Detection of Postpartum Depression using Machine Learning

Abstract

Postpartum depression (PPD) is a prevalent and serious mental health issue that affects a significant number of women after childbirth. Early detection of PPD is crucial for effective intervention, but traditional screening tools often fall short in terms of accuracy and timely prediction. This study focuses on extensive machine learning methods by using psychological and behavioural data from a large survey of postpartum women. Various traditional machine learning algorithms along with CatBoost are implemented in this research. The accuracy of 95.68% demonstrate that the CatBoost-based model outperforms other machine learning models, providing a robust and reliable method for the early detection of postpartum depression.