Predictive Analysis of Postpartum Depression Using Machine Learning

<b>Background:</b> Maternal postpartum depression (PPD) is a major psychological problem affecting mothers, newborns, and their families after childbirth. This study investigated the factors influencing maternal PPD and developed a predictive model using machine learning. <b>Methods/Design:</b> In this study, we applied machine learning techniques to identify significant predictors of PPD and to develop a model for classifying individuals at risk. Data from 2570 subjects were analyzed using the Korean Early Childhood Education and Care Panel (K-ECEC-P) dataset as of January 2025, utilizing Python version 3.12.8. <b>Results:</b> We compared the performance of a decision tree classifier, random forest classifier, AdaBoost classifier, and logistic regression model using metrics such as precision, accuracy, recall, F1-score, and area under the curve. The logistic regression model was selected as the best model. Among the 13 features analyzed, conflict with a partner, stress, and the value of children emerged as significant predictors of PPD. <b>Discussion:</b> Conflict with a partner and stress levels emerged as the strongest predictors. Higher levels of conflict and stress were associated with an increased likelihood of PPD, whereas a higher value of children reduced this risk. Maternal psychological status and environmental features should be managed carefully during the postpartum period.