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

Related Concept Videos

Regression Toward the Mean

Regression Toward the Mean

Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...

You might also read

Related Articles

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

Sort by

Same author

A web-based two-stage prediction model for postoperative pulmonary complications using preoperative and intraoperative data.

Journal of anesthesia and translational medicine·2026

Same author

Predictive performance of artificial intelligence algorithms for gestational diabetes mellitus in pregnant women: a protocol for systematic review and meta-analysis.

Systematic reviews·2026

Same author

Effect of intraoperative hypotension depth and duration on acute kidney injury after Type A acute aortic dissection repair: An observational cohort study based on early risk stratification models.

Journal of anesthesia and translational medicine·2026

Same author

Predictive Performance of Artificial Intelligence Algorithms for Gestational Diabetes Mellitus in Pregnant Women: Systematic Review and Meta-Analysis.

Journal of medical Internet research·2026

Same author

Population Pharmacokinetics of Tigecycline and Implications for Individualized Therapy Optimization: A Systematic Review.

Drug design, development and therapy·2025

Same author

Correction: Dynamic and interpretable deep learning model for predicting respiratory failure following cardiac surgery.

BMC anesthesiology·2025

Search research articles

Related Experiment Video

Updated: Aug 11, 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

An optimization for postpartum depression risk assessment and preventive intervention strategy based machine learning

Hao Liu¹, Anran Dai¹, Zhou Zhou²

¹School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, Nanjing 211198, China; Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing 210006, China.

Journal of Affective Disorders

|February 9, 2023

Summary

This study developed a machine learning model to predict postpartum depression (PPD) risk in cesarean delivery patients. Early intervention significantly reduced PPD incidence in high-risk individuals identified by the model.

Keywords:

Dexmedetomidine Ketamine Machine learning Postpartum depression Prediction model Risk threshold

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: Aug 11, 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

Area of Science:

Obstetrics and Gynecology
Psychiatry
Medical Informatics

Background:

Postpartum depression (PPD) is a common psychiatric disorder affecting women after childbirth.
Effective PPD prediction models are crucial for identifying at-risk individuals and guiding clinical interventions.
Verifying the benefits of drug interventions for high-risk PPD groups is essential for clinical practice.

Purpose of the Study:

To develop and validate a machine learning model for predicting PPD risk in women undergoing cesarean delivery.
To assess the effectiveness of drug interventions (ketamine and dexmedetomidine) in reducing PPD incidence among high-risk and low-risk groups.
To interpret the prediction model using SHapley Additive exPlanations (SHAP) for clinical insights.

Main Methods:

Collected data from parturients undergoing cesarean delivery, divided into training and testing cohorts.
Constructed and compared six machine learning models, selecting Extreme Gradient Enhancement (XGB) for its performance.
Utilized SHapley Additive exPlanations (SHAP) for model interpretation and Propensity Score Matching (PSM) to compare intervention groups.

Main Results:

The XGB model achieved an AUROC of 0.789 in the training cohort and 0.744 in the testing cohort.
A PPD risk probability threshold of 21.5% was established to classify patients.
Post-PSM analysis revealed significantly lower PPD incidence in intervention groups compared to the control group within the high-risk cohort (P < 0.001).

Conclusions:

The XGB algorithm demonstrated superior accuracy in predicting PPD risk.
Early intervention is beneficial for high-risk individuals identified by the XGB model.
The study highlights the potential of machine learning in personalized PPD management.