TY - JOUR
T1 - Multivariate pattern classification of pediatric Tourette syndrome using functional connectivity MRI
AU - Greene, Deanna J.
AU - Church, Jessica A.
AU - Dosenbach, Nico U.F.
AU - Nielsen, Ashley N.
AU - Adeyemo, Babatunde
AU - Nardos, Binyam
AU - Petersen, Steven E.
AU - Black, Kevin J.
AU - Schlaggar, Bradley L.
N1 - Funding Information:
We thank Rebecca Coalson, Rebecca Lepore, Kelly McVey, Jonathan Koller, and Emily Bihun for assistance with data collection, Rashina Seabury for Tables, the children who participated in this study and their families. This project was supported by Tourette Association of America fellowships (DJG, JAC), research grant (DJG), and Neuroimaging Consortium pilot grant (KJB, BLS), NARSAD Young Investigator Award (DJG), NIH K01MH104592 (DJG), NIH R21MH091512 (BLS), NIH R01HD057076 (BLS), NIH K24MH087913 (KJB), NIH R21 NS091635 (BLS, KJB), NIH F32NS065649 (JAC), K12HD076224 (NUFD, Scholar of the Child Health Research Center at Washington University), NIH K23NS088590 (NUFD), the Intellectual and Developmental Disabilities Research Center at Washington University (NIH/NICHD P30HD062171), and the Simons Foundation Autism Research Initiative (‘Brain circuitry in Simplex Autism’, SEP).
Publisher Copyright:
© 2016 The Authors. Developmental Science Published by John Wiley & Sons Ltd.
PY - 2016/7/1
Y1 - 2016/7/1
N2 - Tourette syndrome (TS) is a developmental neuropsychiatric disorder characterized by motor and vocal tics. Individuals with TS would benefit greatly from advances in prediction of symptom timecourse and treatment effectiveness. As a first step, we applied a multivariate method - support vector machine (SVM) classification - to test whether patterns in brain network activity, measured with resting state functional connectivity (RSFC) MRI, could predict diagnostic group membership for individuals. RSFC data from 42 children with TS (8-15 yrs) and 42 unaffected controls (age, IQ, in-scanner movement matched) were included. While univariate tests identified no significant group differences, SVM classified group membership with ~70% accuracy (p < .001). We also report a novel adaptation of SVM binary classification that, in addition to an overall accuracy rate for the SVM, provides a confidence measure for the accurate classification of each individual. Our results support the contention that multivariate methods can better capture the complexity of some brain disorders, and hold promise for predicting prognosis and treatment outcome for individuals with TS.
AB - Tourette syndrome (TS) is a developmental neuropsychiatric disorder characterized by motor and vocal tics. Individuals with TS would benefit greatly from advances in prediction of symptom timecourse and treatment effectiveness. As a first step, we applied a multivariate method - support vector machine (SVM) classification - to test whether patterns in brain network activity, measured with resting state functional connectivity (RSFC) MRI, could predict diagnostic group membership for individuals. RSFC data from 42 children with TS (8-15 yrs) and 42 unaffected controls (age, IQ, in-scanner movement matched) were included. While univariate tests identified no significant group differences, SVM classified group membership with ~70% accuracy (p < .001). We also report a novel adaptation of SVM binary classification that, in addition to an overall accuracy rate for the SVM, provides a confidence measure for the accurate classification of each individual. Our results support the contention that multivariate methods can better capture the complexity of some brain disorders, and hold promise for predicting prognosis and treatment outcome for individuals with TS.
UR - http://www.scopus.com/inward/record.url?scp=85028269104&partnerID=8YFLogxK
U2 - 10.1111/desc.12407
DO - 10.1111/desc.12407
M3 - Article
C2 - 26834084
AN - SCOPUS:85028269104
SN - 1363-755X
VL - 19
SP - 581
EP - 598
JO - Developmental Science
JF - Developmental Science
IS - 4
ER -