterizing ADHD” and on the quest for objective “pathognomonic/endophenotypic diagnostic markers of ADHD”. The first aspect briefly revolves around issues related to identification of pathognomonic/endophenotypic diagnostic markers in ADHD. Issues discussed include changes in ADHD definition, remission/persistence and overlapping-symptoms cum shared-heritability with its co-morbid cross-border mental disorders. The second aspect discussed is neurobiological and EEG-based studies on ADHD. Given the neurobiological and temporal aspects of ADHD symptoms the electroencephalograph (EEG) like NeuralScan by Medeia appears as an appropriate tool. The EEGs appropriateness is further enhanced when coupled with suitable behavior/cognitive/motor/psychological tasks/paradigms yielding EEG-based markers like event-related-potential (ERPs like P3 amplitudes and latency), reaction time variability (RTV), Theta:Beta ratio (TBR) and sensorimotor rhythm (SMR). At present, these markers could potentially help in the neurobiological characterization of ADHD and either help in identifying or lay the groundwork for identifying pathognomonic and/or endophenotypic EEG-based markers enabling its diagnosis, treatment and management.