Heterogeneity Of Autism Spectrum Disorder Research Articles

Integration of Facial Thermography in EEG-based Classification of ASD

Autism spectrum disorder (ASD) is a neurodevelopmental disorder affecting social, communicative, and repetitive behavior. The phenotypic heterogeneity of ASD makes timely and accurate diagnosis challenging, requiring highly trained clinical practitioners. The development of automated approaches to ASD classification, based on integrated psychophysiological measures, may one day help expedite the diagnostic process. This paper provides a novel contribution for classifing ASD using both thermographic and EEG data. The methodology used in this study extracts a variety of feature sets and evaluates the possibility of using several learning models. Mean, standard deviation, and entropy values of the EEG signals and mean temperature values of regions of interest (ROIs) in facial thermographic images were extracted as features. Feature selection is performed to filter less informative features based on correlation. The classification process utilizes Naive Bayes, random forest, logistic regression, and multi-layer perceptron algorithms. The integration of EEG and thermographic features have achieved an accuracy of 94% with both logistic regression and multi-layer perceptron classifiers. The results have shown that the classification accuracies of most of the learning models have increased after integrating facial thermographic data with EEG.

MECP2 Duplication Causes Aberrant GABA Pathways, Circuits and Behaviors in Transgenic Monkeys: Neural Mappings to Patients with Autism.

MECP2 gain-of-function and loss-of-function in genetically engineered monkeys recapitulates typical phenotypes in patients with autism, yet where MECP2 mutation affects the monkey brain and whether/how it relates to autism pathology remain unknown. Here we report a combination of gene-circuit-behavior analyses including MECP2 coexpression network, locomotive and cognitive behaviors, and EEG and fMRI findings in 5 MECP2 overexpressed monkeys (Macaca fascicularis; 3 females) and 20 wild-type monkeys (Macaca fascicularis; 11 females). Whole-genome expression analysis revealed MECP2 coexpressed genes significantly enriched in GABA-related signaling pathways, whereby reduced β-synchronization within fronto-parieto-occipital networks was associated with abnormal locomotive behaviors. Meanwhile, MECP2-induced hyperconnectivity in prefrontal and cingulate networks accounted for regressive deficits in reversal learning tasks. Furthermore, we stratified a cohort of 49 patients with autism and 72 healthy controls of 1112 subjects using functional connectivity patterns, and identified dysconnectivity profiles similar to those in monkeys. By establishing a circuit-based construct link between genetically defined models and stratified patients, these results pave new avenues to deconstruct clinical heterogeneity and advance accurate diagnosis in psychiatric disorders.SIGNIFICANCE STATEMENT Autism spectrum disorder (ASD) is a complex disorder with co-occurring symptoms caused by multiple genetic variations and brain circuit abnormalities. To dissect the gene-circuit-behavior causal chain underlying ASD, animal models are established by manipulating causative genes such as MECP2 However, it is unknown whether such models have captured any circuit-level pathology in ASD patients, as demonstrated by human brain imaging studies. Here, we use transgenic macaques to examine the causal effect of MECP2 overexpression on gene coexpression, brain circuits, and behaviors. For the first time, we demonstrate that the circuit abnormalities linked to MECP2 and autism-like traits in the monkeys can be mapped to a homogeneous ASD subgroup, thereby offering a new strategy to deconstruct clinical heterogeneity in ASD.

Improving Diagnosis of Autism Spectrum Disorder and Disentangling its Heterogeneous Functional Connectivity Patterns Using Capsule Networks.

Functional connectivity (FC) analysis is an appealing tool to aid diagnosis and elucidate the neurophysiological underpinnings of autism spectrum disorder (ASD). Many machine learning methods have been developed to distinguish ASD patients from healthy controls based on FC measures and identify abnormal FC patterns of ASD. Particularly, several studies have demonstrated that deep learning models could achieve better performance for ASD diagnosis than conventional machine learning methods. Although promising classification performance has been achieved by the existing machine learning methods, they do not explicitly model heterogeneity of ASD, incapable of disentangling heterogeneous FC patterns of ASD. To achieve an improved diagnosis and a better understanding of ASD, we adopt capsule networks (CapsNets) to build classifiers for distinguishing ASD patients from healthy controls based on FC measures and stratify ASD patients into groups with distinct FC patterns. Evaluation results based on a large multi-site dataset have demonstrated that our method not only obtained better classification performance than state-of-the-art alternative machine learning methods, but also identified clinically meaningful subgroups of ASD patients based on their vectorized classification outputs of the CapsNets classification model.

Cell Type-Specific Gene Network-Based Analysis Depicts the Heterogeneity of Autism Spectrum Disorder.

Autism spectrum disorder (ASD) is a complex neuropsychiatric disorder characterized by substantial heterogeneity. To identify the convergence of disease pathology on common pathways, it is essential to understand the correlations among ASD candidate genes and study shared molecular pathways between them. Investigating functional interactions between ASD candidate genes in different cell types of normal human brains may shed new light on the genetic heterogeneity of ASD. Here we apply cell type-specific gene network-based analysis to analyze human brain nucleus gene expression data and identify cell type-specific ASD-associated gene modules. ASD-associated modules specific to different cell types are relevant to different gene functions, for instance, the astrocytes-specific module is involved in functions of axon and neuron projection guidance, GABAergic interneuron-specific modules are involved in functions of postsynaptic membrane, extracellular matrix structural constituent, and ion transmembrane transporter activity. Our findings can promote the study of cell type heterogeneity of ASD, providing new insights into the pathogenesis of ASD. Our method has been shown to be effective in discovering cell type-specific disease-associated gene expression patterns and can be applied to other complex diseases.

The Neurochemistry of Autism.

Autism spectrum disorder (ASD) refers to complex neurobehavioral and neurodevelopmental conditions characterized by impaired social interaction and communication, restricted and repetitive patterns of behavior or interests, and altered sensory processing. Environmental, immunological, genetic, and epigenetic factors are implicated in the pathophysiology of autism and provoke the occurrence of neuroanatomical and neurochemical events relatively early in the development of the central nervous system. Many neurochemical pathways are involved in determining ASD; however, how these complex networks interact and cause the onset of the core symptoms of autism remains unclear. Further studies on neurochemical alterations in autism are necessary to clarify the early neurodevelopmental variations behind the enormous heterogeneity of autism spectrum disorder, and therefore lead to new approaches for the treatment and prevention of autism. In this review, we aim to delineate the state-of-the-art main research findings about the neurochemical alterations in autism etiology, and focuses on gamma aminobutyric acid (GABA) and glutamate, serotonin, dopamine, N-acetyl aspartate, oxytocin and arginine-vasopressin, melatonin, vitamin D, orexin, endogenous opioids, and acetylcholine. We also aim to suggest a possible related therapeutic approach that could improve the quality of ASD interventions. Over one hundred references were collected through electronic database searching in Medline and EMBASE (Ovid), Scopus (Elsevier), ERIC (Proquest), PubMed, and the Web of Science (ISI).

Rare genetic susceptibility variants assessment in autism spectrum disorder: detection rate and practical use

Autism spectrum disorder (ASD) is a neurodevelopmental disorder with a strong genetic component whose knowledge evolves quickly. Next-generation sequencing is the only effective technology to deal with the high genetic heterogeneity of ASD in a clinical setting. However, rigorous criteria to classify rare genetic variants conferring ASD susceptibility are currently lacking. We have performed whole-exome sequencing to identify both nucleotide variants and copy number variants (CNVs) in 253 ASD patients, including 68 patients with intellectual disability (ID) and 90 diagnosed as Asperger syndrome. Using explicit criteria to classify both susceptibility genes and susceptibility variants we prioritized 217 genes belonging to the following categories: syndromic genes, genes with an excess of de novo protein truncating variants and genes targeted by rare CNVs. We obtained a susceptibility variant detection rate of 19.7% (95% CI: [15–25.2%]). The rate for CNVs was 7.1% (95% CI: [4.3–11%]) and 12.6% (95% CI: [8.8–17.4%]) for nucleotide variants. The highest rate (30.1%, 95% CI: [20.2–43.2%]) was obtained in the ASD + ID subgroup. A strong contributor for at risk nucleotide variants was the recently identified set of genes (n = 81) harboring an excess of de novo protein truncating variants. Since there is currently no evidence that the genes targeted here are necessary and sufficient to cause ASD, we recommend to avoid the term “causative of ASD” when delivering the information about a variant to a family and to use instead the term “genetic susceptibility factor contributing to ASD”.

A Multimodal Interlocutor-Modulated Attentional BLSTM for Classifying Autism Subgroups During Clinical Interviews

The heterogeneity in Autism Spectrum Disorder (ASD) remains a challenging and unsolved issue in the current clinical practice. The behavioral differences between ASD subgroups are subtle and can be hard to be manually discerned by experts. Here, we propose a computational framework that is capable of modeling both vocal behaviors and body gestural movements of the interlocutors with their intricate dependency captured through a learnable interlocutor-modulated (IM) attention mechanism during dyadic clinical interviews of Autism Diagnostic Observation Schedule (ADOS). Specifically, our multimodal network architecture includes two modality-specific networks, a speech-IM-aBLSTM and a motion-IM-aBLSTM, that are combined in a fusion network to perform the final three ASD subgroups differentiation, i.e., Autistic Disorder (AD) vs. High-Functioning Autism (HFA) vs. Asperger Syndrome (AS). Our model uniquely introduces the IM attention mechanism to capture the non-linear behavior dependency between interlocutors, which is essential in providing improved discriminability in classifying the three subgroups. We evaluate our framework on a large ADOS collection, and we obtain a 66.8% unweighted average recall (UAR) that is 14.3% better than the previous work on the same dataset. Furthermore, based on the learned attention weights, we analyze essential behavior descriptors in differentiating subgroup pairs. We further identify the most critical self-disclosure emotion topics within the ADOS interview sessions, and it shows that anger and fear are the most informative interaction segments for observing the subtle interactive behavior differences between these three sub-types of ASD.

Identifying Language and Cognitive Profiles in Children With ASD via a Cluster Analysis Exploration: Implications for the New ICD-11.

The new version of the International Classification of Diseases (ICD-11) mentions the existence of four different profiles in the verbal part of the Autism Spectrum Disorder (ASD), describing them as combinations of either spared or impaired functional language and intellectual abilities. The aim of the present study was to put ASD heterogeneity to the forefront by exploring whether clear profiles related to language and intellectual abilities emerge when investigation is extended to the entire spectrum, focusing on verbal children. Our study proposed a systematic investigation of both language (specifically, structural language abilities) and intellectual abilities (specifically, nonverbal cognitive abilities) in 51 6- to 12-year-old verbal children with ASD based on explicitly motivated measures. For structural language abilities, sentence repetition and nonword repetition tasks were selected; for nonverbal cognitive abilities, we chose Raven's Progressive Matrices, as well as Matrix Reasoning and Block Design from the Wechsler Scales. An integrative approach based on cluster analyses revealed five distinct profiles. Among these five profiles, all four logically possible combinations of structural language and nonverbal abilities mentioned in the ICD-11 were detected. Three profiles emerged among children with normal language abilities and two emerged among language-impaired children. Crucially, the existence of discrepant profiles of abilities suggests that children with ASD can display impaired language in presence of spared nonverbal intelligence or spared language in the presence of impaired nonverbal intelligence, reinforcing the hypothesis of the existence of a separate language module in the brain. Autism Res 2020, 13: 1155-1167. © 2020 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: The present work put Autism Spectrum Disorder heterogeneity to the forefront by exploring whether clear profiles related to language and cognitive abilities emerge when investigation is extended to the entire spectrum (focusing on verbal children). The use of explicitly motivated measures of both language and cognitive abilities and of an unsupervised machine learning approach, the cluster analysis, (a) confirmed the existence of all four logically possible profiles evoked in the new ICD-11, (b) evoked the existence of (at least) a fifth profile of language/cognitive abilities, and (c) reinforced the hypothesis of a language module in the brain.

Trajectories of Autism Symptoms and IQ into Young Adulthood

Although the prevalence and recognition of heterogeneity of autism spectrum disorder (ASD) have grown in the past decade, relatively few data inform

Seeking Patient-and Family-Centered Care: The Experiences of Families of Children with an Autism Spectrum Disorder

Children with an autism spectrum disorder (ASD) have a higher annual mean number of total clinic, pediatric, and psychiatric outpatient visits, and inpatient and outpatient hospitalizations when compared to children without ASD. Families of individuals with ASD observe and experience specific barriers to medical care. Using a mixedmethods approach and interpretive phenomenological analysis (IPA), the perspectives of 40 families were gathered through a survey to gain a better understanding of positive and negative experiences, and the implications for healthcare providers and medical settings. Among the themes identified, families shared the need for healthcare providers to be more knowledgeable and trained about the heterogeneity of ASD, to presume competence and to view families as allies in facilitating medical encounters. As a result of these improvements, families also hope that healthcare providers develop greater compassion for families of children with ASD.

Influence of De novo mutation in autism

Autism and autism spectrum disorders (ASD) affects the areas of social awareness and interaction, verbal and nonverbal communication, and behaviors and interests, which are grouped among neurobehavioral disorders. One in 68 children is affected with ASD according to the estimate from the Center for Disease Control and Prevention's autism and developmental disabilities monitoring network and an increasing prevalence observed worldwide. A characteristic heterogeneity in ASD determined genetic variability as a major contributor. Whole-exome sequencing of ASD individuals revealed that discrete de novo mutation (single-nucleotide variation or small indels) also contribute to the overall genetic risk of ASD apart from rare genetic variation affecting single nucleotides of protein-coding DNA or rare genomic copy number variants as assessed through other high-throughput genomic methods. These genes are involved in synaptic transmission and regulated during brain development by acting upstream or downstream of Wingless- related integration site (WNT), bone morphogenetic proteins/transforming growth factor-β, sonic hedgehog, fibroblast growth factor, and retinoic acid signaling pathways. The current review focuses on genes involved in synaptic function, undergoing de novo mutation leading to ASD condition.

Vasopressin in Relation to Selected Oxidative Stress Markers as Etiological Mechanism of Autism

The marked heterogeneity of autism spectrum disorders is a challenge for research into biomarkers of these disorders. The present study aimed to assess the association of the thioredoxin (TRX) system and vasopressin with autism in children. Thirty-five autistic children were recruited with thirty-one healthy controls children matched for age and gender. Total antioxidant capacity (TAC), vasopressin, peroxiredoxin (PRDX1, PRDX3), phox domain-containing protein kinase-like protein, and TRX1 levels were measured in plasma and mercury and lead levels were measured in red blood cells. Children with autism had significantly lower levels of PRDX1 and TRX1 and significantly higher levels of lead and mercury compared with controls. Significantly higher levels of vasopressin were also observed in more severe cases of autism. Receiver operating characteristics analysis demonstrated satisfactory specificity and sensitivity of TAC, PRDX1, PRDX3, and TRX1 for the diagnosis of autism. The optimal cut-off value for plasma TRX1 levels, as an indicator of autism, was 10.6 ng/mL. Significant positive correlations existed between TRX system components, lead, and mercury. A negative correlation was found between vasopressin and TRX1, but positive correlations were found between vasopressin and mercury and lead. In conclusion, TAC, PRDX1, PRDX3, and TRX1 may be useful biomarkers for the diagnosis of autism in Saudi populations. Vasopressin-resistance in autistic patients may be due to an increased oxidative burden.

Animal models of autism: a perspective from autophagy mechanisms

Autism spectrum disorder (ASD) is characterized by impairments in social interaction and the presence of stereotypy and restrictive behavior. The clinical heterogeneity of ASD makes it difficult to explain the mechanisms underlying the disease. In recent years, the association between autophagy and neuropsychiatric diseases has been investigated. In this review, we aimed elucidate the relationship between autism and autophagy mechanism in well-known autism relevant animal models. Autophagy is a cell-protective mechanism that allows cell survival in low nutrient conditions, often through the degradation of aging and damaged proteins and organelles. The target of rapamycin (TOR) complex is activated for the activation of autophagy. Apart from mTOR animal models, the valproic acid model is frequently used in autism studies. The coiled-coil and C2 domain containing 1A (CC2D1A) gene is one of the new candidate genes associated with ASD. In a recent study that used Cc2d1a knock-out mice, microtubule-associated protein 1A/1B-light chain 3 (LC3) and Beclin 1 expression levels were dysregulated in the hippocampus. It is thought that the impaired autophagy mechanism contributes to the etiology of ASD. These results showed that CC2D1A acts as a new biological pathway in autophagy. Choosing the right model is crucial for ASD studies, and further progress will be made as these results become available in the clinic. In particular, it is expected that further studies on CC2D1A will provide new information in this field.

Autism spectrum disorder risk prediction: A systematic review of behavioral and neural investigations.

A reliable diagnosis of autism spectrum disorder (ASD) is difficult to make until after toddlerhood. Detection in an earlier age enables early intervention, which is typically more effective. Recent studies of the development of brain and behavior in infants and toddlers have provided important insights in the diagnosis of autism. This extensive review focuses on published studies of predicting the diagnosis of autism during infancy and toddlerhood younger than 3 years using behavioral and neuroimaging approaches. After screening a total of 782 papers, 17 neuroimaging and 43 behavioral studies were reviewed. The features for prediction consist of behavioral measures using screening tools, observational and experimental methods, brain volumetric measures, and neural functional activation and connectivity patterns. The classification approaches include logistic regression, linear discriminant function, decision trees, support vector machine, and deep learning based methods. Prediction performance has large variance across different studies. For behavioral studies, the sensitivity varies from 20% to 100%, and specificity ranges from 48% to 100%. The accuracy rates range from 61% to 94% in neuroimaging studies. Possible factors contributing to this inconsistency may be partially due to the heterogeneity of ASD, different targeted populations (i.e., high-risk group for ASD and general population), age when the features were collected, and validation procedures. The translation to clinical practice requires extensive further research including external validation with large sample size and optimized feature selection. The use of multi-modal features, e.g., combination of neuroimaging and behavior, is worth further investigation to improve the prediction accuracy.

Predicting ASD diagnosis: Pattern classification and stratification reviewed

Pattern classification (populations) and stratification (putting individuals into groups) are two approaches used in research on autism spectrum disorder (ASD), but translating them into clinical applicability is a challenge. How is ASD diagnosed, and how can it be predicted? One of the problems is the heterogeneity of ASD, another is that the initial diagnosis may not be as important as the trajectory, and the third is that regardless of the popularity of pattern classification, the people being treated are individuals, not populations.

Reconciling Dimensional and Categorical Models of Autism Heterogeneity: A Brain Connectomics and Behavioral Study

BackgroundHeterogeneity in autism spectrum disorder (ASD) has hindered the development of biomarkers, thus motivating subtyping efforts. Most subtyping studies divide individuals with ASD into nonoverlapping (categorical) subgroups. However, continuous interindividual variation in ASD suggests that there is a need for a dimensional approach. MethodsA Bayesian model was employed to decompose resting-state functional connectivity (RSFC) of individuals with ASD into multiple abnormal RSFC patterns, i.e., categorical subtypes, henceforth referred to as “factors.” Importantly, the model allowed each individual to express one or more factors to varying degrees (dimensional subtyping). The model was applied to 306 individuals with ASD (5.2–57 years of age) from two multisite repositories. Post hoc analyses associated factors with symptoms and demographics. ResultsAnalyses yielded three factors with dissociable whole-brain hypo- and hyper–RSFC patterns. Most participants expressed multiple (categorical) factors, suggestive of a mosaic of subtypes within individuals. All factors shared abnormal RSFC involving the default mode network, but the directionality (hypo- or hyper–RSFC) differed across factors. Factor 1 was associated with core ASD symptoms. Factors 1 and 2 were associated with distinct comorbid symptoms. Older male participants preferentially expressed factor 3. Factors were robust across control analyses and were not associated with IQ or head motion. ConclusionsThere exist at least three ASD factors with dissociable whole-brain RSFC patterns, behaviors, and demographics. Heterogeneous default mode network hypo- and hyper–RSFC across the factors might explain previously reported inconsistencies. The factors differentiated between core ASD and comorbid symptoms—a less appreciated domain of heterogeneity in ASD. These factors are coexpressed in individuals with ASD with different degrees, thus reconciling categorical and dimensional perspectives of ASD heterogeneity.

VariCarta: A Comprehensive Database of Harmonized Genomic Variants Found in Autism Spectrum Disorder Sequencing Studies.

Recent years have seen a boom in the application of the next-generation sequencing technology to the study of human disorders, including Autism Spectrum Disorder (ASD), where the focus has been on identifying rare, possibly causative genomic variants in ASD individuals. Because of the high genetic heterogeneity of ASD, a large number of subjects is needed to establish evidence for a variant or gene ASD-association, thus aggregating data across cohorts and studies is necessary. However, methodological inconsistencies and subject overlap across studies complicate data aggregation. Here we present VariCarta, a web-based database developed to address these challenges by collecting, reconciling, and consistently cataloging literature-derived genomic variants found in ASD subjects using ongoing semi-manual curation. The careful manual curation combined with a robust data import pipeline rectifies errors, converts variants into a standardized format, identifies and harmonizes cohort overlaps, and documents data provenance. The harmonization aspect is especially important since it prevents the potential double counting of variants, which can lead to inflation of gene-based evidence for ASD-association. The database currently contains 170,416 variant events from 10,893 subjects, collected across 61 publications, and reconciles 16,202 variants that have been reported in literature multiple times. VariCarta is freely accessible at http://varicarta.msl.ubc.ca. Autism Res 2019, 12: 1728-1736. © 2019 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: The search for genetic factors underlying Autism Spectrum Disorder (ASD) yielded numerous studies reporting potentially causative genomic variants found in ASD individuals. However, methodological differences and subject overlap across studies complicate the assembly of these data, diminishing its utility and accessibility. We developed VariCarta, a web-based database that aggregates carefully curated, annotated, and harmonized literature-derived variants identified in individuals with ASD using ongoing semi-manual curation.

Parsing Heterogeneity in Autism Spectrum Disorder and Attention-Deficit/Hyperactivity Disorder with Individual Connectome Mapping.

Traditional diagnostic systems for neurodevelopmental disorders define diagnostic categories that are heterogeneous in behavior and underlying neurobiological alterations. The goal of this study was to parse heterogeneity in a core executive function (EF), cognitive flexibility, in children with a range of abilities (N = 132; children with autism spectrum disorder, attention-deficit/hyperactivity disorder [ADHD], and typically developing children) using directed functional connectivity profiles derived from resting-state functional magnetic resonance imaging data. Brain regions activated in response to a cognitive flexibility task in adults were used to guide region-of-interest selection to estimate individual connectivity profiles in this study. We expected to find subgroups of children who differed in their network connectivity metrics and symptom measures. Unexpectedly, we did not find a stable or valid subgrouping solution, which suggests that categorical models of the neural substrates of cognitive flexibility in children may be invalid. Exploratory analyses revealed dimensional associations between network connectivity metrics and ADHD symptomatology and EF ability across the entire sample. Results shed light on the validity of conceptualizing the neural substrates of cognitive flexibility categorically in children. Ultimately, this work may provide a foundation for the development of a revised nosology focused on neurobiological substrates as an alternative to traditional symptom-based classification systems.

Boys with autism spectrum disorder have distinct cortical folding patterns underpinning impaired self-regulation: a surface-based morphometry study.

Although impaired self-regulation (dysregulation) in autism spectrum disorder (ASD) garnered increasing awareness, the neural mechanism of dysregulation in ASD are far from conclusive. To complement our previous voxel-based morphometry findings, we estimated the cortical thickness, surface area, and local gyrification index based on the surface-based morphometry from structural MRI images in 85 ASD and 65 typically developing control (TDC) boys, aged 7-17years. Levels of dysregulation were measured by the sum of T-scores of Attention, Aggression, and Anxiety/Depression subscales on the Child Behavior Checklist. We found both ASD and TDC shared similar relationships between dysregulation and cortical folding patterns in the left superior and inferior temporal gyri and the left premotor cortex. Significant diagnosis by dysregulation interactions in cortical folding patterns were identified over the right middle frontal and right lateral orbitofrontal regions. The statistical significance of greater local gyrification index in ASD than TDC in several brain regions disappeared when the level of dysregulation was considered. The findings of shared and distinct neural correlates underpinning dysregulation between ASD and TDC may facilitate the development of targeted interventions in the future. The present work also demonstrates that inter-subject variations in self-regulation may explain some extents of ASD-associated brain morphometric differences, likely suggesting that dysregulation is one of the yardsticks for dissecting the heterogeneity of ASD.

How to predict diagnosis of ASD: Pattern classification vs. stratification

Pattern‐classification (populations) and stratification (individuals) approaches may be useful in research on autism spectrum disorder (ASD), but translating them into clinical applicability is a challenge. How is ASD diagnosed, and how can it be predicted? One of the problems is the heterogeneity of ASD, another is that the initial diagnosis may not be as important as the trajectory, and the third is that regardless of the popularity of pattern classification, the people being treated are individuals, not populations.