Support Vector Machines, Multidimensional Scaling and Magnetic Resonance Imaging Reveal Structural Brain Abnormalities Associated With the Interaction Between Autism Spectrum Disorder and Sex

• Published in: Frontiers in computational neuroscience Vol. 12; p. 93
• Main Authors: Irimia, Andrei, Lei, Xiaoyu, Torgerson, Carinna M, Jacokes, Zachary J, Abe, Sumiko, Van Horn, John D
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 26.11.2018; Frontiers Media S.A
• Subjects: Anatomy; Artificial intelligence; Autism; Biomarkers; Brain architecture; Brain research; Communication; Data exchange; DTI; Epidemiology; Gerontology; Learning algorithms; Machine learning; Magnetic resonance imaging; Mathematical models; Medical imaging; Mental disorders; MRI; Multidimensional scaling; Neuroimaging; Neuroscience; NMR; Nuclear magnetic resonance; Psychiatry; Scaling; Statistics; support vector machine; Systematic review; Los Angeles California; United States > US; DTI; support vector machine; machine learning; MRI; autism; neuroimaging
• ISSN: 1662-5188; 1662-5188
• DOI: 10.3389/fncom.2018.00093

Despite substantial efforts, it remains difficult to identify reliable neuroanatomic biomarkers of autism spectrum disorder (ASD) based on magnetic resonance imaging (MRI) and diffusion tensor imaging (DTI). Studies which use standard statistical methods to approach this task have been hampered by numerous challenges, many of which are innate to the mathematical formulation and assumptions of general linear models (GLM). Although the potential of alternative approaches such as machine learning (ML) to identify robust neuroanatomic correlates of psychiatric disease has long been acknowledged, few studies have attempted to evaluate the abilities of ML to identify structural brain abnormalities associated with ASD. Here we use a sample of 110 ASD patients and 83 typically developing (TD) volunteers (95 females) to assess the suitability of support vector machines (SVMs, a robust type of ML) as an alternative to standard statistical inference for identifying structural brain features which can reliably distinguish ASD patients from TD subjects of either sex, thereby facilitating the study of the interaction between ASD diagnosis and sex. We find that SVMs can perform these tasks with high accuracy and that the neuroanatomic correlates of ASD identified using SVMs overlap substantially with those found using conventional statistical methods. Our results confirm and establish SVMs as powerful ML tools for the study of ASD-related structural brain abnormalities. Additionally, they provide novel insights into the volumetric, morphometric, and connectomic correlates of this epidemiologically significant disorder.