Machine Learning-Based Diagnosis of Postpartum Depression Methods and Insights

DOI

10.2991/978-94-6239-727-9_19How to use a DOI?

Keywords

Postpartum Depression; machine learning; SVM; RF; XGBoost; Decision Tree; Kaggle Dataset

Abstract

A serious mental health condition that affects new moms, postpartum depression (PPD) frequently has a negative impact on both the mother and the child. Conventional screening techniques, including the Edinburgh Postnatal Depression Scale (EPDS), limit early intervention because they mainly concentrate on detecting symptoms after they have started. In this study, the scope for further development of ML methods in early detection of PPD is investigated based on the analysis of a Kaggle dataset with 1,503 entries. To classify the risk of PPD following these influential factors, ML algorithms were employed, including Support Vector Machine (SVM), XGBoost, Random Forest, Decision Tree, and RBFNN. Such as Support Vector Machine (SVM), XGBoost, Random Forest, Decision Tree, and K-Nearest Neighbors (KNN). On the other hand, XGBoost and Random Forest tree-based models, when used in conjunction with Recursive Feature Elimination (RFE), obtained the highest accuracy (96.99%), and these two are the best performing models of them all. Through accuracy, precision, recall and F1-score based as performance evaluation. These results demonstrate that ML-based techniques may facilitate early detection of PPD, which may lead to early interventions. Future work will focus on enhancing model generalizability for clinical utility, incorporating multimodal data, as well as enlarging datasets.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Neesha Nayee
AU  - Saurabh Shah
AU  - Hetal Bhaidasna
PY  - 2026
DA  - 2026/07/22
TI  - Machine Learning-Based Diagnosis of Postpartum Depression Methods and Insights
BT  - Proceedings of the International Conference on Sustainable Micro-Nano Materials & Innovative Technology (ICSUMMIT 2026)
PB  - Atlantis Press
SP  - 254
EP  - 265
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-727-9_19
DO  - 10.2991/978-94-6239-727-9_19
ID  - Nayee2026
ER  -