1 April 2017 in The Lancet Psychiatry
20 August 2018 in Nature Neuroscience
1 July 2011 in Brain Stimulation
1 January 2012 in Frontiers in Systems Neuroscience
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 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 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.
1 November 2014 in NeuroImage
24 September 2002 in Human Mutation
PEX7 encodes the cytosolic receptor for the set of peroxisomal matrix enzymes targeted to the organelle by the peroxisome targeting signal 2 (PTS2). Mutations in PEX7 cause rhizomelic chondrodysplasia punctata (RCDP), a distinct peroxisome biogenesis disorder. In previous work we described three novel PEX7 mutant alleles, including one, L292X, with a high frequency due to a founder effect. We have now extended our analysis to 60 RCDP probands and identified a total of 24 PEX7 alleles, accounting for 95% of the mutant PEX7 genes in our sample. Of these, 50% are L292X, 13% are IVS9+1G>C, and the remainder are mostly private. IVS9+1G>C occurs on at least three different haplotypes and thus appears to result from recurrent mutation. The phenotypic spectrum of RCDP is broader than commonly recognized and includes minimally affected individuals at the mild end of the spectrum. To relate PEX7 genotype and phenotype, we evaluated the consequence of the disease mutation on PEX7 RNA by Northern analysis and RT/PCR. We evaluated the function of the encoded Pex7 protein (Pex7p) by expressing selected alleles in fibroblasts from RCDP patients and assaying their ability to restore import of a PTS2 marker protein. We find that residual activity of mutant Pex7p and reduced amounts of normal Pex7p are associated with milder and variant phenotypes. Hum Mutat 20:284–297, 2002.