Copyright (c) 2025 Publicaciones e Investigación
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
When the Publicaciones e Investigaciones Journal receives an original study or article from its author(s), whether by email, postal service, or the platforms available for said purpose, know that it may be published in physical or electronic formats in national or international archives, databases, or SIRES. As such, Publications and Research authorizes the reproduction and citation of said material, provided that the description of information is carried out in conformity with bibliographic norms, and mention the corresponding names, authors, article, issue, and pages. Publications and Research, in advance, expresses that the information, concepts, and methods are the responsibility of the author(s). As such, the UNAD does not have any influence whatsoever over that expressed in the manuscript.
Profiles of Mental Health Risk in University Students Using GHQ-28 and Machine Learning Techniques
University students’ psychological well-being is essential for their academic persistence and performance. This study aimed to identify and characterize psychological risk profiles among students of Agricultural Engineering and Social Sciences at the University of Cundinamarca, using the General Health Questionnaire (GHQ-28), which assesses four subscales: somatization, anxiety/insomnia, social dysfunction, and severe depression. This quantitative research, with a descriptive, exploratory, and predictive approach, included 227 students who voluntarily completed the instrument. Responses were coded using the Likert method (0-1-2-3) and analyzed along with sociodemographic variables. Descriptive statistics, dimensionality reduction through Principal Component Analysis (PCA), and unsupervised clustering with K-Means identified three distinct risk profiles: low, intermediate, and high. For predictive classification, logistic regression and Random Forest models were implemented, with logistic regression showing superior performance (AUC = 0.96) compared to Random Forest (AUC = 0.57). Findings support the design of targeted intervention strategies and highlight the GHQ-28’s utility as a screening tool in university settings.
How to Cite
