Neural Dynamics for Facilitating ADHD Diagnosis in Preschoolers: Central and Parietal Delta Synchronization in the Kiddie Continuous Performance Test

Electroencephalogram-Based ConvMixer Architecture for Recognizing Attention Deficit Hyperactivity Disorder in Children

Attention deficit hyperactivity disorder (ADHD) is a neuro-developmental disorder that affects approximately 5-10% of school-aged children worldwide. Early diagnosis and intervention are essential to improve the quality of life of patients and their families. In this study, we propose ConvMixer-ECA, a novel deep learning architecture that combines ConvMixer with efficient channel attention (ECA) blocks for the accurate diagnosis of ADHD using electroencephalogram (EEG) signals. The model was trained and evaluated using EEG recordings from 60 healthy children and 61 children with ADHD. A series of experiments were conducted to evaluate the performance of the ConvMixer-ECA. The results showed that the ConvMixer-ECA performed well in ADHD recognition with 94.52% accuracy. The incorporation of attentional mechanisms, in particular ECA, improved the performance of ConvMixer; it outperformed other attention-based variants. In addition, ConvMixer-ECA outperformed state-of-the-art deep learning models including EEGNet, CNN, RNN, LSTM, and GRU. t-SNE visualization of the output of this model layer validated the effectiveness of ConvMixer-ECA in capturing the underlying patterns and features that separate ADHD from typically developing individuals through hierarchical feature learning. These outcomes demonstrate the potential of ConvMixer-ECA as a valuable tool to assist clinicians in the early diagnosis and intervention of ADHD in children.

Reduced recruitment of inhibitory control regions in very young children with ADHD during a modified Kiddie Continuous Performance Task: a fMRI study

Attention-Deficit/Hyperactivity Disorder (ADHD) symptom profiles are known to undergo changes throughout development, rendering the neurobiological assessment of ADHD challenging across different developmental stages. Particularly in young children (ages 4 to 7 years), measuring inhibitory control network activity in the brain has been a formidable task due to the lack of child-friendly functional Magnetic Resonance Imaging (fMRI) paradigms. This study aims to address these difficulties by focusing on measuring inhibitory control in very young children within the MRI environment. A total of 56 children diagnosed with ADHD and 78 typically developing (TD) 4-7-year-old children were examined using a modified version of the Kiddie-Continuous Performance Test (K-CPT) during BOLD fMRI to assess inhibitory control. We concurrently evaluated their performance on the established and standardized K-CPT outside the MRI scanner. Our findings suggest that the modified K-CPT effectively elicited robust and expected brain activity related to inhibitory control in both groups. Comparisons between the two groups revealed subtle differences in brain activity, primarily observed in regions associated with inhibitory control, such as the inferior frontal gyrus, anterior insula, dorsal striatum, medial pre-supplementary motor area (pre-SMA), and cingulate cortex. Notably, increased activity in the right anterior insula was associated with improved response time (RT) and reduced RT variability on the K-CPT administered outside the MRI environment, although this did not survive statistical correction for multiple comparisons. In conclusion, our study successfully overcame the challenges of measuring inhibitory control in very young children within the MRI environment by utilizing a modified K-CPT during BOLD fMRI. These findings shed light on the neurobiological correlates of inhibitory control in ADHD and TD children, provide valuable insights for understanding ADHD across development, and potentially inform ADHD diagnosis and intervention strategies. The research also highlights remaining challenges with task fMRI in very young clinical samples.

Classification of attention deficit/hyperactivity disorder based on EEG signals using a EEG-Transformer model∗

Objective. Attention-deficit/hyperactivity disorder (ADHD) is the most common neurodevelopmental disorder in adolescents that can seriously impair a person's attention function, cognitive processes, and learning ability. Currently, clinicians primarily diagnose patients based on the subjective assessments of the Diagnostic and Statistical Manual of Mental Disorders-5, which can lead to delayed diagnosis of ADHD and even misdiagnosis due to low diagnostic efficiency and lack of well-trained diagnostic experts. Deep learning of electroencephalogram (EEG) signals recorded from ADHD patients could provide an objective and accurate method to assist physicians in clinical diagnosis.Approach. This paper proposes the EEG-Transformer deep learning model, which is based on the attention mechanism in the traditional Transformer model, and can perform feature extraction and signal classification processing for the characteristics of EEG signals. A comprehensive comparison was made between the proposed transformer model and three existing convolutional neural network models.Main results. The results showed that the proposed EEG-Transformer model achieved an average accuracy of 95.85% and an average AUC value of 0.9926 with the fastest convergence speed, outperforming the other three models. The function and relationship of each module of the model are studied by ablation experiments. The model with optimal performance was identified by the optimization experiment.Significance. The EEG-Transformer model proposed in this paper can be used as an auxiliary tool for clinical diagnosis of ADHD, and at the same time provides a basic model for transferable learning in the field of EEG signal classification.

Deep-Learning-Based ADHD Classification Using Children's Skeleton Data Acquired through the ADHD Screening Game

The identification of attention deficit hyperactivity disorder (ADHD) in children, which is increasing every year worldwide, is very important for early diagnosis and treatment. However, since ADHD is not a simple disease that can be diagnosed with a simple test, doctors require a large period of time and substantial effort for accurate diagnosis and treatment. Currently, ADHD classification studies using various datasets and machine learning or deep learning algorithms are actively being conducted for the screening diagnosis of ADHD. However, there has been no study of ADHD classification using only skeleton data. It was hypothesized that the main symptoms of ADHD, such as distraction, hyperactivity, and impulsivity, could be differentiated through skeleton data. Thus, we devised a game system for the screening and diagnosis of children's ADHD and acquired children's skeleton data using five Azure Kinect units equipped with depth sensors, while the game was being played. The game for screening diagnosis involves a robot first travelling on a specific path, after which the child must remember the path the robot took and then follow it. The skeleton data used in this study were divided into two categories: standby data, obtained when a child waits while the robot demonstrates the path; and game data, obtained when a child plays the game. The acquired data were classified using the RNN series of GRU, RNN, and LSTM algorithms; a bidirectional layer; and a weighted cross-entropy loss function. Among these, an LSTM algorithm using a bidirectional layer and a weighted cross-entropy loss function obtained a classification accuracy of 97.82%.

Machine learning-based ABA treatment recommendation and personalization for autism spectrum disorder: an exploratory study

Autism spectrum is a brain development condition that impairs an individual's capacity to communicate socially and manifests through strict routines and obsessive-compulsive behavior. Applied behavior analysis (ABA) is the gold-standard treatment for autism spectrum disorder (ASD). However, as the number of ASD cases increases, there is a substantial shortage of licensed ABA practitioners, limiting the timely formulation, revision, and implementation of treatment plans and goals. Additionally, the subjectivity of the clinician and a lack of data-driven decision-making affect treatment quality. We address these obstacles by applying two machine learning algorithms to recommend and personalize ABA treatment goals for 29 study participants with ASD. The patient similarity and collaborative filtering methods predicted ABA treatment with an average accuracy of 81-84%, with a normalized discounted cumulative gain of 79-81% (NDCG) compared to clinician-prepared ABA treatment recommendations. Additionally, we assess the two models' treatment efficacy (TE) by measuring the percentage of recommended treatment goals mastered by the study participants. The proposed treatment recommendation and personalization strategy are generalizable to other intervention methods in addition to ABA and for other brain disorders. This study was registered as a clinical trial on November 5, 2020 with trial registration number CTRI/2020/11/028933.

Atypical functional connectivity during rest and task-related dynamic alteration in young children with attention deficit hyperactivity disorder: An analysis using the phase-locking value

AIM

The study investigated the electroencephalography (EEG) functional connectivity (FC) profiles during rest and tasks of young children with attention deficit hyperactivity disorder (ADHD) and typical development (TD).

METHODS

In total, 78 children (aged 5-7 years) were enrolled in this study; 43 of them were diagnosed with ADHD and 35 exhibited TD. Four FC metrics, coherence, phase-locking value (PLV), pairwise phase consistency, and phase lag index, were computed for feature selection to discriminate ADHD from TD.

RESULTS

The support vector machine classifier trained by phase-locking value (PLV) features yielded the best performance to differentiate the ADHD from the TD group and was used for further analysis. In comparing PLVs with the TD group at rest, the ADHD group exhibited significantly lower values on left intrahemispheric long interelectrode lower-alpha and beta as well as frontal interhemispheric beta frequency bands. However, the ADHD group showed higher values of central interhemispheric PLVs on the theta, higher-alpha, and beta bands. Regarding PLV alterations within resting and task conditions, left intrahemispheric long interelectrode beta PLVs declined from rest to task in the TD group, but the alterations did not differ in the ADHD group. Negative correlations were observed between frontal interhemispheric beta PLVs and the Disruptive Behavior Disorder Rating Scale as rated by teachers.

CONCLUSIONS

These results, which complement the findings of other sparse studies that have investigated task-related brain FC dynamics, particularly in young children with ADHD, can provide clinicians with significant and interpretable neural biomarkers for facilitating the diagnosis of ADHD.

Task-Rate-Related Neural Dynamics Using Wireless EEG to Assist Diagnosis and Intervention Planning for Preschoolers with ADHD Exhibiting Heterogeneous Cognitive Proficiency

This study used a wireless EEG system to investigate neural dynamics in preschoolers with ADHD who exhibited varying cognitive proficiency pertaining to working memory and processing speed abilities. Preschoolers with ADHD exhibiting high cognitive proficiency (ADHD-H, n = 24), those with ADHD exhibiting low cognitive proficiency (ADHD-L, n = 18), and preschoolers with typical development (TD, n = 31) underwent the Conners’ Kiddie Continuous Performance Test and wireless EEG recording under different conditions (rest, slow-rate, and fast-rate task). In the slow-rate task condition, compared with the TD group, the ADHD-H group manifested higher delta and lower beta power in the central region, while the ADHD-L group manifested higher parietal delta power. In the fast-rate task condition, in the parietal region, ADHD-L manifested higher delta power than those in the other two groups (ADHD-H and TD); additionally, ADHD-L manifested higher theta as well as lower alpha and beta power than those with ADHD-H. Unlike those in the TD group, the delta power of both ADHD groups was enhanced in shifting from rest to task conditions. These findings suggest that task-rate-related neural dynamics contain specific neural biomarkers to assist clinical planning for ADHD in preschoolers with heterogeneous cognitive proficiency. The novel wireless EEG system used was convenient and highly suitable for clinical application.