Letter to the Editor
Copyright ©The Author(s) 2025.
World J Psychiatry. May 19, 2025; 15(5): 102953
Published online May 19, 2025. doi: 10.5498/wjp.v15.i5.102953
Table 1 Results of previous studies using neuroimaging techniques, machine learning, and deep learning in the context of major depressive disorder
Neuroimaging technique
Machine learning approaches
Deep learning approaches
Findings/applications
Ref.
fMRISVM, XGBoostCNNIdentification of functional connectivity alterations, prediction of treatment response, generalizable markers across imaging sitesAnderson et al[21], Shi et al[22], Yamashita et al[23]
sMRIPCA, ICAAutoencodersDetection of gray matter volume reductions, feature extraction, and identification of structural biomarkersZhang et al[24], Ho et al[25]
PETFeature selectionEvaluation of altered glucose metabolism, identification of treatment-specific biomarkersMcGrath et al[26], Kang and Cho[27]
EEGTime-series analysisCNN, RNN, LSTMAnalysis of altered neural oscillations, connectivity patterns, and prediction models using EEG-based approachesUyulan et al[28], Yang et al[29]
Table 2 Demographic and clinical characteristics
Variable
MDD group (n = 44)
Control group (n = 43)
P value
Age (years)15 ± 215 ± 2> 0.05
Sex (male/female)10/3411/32> 0.05
Education (years)10 ± 310 ± 3> 0.05
HAMD-17 Score21 ± 55 ± 3< 0.05