Dataset Information

Applications of node-based resilience graph theoretic framework to clustering autism spectrum disorders phenotypes.

ABSTRACT: With the growing ubiquity of data in network form, clustering in the context of a network, represented as a graph, has become increasingly important. Clustering is a very useful data exploratory machine learning tool that allows us to make better sense of heterogeneous data by grouping data with similar attributes based on some criteria. This paper investigates the application of a novel graph theoretic clustering method, Node-Based Resilience clustering (NBR-Clust), to address the heterogeneity of Autism Spectrum Disorder (ASD) and identify meaningful subgroups. The hypothesis is that analysis of these subgroups would reveal relevant biomarkers that would provide a better understanding of ASD phenotypic heterogeneity useful for further ASD studies. We address appropriate graph constructions suited for representing the ASD phenotype data. The sample population is drawn from a very large rigorous dataset: Simons Simplex Collection (SSC). Analysis of the results performed using graph quality measures, internal cluster validation measures, and clinical analysis outcome demonstrate the potential usefulness of resilience measure clustering for biomedical datasets. We also conduct feature extraction analysis to characterize relevant biomarkers that delineate the resulting subgroups. The optimal results obtained favored predominantly a 5-cluster configuration.

SUBMITTER: Matta J

PROVIDER: S-EPMC6214326 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAtypical reactions to the sensory environment are often reported in autistic individuals, with a high degree of variability across the sensory modalities. These sensory differences have been shown to promote challenging behaviours and distress in autistic individuals and are predictive of other functions including motor, social, and cognitive abilities. Preliminary research suggests that specific sensory differences may cluster together within individuals creating discrete sensory phenotypes. However, the manner in which these sensory differences cluster, and whether the resulting phenotypes are associated with specific cognitive and social challenges is unclear.MethodsShort sensory profile data from 599 autistic children and adults between the ages of 1 and 21 years were subjected to a K-means cluster analysis. Analysis of variances compared age, adaptive behaviour, and traits associated with autism, attention-deficit and hyperactivity disorder, and obsessive and compulsive disorder across the resultant clusters.ResultsA five-cluster model was found to minimize error variance and produce five sensory phenotypes: (1) sensory adaptive, (2) generalized sensory differences, (3) taste and smell sensitivity, (4) under-responsive and sensation seeking, and (5) movement difficulties with low energy. Age, adaptive behaviour, and traits associated with autism, attention-deficit and hyperactivity disorder, and obsessive and compulsive disorder were found to differ significantly across the five phenotypes.LimitationsThe results were based on parent-report measures of sensory processing, adaptive behaviour, traits associated with autism, attention-deficit and hyperactivity disorder, and obsessive and compulsive disorder, which may limit the generalizability of the findings. Further, not all measures are standardized, or psychometrically validated with an autism population. Autistic individuals with an intellectual disability were underrepresented in this sample. Further, as these data were obtained from established records from a large provincial database, not all measures were completed for all individuals.ConclusionsThese findings suggest that sensory difficulties in autistic individuals can be clustered into sensory phenotypes, and that these phenotypes are associated with behavioural differences. Given the large degree of heterogeneity in sensory difficulties seen in the autistic population, these sensory phenotypes represent an effective way to parse that heterogeneity and create phenotypes that may aid in the development of effective treatments and interventions for sensory difficulties.

Dataset Information

Applications of node-based resilience graph theoretic framework to clustering autism spectrum disorders phenotypes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets