Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 31, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Development and application of a machine learning-based antenatal depression prediction model.

Chunfei Hu¹, Hongmei Lin², Yupin Xu³

¹School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China; Department of Obstetrics and Gynecology, Shaoxing Maternal and Child Health Hospital, Shaoxing, Zhejiang, China.

Journal of Affective Disorders

|January 23, 2025

Summary

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

Genome-wide analysis of <i>HSP70</i> gene superfamily in kelp (<i>Saccharina japonica</i>): identification, characterization, and heat stress-responsive expression profiles.

PeerJ·2026

Same author

Mitochondria-Targeted MPDA Nanosystem Co-Delivering Evodiamine and IR820 for Chemo-Photothermal Therapy of Hepatocellular Carcinoma.

International journal of nanomedicine·2026

Same author

Metal-Organic Framework Nanoplatform Synergizes Fenton-Driven Ferroptosis and Photodynamic Apoptosis for Enhanced Hepatocellular Carcinoma Therapy.

International journal of nanomedicine·2026

Same author

The Underlying Pharmacological Mechanisms and Active Components of XZZTP in Modulating Bacterial Inflammation Elucidated by LC-MS/MS, Network Pharmacology, In Vitro Experiments, Molecular Docking, and Dynamics Simulations.

Pharmaceuticals (Basel, Switzerland)·2026

Same author

Genome-Wide Analysis of Heat Shock Transcription Factors (HSFs) in Kelp (<i>Saccharina japonica</i>) and Analysis of Their Expression in Response to Abiotic Stresses.

Plants (Basel, Switzerland)·2026

Same author

Essential Metal Based Single-Atom Nanozymes for Myocardial Infarction Therapeutics.

Advanced healthcare materials·2026

Machine learning models can now predict antenatal depression (AND) risk in pregnant women. This allows for earlier identification and intervention, improving maternal and infant outcomes.

Area of Science:

Perinatal mental health
Clinical informatics
Machine learning in healthcare

Background:

Antenatal depression (AND) poses significant risks to maternal and infant well-being.
Current clinical methods for predicting AND lack objectivity and universal applicability.
There is a critical need for reliable tools to identify pregnant women at risk of depression.

Purpose of the Study:

To develop and validate a machine learning (ML)-based prediction model for antenatal depression (AND).
To leverage sociodemographic and pregnancy-related data for accurate AND risk assessment.
To enable early and precise identification of pregnant women at risk of AND.

Main Methods:

Utilized data from 20,950 pregnant women across three hospitals.

Keywords:

Antenatal depression Machine learning Prediction model

More Related Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Using Chronic Social Stress to Model Postpartum Depression in Lactating Rodents

Using Chronic Social Stress to Model Postpartum Depression in Lactating Rodents

Published on: June 10, 2013

Related Experiment Videos

Last Updated: May 31, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Using Chronic Social Stress to Model Postpartum Depression in Lactating Rodents

Using Chronic Social Stress to Model Postpartum Depression in Lactating Rodents

Published on: June 10, 2013

Defined AND using an Edinburgh Postnatal Depression Scale (EPDS) score of 10 or higher.

Developed four random forest models (Base, Base+General, Base+Obstetric, Full) using 34 selected variables categorized for clinical relevance.

Main Results:

The best performing model, Base+General, achieved an Area Under the Curve (AUC) of 0.710 in the test set for predicting late pregnancy AND.
The Base Model demonstrated strong performance with an AUC only 0.022 lower than the top model, suggesting its utility for early screening.
Model performance ranged from AUC 0.687-0.710 in the test set.

Conclusions:

Machine learning models can predict AND risk across various pregnancy stages.
Early and accurate identification of at-risk individuals facilitates timely interventions.
These ML models offer a promising approach to improve perinatal mental health outcomes for mothers and offspring.