The Weak Link: Hypotonia in Infancy and Autism Early Identification

Predicting autism traits from baby wellness records: A machine learning approach

LAY ABSTRACT

Timely identification of autism spectrum conditions is a necessity to enable children to receive the most benefit from early interventions. Emerging technological advancements provide avenues for detecting subtle, early indicators of autism from routinely collected health information. This study tested a model that provides a likelihood score for autism diagnosis from baby wellness visit records collected during the first 2 years of life. It included records of 591,989 non-autistic children and 12,846 children with autism. The model identified two-thirds of the autism spectrum condition group (boys 63% and girls 66%). Sex-specific models had several predictive features in common. These included language development, fine motor skills, and social milestones from visits at 12-24 months, mother's age, and lower initial growth but higher last growth measurements. Parental concerns about development or hearing impairment were other predictors. The models differed in other growth measurements and birth parameters. These models can support the detection of early signs of autism in girls and boys by using information routinely recorded during the first 2 years of life.

A Prediction Model of Autism Spectrum Diagnosis from Well-Baby Electronic Data Using Machine Learning

Early detection of autism spectrum disorder (ASD) is crucial for timely intervention, yet diagnosis typically occurs after age three. This study aimed to develop a machine learning model to predict ASD diagnosis using infants' electronic health records obtained through a national screening program and evaluate its accuracy. A retrospective cohort study analyzed health records of 780,610 children, including 1163 with ASD diagnoses. Data encompassed birth parameters, growth metrics, developmental milestones, and familial and post-natal variables from routine wellness visits within the first two years. Using a gradient boosting model with 3-fold cross-validation, 100 parameters predicted ASD diagnosis with an average area under the ROC curve of 0.86 (SD < 0.002). Feature importance was quantified using the Shapley Additive explanation tool. The model identified a high-risk group with a 4.3-fold higher ASD incidence (0.006) compared to the cohort (0.001). Key predictors included failing six milestones in language, social, and fine motor domains during the second year, male gender, parental developmental concerns, non-nursing, older maternal age, lower gestational age, and atypical growth percentiles. Machine learning algorithms capitalizing on preventative care electronic health records can facilitate ASD screening considering complex relations between familial and birth factors, post-natal growth, developmental parameters, and parent concern.

Relationship and New Prospectives in Joint Hypermobility in Children with Autism Spectrum Disorder: Preliminary Data

Autism spectrum disorder (ASD) and joint hypermobility (JH) are considered two different etiological and clinical entities that most often appear in childhood. Despite growing increased research showing a co-occurrence for both conditions, a link between them is rarely established in clinical settings, and the relationship between ASD and JH has not so far been completely investigated in all age groups of ASD children. This preliminary study examined a cohort of 67 non-syndromic ASD children aged 2-18 years (sex ratio M:F = 12:1) showing different degrees of cognitive impairment and autism severity, using the Beighton scale and its revised version. A total of 63% of ASD patients aged 2-4 years and 73% of ASD patients aged ≥5 years presented significant scores of hypermobility. No significant correlation was found comparing total laxity score and cognitive assessments and severity of autistic symptomatology (p > 0.05). The results suggest that JH could be considered as a clinical characteristic of ASD patients and it needs to be assessed in order to schedule a better rehabilitation program.

Sleep Disordered Breathing in Children with Autism Spectrum Disorder: An In-Depth Review of Correlations and Complexities

Sleep-disordered breathing is a significant problem affecting the pediatric population. These conditions can affect sleep quality and children's overall health and well-being. Difficulties in social interaction, communication, and repetitive behavioral patterns characterize autism spectrum disorder. Sleep disturbances are common in children with ASD. This literature review aims to gather and analyze available studies on the relationship between SDB and children with autism spectrum disorder. We comprehensively searched the literature using major search engines (PubMed, Scopus, and Web of Science). After removing duplicates, we extracted a total of 96 records. We selected 19 studies for inclusion after a thorough title and abstract screening process. Seven articles were ultimately incorporated into this analysis. The research findings presented herein emphasize the substantial influence of sleep-disordered breathing on pediatric individuals diagnosed with autism spectrum disorder (ASD). These findings reveal a high incidence of SDB in children with ASD, emphasizing the importance of early diagnosis and specialized treatment. Obesity in this population further complicates matters, requiring focused weight management strategies. Surgical interventions, such as adenotonsillectomy, have shown promise in improving behavioral issues in children with ASD affected by OSA, regardless of their obesity status. However, more comprehensive studies are necessary to investigate the benefits of A&T treatment, specifically in children with ASD and OSA. The complex relationship between ASD, SDB, and other factors, such as joint hypermobility and muscle hypotonia, suggests a need for multidisciplinary treatment approaches. Physiotherapy can play a critical role in addressing these intricate health issues. Early sleep assessments and tailored weight management strategies are essential for timely diagnosis and intervention in children with ASD. Policy initiatives should support these efforts to enhance the overall well-being of this population. Further research is crucial to understand the complex causes of sleep disturbances in children with ASD and to develop effective interventions considering the multifaceted nature of these conditions.

Comorbidities Affecting Children with Autism Spectrum Disorder: A Retrospective Chart Review

Autism spectrum disorder (ASD) is a developmental disorder characterized by deficits in social interaction/communication, restricted interests, and repetitive behaviors. Recent discussions have emerged worldwide regarding the heterogeneity around presentation/etiology and comorbidities. This study aimed to determine the frequency and characteristics of comorbidities among children diagnosed with ASD in Manitoba and to evaluate differences in presentation between those with and without medical comorbidities. We conducted a retrospective chart review of >1900 electronic charts at the only publicly funded referral site for children ≤6 years requiring evaluation for ASD in Manitoba. All children aged 0-6 years diagnosed with ASD at this site between May 2016 and September 2021 were identified. χ2 and t-tests were used to compare groups. Of the total of 1858 children identified, 1452 (78.1%) were boys, 251 (13.5%) were prematurely born, and 539 (29.0%) had ≥1 medical comorbidity. Global developmental delay (GDD) was diagnosed in 428 (23.0%). The age of referral and diagnosis did not differ between groups. Comorbidities were more common among premature children (16.0% vs. 12.5%, p: 0.005) and children with comorbid GDD (34.9% vs. 18.2%, p < 0.001). Neurological comorbidities were most common (37.1%). No sex difference in the overall presence of comorbidities was found (boys = 77.1% vs. 78.5%, p: 0.518); however, girls had a higher incidence of neurological comorbidities, e.g., cerebral palsy, seizures, hypotonia (14.8% vs. 9.64%, p: 0.009), as well as genetic comorbidities (4.92% vs. 2.75%, p: 0.04). The high rates of associated neurological conditions, GDD, and prematurity add heterogeneity to this group leading to potential difficulties with prognosis and service allocation. Primary vs. secondary ASD can be a way of separating individuals based on relevant medical comorbidities.

Dysregulated phosphate metabolism in autism spectrum disorder: associations and insights for future research

Studies of autism spectrum disorder (ASD) related to exposure to toxic levels of dietary phosphate are lacking. Phosphate toxicity from dysregulated phosphate metabolism can negatively impact almost every major organ system of the body, including the central nervous system. The present paper used a grounded theory-literature review method to synthesise associations of dysregulated phosphate metabolism with the aetiology of ASD. Cell signalling in autism has been linked to an altered balance between phosphoinositide kinases, which phosphorylate proteins, and the counteracting effect of phosphatases in neuronal membranes. Glial cell overgrowth in the developing ASD brain can lead to disturbances in neuro-circuitry, neuroinflammation and immune responses which are potentially related to excessive inorganic phosphate. The rise in ASD prevalence has been suggested to originate in changes to the gut microbiome from increasing consumption of additives in processed food, including phosphate additives. Ketogenic diets and dietary patterns that eliminate casein also reduce phosphate intake, which may account for many of the suggested benefits of these diets in children with ASD. Dysregulated phosphate metabolism is causatively linked to comorbid conditions associated with ASD such as cancer, tuberous sclerosis, mitochondrial dysfunction, diabetes, epilepsy, obesity, chronic kidney disease, tauopathy, cardiovascular disease and bone mineral disorders. Associations and proposals presented in this paper offer novel insights and directions for future research linking the aetiology of ASD with dysregulated phosphate metabolism and phosphate toxicity from excessive dietary phosphorus intake.

Effects of Square-Stepping Exercise on Motor and Cognitive Skills in Autism Spectrum Disorder Children and Adolescents: A Study Protocol

Individuals with autism spectrum disorder (ASD) diagnoses present not only cognitive, emotional, communicative, and social challenges but also movement issues that affect their everyday activities, learning, and leisure. The use of the square-stepping exercise (SSE), a motor program initially created to strengthen the lower limbs of older adults, is spreading because of its advantages (e.g., balance and lower limb strength improvements). A study protocol to assess the SSE effects on motor, sensory, and cognitive skills in Spanish children and adolescents between 6 and 12 years old with ASD diagnoses is presented. A randomised clinical will be performed, recruiting 52 children and adolescents with ASD who will be distributed into two groups: an experimental (n = 26) and a control (n = 26) group. The SSE sessions will be held for 9 weeks (two times per week). The main variable will be balance, which will be measured with the Movement Assessment Battery for Children 2 (MABC2), and secondary outcomes will include sensory processing, attention, and executive functions. Assessments will be carried out before and at the end of the program implementation, including an additional follow up one month later. If this program obtains positive results, it should be implemented in different settings (schools, clinics, associations, etc.) to improve the quality of movement and development in children and adolescents with ASD, as it is an easy-to-use and structured tool.