International Journal of Sport, Exercise and Health Research 2026; 10(1): 7-11 ; DOI:10.31254/sportmed.10102
Predicting Mental Wellbeing in University Students Using Machine Learning and Lifestyle Data
1. Department of Physicat Education and Special Motricity, Faculty of Physical Education and Mountain Sports, Transilvania University, Brasov, Romania
*Author to whom correspondence should be addressed.
Received: 12th April, 2026 / Revised: 1st January, 1970 / Accepted: 25th June, 2026 / Published : 30th June, 2026
Background: Mental well-being among university students is shaped by multiple lifestyle factors. This study examined the associations between lifestyle behaviors and mental well-being and evaluated the predictive performance of several machine learning models. Methods: Data were collected from 154 university students using validated instruments, including the WHO-5 Well-Being Index and the International Physical Activity Questionnaire-Short Form (IPAQ-SF). Key variables included sleep duration, screen time, nutrition quality, and physical activity. Results: Mental well-being was significantly associated with multiple lifestyle behaviors. Physical activity (r = 0.42), sleep duration (r = 0.38), and nutrition quality (r = 0.33) correlated positively with well-being, while screen time showed a negative association (r = −0.35). A multiple regression model explained 48% of the variance in well-being, with sleep duration and physical activity as the strongest predictors. Machine learning models improved prediction accuracy compared with traditional regression; the Random Forest model achieved the best performance (R² = 0.58), indicating the presence of non-linear relationships among variables. Conclusion: Student well-being depends on a combination of modifiable behaviors rather than a single factor. Integrated, personalized interventions targeting sleep, physical activity, and screen habits may improve student well-being, and machine learning shows promise for identifying complex behavioral patterns to strengthen health predictions.
Mental health, University students, Lifestyle factors, Machine learning,Physical activity
Creative Commons (CC) License-
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY 4.0) license. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. (http://creativecommons.org/licenses/by/4.0/).
Copyright
Copyright © 2026 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0.
