Insights into multimodal imaging classification of ADHD

Abstract

Attention deficit hyperactivity disorder (ADHD) currently is diagnosed in children by clinicians via subjective ADHD-specific behavioral instruments and by reports from the parents and teachers. Considering its high prevalence and large economic and societal costs, a quantitative tool that aids in diagnosis by characterizing underlying neurobiology would be extremely valuable. This provided motivation for the ADHD-200 machine learning (ML) competition, a multisite collaborative effort to investigate imaging classifiers for ADHD. Here we present our ML approach, which used structural and functional magnetic resonance imaging data, combined with demographic information, to predict diagnostic status of individuals with ADHD from typically developing (TD) children across eight different research sites. Structural features included quantitative metrics from 113 cortical and non-cortical regions. Functional features included Pearson correlation functional connectivity matrices, nodal and global graph theoretical measures, nodal power spectra, voxelwise global connectivity, and voxelwise regional homogeneity. We performed feature ranking for each site and modality using the multiple support vector machine recursive feature elimination (SVM-RFE) algorithm, and feature subset selection by optimizing the expected generalization performance of a radial basis function kernel SVM (RBF-SVM) trained across a range of the top features. Site-specific RBF-SVMs using these optimal feature sets from each imaging modality were used to predict the class labels of an independent hold-out test set. A voting approach was used to combine these multiple predictions and assign final class labels. With this methodology we were able to predict diagnosis of ADHD with 55% accuracy (versus a 39% chance level in this sample), 33% sensitivity, and 80% specificity. This approach also allowed us to evaluate predictive structural and functional features giving insight into abnormal brain circuitry in ADHD.

Machine learning classification of mesial temporal sclerosis in epilepsy patients

“…The methods were implemented in a similar fashion as Colby et al (2012). We applied linear support vector machine recursive feature elimination (SVM-RFE; Guyon et al, 2002) in order to obtain a ranked list of features that best distinguished the 85 epilepsy patients with defined MTS from the 84 without.…”

“…Support vector machines (SVM) are a class of machine learning algorithms that are well suited for neuroimaging data as they are fast, flexible and can be readily automated. They have been studied extensively in computer science and have been applied to neuroimaging data from a variety of neurological diseases including Alzheimer's disease (Klöppel et al, 2008), autism spectrum disorder (Ecker et al, 2010) and ADHD (Colby et al, 2012).…”

Inter-hemispherical asymmetry in default-mode functional connectivity and BAIAP2 gene are associated with anger expression in ADHD adults

“…From a neuroimaging viewpoint, compelling evidence points to rather large-scale abnormalities in network organization in ADHD (Sergeant et al, 2006;Konrad and Eickhoff, 2010;Cao et al, 2013), affecting both functional (Cocchi et al, 2012;Colby et al, 2012;Fair et al, 2012;Tomasi and Volkow, 2012;Cao et al, 2013;Di Martino et al, 2013) and structural (Cao et al, 2013;Hong et al, 2014) connectivity. Moreover, an abnormal hemispheric asymmetry of brain structure and function was also consistently reported in ADHD (Dennis and Thompson, 2013;Shang et al, 2013;Cao et al, 2014;Hale et al, 2014Hale et al, , 2015Keune et al, 2015;Silk et al, 2015), suggesting a possible neurodevelopmental scenario for this disorder.…”

Network Construction and Graph Theoretical Analysis of Functional Language Networks in Pediatric Epilepsy

“…On the other hand, the intensity of activation network yielded clusters with fair precision, which is close to other studies that reported precision values around 75% in: epilepsy (J. Zhang et al, 2012), attention-deficit hyperactivity disorder (Colby, 2012;Dai et al, 2012), autism (Anderson et al, 2011), Alzheimer's disease J. Wang et al, 2013b), schizophrenia (Bassett et al, 2012), and unipolar or severe depression (Lord et al, 2012;Zeng et al, 2012).…”