Related Experiment Video
Updated: Jun 12, 2025
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
7.5K
Screening depression among university students utilizing GHQ-12 and machine learning
Nasirul Mumenin1, A B M Kabir Hossain1, Md Arafat Hossain1
1Bangladesh Army University of Engineering and Technology, Rajshahi, Bangladesh.
Heliyon
|September 19, 2024
Summary
Machine learning accurately screens university students for depression using the GHQ-12. The Extremely Randomized Tree model achieved 90.26% accuracy, identifying key predictors for early intervention.
Area of Science:
- Psychiatry
- Computer Science
- Public Health
Background:
- University students face increasing mental health challenges, necessitating efficient depression screening.
- The General Health Questionnaire-12 (GHQ-12) is a recognized tool for assessing psychological distress.
Purpose of the Study:
- To develop and evaluate machine learning models for accurate depression screening in university students.
- To identify socio-demographic and career-related predictors of depression in this population.
Main Methods:
- A comprehensive questionnaire including GHQ-12, socio-demographic, and career-related items was administered to 804 Bangladeshi university students.
- Data preprocessing and analysis were performed, followed by the application and evaluation of 16 machine learning models.
- The Extremely Randomized Tree (ET) model was assessed for its classification effectiveness.
Main Results:
- Approximately 60% of the study population reported symptoms consistent with depression.
- The Extremely Randomized Tree (ET) model demonstrated the highest accuracy at 90.26% in classifying depression risk.
- The study identified key trends and predictors associated with depression in university students.
Conclusions:
- Machine learning, particularly the ET model, offers a highly accurate and effective method for early depression detection in university students.
- Findings highlight the interplay between socio-demographic factors, career stressors, and student mental well-being.
- This research provides a novel perspective on applying machine learning in psychological research for mental health screening.
