Trajectory on postpartum depression of Chinese women and the risk prediction models: A machine-learning based three-wave follow-up research.

Background: Our study delves into postpartum depression (PPD) extending observation up to six months postpartum, addressing the gap in long-term follow-ups and uncover critical intervention points.

Method: Through a continuous three-wave cohort study involving 3174 of 10,730 invited postpartum women, we utilized machine learning to predict PPD risk, incorporating self-reported surveys and health records from October 2021 to Jan 2023.

Results: PPD prevalence slightly decreased from 30.9 % to 29.1 % over six months. The Random Forest model emerged as the most effective, identifying key predictors of PPD at different stages. The top three factors at first month were newborn's birth weight, maternal weight before delivery and before pregnancy. The EPDS scores of last time, newborn's birth weight and maternal weight before pregnancy and before delivery were main predictors for EPDS scores at third and sixth months postpartum.

Limitation: The study faces limitations such as potential selection bias due to the convenience sampling method and the reliance on self-reported measures, which may introduce reporting bias. Furthermore, the high attrition rate could affect the representativeness of the sample and the generalizability of the findings.

Conclusion: There is a slight decrease in PPD rates over six months, yet the prevalence remains high. This underscores the need for early and ongoing mental health support for new mothers. Our study highlights the efficacy of machine learning in enhancing PPD risk assessment and tailoring intervention strategies, paving the way for more personalized healthcare approaches in postpartum care.