Search

Autism spectrum disorder is a heterogeneous neurodevelopmental disorder. Early brain overgrowth yet reduced cerebellar size is well recognized for autism, but cortical regions involved show inconsistent patterns of alteration. No complete and replicable map of early regional brain size alterations has been charted. It is also not clear whether individual differences in brain size relate to autism symptom severity and cognitive deficits and predict later language outcomes. We leveraged structural MRI data from 166 autistic and 109 typical developing toddlers to comprehensively and systematically investigate regional gray matter volume alterations and cortical surface area and thickness perturbations in autism compared to typical developing toddlers using linear mixed-effect models. We then examined their replicability in an independent cohort of 38 autistic and 37 typical developing toddlers. We further investigated associations between regional brain size and symptom severity, Mullen and Vineland cognitive performance using linear regression models. Lastly, we investigated whether early brain size (at intake mean age of 2.5 years) can improve support vector machine prediction of language outcome at 3-4 years of age when added to a model containing intake clinical and behavioral measures. Compared to typical developing toddlers, autistic toddlers presented larger or thicker lateral temporal regions, smaller or thinner frontal lobe and midline structures, larger callosal subregion volume, and smaller cerebellum. Most of these differences were replicated in an independent toddler cohort. Moreover, the identified gray matter alterations were related to autism symptom severity and cognitive impairments at intake, and, remarkably, they improved the accuracy for predicting later language outcome beyond intake clinical and demographic variables. Gray matter volume, thickness, and surface area in regions involved in language, social, and face processing were altered in autistic toddlers. Alterations in these regions are major early-age developmental attributes of autism. The early-age alterations in these cortical attributes in different regions may be the result of dysregulation in multiple neural processes and stages, consistent with prenatal multi-process, multi-stage models of autism. Here we also show these gray matter alterations are promising prognostic biomarkers for language outcome prediction.

Autism Spectrum Disorder (ASD) diagnosis remains behavior-based and the median age of diagnosis is ~52 months, nearly 5 years after its first-trimester origin. Accurate and clinically-translatable early-age diagnostics do not exist due to ASD genetic and clinical heterogeneity. Here we collected clinical, diagnostic, and leukocyte RNA data from 240 ASD and typically developing (TD) toddlers (175 toddlers for training and 65 for test). To identify gene expression ASD diagnostic classifiers, we developed 42,840 models composed of 3570 gene expression feature selection sets and 12 classification methods. We found that 742 models had AUC-ROC ≥ 0.8 on both Training and Test sets. Weighted Bayesian model averaging of these 742 models yielded an ensemble classifier model with accurate performance in Training and Test gene expression datasets with ASD diagnostic classification AUC-ROC scores of 85–89% and AUC-PR scores of 84–92%. ASD toddlers with ensemble scores above and below the overall ASD ensemble mean of 0.723 (on a scale of 0 to 1) had similar diagnostic and psychometric scores, but those below this ASD ensemble mean had more prenatal risk events than TD toddlers. Ensemble model feature genes were involved in cell cycle, inflammation/immune response, transcriptional gene regulation, cytokine response, and PI3K-AKT, RAS and Wnt signaling pathways. We additionally collected targeted DNA sequencing smMIPs data on a subset of ASD risk genes from 217 of the 240 ASD and TD toddlers. This DNA sequencing found about the same percentage of SFARI Level 1 and 2 ASD risk gene mutations in TD (12 of 105) as in ASD (13 of 112) toddlers, and classification based only on the presence of mutation in these risk genes performed at a chance level of 49%. By contrast, the leukocyte ensemble gene expression classifier correctly diagnostically classified 88% of TD and ASD toddlers with ASD risk gene mutations. Our ensemble ASD gene expression classifier is diagnostically predictive and replicable across different toddler ages, races, and ethnicities; out-performs a risk gene mutation classifier; and has potential for clinical translation.