Abstract
This study developed a multivariable predictive model for the early identification of psychosocial impairment among university students. Data from 440 students were analyzed using logistic regression, Random Forest, and Gradient Boosting, integrating academic, family, and social factors. The models achieved AUC values close to 0.80, with Random Forest showing the highest discriminative performance (AUC = 0.805). Social factors demonstrated the strongest individual predictive capacity, although the integration of all three domains improved the representation of risk. The findings support the use of these models as decision-support tools for early detection and subsequent assessment.
References
[2] M. Kamruzzaman, A. Hossain, M. A. Islam, M. S. Ahmed, E. Kabir, and M. N. Khan, "Exploring the prevalence of depression, anxiety, and stress among university students in Bangladesh and their determinants," Clinical Epidemiology and Global Health, vol. 28, p. 101677, 2024.
[3] M. E. Hasan et al., "Prevalence, associated factors, and machine learning-based prediction of depression, anxiety, and stress among university students: a cross-sectional study from Bangladesh," Journal of Health, Population and Nutrition, vol. 44, no. 1, p. 361, 2025.
[4] M. M. Hossain, M. A. Alam, and M. H. Masum, "Prevalence of anxiety, depression, and stress among students of Jahangirnagar University in Bangladesh," Health Science Reports, vol. 5, p. e559, 2022.
[5] M. D. Manzar, M. Salahuddin, D. Nureye, F. Z. Kashoo, M. M. Noohu, J. S. Alotaibi, M. S. Alamri, and M. D. Griffiths, "Depression, Anxiety, and Stress Scale-21 (DASS-21): Further psychometric exploration using robust item response theory and classical theory measures among university students," PLoS ONE, vol. 20, no. 7, p. e0325238, 2025.
[6] A. Osman, J. L. Wong, C. L. Bagge, S. Freedenthal, P. M. Gutierrez, and G. Lozano, "The Depression Anxiety Stress Scales-21 (DASS-21): Further examination of dimensions, scale reliability, and correlates," Journal of Clinical Psychology, vol. 68, no. 12, pp. 1322–1338, 2012.
[7] J. D. Henry and J. R. Crawford, "The short-form version of the Depression Anxiety Stress Scales (DASS-21): Construct validity and normative data in a large non-clinical sample," British Journal of Clinical Psychology, vol. 44, no. 2, pp. 227–239, 2005.
[8] Z. Antúnez and E. V. Vinet, "Escalas de depresión, ansiedad y estrés (DASS-21): Validación de la versión abreviada en estudiantes universitarios chilenos," Terapia Psicológica, vol. 30, no. 3, pp. 49–55, 2012.
[9] J. J. B. R. Aruta, "Screening psychological symptoms in Filipino university students during the COVID-19 pandemic: Translation and structural validation of the Filipino version of the DASS-21," Psychology in the Schools, vol. 61, no. 8, pp. 3243–3262, 2024.
[10] A. Estrella-Proaño, M. F. Rivadeneira, J. Alvarado, M. Murtagh, S. Guijarro, L. Alomoto, and G. Cañarejo, "Anxiety and depression in first-year university students: the role of family and social support," Frontiers in Psychology, vol. 15, p. 1462948, 2024.
[11] M. Kotyśko and J. Frankowiak, "The importance of perceived social support for symptoms of depression and academic stress among university students—a latent profile analysis," PLoS ONE, vol. 20, no. 5, p. e0324785, 2025.
[12] S. Howlader, S. Abedin, and M. M. Rahman, "Social support, distress, stress, anxiety, and depression as predictors of suicidal thoughts among selected university students in Bangladesh," PLOS Global Public Health, vol. 4, no. 4, p. e0002924, 2024.
[13] G. Nakie et al., "Sleep quality and associated factors among university students in Africa: a systematic review and meta-analysis study," Frontiers in Psychiatry, vol. 15, p. 1370757, 2024.
[14] A. Arif, M. A. Qadir, R. S. Martins, and H. M. A. Khuwaja, "The impact of cyberbullying on mental health outcomes amongst university students: A systematic review," PLOS Mental Health, vol. 1, no. 6, p. e0000166, 2024.
[15] C. E. Morr, M. Jammal, I. Bou-Hamad, S. Hijazi, D. Ayna, M. Romani, and R. Hoteit, "Predictive machine learning models for assessing Lebanese university students' depression, anxiety, and stress during COVID-19," Journal of Primary Care & Community Health, vol. 15, p. 21501319241235588, 2024.
[16] B. L. Schaab et al., "How do machine learning models perform in the detection of depression, anxiety, and stress among undergraduate students? A systematic review," Cadernos de Saúde Pública, vol. 40, no. 11, p. e00029323, 2024.
[17] A. Daza, N. Saboya, J. I. Necochea-Chamorro, K. Z. Ramos, and Y. del R. Vásquez Valencia, "Systematic review of machine learning techniques to predict anxiety and stress in college students," Informatics in Medicine Unlocked, vol. 43, p. 101391, 2023.
[18] L. Carmona, C. Costa, S. Gascón, G. Ribeiro, and M. J. Chambel, "Prevalence and risk factors for anxiety, stress and depression among higher education students in Portugal and Brazil," Journal of Affective Disorders Reports, vol. 17, p. 100825, 2024.
[19] G. X. D. Tan, X. C. Soh, A. Hartanto, A. Y. H. Goh, and N. M. Majeed, "Prevalence of anxiety in college and university students: An umbrella review," Journal of Affective Disorders Reports, vol. 14, p. 100658, 2023.
[20] Iqra, "A systematic review of academic stress intended to improve the educational journey of learners," Methods in Psychology, vol. 11, p. 100163, 2024.

This work is licensed under a Creative Commons Attribution 4.0 International License.

