Intellectual Profiles in Children With ADHD and Comorbid Learning and Motor Disorders

Prediction of attention deficit hyperactivity disorder based on explainable artificial intelligence

Accurate assessment of Attention Deficit Hyperactivity Disorder (ADHD) is crucial for the effective treatment of affected individuals. Traditionally, psychometric tests such as the WISC-IV have been utilized to gather evidence and identify patterns or factors contributing to ADHD diagnosis. However, in recent years, the use of machine learning (ML) models in conjunction with post-hoc eXplainable Artificial Intelligence (XAI) techniques has improved our ability to make precise predictions and provide transparent explanations. The objective of this study is twofold: firstly, to predict the likelihood of an individual receiving an ADHD diagnosis using ML algorithms, and secondly, to offer interpretable insights into the decision-making process of the ML model. The dataset under scrutiny comprises 694 cases collected over the past decade in Spain, including information on age, gender, and WISC-IV test scores. The outcome variable is the professional diagnosis. Diverse ML algorithms representing various learning styles were rigorously evaluated through a stratified 10-fold cross-validation, with performance assessed using key metrics, including accuracy, area under the receiver operating characteristic curve, sensitivity, and specificity. Models were compared using both the full set of initial features and a well-suited wrapper-type feature selection algorithm (Boruta). Following the identification of the most suitable model, Shapley additive values were computed to assign weights to each predictor based on their additive contribution to the outcome and to elucidate the predictions. Strikingly, a reduced set of 8 out of the initial 20 variables produced results comparable to using the full feature set. Among the ML models tested, the Random Forest algorithm outperformed others on most metrics (ACC = 0.90, AUC = 0.94, Sensitivity = 0.91, Specificity = 0.92). Notably, the principal predictors, ranked by importance, included GAI - CPI, WMI, CPI, PSI, VCI, WMI - PSI, PRI, and LN. Individual case examples exhibit variations in predictions depending on unique characteristics, including instances of false positives and negatives. Our ML model adeptly predicted ADHD diagnoses in 90% of cases, with potential for further enhancement by expanding our database. Furthermore, the use of XAI techniques enables the elucidation of salient factors in individual cases, thereby aiding inexperienced professionals in the diagnostic process and facilitating comparison with expert assessments. It is important to note that this tool is designed to support the ADHD diagnostic process, where the medical professional always has the final say in decision-making.

Measurement Invariance of the WISC-V across a Clinical Sample of Children and Adolescents with ADHD and a Matched Control Group

Measurement invariance of the Wechsler Intelligence Scale for Children, Fifth Edition (WISC-V) 10-primary subtest battery was analyzed across a group of children and adolescents with ADHD (n = 91) and a control group (n = 91) matched by sex, age, migration background, and parental education or type of school. First, confirmatory factor analyses (CFAs) were performed to establish the model fit for the WISC-V second-order five-factor model in each group. A sufficiently good fit of the model was found for the data in both groups. Subsequently, multigroup confirmatory factor analyses (MGCFAs) were conducted to test for measurement invariance across the ADHD and control group. Results of these analyses indicated configural and metric invariance but did not support full scalar invariance. However, after relaxing equality constraints on the Vocabulary (VC), Digit Span (DS), Coding (CD), Symbol Search (SS), and Picture Span (PS) subtest intercepts as well as on the intercepts of the first-order factors Working Memory (WM) and Processing Speed (PS), partial scalar invariance could be obtained. Furthermore, model-based reliability coefficients indicated that the WISC-V provides a more precise measurement of general intelligence (e.g., represented by the Full-Scale IQ, FSIQ) than it does for cognitive subdomains (e.g., represented by the WISC-V indexes). Group comparisons revealed that the ADHD group scored significantly lower than the control group on four primary subtests, thus achieving significantly lower scores on the corresponding primary indexes and the FSIQ. Given that measurement invariance across the ADHD and the control group could not be fully confirmed for the German WISC-V, clinical interpretations based on the WISC-V primary indexes are limited and should only be made with great caution regarding the cognitive profiles of children and adolescents with ADHD.

Cognition and maths in children with Attention-Deficit/Hyperactivity disorder with and without co-occurring movement difficulties

BACKGROUND

Movement difficulties are common in ADHD, however, the implications of their co-occurrences on cognitive and maths performance is unknown.

AIMS

This study set out to examine whether cognitive and maths performance of children with high ADHD symptoms differs depending on the co-occurrence of movement difficulties given evidence that weaker visuospatial processing, known to be important for maths performance, differentiates ADHD and DCD. We also aimed to examine whether relationships between cognition and maths in ADHD differs depending on co-occurring movement difficulties.

METHODS

Participants were 43 drug naïve children between 6 and 12 years old (M = 101.53 months SD = 19.58). The ADHD-only group (n = 18) included children with high ADHD scores, and those in the ADHD+DCD group (n = 25) concurrently had high movement difficulty scores. All completed executive function and memory, including 2 visuo-spatial memory tasks from the CANTAB battery and Mathematics Problem Solving, Numeracy, and Maths Fluency tasks from the WIAT-III and specific factual, conceptual, and procedural maths component tasks.

RESULTS

Children in the ADHD+DCD group scored significantly lower on visuospatial working memory (WM) capacity, than those in the ADHD-only group. Both groups were comparable on all other cognitive assessments of executive functions, memory, and processing speed. The groups did not differ in their maths attainment scores, nor on more specific maths skills. Comparison of the correlations between cognitive processes and maths revealed that the association between visuospatial WM updating and procedural skill efficiency was stronger for the ADHD-only group. Moreover, associations between visuospatial WM and maths problem solving attainment were stronger in the ADHD+DCD group.

CONCLUSIONS

Despite similarities in maths performance, children with ADHD+DCD could be distinguished by lower visuospatial WM. Differential associations with some of the maths domain implicate recruitment of different cognitive processes for some aspects of maths. This distinction can be particularly useful for conceptualising cognitive characteristics of different clinical groups and understanding cognitive pathways of maths difficulties. Implications for interventions are discussed.

Working Memory and Manual Dexterity in Dyslexic Children: A Systematic Review and Meta-Analysis

Dyslexic children have impairments in working memory and manual dexterity. Studies have shown that when cognitive development has deficits, motor development is often impaired, indicating a strong interconnection between both domains, and the possibility of interference with each other's proper functioning. Thus, a new literature review is necessary to understand which components of working memory and manual dexterity are affected in dyslexic children and the possible relationship between them. This review aimed to perform a systematic review and meta-analysis to analyze both skills in dyslexic children. The protocol was carried out according to the criteria established by PRISMA being registered at PROSPERO under number CRD 42021238901. Six literature databases were searched to locate studies published between 2001 and 2021: EMBASE, ERIC, ISI Web of Science, PubMed, PsycINFO, and Scopus. 21 studies met the inclusion criteria. The findings suggest that dyslexic children have significantly poorer visuospatial and verbal working memory with more impairments in the phonological loop. No significant differences were found in manual dexterity.

The structure, profile, and diagnostic significance of intelligence in children with ADHD are impressively similar to those of children with a specific learning disorder

This study examines the structure, profile, and diagnostic significance of intelligence in a group of 948 children diagnosed with attention deficit/hyperactivity disorder (ADHD) assessed with the WISC-IV and compared with children with specific learning disorders (SLDs) and with typically developing children. Based on four indexes, the WISC-IV configuration found in TD resulted applicable to ADHD, but with generally lower loadings on g. The Perceptual Reasoning and Verbal Comprehension indexes not only had higher loadings compared to the other two indexes but also represented the relative strengths of children with ADHD, as previously observed for children with SLD. In fact, the WISC pattern could be successfully used for discriminating between ADHD and TD, but not between ADHD and SLD. The latter result was not due to a co-occurrence of a learning disorder because the presence or absence of an associated diagnosis of SLD negligibly affected the pattern observed in ADHD. We concluded that the characteristics of intelligence in children with ADHD can be relevant for assessing this disorder, and that ADHD and SLDs share largely similar underlying cognitive features.

Cognitive, perceptual, and motor profiles of school-aged children with developmental coordination disorder

Developmental coordination disorder (DCD) is a heterogeneous condition. Besides motor impairments, children with DCD often exhibit poor visual perceptual skills and executive functions. This study aimed to characterize the motor, perceptual, and cognitive profiles of children with DCD at the group level and in terms of subtypes. A total of 50 children with DCD and 31 typically developing (TD) peers (7–11 years old) underwent a comprehensive neuropsychological (15 tests) and motor (three subscales of the Movement Assessment Battery for Children-2) assessment. The percentage of children with DCD showing impairments in each measurement was first described. Hierarchical agglomerative and K-means iterative partitioning clustering analyses were then performed to distinguish the subtypes present among the complete sample of children (DCD and TD) in a data-driven way. Moderate to large percentages of children with DCD showed impaired executive functions (92%) and praxis (meaningless gestures and postures, 68%), as well as attentional (52%), visual perceptual (46%), and visuomotor (36%) skills. Clustering analyses identified five subtypes, four of them mainly consisting of children with DCD and one of TD children. These subtypes were characterized by: (i) generalized impairments (8 children with DCD), (ii) impaired manual dexterity, poor balance (static/dynamic), planning, and alertness (15 DCD and 1 TD child), (iii) impaired manual dexterity, cognitive inhibition, and poor visual perception (11 children with DCD), (iv) impaired manual dexterity and cognitive inhibition (15 DCD and 5 TD children), and (v) no impairment (25 TD and 1 child with DCD). Besides subtle differences, the motor and praxis measures did not enable to discriminate between the four subtypes of children with DCD. The subtypes were, however, characterized by distinct perceptual or cognitive impairments. These results highlight the importance of assessing exhaustively the perceptual and cognitive skills of children with DCD.

Interpersonal Negotiation Skills in ADHD

Social interaction difficulties are amongst the most prevalent and pervasive adverse outcomes for children and adolescents with ADHD. Problem-solving strategies are impaired in affected individuals, according to the literature. This study aimed to investigate the social problem-solving skills of children and adolescents with and without ADHD, using objective quantitative measures provided by the Interpersonal Negotiation Strategies Interview (INSI). Because verbal communication skills and working memory may be impaired in ADHD, we investigated their contribution to the performance. Forty-three children and adolescents with ADHD and 27 clinical controls with clinical diagnoses other than ADHD completed the INSI along with measures of verbal communication skills (Verbal Comprehension Index [VCI]): Similarities, Vocabulary and Comprehension subtests from the Wechsler Battery, visual (Corsi Blocks) and verbal (Digit Span) working memory tasks. Groups performed similarly on measures of intellectual functioning, working memory, and verbal communication. For the entire sample, VCI scores were positively correlated with INSI performance scores. The ADHD group performed worse on the INSI than the clinical control group. Linear regression analysis showed that inattention and hyperactivity/impulsivity levels and Similarities predicted INSI's performance. Our findings indicate that interpersonal negotiation difficulties in ADHD are related to DSM-5 defining symptoms of the disorder.

Cognitive Profiles in the WISC-V of Children with ADHD and Specific Learning Disorders

Attention Deficit Hyperactivity Disorder (ADHD) has a high comorbidity with specific learning disorders (SLD). Children with ADHD and children with SLD show specific cognitive deficits. This study aims to examine similarities and differences between cognitive profiles of children with ADHD + SLD, children with SLD only, and a control group to find out whether specific or shared deficits can be identified for the groups. We compared the WISC-V profiles of 62 children with ADHD and SLD (19 girls, M-age = 10.44; SD = 2.44), 35 children with SLD (13 girls, M-age = 10.21; SD = 2.11) and 62 control children without ADHD or SLD (19 girls, M-age = 10.42; SD = 2.39). The ADHD + SLD group performed worse than the control group in the WISC-V indices WMI, PSI, FSIQ, AWMI, CPI and worse than the SLD group in these indices and the VCI, NVI and GAI. Therefore, compared to children with SLD, children with ADHD + SLD did not show specific impairments in any particular cognitive domain but rather non-specific impairment in almost all indices. Hence, the WISC-V is suited to depict the cognitive strength and weaknesses of an individual child as a basis for targeted intervention.

[Intellectual characteristics of children with attention deficit hyperactivity disorder and developmental dyslexia]

OBJECTIVE

To study the intellectual characteristics of children with attention deficit hyperactivity disorder (ADHD) and developmental dyslexia (DD).

METHODS

A total of 55 children with ADHD and DD (ADHD+DD group), 150 children with ADHD alone (ADHD group), and 22 children with DD alone (DD group) were enrolled as subjects. Wechsler Intelligence Scale for Children-Fourth Edition (WISC-IV) was used to evaluate and compare intellectual characteristics among the three groups.

RESULTS

There were significant differences in the scores of full-scale intelligence quotient (FSIQ), verbal comprehension index, perceptual reasoning index, and working memory index among the three groups (P < 0.05):the ADHD+DD group had significantly lower scores of FSIQ, verbal comprehension index, perceptual reasoning index, and working memory index than the ADHD group, as well as a significantly lower FSIQ score than the DD group. A comparison of the 10 core subtests in WISC-IV showed that compared with the ADHD group, the ADHD+DD group had significantly lower scores of similarities, vocabulary, comprehension, recitation, picture concepts, matrix reasoning, and letter-number sequencing (P < 0.05). Compared with the DD group, the ADHD+DD group had significantly lower scores of vocabulary, similarities, picture concepts, matrix reasoning, and recitation (P < 0.05).

CONCLUSIONS

Compared with the children with ADHD alone, the children with ADHD and DD have more severe impairment of FSIQ, verbal comprehension, perceptual reasoning, and working memory, and therefore, it is suggested to enhance the training on similarities, vocabulary, matrix reasoning, picture concepts, and recitation for children with ADHD and DD in clinical practice.

Social Cognition in Children With ADHD

Objective: Despite evidence of social skill deficits in children with ADHD, there is no consensus regarding a social cognitive profile and whether these skills predict behavior. Therefore, a comprehensive battery was used to investigate the relationship between social cognition and behavioral functioning. Method: Children ages 7 to 13 with ADHD (n = 25) and controls (n = 25) completed tests assessing social cognitive domains (affect recognition and theory of mind [ToM]). Parents completed measures of social cognition (pragmatic language ability and empathy), behavioral symptoms, and adaptive functioning. Results: Children with ADHD performed significantly worse on measures of cognitive ToM and affect recognition and received lower ratings of pragmatic language and cognitive empathy than typically developing peers. These domains, particularly pragmatic language, predicted parent ratings of problematic and adaptive behaviors. Conclusion: Results establish a relationship between specific social cognitive abilities and daily functioning, which has implications for treatment.

IQ and Sensory Symptom Severity Best Predict Motor Ability in Children With and Without Autism Spectrum Disorder

Motor challenges are commonly reported in autism spectrum disorder (ASD). Yet, there is substantial heterogeneity in motor ability within ASD, and it is unknown what behavioral characteristics best explain individual differences in motor ability in ASD and related conditions. This observational study examined motor ability as a function of sensory features, attention deficit/hyperactivity symptoms, ASD symptoms, and IQ in 110 children with ASD, typical development, or an intermediate behavioral profile. While motor challenges were more prevalent in the ASD group compared to other groups, sensory symptom severity and IQ across all individuals best predicted motor performance above-and-beyond group status. Therefore, motor challenges may be best characterized by individual variation in sensory features and cognitive abilities rather than diagnostic group.

ADHD subtype-specific cognitive correlates and association with self-esteem: a quantitative difference

BACKGROUND

Attention-deficit hyperactivity disorder (ADHD) is a major neurodevelopmental disorder with heterogeneous symptoms, subtypes, and cognitive deficits. Cognitive deficits are central to ADHD pathophysiology and one potential source of heterogeneity in ADHD. Subtype-specific cognitive correlates are not, however, well-studied. We explored cognitive correlates of ADHD subtypes based on the Wechsler Intelligence Scale for Children (WISC-IV) scores. We also assessed subtype-specific self-esteem rating in ADHD subtypes and explored its association with cognitive correlates.

METHODS

One hundred thirty-nine children with ADHD (80.6% boy, 19.4% girl) were categorized into the predominantly "hyperactive (ADHD-H)", "inattentive (ADHD-I)" and "combined (ADHD-C)" subtype based on their symptoms and scores on the Kiddie Schedule for Affective Disorders and Schizophrenia (K-SADS-PL) and Conners Parent-Rating Scale (CPRS-RS). They were then individually administrated the WISC-IV and completed a self-esteem inventory. Group differences in the WISC-IV indices and their predictability in discriminating ADHD subtypes were analyzed.

RESULTS

We found a quantitative differentiation of cognitive abilities among ADHD subtypes with "working memory" as the most compromised cognitive domain. ADHD-I had the poorest cognitive profile while ADHD-H scored highest in all cognitive domains. Importantly, cognitive abilities were negatively correlated with inattention and positively correlated with hyperactive symptoms. Moreover, self-esteem ratings were positively correlated with the cognitive domains and were rated differently based on the subtypes. ADHD-H, with the highest cognitive strength, reported the highest level of self-esteem among all subtypes.

CONCLUSIONS

ADHD subtype-specific symptoms, cognitive deficits, and self-esteem problems should be considered for precise diagnosis and effective and personalized treatment in ADHD in light of further supporting evidence and assessments. Cognitive interventions might be more compatible with and effective in inattentive and combined subtypes of ADHD. Working memory improving-based interventions can benefit all ADHD subtypes. A supportive educational system in school and providing adjunct supportive interventions should be considered for children with ADHD as well.

WISC-III Cognitive Profiles in Children with ADHD: Specific Cognitive Impairments and Diagnostic Utility

This study aimed to investigate the presence of specific cognitive impairments and the diagnostic utility of the WISC-III in children with ADHD. Ninety-eight children with ADHD and 81 children without ADHD matched by age and gender (control group), between the ages of 6 and 12 years, participated in the study. Children with ADHD revealed the most pronounced deficits in the subtests tapping working memory and processing speed. Freedom from Distractibility was the cognitive profile most impaired and that showed the highest diagnostic accuracy to discriminate children with ADHD. The optimal cutoff scores of the most common WISC-III cognitive profiles revealed greater diagnostic accuracy than the traditional approach of full or partial profiles. Taken together, these results suggested that in the context of a comprehensive psychological assessment, the WISC may provide knowledge about the specific cognitive strengths and weaknesses that characterize this disorder and may be useful in the decision-making process relative to ADHD diagnosis.

Investigating the Impact of Cognitive Load and Motivation on Response Control in Relation to Delay Discounting in Children with ADHD

Attention-deficit/hyperactivity disorder (ADHD) is characterized by deficits in impulse control across a range of behaviors, from simple actions to those involving complex decision-making (e.g., preference for smaller-sooner versus larger later rewards). This study investigated whether changes in motor response control with increased cognitive load and motivational contingencies are associated with decision-making in the form of delay discounting among 8-12 year old children with and without ADHD. Children with ADHD (n = 26; 8 girls) and typically developing controls (n = 40; 11 girls) completed a standard go/no-go (GNG) task, a GNG task with motivational contingencies, a GNG task with increased cognitive load, and two measures of delay discounting: a real-time task in which the delays and immediately consumable rewards are experienced in real-time, and a classic task involving choices about money at longer delays. Children with ADHD, particularly girls, exhibited greater delay discounting than controls during the real-time discounting task, whereas diagnostic groups did not significantly differ on the classic discounting task. The effect of cognitive load on response control was uniquely associated with greater discounting on the real-time task for children with ADHD, but not for control children. The effect of motivational contingencies on response control was not significantly associated with delay discounting for either diagnostic group. The findings from this study help to inform our understanding of the factors that influence deficient self-control in ADHD, suggesting that impairments in cognitive control may contribute to greater delay discounting in ADHD.

Increased Delay Discounting on a Novel Real-Time Task among Girls, but not Boys, with ADHD

The aim of this study was to examine delay discounting in girls and boys with ADHD-Combined type (ADHD-C) relative to typically developing (TD) children on two tasks that differ in the extent to which the rewards and delays were experienced by participants. Children ages 8-12 years with ADHD-C (n=65; 19 girls) and TD controls (n=55; 15 girls) completed two delay discounting tasks involving a series of choices between smaller, immediate and larger, delayed rewards. The classic delay discounting task involved choices about money at delays of 1-90 days and only some of the outcomes were actually experienced by the participants. The novel real-time discounting task involved choices about an immediately consumable reward (playing a preferred game) at delays of 25-100 s, all of which were actually experienced by participants. Participants also provided subjective ratings of how much they liked playing the game and waiting to play. Girls with ADHD-C displayed greater delay discounting compared to boys with ADHD-C and TD girls and boys on the real-time discounting task. Diagnostic group differences were not evident on the classic discounting task. In addition, children with ADHD-C reported wanting to play the game more and liking waiting to play the game less than TD children. This novel demonstration of greater delay discounting among girls with ADHD-C on a discounting task in which the rewards are immediately consumable and the delays are experienced in real-time informs our understanding of sex differences and motivational processes in children with ADHD. (JINS, 2016, 22, 12-23).