An Uncertainty-Aware Ensemble of Support Vector Machine and Gaussian Process Models for Maternal Mental Health Risk Prediction Using Psychosocial and Clinical Risk Factors
Study develops an uncertainty-aware ensemble machine learning model combining SVM and Gaussian Process algorithms to predict postpartum depression risk using clinical and psychosocial factors from multicountry datasets. Random Forest achieved highest accuracy (97.75%), while the proposed hybrid model demonstrated superior uncertainty calibration for clinical reliability.