Postpartum Depression Detection and Its Features Analysis By Machine Learning Approach

Abstract

Postpartum depression (PPD) poses a significant health concern affecting mothers globally, yet early detection remains a challenge. This research explores a pioneering approach to PPD detection and feature analysis using machine learning algorithms. Leveraging a dataset sourced from Kaggle, encompassing 1503 records obtained through a medical hospital questionnaire, the study meticulously examines ten selected attributes, with "Feeling Anxious" as the target variable. Notably, the dataset holds a 65% prevalence of anxiety and 35% non-anxiety cases. The study employed three machine learning algorithms – Decision Tree, Random Forest, and K-Nearest Neighbors (KNN) – showcasing promising results. Decision Tree achieved an accuracy of 98.01%, Random Forest excelled with 98.67%, and KNN demonstrated 92.03% accuracy. The precision, recall, and F1 scores complemented these outcomes, affirming the models' robustness. Feature importance analyses were conducted, unraveling insights into the factors contributing to PPD. Notable features included trouble sleeping at night, problems of bonding with the baby, and feelings of guilt. The algorithmic output, coupled with permutation feature importance, elucidated the nuanced relationships between these attributes and PPD. Furthermore, an exploration of age categories revealed distinctive patterns, with mothers aged 30-35 and 40-45 displaying higher susceptibility. The discussion extends to the interplay of variables like trouble sleeping, overeating, and irritability, contributing to a comprehensive understanding of PPD indicators.