A predictive model for postpartum depression: ensemble learning strategies in machine learning

Abstract

Postpartum depression (PPD) presents a significant mental health challenge for mothers following childbirth. While the precise cause of this condition remains unknown, preventive measures and treatments are available. This study aims to employ ensemble learning techniques, utilizing C4.5 decision tree (DT), gradient boosting tree (GBT), and extreme gradient boosting (XGBoost), to predict the occurrences of PPD in the Banjarmasin, South Kalimantan, Indonesia. The predictive model developed encompasses a dataset comprising 317 records gathered from postpartum mothers in hospitals, community health services, and midwifery clinics (referred to as Model 1). Furthermore, resampling techniques (Model 2) were employed to address class imbalance. Additionally, feature selection including forward selection and backward elimination (Model 3) were implemented to enhance model performance. The findings reveal that XGBoost, combined with resampling methods, achieved the highest accuracy rate at 87.57%. Feature selection identified five crucial factors associated with PPD incidence: marital status, number of living children, history of depression, fear of delivery, and family relationships. The utilization of ensemble learning strategies for PPD prediction yields reliable outcomes that can be applied within clinical settings. Exploring alternative ensemble learning strategies such as random forest and adaptive boosting could further optimize model performance and warrant consideration in future research endeavours.