TY - JOUR
T1 - Discriminative analysis of schizophrenia using support vector machine and recursive feature elimination on structural MRI images
AU - Lu, Xiaobing
AU - Yang, Yongzhe
AU - Wu, Fengchun
AU - Gao, Minjian
AU - Xu, Yong
AU - Zhang, Yue
AU - Yao, Yongcheng
AU - Du, Xin
AU - Li, Chengwei
AU - Wu, Lei
AU - Zhong, Xiaomei
AU - Zhou, Yanling
AU - Fan, Ni
AU - Zheng, Yingjun
AU - Xiong, Dongsheng
AU - Peng, Hongjun
AU - Escudero, Javier
AU - Huang, Biao
AU - Li, Xiaobo
AU - Ning, Yuping
AU - Wu, Kai
N1 - Publisher Copyright:
Copyright © 2016 the Author(s). Published by Wolters Kluwer Health, Inc. All rights reserved.
PY - 2016/7/1
Y1 - 2016/7/1
N2 - Structural abnormalities in schizophrenia (SZ) patients have been well documented with structural magnetic resonance imaging (MRI) data using voxel-based morphometry (VBM) and region of interest (ROI) analyses. However, these analyses can only detect group-wise differences and thus, have a poor predictive value for individuals. In the present study, we applied a machine learning method that combined support vector machine (SVM) with recursive feature elimination (RFE) to discriminate SZ patients from normal controls (NCs) using their structural MRI data. We first employed both VBM and ROI analyses to compare gray matter volume (GMV) and white matter volume (WMV) between 41 SZ patients and 42 age- and sex-matched NCs. The method of SVM combined with RFE was used to discriminate SZ patients from NCs using significant between-group differences in both GMV and WMV as input features. We found that SZ patients showed GM and WM abnormalities in several brain structures primarily involved in the emotion, memory, and visual systems. An SVM with a RFE classifier using the significant structural abnormalities identified by the VBM analysis as input features achieved the best performance (an accuracy of 88.4%, a sensitivity of 91.9%, and a specificity of 84.4%) in the discriminative analyses of SZ patients. These results suggested that distinct neuroanatomical profiles associated with SZ patients might provide a potential biomarker for disease diagnosis, and machine-learning methods can reveal neurobiological mechanisms in psychiatric diseases.
AB - Structural abnormalities in schizophrenia (SZ) patients have been well documented with structural magnetic resonance imaging (MRI) data using voxel-based morphometry (VBM) and region of interest (ROI) analyses. However, these analyses can only detect group-wise differences and thus, have a poor predictive value for individuals. In the present study, we applied a machine learning method that combined support vector machine (SVM) with recursive feature elimination (RFE) to discriminate SZ patients from normal controls (NCs) using their structural MRI data. We first employed both VBM and ROI analyses to compare gray matter volume (GMV) and white matter volume (WMV) between 41 SZ patients and 42 age- and sex-matched NCs. The method of SVM combined with RFE was used to discriminate SZ patients from NCs using significant between-group differences in both GMV and WMV as input features. We found that SZ patients showed GM and WM abnormalities in several brain structures primarily involved in the emotion, memory, and visual systems. An SVM with a RFE classifier using the significant structural abnormalities identified by the VBM analysis as input features achieved the best performance (an accuracy of 88.4%, a sensitivity of 91.9%, and a specificity of 84.4%) in the discriminative analyses of SZ patients. These results suggested that distinct neuroanatomical profiles associated with SZ patients might provide a potential biomarker for disease diagnosis, and machine-learning methods can reveal neurobiological mechanisms in psychiatric diseases.
KW - recursive feature elimination
KW - region of interest
KW - schizophrenia
KW - support vector machine
KW - voxel-based morphometry
UR - http://www.scopus.com/inward/record.url?scp=84982803482&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84982803482&partnerID=8YFLogxK
U2 - 10.1097/MD.0000000000003973
DO - 10.1097/MD.0000000000003973
M3 - Article
C2 - 27472673
AN - SCOPUS:84982803482
SN - 0025-7974
VL - 95
JO - Medicine (United States)
JF - Medicine (United States)
IS - 30
M1 - 176
ER -