Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Predicting Postpartum Depression Using Imbalance-Aware Machine Learning.

Aliya Tabassum1, Mais Alkhateeb2, Almuthana Alhussain3

  • 1Qatar University, Doha, Qatar.

Studies in Health Technology and Informatics
|July 3, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

WearAware: A Wearable-Based Early Warning Framework for Out-of-Hospital Cardiac Risk Monitoring.

Studies in health technology and informatics·2026
Same author

Semi-synthesis of novel dispiro hybrids of sesquiterpene lactones by using benzylamines <i>via</i> azomethine ylide cycloaddition.

Natural product research·2026
Same author

Artificial Intelligence-Based Prediction of Progression from Gestational Diabetes to Type 2 Diabetes.

Studies in health technology and informatics·2026
Same author

Patients' mHealth Apps Usage and Data Privacy, Security, and Confidentiality Concerns: Exploratory Study.

JMIR formative research·2026
Same author

Temporal and Behaviour-Aware Multimodal Modelling for Hour-Ahead Hypoglycaemia Prediction During Ramadan Fasting in Type 1 Diabetes.

Sensors (Basel, Switzerland)·2026
Same author

Perspectives Regarding the Privacy, Security, and Confidentiality of Data Collected via mHealth Apps in Saudi Arabia: Qualitative Analysis.

Journal of medical Internet research·2026
Same journal

A GenAI Pipeline for Violinist Kinematic Data Management.

Studies in health technology and informatics·2026
Same journal

AMAL-For-Qatar: A Comprehensive AI Ecosystem for Fetal Ultrasound Analysis - Project Overview and Achievements.

Studies in health technology and informatics·2026
Same journal

Longitudinal Treatment-Aware Multimodal AI for Dermatology: A Scoping Review.

Studies in health technology and informatics·2026
Same journal

Validation of Deep-Learning Models for Autosegmentation of Brain Metastases.

Studies in health technology and informatics·2026
Same journal

Delay-Dependent Gating in Modular RNNs.

Studies in health technology and informatics·2026
Same journal

Exact Forecasting and Event-Based Prediction in Annual EARS-Net Antimicrobial Resistance Series.

Studies in health technology and informatics·2026
See all related articles

This study developed a machine learning model to predict postpartum depression (PPD) risk in pregnant women using psychosocial data. The model shows high recall, enabling early screening for PPD.

Area of Science:

  • Reproductive Health
  • Computational Psychiatry
  • Machine Learning in Healthcare

Background:

  • Postpartum depression (PPD) affects a significant number of mothers, with many cases undiagnosed.
  • Early detection of PPD is crucial for timely intervention and improved maternal outcomes.

Purpose of the Study:

  • To develop and validate a robust machine learning pipeline for the early prediction of postpartum depression risk.
  • To identify key psychosocial predictors of PPD using advanced data analysis techniques.

Main Methods:

  • Utilized a leakage-resistant machine learning pipeline with psychosocial data from 1,430 pregnant women.
  • Employed concept-level feature harmonization, group-aware cross-validation, and recall-oriented thresholding for robust evaluation.
  • Addressed class imbalance using weighting and SMOTE (Synthetic Minority Over-sampling Technique).
Keywords:
Machine LearningPostpartum DepressionRisk Prediction

Related Experiment Videos

Main Results:

  • Machine learning models demonstrated strong predictive performance (ROC-AUC: 0.762-0.801; PR-AUC: 0.400-0.490).
  • Logistic regression and ensemble methods achieved the best results.
  • SHAP analysis identified anxious attachment and coping mechanisms as significant predictors of PPD.

Conclusions:

  • A well-designed machine learning pipeline can enable early and reliable risk stratification for postpartum depression.
  • High recall rates suggest the utility of this approach for screening purposes.
  • Moderate precision indicates the necessity of clinical follow-up for confirmed high-risk individuals.