Back to Search
Start Over
Discriminative analysis of schizophrenia using support vector machine and recursive feature elimination on structural MRI images
- Source :
- Medicine, Lu, X, Yang, Y, Wu, F, Gao, M, Xu, Y, Yang, Y, Yao, Y, Du, X, Li, C, Wu, L, Zhong, X, Zhou, Y, Fan, N, Zheng, Y, Xiong, D, Peng, H, Escudero, J, Huang, B, Li, X, Ning, Y & Wu, K 2016, ' Discriminative analysis of schizophrenia using support vector machine and recursive feature elimination on structural MRI images ', Medicine, vol. 95, no. 30, e3973 . https://doi.org/10.1097/MD.0000000000003973
- Publication Year :
- 2016
- Publisher :
- Wolters Kluwer Health, 2016.
-
Abstract
- Supplemental Digital Content is available in the text<br />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.
- Subjects :
- Adult
Male
Observational Study
computer.software_genre
Sensitivity and Specificity
White matter
03 medical and health sciences
Mri image
0302 clinical medicine
Text mining
Discriminative model
Voxel
Region of interest
mental disorders
recursive feature elimination
medicine
Image Processing, Computer-Assisted
Humans
voxel-based morphometry
support vector machine
Gray Matter
medicine.diagnostic_test
business.industry
Pattern recognition
Magnetic resonance imaging
General Medicine
Magnetic Resonance Imaging
White Matter
030227 psychiatry
Support vector machine
schizophrenia
medicine.anatomical_structure
Case-Control Studies
ComputingMethodologies_DOCUMENTANDTEXTPROCESSING
Female
Artificial intelligence
region of interest
business
computer
030217 neurology & neurosurgery
Research Article
Subjects
Details
- Language :
- English
- ISSN :
- 15365964 and 00257974
- Volume :
- 95
- Issue :
- 30
- Database :
- OpenAIRE
- Journal :
- Medicine
- Accession number :
- edsair.doi.dedup.....8ab76f3c19c531cd4c61c16c91d80ca6