Prediction Of Autism Spectrum Disorder Research Articles

Does increased neutrophil-lymphocyte ratio predict autism spectrum disorder?

Objective: Although autism spectrum disorder (ASD) is one of the most studied neurodevelopmental disorders, its etiology has not been fully elucidated. A growing body of evidence suggest the role of neuroinflammation in the etiology of ASD. Neutrophil to lymphocyte ratio (NLR) and platelet to lymphocyte ratio (PLR) are markers of systemic inflammation. In this study, we aimed to evaluate NLR and PLR in children with ASD comparison to healthy controls. Methods: We reviewed the medical files of children with ASD in the ages of 2 to 5. The ASD group were consisted of drug-naive 64 children who had complete blood count within a month of assessment. Age and sex matched 64 healthy children without any psychiatric disorders were recruited from the healthy child outpatient unit of the hospital. Results: NLRs were significantly higher in ASD. Children with ASD had significantly higher neutrophil counts but lower platelet and lymphocyte counts compared to those of healthy controls. NLR was found to be a predictor of ASD. Conclusions: Increased NLRs support the hypothesis of the involvement of neuroinflammation in the under-lying physiopathology of ASD. Even though recent evidence is not enough to suggest that in young children increased NLR levels may be used as screening and early intervention predictor, it should be kept in mind and may inspire new studies. Further longitudinal studies with larger sample size and homogeneous groups regarding the age and subtypes may clarify the inflammatory involvement in ASD.

P.7.a.004 - Predicting autism spectrum disorder using blood-based gene expression signatures and machine learning

P.7.a.004 - Predicting autism spectrum disorder using blood-based gene expression signatures and machine learning

Neurocognitive and observational markers: prediction of autism spectrum disorder from infancy to mid-childhood

BackgroundProspective studies of infants at high familial risk for autism spectrum disorder (ASD) have identified a number of putative early markers that are associated with ASD outcome at 3 years of age. However, some diagnostic changes occur between toddlerhood and mid-childhood, which raises the question of whether infant markers remain associated with diagnosis into mid-childhood.MethodsFirst, we tested whether infant neurocognitive markers (7-month neural response to eye gaze shifts and 14-month visual disengagement latencies) as well as an observational marker of emerging ASD behaviours (the Autism Observation Scale for Infants; AOSI) predicted ASD outcome in high-risk (HR) 7-year-olds with and without an ASD diagnosis (HR-ASD and HR-No ASD) and low risk (LR) controls. Second, we tested whether the neurocognitive markers offer predictive power over and above the AOSI.ResultsBoth neurocognitive markers distinguished children with an ASD diagnosis at 7 years of age from those in the HR-No ASD and LR groups. Exploratory analysis suggested that neurocognitive markers may further differentiate stable versus lost/late diagnosis across the 3 to 7 year period, which will need to be tested in larger samples. At both 7 and 14 months, combining the neurocognitive marker with the AOSI offered a significantly improved model fit over the AOSI alone.ConclusionsInfant neurocognitive markers relate to ASD in mid-childhood, improving predictive power over and above an early observational marker. The findings have implications for understanding the neurodevelopmental mechanisms that lead from risk to disorder and for identification of potential targets of pre-emptive intervention.

Predicting Autism Spectrum Disorder Using Blood-based Gene Expression Signatures and Machine Learning

ObjectiveThe aim of this study was to identify a transcriptomic signature that could be used to classify subjects with autism spectrum disorder (ASD) compared to controls on the basis of blood gene expression profiles. The gene expression profiles could ultimately be used as diagnostic biomarkers for ASD.MethodsWe used the published microarray data (GSE26415) from the Gene Expression Omnibus database, which included 21 young adults with ASD and 21 age- and sex-matched unaffected controls. Nineteen differentially expressed probes were identified from a training dataset (n=26, 13 ASD cases and 13 controls) using the limma package in R language (adjusted p value <0.05) and were further analyzed in a test dataset (n=16, 8 ASD cases and 8 controls) using machine learning algorithms.ResultsHierarchical cluster analysis showed that subjects with ASD were relatively well-discriminated from controls. Based on the support vector machine and K-nearest neighbors analysis, validation of 19-DE probes with a test dataset resulted in an overall class prediction accuracy of 93.8% as well as a sensitivity and specificity of 100% and 87.5%, respectively.ConclusionThe results of our exploratory study suggest that the gene expression profiles identified from the peripheral blood samples of young adults with ASD can be used to identify a biological signature for ASD. Further study using a larger cohort and more homogeneous datasets is required to improve the diagnostic accuracy.

Parent Prediction of Autism Spectrum Disorder in Infants at Risk: A Follow-up Study

Later-born siblings of children with autism spectrum disorder are considered at biological risk for autism spectrum disorder and the broader phenotype. Early screening may detect first signs of autism spectrum disorder and expedite diagnosis and early intervention. In this follow-up study, we re-examine a validated second-degree autism spectrum disorder screener for children at biological risk of autism spectrum disorder, the parent observation of early markers scale. Using available follow-up information up to age 13 years, 110 children (the original 108 infants plus 2 infants recruited after the completion of the original study) were divided into three groups: diagnosed group (n = 13), lost diagnosis group (n = 5), and undiagnosed group (n = 92). The parent observation of early markers scale continued to show acceptable predictive validity. The parent observation of early markers scale total scores and mean number of elevated items were significantly higher in the diagnosed group than the undiagnosed group. The lost-diagnosis group did not differ from the undiagnosed group on parent observation of early markers scale total scores and elevated items at any age, but the lost-diagnosis group had significantly lower total scores, and number of elevated items than the diagnosed group starting at 18 months. Both autism spectrum disorder core and subsidiary behaviors differentiated the diagnosed and undiagnosed groups from 9 to 36 months of age. We hereby provide further evidence that the parent observation of early markers scale may serve as a low-cost early screener for autism spectrum disorder in at-risk children and pinpoint specific developmental ,and behavioral problems that may be amenable to very early intervention.

Can Parents’ Concerns Predict Autism Spectrum Disorder? A Prospective Study of High-Risk Siblings From 6 to 36 Months of Age

This prospective study characterized parents' concerns about infants at high risk for developing autism spectrum disorder (ASD; each with an older sibling with ASD) at multiple time points in the first 2 years, and assessed their relation to diagnostic outcome at 3 years. Parents of low-risk controls (LR) and high-risk infant siblings (HR) reported any concerns that they had regarding their children's development between 6 and 24 months of age regarding sleep, diet, sensory behavior, gross/fine motor skills, repetitive movements, communication, communication regression, social skills, play, and behavioral problems, using a parent concern form designed for this study. At 3 years of age, an independent, gold-standard diagnostic assessment for ASD was conducted for all participants. As predicted, parents of HR children who received an ASD diagnosis reported more concerns than parents of LR and HR children who did not have ASD. The total number of concerns predicted a subsequent diagnosis of ASD as early as 12 months within the HR group. Concerns regarding sensory behavior and motor development predicted a subsequent diagnosis of ASD as early as 6 months, whereas concerns about social communication and repetitive behaviors did not predict diagnosis of ASD until after 12 months. Parent-reported concerns can improve earlier recognition of ASD in HR children.

Predicting autism diagnosis by 7 years of age using parent report of infant social communication skills

The aim of this study is to identify social communication skills in infancy which predict autism spectrum disorder (ASD) diagnosis by 7 years as compared with children with other developmental difficulties or typical development from within a population sample. Children with an ASD (n = 41), developmental delay (n = 28), language impairment (n = 47) and typical development (n = 41) were drawn from a large, longitudinal community sample following children from 8 months to 7 years of age, the Early Language in Victoria Study. At 7 years of age, early social communication skills at 8, 12 and 24 months from the Communication and Symbolic Behavior Scales Infant-Toddler Checklist and the MacArthur-Bates Communicative Development Inventory: Words and Gestures were compared between groups and used to predict ASD diagnosis. Significant predictors of ASD diagnosis were found from 8 months, predominantly focused on gesture use and communicative behaviours, such as requesting and joint attention. While comparisons between children with ASD and children with language impairment and typical development revealed differences from 8 months of age, the developmental delay group did not differ significantly from ASD on any measure until 24 months of age. At 24 months, children with ASD had lower Communication and Symbolic Behavior Scales Use of Communication scores as compared with all other groups. The capacity to identify early markers of ASD should facilitate awareness of the risk of an ASD as compared with other developmental problems and point to the need for further developmental assessment, monitoring and provision of early intervention if indicated.