Discriminative Analysis of Depression Patients Studied with Structural MR Images Using Support Vector Machine and Recursive Feature Elimination
- 97 Downloads
Currently, the diagnosis of depression is largely based on clinical judgments due to the absence of objective biomarkers. There are increasing evidences that depression (DP) is associated with structural abnormalities. However, the previous analyses have a poor predictive power for individuals. To discriminate DP patients from normal controls (NCs) studied with structural magnetic resonance images using the method of support vector machine (SVM) combined with recursive feature elimination (RFE). In this study, 40 DP patients and 40 age- and sex-matched NCs were recruited from Guangzhou Brain Hospital and the local community, respectively. We calculated gray matter volume (GMV) and white matter volume (WMV) of 210 cortical and 36 subcortical regions, defined by the Human Brainnetome Atlas. The group differences between DP patients and NCs were compared. The method of SVM combined with RFE was applied into the discriminative analysis of DP patients from NCs, in which discriminative features were drawn from GMV and WMV. We found that the DP patients showed significant GMV reductions in eight brain regions and showed significant WMV reductions in ten brain regions. The classifier using GMV as input features achieved the best performance (an accuracy of 86.25%, a sensitivity of 85%, and a specificity of 87.5%) in the discriminative analyses between DP patients and NCs. These findings provided evidences that specific structural brain regions associated with DP patients might qualify as a potential biomarker for disease diagnosis, and the machine-learning method of SVM with RFE may reveal neurobiological mechanisms in distinguishing DP patients from NCs.
KeywordsDepression Region of interest Support vector machine Recursive feature elimination
This work was supported by the National Natural Science Foundation of China (NSFC; 31400845, 31771074), the National Key Technology Research and Development Program of the Ministry of Science and Technology of China (2015BAI13B01, 2015BAI13B02), the Guangdong Natural Science Foundation (2015A030313800), the Science and Technology Program of Guangdong (2016B010108003, 2016A020216004), the Science and Technology Program of Guangzhou (201604020170, 2017010160496, 201704020168, 201807010064), the Guangzhou Medical and Health Science and Technology Project (20171A011268, 20171A010283), and the Youth Innovation Talent Project of Guangdong Education Department (2017KQNCX259).
- 13.Arbabshirani, M. R., Castro, E., & Calhoun, V, D. (2014). Accurate classification of schizophrenia patients based on novel resting-state fMRI features. In IEEE engineering in medicine and biology society conference proceedings (pp. 6691–6694).Google Scholar
- 14.Wu, F., Zhang, Y., & Yang, Y., et al. (2018). Structural and functional brain abnormalities in drug-naive, first-episode, and chronic patients with schizophrenia: a multimodal MRI study. Neuropsychiatric Disease and Treatment.Google Scholar
- 17.Xiao, Y., Yan, Z., & Zhao, Y, et al. (2017). Support vector machine-based classification of first episode drug-naïve schizophrenia patients and healthy controls using structural MRI. Schizophrenia Research.Google Scholar
- 22.Bobo, W. V., Anglero, G. C., Jenkins, G., et al. (2016). Validation of the 17-item Hamilton depression rating scale definition of response for adults with major depressive disorder using equipercentile linking to clinical global impression scale ratings: Analysis of pharmacogenomic research network antidepressant medication pharmacogenomic study (PGRN-AMPS) data. Human Psychopharmacology, 31(3), 185–192.CrossRefGoogle Scholar
- 30.Chi, M., Guo, S., Ning, Y., et al. (2014). Using support vector machine to identify imaging biomarkers of major depressive disorder and anxious depression (Vol. 472, pp. 63–67). Wuhan: Springer.Google Scholar