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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Reimagining procedural distress as a candidate quality domain in pediatric emergency medicine.

Frontiers in pediatrics·2026
Same author

Association between post-void residual urine volume trajectories and incident urinary tract infection in patients receiving maintenance hemodialysis.

BMC nephrology·2026
Same author

Spent Mushroom Substrate Reused as Organic Fertilizer Enhances Lettuce (<i>Lactuca sativa</i> L.) Quality and Soil Nutrients: Insights from Physicochemical and Microbiome Analyses.

Microorganisms·2026
Same author

Structural Design and Advanced Diagnostics of Lithium Metal Anodes for High-Energy-Density Batteries.

Chemistry, an Asian journal·2026
Same author

Periodontitis and Chronic Liver Disease: Mechanistic Insights Focusing on <i>Porphyromonas gingivalis</i>-A Narrative Review.

Microorganisms·2026
Same author

Assessment of gut-brain interactions: reframing DGBI symptoms from visceral hypersensitivity to computational interoceptive overfitting.

Frontiers in physiology·2026

Related Experiment Video

Updated: May 20, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

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

Published on: January 11, 2020

7.4K

Machine learning-driven development of a stratified CES-D screening system: optimizing depression assessment through

Ruo-Fei Xu1, Zhen-Jing Liu1, Shunan Ouyang1

  • 1School of Mental Health, Wenzhou Medical University, Wenzhou, China.

BMC Psychiatry
|March 26, 2025
PubMed
Summary

This study developed a machine learning tool to efficiently screen for depression using the Center for Epidemiologic Studies Depression Scale (CES-D-20). The new stratified approach maintains accuracy while reducing assessment burden in large populations.

Keywords:
CES-DDepression screeningMachine learningPredictive modelingRecursive Feature EliminationStratified screening

More Related Videos

Computerized Adaptive Testing System of Functional Assessment of Stroke
05:21

Computerized Adaptive Testing System of Functional Assessment of Stroke

Published on: January 7, 2019

5.7K
A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis
04:19

A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis

Published on: May 10, 2022

3.5K

Related Experiment Videos

Last Updated: May 20, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

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

Published on: January 11, 2020

7.4K
Computerized Adaptive Testing System of Functional Assessment of Stroke
05:21

Computerized Adaptive Testing System of Functional Assessment of Stroke

Published on: January 7, 2019

5.7K
A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis
04:19

A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis

Published on: May 10, 2022

3.5K

Area of Science:

  • Psychiatry and Mental Health
  • Machine Learning in Healthcare
  • Psychometrics

Background:

  • Large-scale depression screening is crucial but faces efficiency challenges.
  • The Center for Epidemiologic Studies Depression Scale (CES-D-20) is widely used but lengthy.
  • Optimizing assessment burden while maintaining diagnostic accuracy is a key objective.

Purpose of the Study:

  • To develop a machine learning-driven, stratified screening tool for the CES-D-20.
  • To enhance efficiency in large-scale mental health applications.
  • To maintain high diagnostic accuracy and psychometric properties.

Main Methods:

  • Utilized a two-stage machine learning approach on data from the Chinese Psychological Health Guard Project and China Labor-force Dynamics Survey.
  • Employed Recursive Feature Elimination with multiple linear regression for item identification, followed by logistic regression for classification.
  • Validated model performance using ROC analysis, Brier score, decision curve analysis, random forest, and support vector machine algorithms.

Main Results:

  • A four-item rapid screening layer achieved high accuracy (AUC=0.982) for probable depression.
  • An expanded nine-item version accurately predicted full CES-D-20 scores (R²=0.957).
  • The stratified system demonstrated robust generalizability across age groups and time, with optimal clinical utility.

Conclusions:

  • Developed a machine learning-derived, stratified screening version of the CES-D-20.
  • Offers an efficient, reliable, and psychometrically sound alternative for large-scale screening.
  • Facilitates efficient risk stratification and targeted assessment allocation in mental health programs.