Abstract
Postpartum depression (PPD) poses significant risks to maternal and infant health, yet proteomic analyses of PPD-risk women remain limited. This study analyzed plasma samples from 30 healthy postpartum women and 30 PPD-risk women using mass spectrometry, identifying 98 differentially expressed proteins (29 upregulated and 69 downregulated). Principal component analysis revealed distinct protein expression profiles between the groups. Functional enrichment and PPI analyses further explored the biological functions of these proteins. Machine learning models (XGBoost and LASSO regression) identified 17 key proteins, with the optimal logistic regression model comprising P13797 (PLS3), P56750 (CLDN17), O43173 (ST8SIA3), P01593 (IGKV1D-33), and P43243 (MATR3). The model demonstrated excellent predictive performance through ROC curves, calibration, and decision curves. These findings suggest potential biomarkers for early PPD risk assessment, paving the way for personalized prediction. However, limitations include the lack of diagnostic interviews, such as the Structured Clinical Interview for DSM-V (SCID), to confirm PPD diagnosis, a small sample size, and limited ethnic diversity, affecting generalizability. Future studies should expand sample diversity, confirm diagnoses with SCID, and validate biomarkers in larger cohorts to ensure their clinical applicability.