Dataset Information

Motor and sensory features successfully decode autism spectrum disorder and combine with the original RDoC framework to boost diagnostic classification.

ABSTRACT: Sensory processing and motor coordination atypicalities are not commonly identified as primary characteristics of autism spectrum disorder (ASD), nor are they well captured in the NIMH's original Research Domain Criteria (RDoC) framework. Here, motor and sensory features performed similarly to RDoC features in support vector classification of 30 ASD youth against 33 typically developing controls. Combining sensory with RDoC features boosted classification performance, achieving a Matthews Correlation Coefficient (MCC) of 0.949 and balanced accuracy (BAcc) of 0.971 (p = 0.00020, calculated against a permuted null distribution). Sensory features alone successfully classified ASD (MCC = 0.565, BAcc = 0.773, p = 0.0222) against a clinically relevant control group of 26 youth with Developmental Coordination Disorder (DCD) and were in fact required to decode against DCD above chance. These findings highlight the importance of sensory and motor features to the ASD phenotype and their relevance to the RDoC framework.

SUBMITTER: Harrison LA

PROVIDER: S-EPMC8035204 | biostudies-literature | 2021 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Motor and sensory features successfully decode autism spectrum disorder and combine with the original RDoC framework to boost diagnostic classification.

Harrison Laura A LA Kats Anastasiya A Kilroy Emily E Butera Christiana C Jayashankar Aditya A Keles Umit U Aziz-Zadeh Lisa L

Scientific reports 20210409 1

Sensory processing and motor coordination atypicalities are not commonly identified as primary characteristics of autism spectrum disorder (ASD), nor are they well captured in the NIMH's original Research Domain Criteria (RDoC) framework. Here, motor and sensory features performed similarly to RDoC features in support vector classification of 30 ASD youth against 33 typically developing controls. Combining sensory with RDoC features boosted classification performance, achieving a Matthews Correl ...[more]

PMID: 33837251

Similar Datasets

Project description:Background: Autism spectrum disorder (ASD) involves alterations in both cortical morphology and sensory processing. These structural and perceptual changes may lie on a continuum with typically developing (TD) individuals. However, investigations on possible links between these two factors are lacking, and it remains to be seen if their relationship differs by sex. We hypothesized that cortical thickness in the postcentral gyrus (a somatosensory processing hub) would correlate with sensory processing symptoms in a combined cohort of autistic and TD individuals. We also hypothesized that these correlations would differ based on sex. Methods: We studied 23 autistic adults and 27 TD adults using magnetic resonance imaging to measure the cortical thickness of the postcentral gyrus and the Ritvo Autism Asperger Diagnostic Scale-Revised (RAADS-R) to measure autism characteristics, with a particular focus on the sensory motor subscale. Results: The left postcentral gyrus (PCG) was found to be thicker in the autism group than in the TD group (d = 0.946, p = 0.003), particularly in autistic males compared to TD males and TD females. The RAADS-R sensory motor subscale and bilateral PCG cortical thickness were positively correlated across both autistic and TD males (Spearman's rho = 0.481, p = 0.008) but not females. These correlations were specific to the sensory motor subscale, as no correlations were found for RAADS-R total score or any of the other subscales. Conclusions: These results demonstrate sex-specific differences in the relationship between cortical thickness at the PCG and sensory processing in autistic individuals and that these differences exist along a continuum that extends into the TD population. Our findings contribute to furthering our understanding of sex-specific neuroanatomical differences in people on the autism spectrum. The left PCG thickness could be a potential sex-specific biomarker for sensorimotor function that is generally applicable in both neurotypical and autism populations. With further validations, this biomarker could be used to track responses to interventions targeting sensorimotor challenges in people on the autism spectrum.

Dataset Information

Motor and sensory features successfully decode autism spectrum disorder and combine with the original RDoC framework to boost diagnostic classification.

Publications

Motor and sensory features successfully decode autism spectrum disorder and combine with the original RDoC framework to boost diagnostic classification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets