Comparison of the K-WISC-IV profiles of boys with autism spectrum disorder and attention-deficit/hyperactivity disorder

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.

Surgical treatment of interhemispheric arachnoid cysts

OBJECTIVE

In children, interhemispheric arachnoid cysts (IHACs) are rare lesions often associated with corpus callosum dysgenesis. It is still controversial about surgical treatments for IHACs. We aim to report our experience with pediatric IHAC patients and evaluate surgical courses and neurological developments.

METHODS

Pediatric IHACs treated between 2001 and 2021 were reviewed retrospectively. IHAC was observed until they represented rapid cyst enlargement or neurological symptoms. Cyst fenestration was done by microscope or endoscope, depending on the IHAC's location. Cyst size and corpus callosum dysgenesis were evaluated with neuroimaging. Neurological development was assessed from medical records at the last follow-up.

RESULTS

Fifteen children received cyst fenestration surgery (mean age 11.4 months). Eleven patients (73.3%) under observation showed rapid cyst enlargement in a short period (median 5 months). Cysto-ventriculostomy (CVS) and cysto-cisternostomy (CCS) regressed the cyst size significantly (p = 0.003). The median follow-up duration was 51 months (range 14-178 months). Corpus callosum dysgenesis was observed in eleven patients (73.3%, complete = 5, partial = 6). Among eight patients (53.3%) having developmental delay, five patients (33.3%) showed speech delay, including one patient with intractable seizures.

CONCLUSION

Pediatric IHACs frequently present within 1 year after birth, with rapid cyst enlargement. CVS and CCS were effective in regressing the cyst size. Corpus callosum dysgenesis accompanied by IHAC might have a risk of language achievement; however, development delay could rely on multifactorial features, such as epilepsy or other brain anomalies.

Unrecognized comorbid autism spectrum disorder in children initially diagnosed with only attention deficit hyperactivity disorder

The present study examined the prevalence of autism spectrum disorder (ASD) in intellectually capable children with attention deficit hyperactivity disorder (ADHD). Retrospective chart review on 103 children (mean age= 7.83 ± 1.72 years female=15.53%), without intellectual disability, who were diagnosed with only ADHD were done. Among the 103 children 27 children (26.21%) were later co-diagnosed with ASD. The results of the present study provide helpful insights in accurate recognition of co-occurring ASD in intellectually capable children diagnosed with ADHD. The potential for the coexistence of ASD should always be given careful consideration when examining children with ADHD.

Neuropsychological Profile, Emotional/Behavioral Problems, and Parental Stress in Children with Neurodevelopmental Disorders

Background: The aim of our study was to trace a specific neuropsychological profile, to investigate emotional-behavioral problems and parental stress in children with Autism Spectrum Disorder Level 1/High functioning (ASD-HF), Specific Learning Disorders (SLD) and Attention Deficit/Hyperactivity Disorder (ADHD) disorders and to highlight similarities and differences among the three groups. Methods: We retrospectively collected the data from a total of 62 subjects with ASD-HF (n = 19) ADHD (n = 21), SLD (n = 22) and 20 typical development. All the participants underwent neuropsychological standardized test for the evaluation of cognitive profile (Wechsler Intelligence Scale for Children Fourth Edition—WISC-IV), behavioral and emotional problems (Child Behavior CheckList CBCL), and parental stress (Parental Stress Index Short Form—PSI-SF). The scores of the ASD-HF, ADHD, and SLD groups were compared using non-parametric statistic methods (Kruskall–Wallis H test and U Mann–Whitney for post-hoc analysis). Results: The ASD-HF group were significantly higher in all areas of the WISC-IV than the other two clinical groups. The SLD group performed significantly lower than ASD-HF in Working Memory Index. The SLD group showed lower scores on the somatic problems subscale than the other two groups. In the Difficult Child subscale of the PSI-SF, parents of ADHD children scored lower than the mothers of SLD subjects and higher than the fathers of SLD subjects. In all three groups there are specific deficiencies compared to the control group in the cognitive profile, behavioral and emotional problems, and parental stress. Conclusions: Our comparative analysis highlighted similarities and differences in three groups of children with different neurodevelopmental disorders, helping to better define cognitive, behavioral, and emotional characteristics of these children and parental stress of their parents.

A Developmental Profile of Children With Autism Spectrum Disorder in China Using the Griffiths Mental Development Scales

The purpose of this study was to profile the mental development of children aged 18 to 96 months with autism spectrum disorder (ASD) using the Chinese version of the Griffiths Mental Development Scales (GMDS), and to explore the relationships between developmental levels and ASD severity, the sex of the child and the age of ASD diagnosis. Children with ASD (n = 398; 337 boys, 61 girls) were recruited and ASD severity evaluated using the Autism Behavior Checklist and the Childhood Autism Rating Scale, while the GMDS was used to evaluate the children's mental development. Study participants were divided into groups according to GMDS general and subscale quotients, ASD severity, sex, and age. The majority of groups divided according to the GMDS quotients exhibited an unbalanced distribution in respect of the six domains of the GMDS and there were significant differences within the six subscale quotients. Autism severity, sex and age had significant effects on the overall level of development of autistic children. The quotients recorded for the children with more severe ASD were significantly lower than those for the children with less severe ASD. A markedly higher proportion of developmental delay was recorded for girls than boys in relation to the performance subscale. The locomotor quotient decreased in line with age at diagnosis, while autism severity and age had significant effects on the general and subscale quotients and sex had a significant effect on performance quotient. Children with ASD exhibit an uneven cognitive development profile, and their overall developmental levels are affected by autism severity, sex and age. Specific cognitive domains differ according to sex in children with ASD. Locomotor skills tend to decrease according to the age at diagnosis for autistic children aged 18 to 84 months. Autism severity and age are also associated with the level of functioning in different cognitive areas. These findings contribute to define the cognitive developmental profiles of children with ASD.