Deviations from Typical Developmental Trajectories Detectable at 9 Months of Age in Low Risk Children Later Diagnosed with Autism Spectrum Disorder

Early developmental milestone clusters of autistic children based on electronic health records

Autistic children vary in symptoms, co-morbidities, and response to interventions. This study aimed to identify clusters of autistic children with a distinct pattern of attaining early developmental milestones (EDMs). The clustering of 5836 autistic children was based on the attainment of 43 gross motor, fine motor, language, and social developmental milestones during the first 3 years of life as recorded in baby wellness visits. K-means cluster analysis detected four EDM clusters: mild (n = 1686); moderate (n = 1691); severe (n = 2265); and global (n = 194). The most prominent cluster differences were in the language domain. The global cluster showed earlier and greater developmental delay across domains, unique early gross motor delays, and more were born preterm via cesarean section. The severe cluster had poor language development prominently in the second year of life, and later fine motor delays. Moderate cluster had mainly language delays in the third year of life. The mild cluster mostly passed milestones. EDM clusters differed demographically, with higher socioeconomic status in mild cluster and lowest in global cluster. However, the severe cluster had more immigrant and non-Jewish mothers followed by the moderate cluster. The rates of parental concerns and provider developmental referrals were significantly higher in the global, followed by the severe, moderate, and mild EDM clusters. Autistic children's language and motor delay in the first 3 years can be grouped by common magnitude and onset profiles as distinct groups that may link to specific etiologies (like prematurity or genetics) and specific intervention programs. Early autism screening should be tailored to these different developmental profiles.

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.

Altered Developmental Trajectory in Male and Female Rats in a Prenatal Valproic Acid Exposure Model of Autism Spectrum Disorder

Early motor and sensory developmental delays precede Autism Spectrum Disorder (ASD) diagnosis and may serve as early indicators of ASD. The literature on sensorimotor development in animal models is sparse, male centered, and has mixed findings. We characterized early development in a prenatal valproic acid (VPA) model of ASD and found sex-specific developmental delays in VPA rats. We created a developmental composite score combining 15 test readouts, yielding a reliable gestalt measure spanning physical, sensory, and motor development, that effectively discriminated between VPA and control groups. Considering the heterogeneity in ASD phenotype, the developmental composite offers a robust metric that can enable comparison across different animal models of ASD and can serve as an outcome measure for early intervention studies.

Association Between Early Developmental Milestones and Autism Spectrum Disorder

Early diagnosis and treatment of autism spectrum disorder (ASD) has been shown to lead to better prognosis. Here, we examined the association of commonly measured early developmental milestones (DMs) with later diagnosis of ASD. We conducted a case-control study of 280 children with ASD (cases) and 560 typically developed children (controls) matched to cases by date of birth, sex, and ethnicity in a control/case ratio of 2:1. Both cases and controls were ascertained from all children whose development was monitored at mother-child health clinics (MCHCs) in southern Israel. DM failure rates during the first 18 months of life in three developmental categories (motor, social, and verbal) were compared between cases and controls. Conditional logistic regression models were used to assess the independent association of specific DMs with the risk of ASD, while adjusting for demographic and birth characteristics.Significant case-control differences in DM failure rates were observed as early as 3 months of age (p < 0.001), and these differences increased with age. Specifically, cases were 2.4 times more likely to fail ≥ 1 DM at 3 months (aOR = 2.39; 95%CI = 1.41-4.06), and 15.3 times more likely to fail ≥ 3 DMs at 18 months (aOR = 15.32; 95%CI = 7.75-30.28). The most notable DM-ASD association was observed for social DM failure at 9-12 months (aOR = 4.59; 95%CI = 2.59-8.13). Importantly, the sex or ethnicity of the participants did not affect these DM-ASD associations. Our findings highlight the potential role of DMs as early signs of ASD that could facilitate earlier referral and diagnosis of ASD.

Machine learning approaches for electroencephalography and magnetoencephalography analyses in autism spectrum disorder: A systematic review

There are growing application of machine learning models to study the intricacies of non-linear and non-stationary characteristics of electroencephalography (EEG) and magnetoencephalography (MEG) data in neurobiologically complex and heterogeneous conditions such as autism spectrum disorder (ASD). Such tools have potential diagnostic applications, and given the highly heterogeneous presentation of ASD, might prove fruitful in early detection and therefore could facilitate very early intervention. We conducted a systematic review (PROSPERO ID#CRD42021257438) by searching PubMed, EMBASE, and PsychINFO for machine learning approaches for EEG and MEG analyses in ASD. Thirty-nine studies were identified, of which the majority (18) used support vector machines for classification; other successful methods included deep learning. Thirty-seven studies were found to employ EEG and two were found to employ MEG. This systematic review indicate that machine learning methods can be used to classify ASD, predict ASD diagnosis in high-risk infants as early as 3 months of age, predict ASD symptom severity, and classify states of cognition in ASD with high accuracy. Replication studies testing validity, reproducibility and generalizability in tandem with randomized controlled trials in ASD populations will likely benefit the field.

Community-based postural control assessment in autistic individuals indicates a similar but delayed trajectory compared to neurotypical individuals

Autistic individuals exhibit significant sensorimotor differences. Postural stability and control are foundational motor skills for successfully performing many activities of daily living. In neurotypical development, postural stability and control develop throughout childhood and adolescence. In autistic development, previous studies have focused primarily on individual age groups (e.g., childhood, adolescence, adulthood) or only controlled for age using age-matching. Here, we examined the age trajectories of postural stability and control in autism from childhood through adolescents using standardized clinical assessments. In study 1, we tested the postural stability of autistic (n = 27) and neurotypical (n = 41) children, adolescents, and young adults aged 7-20 years during quiet standing on a force plate in three visual conditions: eyes open (EO), eyes closed (EC), and eyes open with the head in a translucent dome (Dome). Postural sway variability decreased as age increased for both groups, but autistic participants showed greater variability than neurotypical participants across age. In study 2, we tested autistic (n = 21) and neurotypical (n = 32) children and adolescents aged 7-16 years during a dynamic postural control task with nine targets. Postural control efficiency increased as age increased for both groups, but autistic participants were less efficient compared to neurotypical participants across age. Together, these results indicate that autistic individuals have a similar age trajectory for postural stability and control compared to neurotypical individuals, but have lower postural stability and control overall.

Autistic Children Use Less Efficient Goal-Directed Whole Body Movements Compared to Neurotypical Development

Autistic children have differences in their movements which impact their functional performance. Virtual-reality enables researchers to study movement in safe, engaging environments. We used motion-capture to measure how 7-13-year-old autistic and neurotypical children make whole-body movements in a virtual-reality task. Although children in both groups were successful, we observed differences in their movements. Autistic children were less efficient moving to the target. Autistic children did not appear to use a movement strategy. While neurotypical children were more likely to overshoot near targets and undershoot far targets, autistic children did not modulate their strategy. Using kinematic data from tasks in virtual-reality, we can begin to understand the pattern of movement challenges experienced by autistic children.

Early Motor Signs in Autism Spectrum Disorder

A growing number of literature data suggest the presence of early impairments in the motor development of children with autism spectrum disorder, which could be often recognized even before the appearance of the classical social communication deficits of autism. In this narrative review, we aimed at performing an update about the available data on the early motor function in children with autism spectrum disorder. Early motor impairment in these children can manifest itself both as a mere delay of motor development and as the presence of atypicalities of motor function, such as a higher rate and a larger inventory, of stereotyped movements both with and without objects. In the perspective of a timely diagnosis, the presence of early motor signs can be an important clue, especially in an individual considered at high risk for autism. Motor and communication (both verbal and non-verbal) skills are connected and a pathogenetic role of early motor dysfunctions in the development of autism can be hypothesized. From this, derives the importance of an early enabling intervention aimed at improving motor skills, which could also have favorable effects on other aspects of development.

Shared Features or Co-occurrence? Evaluating Symptoms of Developmental Coordination Disorder in Children and Adolescents with Autism Spectrum Disorder

Motor differences are common in Autism Spectrum Disorder (ASD), but rarely evaluated against diagnostic criteria for Developmental Coordination Disorder (DCD). We aimed to determine whether motor problems in ASD represent the possible co-occurrence of DCD. We retrospectively reviewed standardized assessments and parent-reports to evaluate motor ability in 43 individuals with ASD against diagnostic criteria for DCD, and compared to 18 individuals with DCD. Over 97% of cases in the ASD group scored below the 16th percentile in motor ability, with most below the 5th percentile. Over 90% of cases in the ASD group met criteria for co-occurring DCD. Motor challenges are a clinically-significant problem in ASD; systematically assessing the prevalence of co-occurring ASD + DCD is necessary to optimize assessment and intervention.

Towards a Multivariate Biomarker-Based Diagnosis of Autism Spectrum Disorder: Review and Discussion of Recent Advancements

An ever-evolving understanding of autism spectrum disorder (ASD) pathophysiology necessitates that diagnostic standards also evolve from being observation-based to include quantifiable clinical measurements. The multisystem nature of ASD motivates the use of multivariate methods of statistical analysis over common univariate approaches for discovering clinical biomarkers relevant to this goal. In addition to characterization of important behavioral patterns for improving current diagnostic instruments, multivariate analyses to date have allowed for thorough investigation of neuroimaging-based, genetic, and metabolic abnormalities in individuals with ASD. This review highlights current research using multivariate statistical analyses to quantify the value of these behavioral and physiological markers for ASD diagnosis. A detailed discussion of a blood-based diagnostic test for ASD using specific metabolite concentrations is also provided. The advancement of ASD biomarker research promises to provide earlier and more accurate diagnoses of the disorder.

Early Screening of the Autism Spectrum Disorders: Validity Properties and Cross-Cultural Generalizability of the First Year Inventory in Italy

This study examined the cross-cultural generalisability of the First Year Inventory (FYI) on an Italian sample, testing its construct validity, consistency, and structural validity. Six hundred ninety-eight parents of children aged 11–13 months completed the questionnaire. Similarities between analyses of Italian and American/Israeli samples were found, as were demonstrations of the instrument’s construct validity and internal consistency with both groups. The original factorial structure was not demonstrated; thus, a new factorial structure was tested, and a short version of the FYI was demonstrated via confirmatory factor analysis. The findings supported the generalisability of the Italian version of the FYI and its validity. The FYI may aid in medical decision-making on further steps for referral of the child to an early diagnostic assessment.

Introduction to Special Topic: Serving Children with Disabilities Within Multitiered Systems of Support

Since the conception of the Education for All Handicapped Children Act in 1975 there has been substantial progress regarding the education of learners with disabilities. Nevertheless, significant challenges remain for addressing the diverse needs of these learners and improving in- and out-of-school outcomes. This special issue focuses on an approach that holds promise for the delivery of interventions that are aligned to learners' social, emotional, behavioral, and learning needs - multi-tiered systems of support (MTSS). The four articles that comprise the special issue highlight the need for actionable information for schools implementing MTSS, early intervention for children with or at risk for disabilities, and an enhanced focus on intensive interventions. This introduction to the special issue provides information on the meeting that motivated the special issue, a summary of each of the four articles, and paths forward for early and sustained intervention for learners with or at risk for disabilities.