Abstract
Yu et al's study has advanced the understanding of the neural mechanisms underlying major depressive disorder (MDD) in adolescents, emphasizing the significant role of the amygdala. While traditional diagnostic methods have limitations in objectivity and accuracy, this research demonstrates a notable advancement through the integration of machine learning techniques with neuroimaging data. Utilizing resting-state functional magnetic resonance imaging (fMRI), the study investigated functional connectivity (FC) in adolescents with MDD, identifying notable reductions in regions such as the left inferior temporal gyrus and right lingual gyrus, alongside increased connectivity in Vermis-10. The application of support vector machines (SVM) to resting-state fMRI (rs-fMRI) data achieved an accuracy of 83.91%, sensitivity of 79.55%, and specificity of 88.37%, with an area under the curve of 0.6765. These results demonstrate how SVM analysis of rs-fMRI data represents a significant improvement in diagnostic precision, with reduced FC in the right lingual gyrus emerging as a particularly critical marker. These findings underscore the critical role of the amygdala in MDD pathophysiology and highlight the potential of rs-fMRI and SVM as tools for identifying reliable neuroimaging biomarkers.