Applications of novel graph theoretic methods to clustering autism spectrum disorders phenotypes

Abstract

This paper applies two node-based graph theoretic algorithms to cluster a set of 2680 Autism Spectrum Disorder (ASD) subjects using ASD phenotype features. The two node-based resilience measures are vertex attack tolerance (VAT) and integrity. Analysis of the results performed using internal cluster validation measures and clinical analysis outcome demonstrate the potential usefulness of resilience measure clustering for biomedical datasets.

Department(s)

Engineering Program

Document Type

Conference Proceeding

Keywords

Autism spectrum disorders, Clustering, Graph theory, Resilience measures

Publication Date

1-1-2017

Journal Title

Proceedings of the 9th International Conference on Bioinformatics and Computational Biology, BICOB 2017

Citation-only

Share

COinS