Classification of pure conduct disorder from healthy controls based on indices of brain networks during resting state

• Published in: Medical & biological engineering & computing Vol. 58; no. 9; pp. 2071 - 2082
• Main Authors: Zhang, Jiang, Liu, Yuyan, Luo, Ruisen, Du, Zhengcong, Lu, Fengmei, Yuan, Zhen, Zhou, Jiansong, Li, Shasha
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2020; Springer Nature B.V
• Subjects: Bayesian analysis; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Brain; Children; Classification; Classifiers; Computer Applications; Conduct disorder; Control methods; Emotional disorders; Feature extraction; Feature selection; Human Physiology; Imaging; Mental health; Networks; Original Article; Radiology; Singular value decomposition; Support vector machines; Conduct disorder; Functional magnetic resonance imaging; Classification scheme; Feature selection; Small-world networks
• DOI: 10.1007/s11517-020-02215-8
• ISSN: 0140-0118; 1741-0444

Conduct disorder (CD) is an important mental health problem in childhood and adolescence. There is presently a trend of revealing neural mechanisms using measures of brain networks. This study goes further by presenting a classification scheme to distinguish subjects with CD from typically developing healthy subjects based on measures of small-world networks. In this study, small-world networks were constructed, and feature data were generated for both the CD and healthy control (HC) groups. Two methods of feature selection, including the F -score and feature projection with singular value decomposition (SVD), were used to extract the feature data. Furthermore, and importantly, the classification performances were compared between the results from the two methods of feature selection. The selected feature data by SVD were employed to train three classifiers—least squares support vector machine (LS-SVM), naive Bayes and K-nearest neighbour (KNN)—for CD classification. Cross-validation results from 36 subjects showed that CD patients can be separated from HC with a sensitivity, specificity and overall accuracy of 88.89%, 100% and 94.44%, respectively, by using the LS-SVM classifier. These findings suggest that the combination of the LS-SVM classifier with SVD can achieve a higher degree of accuracy for CD diagnosis than the naive Bayes and KNN classifiers. Graphical abstract