Diagnostic Autism Spectrum Disorder Research Articles

A new diagnostic autism spectrum disorder (DASD) strategy using ensemble diagnosis methodology based on blood tests

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disease that impacts a child’s way of behavior and social communication. In early childhood, children with ASD typically exhibit symptoms such as difficulty in social interaction, limited interests, and repetitive behavior. Although there are symptoms of ASD disease, most people do not understand these symptoms and therefore do not have enough knowledge to determine whether or not a child has ASD. Thus, early detection of ASD children based on accurate diagnosis model based on Artificial Intelligence (AI) techniques is a critical process to reduce the spread of the disease and control it early. Through this paper, a new Diagnostic Autism Spectrum Disorder (DASD) strategy is presented to quickly and accurately detect ASD children. DASD contains two layers called Data Filter Layer (DFL) and Diagnostic Layer (DL). Feature selection and outlier rejection processes are performed in DFL to filter the ASD dataset from less important features and incorrect data before using the diagnostic or detection method in DL to accurately diagnose the patients. In DFL, Binary Gray Wolf Optimization (BGWO) technique is used to select the most significant set of features while Binary Genetic Algorithm (BGA) technique is used to eliminate invalid training data. Then, Ensemble Diagnosis Methodology (EDM) as a new diagnostic technique is used in DL to quickly and precisely diagnose ASD children. In this paper, the main contribution is EDM that consists of several diagnostic models including Enhanced K-Nearest Neighbors (EKNN) as one of them. EKNN represents a hybrid technique consisting of three methods called K-Nearest Neighbors (KNN), Naïve Bayes (NB), and Chimp Optimization Algorithm (COA). NB is used as a weighed method to convert data from feature space to weight space. Then, COA is used as a data generation method to reduce the size of training dataset. Finally, KNN is applied on the reduced data in weight space to quickly and accurately diagnose ASD children based on new training dataset with small size. ASD blood tests dataset is used to test the proposed DASD strategy against other recent strategies [1]. It is concluded that the DASD strategy is superior to other strategies based on many performance measures including accuracy, error, recall, precision, micro_average precision, macro_average precision, micro_average recall, macro_average recall, F1-measure, and implementation-time with values equal to 0.93, 0.07, 0.83, 0.82, 0.80, 0.83, 0.79, 0.81, 0.79, and 1.5 s respectively.

Developmental and family environment predictors of diagnostic decision-making in children with autism spectrum disorder and comorbid disorders

BackgroundClinical psychologists are observing an increasing number of children with comorbid disorders such as autism spectrum dis-order (ASD), attention-deficit/hyperactivity disorder (ADHD), anxiety disorders, depressive disorders and others. Due to the importance of higher efficacy of implementing early therapeutic interventions, factors determining the age of first diagnos-tic intervention and the age of diagnosis are particularly significant aspects when considering this topic.Participants and procedureAn in-depth analysis of the documentation of 112 patients of one of the psychological and pedagogical counselling centres was conducted to identify family and developmental factors that contribute to the diagnostic decision-making process in children with comorbid disorders. These children were 2-17 years old and diagnosed with co-occurrence of ASD and other disorders.ResultsThe results indicate that children with comorbid disorders are reported for diagnostic intervention at the age of 4 years old and 3 months old (M = 4.24, SD = 2.29) and the mean age of receiving an ASD diagnosis is 7 years old and 3 months old (M = 7.28, SD = 3.25). Predictors of the age of diagnostic intervention and ASD diagnosis were also identified. Somatic dis-eases and potentially speech disorders were related to the earlier age of diagnostic intervention, whereas learning difficul-ties were related to the later age of diagnostic intervention. Moreover, it has been found that children with comorbid ex-ternalizing disorders have an earlier age of diagnostic intervention than children without disrupting behaviours. However, this circumstance does not affect the age of ASD diagnosis.ConclusionsIt is important to raise parents’ awareness of detecting early markers of disorders as intervention and diagnosis are imple-mented too late. In such circumstances, therapeutic interventions under-taken may have limited effectiveness.

Description of Clinician-Diagnosed Regression at Time of Autism Spectrum Disorder Diagnosis in Toddlers.

Previous studies have reported varying rates of regression in children with autism spectrum disorder (ASD). We sought to (1) determine the rate of clinician-diagnosed regression for young children with ASD and (2) compare developmental functioning and ASD symptoms of children with versus without regression. We conducted a retrospective chart review of toddlers (age 18-36 months) with Diagnostic and Statistical Manual-5 ASD. We abstracted cognitive, language, adaptive, and motor functioning standard scores and ASD core symptoms. Regression was defined as "clinician-diagnosed regression accompanied by recommendation for a medical workup." We used propensity scores to match each participant with regression (n = 20) one-to-one with a participant without regression (n = 20). We compared the groups on developmental scores using independent sample t tests and on core ASD symptoms using Pearson's χ 2 test. Of the 500 children with ASD, n = 20 (4%) had regression (defined above). Children with regression had lower Bayley cognitive and language scores and lower Vineland adaptive scores compared with those without regression (cognitive: 78.0 vs 85.5, p < 0.05; language: 56.9 vs 68.2, p < 0.01; adaptive: 70.0 vs 80.3; p < 0.01). There was no difference in motor scores across groups. There were no significant differences in the frequency of exhibiting core ASD symptoms for those with versus without regression. In this clinical sample of children with ASD, regression was diagnosed in a small percentage (4%). Those with regression had lower cognitive, language, and adaptive skills compared with those without regression. Rates of clinician-diagnosed regression referred for medical workup are significantly lower than prior estimates based on parent report.

A Comparison of Fundamental Movement Skills in Children with Autism Spectrum Disorder and Typically Developing Children

Autism Spectrum Disorders (ASD) is urodevelopmental disorder characterized by social and communication impairments as well as a wide range of behavior deficits. For years, motor disturbance reported in ASD has not been treated as a major core deficit because of the overwhelming problems in sociability and communication. Recent studies, however, reveal that motor deficits are associated with the core symptoms of ASD. Because limited studies have addressed motor behavior of children with ASD, especially in China, the purpose of this study is to explore the development of fundamental movement skills in children with ASD and compare it to that of typically developing (TD) children. A total of 108 children with ASD aged 5-14 years and 108 age- and gender-matched TD children were evaluated. FMS were assessed with the Movement Assessment Battery for Children 2nd edition (MABC-2) including manual dexterity, aiming and catching, static and dynamic balance, and overall motor skills. The results included: (1) The development of FMS of children with ASD was significantly behind that of the children with TD at the same age. About 80% of children with ASD experienced motor difficulty or were at risk for motor delay. (2) Children with ASD showed significantly lower standard scores than typically developing children at the same age on manual dexterity, ball skills, and static and dynamic balance and overall MABC-2 scores (all p &lt; 0.001), and there was no significant gender difference (all p &gt; 0.05). Besides the core areas of developmental deficits described in the diagnostic manual for ASD, clinicians should assess motor deficits when diagnosing and treating children with ASD. Evidence-based interventions on FMS should be introduced when motor deficits are present.

The Autism Detection in Early Childhood Tool: Level 2 autism spectrum disorder screening in a NICU Follow-up program

ObjectiveChildren born preterm are at increased risk for autism spectrum disorder (ASD). However, early diagnosis of ASD is challenging because conventional screening Level 1 tools are less reliable in this population. We sought to determine whether the Autism Detection in Early Childhood (ADEC) and Child Behavior Checklist (CBCL) could accurately identify children at risk for ASD in a NICU Follow-up setting and thus facilitate referral for formal ASD evaluation. MethodChildren aged 18–36 months were recruited from a NICU Follow-up program. All children received presumptive diagnoses based on DSM-5 criteria and were screened for ASD risk with the ADEC and CBCL. Children scoring in the “at risk” range on either tool were referred for a full diagnostic ASD evaluation. ResultsSixty-nine patients (median birth weight 1140 g; median gestational age 28 weeks) were included with 18 designated “at risk” for ASD. Nine (13 %) scored “at risk” on the ADEC and 12 (17 %) on the CBCL. Thirteen children underwent diagnostic ASD evaluation with 9 receiving a formal diagnosis of ASD. The ADEC demonstrated the best performance (sensitivity 89 %, specificity 98 %). The CBCL was less sensitive (sensitivity 50 %, specificity 90 %). Requiring elevated scores on both the CBCL and ADEC was specific but not sensitive (sensitivity 33 %, specificity 100 %). ConclusionThe ADEC performed well in identifying children at risk for ASD within this high-risk NICU cohort, adding benefit as an autism-specific screening tool over the CBCL alone.

First Psychometric Properties of the Dutch Interview for Diagnostic Assessment of Autism Spectrum Disorder in Adult Males Without Intellectual Disability.

For autism spectrum disorder (ASD) in adults there are several diagnostic instruments available with a need for consideration of the psychometric properties. This study aimed to conduct a first psychometric evaluation of a new diagnostic ASD instrument, the NIDA (Dutch Interview for Diagnostic assessment of ASD in adults) in 90 adult males without intellectual disability (age 18-65years) in the Netherlands: 30 with ASD, 30 with a Personality Disorder and 30 nonpatient controls. The interrater agreement ranged from 0.79 to 1.00, the convergent validity including sensitivity and specificity ranged from 0.76 to 1.00, and we observed an adequate concurrent criterion-related validity. These promising findings can serve as foundation for future psychometric NIDA studies in a more diverse population. TRIAL REGISTRATION: The Netherlands National Trial Register NTR6391. Registered 04 May 2017.

Parents\u2019 multi-layered expectations when requesting an Autism Spectrum Disorder assessment of their young child: an in-depth interview study

BackgroundParents are valued stakeholders in research, clinical practice and policy development concerning autism spectrum disorder (ASD). However, little is known about what drives and moves parents besides their obvious worries and help request when they ask for a diagnostic ASD assessment of their child.MethodsSeventeen Flemish parents of 11 young children participated in a longitudinal study consisting of three in-depth interviews before and after their child’s diagnostic ASD assessment. Data were analysed in Nvivo 11 according to the procedures of Interpretative Phenomenological Analysis.ResultsIn this paper we report the results of the first series of interviews which were conducted after parents had asked for an ASD assessment of their young child, and before this assessment started. The pre-assessment experiences of the parents were dominated by the anticipation of various implications of an ASD diagnosis, comprising both positive and negative expectations. The theme of positive expectations consisted of two equally prominent subthemes: treatment-related implications but also expectations pertaining to their psychological and relational experiences.ConclusionsThis study suggests important issues for clinicians to bear in mind during a consultation with parents who request an ASD assessment of their young child. We argue that attending to and communicating about parents’ expectations prior to their child’s ASD assessment may help clinicians to better understand parents’ requests for help, and to address their needs more effectively.

Parents' views and experiences of the autism spectrum disorder diagnosis of their young child: a longitudinal interview study.

Parents are valuable stakeholders in research, clinical practice and policy development concerning autism spectrum disorder (ASD). Little is known, however, about how parents view and experience an ASD diagnosis. We investigated the evolution of parents' views and experiences of the ASD diagnosis before, right after and 12months after their child was diagnosed. Seventeen Flemish parents waiting for their young child's diagnostic ASD assessment participated in a longitudinal study consisting of three in-depth interviews. They described their views and experiences concerning their child's ASD diagnosis at three separate moments: (T1) prior to a diagnostic ASD assessment; (T2) immediately after their final feedback session at the end of the assessment; and (T3) 12months later. Interviews were digitally recorded, transcribed and analysed in Nvivo 11 according to the procedures of interpretative phenomenological analysis. We extracted three themes from the interview material throughout the parental journey: (T1) expecting certainty and exculpation; (T2) vulnerabilisation of the child; and (T3) pragmatic attitude and some disappointment. At T3, the parents overall had come to value the diagnosis because of two reasons: they were satisfied with their child's entitlement to ASD-related support at school, and with the diagnosis' impact on the child's relationships with parents and teachers. Many parents experienced their child with an ASD diagnosis as vulnerable, and themselves as acutely responsible for his development and future. Our findings may lead to a higher satisfaction with the clinical trajectory in both clinician and parents by inspiring a conversation between them about parents' evolving views, hopes and concerns related to their child's ASD diagnosis.

Correction: Air Pollution and Newly Diagnostic Autism Spectrum Disorders: A Population-Based Cohort Study in Taiwan.

[This corrects the article DOI: 10.1371/journal.pone.0075510.].

Early Intervention Before Autism Diagnosis in Children Referred to a Regional Autism Clinic.

To determine the prevalence of receipt of early intervention and therapeutic services in children suspected of having possible autism spectrum disorder (ASD) before their diagnostic ASD evaluations. The electronic medical records of all children ≤5 years of age evaluated at a single regional ASD clinic between September 2012 and June 2014 were reviewed. Information regarding type of services, clinical diagnoses, and demographic information was abstracted for each patient. Five hundred sixty-one children (mean age = 44 mo [SD, 10 mo]; 80% [N = 450] male; 20% [N = 111] female) completed a diagnostic ASD evaluation. Of these children, 497 (89%) were already receiving early intervention services, and only 64 (11%) were not receiving any services. Receipt of services did not vary based on race, ethnicity, insurance type, or primary language. Children who were already receiving services were more likely to receive an ASD diagnosis (67%, N = 332) than those not receiving services (44% [N = 28]; p ≤ .001). Despite concerns that long wait lists for diagnostic ASD evaluations may delay initiation of critical early interventions, our data indicate that most children are receiving early intervention services before their diagnostic ASD evaluations, particularly if an ASD diagnosis is confirmed. This may be attributable to increased awareness among primary care providers and families of the importance of early interventions. Further investigation into access to more intensive interventions (such as applied behavioral analysis) once an ASD diagnosis is established is warranted.

A New Interactive Screening Test for Autism Spectrum Disorders in Toddlers

To develop a clinically valid interactive level 2 screening assessment for autism spectrum disorders (ASD) in toddlers that is brief, easily administered, and scored by clinicians. We describe the development, training, standardization, and validation of the Rapid Interactive Screening Test for Autism in Toddlers (RITA-T) with ASD-specific diagnostic instruments. The RITA-T can be administered and scored in 10 minutes. We studied the validity of the RITA-T to distinguish between toddlers with ASD from toddlers with developmental delay (DD)/non-ASD in an early childhood clinic. We also evaluated the test's performance in toddlers with no developmental concerns. We identified a cutoff score based on sensitivity, specificity, and positive predictive value of the RITA-T that best differentiates between ASD and DD/non-ASD. A total of 61 toddlers were enrolled. RITA-T scores were correlated with ASD-specific diagnostic tools (r = 0.79; P < .01) and ASD clinical diagnoses (r = 0.77; P < .01). Mean scores were significantly different in subjects with ASD, those with DD/non-ASD, and those with no developmental concerns (20.8 vs 13 vs 10.6, respectively; P < .0001). At a cutoff score of >14 , the RITA-T had a sensitivity of 1.00, specificity of 0.84, and positive predictive value of 0.88 for identifying ASD risk in a high-risk group. The RITA-T is a promising new level 2 interactive screening tool for improving the early identification of ASD in toddlers in general pediatric and early intervention settings and allowing access to treatment.

An ontology for Autism Spectrum Disorder (ASD) to infer ASD phenotypes from Autism Diagnostic Interview-Revised data

ObjectiveOur goal is to create an ontology that will allow data integration and reasoning with subject data to classify subjects, and based on this classification, to infer new knowledge on Autism Spectrum Disorder (ASD) and related neurodevelopmental disorders (NDD). We take a first step toward this goal by extending an existing autism ontology to allow automatic inference of ASD phenotypes and Diagnostic & Statistical Manual of Mental Disorders (DSM) criteria based on subjects’ Autism Diagnostic Interview-Revised (ADI-R) assessment data. Materials and methodsKnowledge regarding diagnostic instruments, ASD phenotypes and risk factors was added to augment an existing autism ontology via Ontology Web Language class definitions and semantic web rules. We developed a custom Protégé plugin for enumerating combinatorial OWL axioms to support the many-to-many relations of ADI-R items to diagnostic categories in the DSM. We utilized a reasoner to infer whether 2642 subjects, whose data was obtained from the Simons Foundation Autism Research Initiative, meet DSM-IV-TR (DSM-IV) and DSM-5 diagnostic criteria based on their ADI-R data. ResultsWe extended the ontology by adding 443 classes and 632 rules that represent phenotypes, along with their synonyms, environmental risk factors, and frequency of comorbidities. Applying the rules on the data set showed that the method produced accurate results: the true positive and true negative rates for inferring autistic disorder diagnosis according to DSM-IV criteria were 1 and 0.065, respectively; the true positive rate for inferring ASD based on DSM-5 criteria was 0.94. DiscussionThe ontology allows automatic inference of subjects’ disease phenotypes and diagnosis with high accuracy. ConclusionThe ontology may benefit future studies by serving as a knowledge base for ASD. In addition, by adding knowledge of related NDDs, commonalities and differences in manifestations and risk factors could be automatically inferred, contributing to the understanding of ASD pathophysiology.

Prevalence of Autism Spectrum Disorder in Children Referred for Diagnostic Autism Evaluation.

Increased public awareness of autism spectrum disorders (ASD) and routine screening in primary care have contributed to increased requests for diagnostic ASD evaluations. However, given the scarcity of subspecialty autism diagnostic resources, overreferral of children suspected of having ASD may be contributing to long waiting lists at tertiary care autism centers and delaying diagnosis for those children who truly have ASD. To determine whether children are being excessively referred to ASD-specific diagnostic clinics, our objective was to determine the prevalence of true ASD diagnoses in children referred for diagnostic ASD evaluation. Charts of all patients referred to a regional autism center between April 2011 and August 2012 for suspicion of a possible ASD were retrospectively reviewed and demographic and clinical diagnoses abstracted. Only 214 of 348 patients evaluated (61%) received an ASD diagnosis. Thus, concerns about autism are not confirmed by an ASD diagnosis in a significant number of children.

Air Pollution and Newly Diagnostic Autism Spectrum Disorders: A Population-Based Cohort Study in Taiwan

There is limited evidence that long-term exposure to ambient air pollution increases the risk of childhood autism spectrum disorder (ASD). The objective of the study was to investigate the associations between long-term exposure to air pollution and newly diagnostic ASD in Taiwan. We conducted a population-based cohort of 49,073 children age less than 3 years in 2000 that were retrieved from Taiwan National Insurance Research Database and followed up from 2000 through 2010. Inverse distance weighting method was used to form exposure parameter for ozone (O3), carbon monoxide (CO), nitrogen dioxide (NO2), sulfur dioxide (SO2), and particles with aerodynamic diameter less than 10 µm (PM10). Time-dependent Cox proportional hazards (PH) model was performed to evaluate the relationship between yearly average exposure air pollutants of preceding years and newly diagnostic ASD. The risk of newly diagnostic ASD increased according to increasing O3, CO, NO2, and SO2 levels. The effect estimate indicating an approximately 59% risk increase per 10 ppb increase in O3 level (95% CI 1.42–1.79), 37% risk increase per 10 ppb in CO (95% CI 1.31–1.44), 340% risk increase per 10 ppb increase in NO2 level (95% CI 3.31–5.85), and 17% risk increase per 1 ppb in SO2 level (95% CI 1.09–1.27) was stable with different combinations of air pollutants in the multi-pollutant models. Our results provide evident that children exposure to O3, CO, NO2, and SO2 in the preceding 1 year to 4 years may increase the risk of ASD diagnosis.

A Training Model for the Diagnosis of Autism in Community Pediatric Practice

Early diagnosis of autism spectrum disorders (ASD) currently represents a critical public health and clinical practice issue. Waits for diagnostic services are quite lengthy and hinder the start of early intervention services thought to be crucial for optimizing functional developmental outcomes for children and their families. In this study, we present data from a newly developed training program (Screening Tools and Referral Training-Evaluation and Diagnosis training) designed to help pediatricians diagnose young children with ASD in the context of traditional community practice settings. A small, targeted group of community pediatricians participated in an intensive training, conducted specialized ASD evaluations within their own practices, and then referred a consecutive series of children to a medical center diagnostic clinic for an independent assessment of ASD. Results of this small pilot study indicate good agreement (71%) between pediatrician judgments and independent diagnostic ASD evaluations, but a significant trend toward overidentification when a diagnostic decision is forced. We discuss the implications of this study with regard to revisiting traditional service models of diagnostic assessment for young children with ASD.