Development of a Physical Fitness Prediction Model Using Machine Learning Algorithms

Dongjun  Li; Xudong  Chen

doi:10.6180/jase.202608_31.056

Development of a Physical Fitness Prediction Model Using Machine Learning Algorithms

Electrical Engineering Mechanical Engineering

Dongjun Li¹ and Xudong Chen^2,3This email address is being protected from spambots. You need JavaScript enabled to view it.

¹Kaifeng Vocational College, Kaifeng, 475100, China

²Henan Mechanical and Electrical Vocational College, Zhengzhou, 450000, China

³Suan Sunandha Rajabhat University, Bangkok 10300, Thailand

Received: November 10, 2025
Accepted: December 20, 2025
Publication Date: March 14, 2026

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202608_31.056

Physical fitness is vital for good health and quality of life. On the other hand, it is declining, especially among university students, due to a sedentary lifestyle. Traditional fitness evaluation methods-using manual assessments and self-reported questionnaires-suffer from a lack of accuracy in identifying specific areas needing improvement. This paper proposes a physical fitness evaluation and prediction model using the integration of Covariance-Based Equation Modelling (CB-SEM) and Light Gradient Boosting Machine (LightGBM). It uses data drawn from an online survey targeting the assessment of key variables such as physical activity level, motivation to perform physical activity, measures of health status, and Body Mass Index (BMI). Next, CB-SEM is used to analyse the relations among latent variables, while LightGBM predicts the result of fitness (low, medium, or high). The LightGBM algorithm shows that the most important features related to physical fitness outcomes are physical activity levels and health measures. The integration of CB-SEM enhances the understanding of the causal relationship and thus increases the prediction accuracy. This model offers more efficiency and personalisation in evaluating fitness than traditional approaches do. The personalised results make it possible to provide relevant recommendations and track the individual’s fitness improvement for better health outcomes. The LightGBM model attained a total prediction accuracy of 85.7% and showed a promising ability to classify students into low, medium, and high fitness categories.

Keywords: Physical fitness, Covariance-Based Structural Equation Modelling, Light Gradient Boosting Machine, fitness evaluation, university students, Machine Learning

[1] D. Hansen et al., (2022) “Exercise intensity assessment and prescription in cardiovascular rehabilitation and be yond: why and how: a position statement from the Secondary Prevention and Rehabilitation Section of the European Association of Preventive Cardiology" European Journal of Preventive Cardiology 29(1): 230–245. DOI: 10.1093/eurjpc/zwab007.
[2] J.A.Kanaleyetal.,(2022)“Exercise/Physical Activity in Individuals with Type 2 Diabetes: A Consensus Statement from the American College of Sports Medicine" Medicine &Science in Sports & Exercise 54(2): 353–368. DOI: 10.1249/MSS.0000000000002800.
[3] I. Bajramovic, D. Bjelica, D. Krivokapi´c, S. Likic, E. Je leskovic, M. Curic, and J. Vukovi´c, (2022) “Gender Differences in Physical Activity, Physical Fitness and Well being of Students During The Lock-Down Due to Covid 19 Pandemic" Journal of Anthropology of Sport and Physical Education 6(1): 21–23. DOI: 10.26773/jaspe. 220104.
[4] M.Kim,(2022) “How can I be as attractive as a Fitness YouTuber in the era of COVID-19? The impact of digital attributes on flow experience, satisfaction, and behavioral intention" Journal of Retailing and Consumer Ser vices 64: 102778. DOI: 10.1016/j.jretconser.2021.102778.
[5] P. Moitra and J. Madan, (2022) “Impact of screen time during COVID-19 on eating habits, physical activity, sleep, and depression symptoms: A cross-sectional study in Indian adolescents" PLoS ONE 17(3): e0264951. DOI: 10.1371/journal.pone.0264951.
[6] P. L. Valenzuela et al., (2022) “Joint association of physi cal activity and body mass index with cardiovascular risk: a nationwide population-based cross-sectional study" European Journal of Preventive Cardiology 29(2): e50 e52. DOI: 10.1093/eurjpc/zwaa151.
[7] A. Hammami, B. Harrabi, M. Mohr, and P. Krustrup, (2022) “Physical activity and coronavirus disease 2019 (COVID-19): specific recommendations for home-based physical training" Managing Sport and Leisure 27(1 2): 26–31. DOI: 10.1080/23750472.2020.1757494.
[8] P.N.Bennettetal.,(2022)“Physicalactivity and exercise in peritoneal dialysis: International Society for Peritoneal Dialysis and the Global Renal Exercise Network practice recommendations" Peritoneal Dialysis International 42(1): 8–24. DOI: 10.1177/08968608211055290.
[9] K. Toivo et al., (2023) “Physical activity measured by accelerometry among adolescents participating in sports clubs and non-participating peers" European Journal of Sport Science 23(7): 1426–1434. DOI: 10.1080/17461391.2022.2103740.
[10] C. Deng, L. Feng, and Q. Ye, (2023) “Smart Physical Education: Governance of School Physical Education in the Era of New Generation of Information Technology and Knowledge" Journal of the Knowledge Economy 15(3): 13857–13889. DOI: 10.1007/s13132-023-01668 0.
[11] R. Ramírez-Campillo, A. García-Hermoso, J. Moran, H. Chaabene, Y. Negra, and A. T. Scanlan, (2022) “The effects of plyometric jump training on physical fitness attributes in basketball players: A meta-analysis" Journal of Sport and Health Science 11(6): 656–670. DOI: 10.1016/j.jshs.2020.12.005.
[12] L. Dallolio et al., (2022) “The impact of COVID-19 on physical activity behaviour in Italian primary school children: a comparison before and during pandemic considering gender differences" BMC Public Health 22(1): 52. DOI: 10.1186/s12889-021-12483-0.
[13] D. A. Marinho, H. P. Neiva, L. Marques, V. P. Lopes, and J. E. Morais, (2022) “The influence of a specific high intensity circuit training during physical education classes in children’s physical activity and body composition markers" Montenegrin Journal of Sports Science &Medicine 11(2): DOI: 10.26773/mjssm.220904.
[14] R. Gottlieb, A. Shalom, P. E. Alcaraz, and J. Calleja González, (2022) “Validity and reliability of a unique aerobic field test for estimating VO2max among basketball players" Science Journal of Sport Performance 1(2): 112–123. DOI: 10.55860/TRMF2461.
[15] A. Alnaqbi, W. Zeiada, and G. Al-Khateeb, (2025) “A hybrid machine learning method of support vector regression with particle swarm optimization for predicting IRI in continuously reinforced concrete pavement" Journal of Engineering and Applied Science 72(1): 128. DOI: 10.1186/s44147-025-00706-9.
[16] B. U. A. Stephen, B. C. Uzoewulu, P. M. Asuquo, and S. Ozuomba, (2023) “Diabetes and hypertension MobileHealth systems: a review of general challenges and advancements" Journal of Engineering and Applied Science 70(1): 78.
[17] J. Durau, S. Diehl, and R. Terlutter, (2022) “Motivate me to exercise with you: The effects of social media fitness influencers on users’ intentions to engage in physical activity and the role of user gender" Digital Health 8: 20552076221102769. DOI: 10.1177/ 20552076221102769.
[18] M. Albaladejo-Saura, R. Vaquero-Cristóbal, J. A. García-Roca, and F. Esparza-Ros, (2022) “The effect of age, biological maturation, and birth quartile in the kinan thropometric and physical fitness differences between male and female adolescent volleyball players" Children 9(1): 58. DOI: 10.3390/children9010058.
[19] A. Jimeno-Almazán et al., (2022) “Rehabilitation for post-COVID-19 condition through a supervised exercise intervention: A randomized controlled trial" Scandinavian Journal of Medicine &ScienceinSports32(12): 1791–1801. DOI: 10.1111/sms.14240.
[20] J. A. Laukkanen, N. M. Isiozor, and S. K. Kunut sor, (2022) “Objectively assessed cardiorespiratory fitness and all-cause mortality risk" Mayo Clinic Proceedings 97(6): 1054–1073. DOI: 10.1016/j.mayocp.2022.02.029.
[21] A. C. Jeffries, S. M. Marcora, A. J. Coutts, L. Wallace, A. McCall, and F. M. Impellizzeri, (2022) “Development of a revised conceptual framework of physical training for use in research and practice" Sports Medicine 52(4): 709–724. DOI: 10.1007/s40279-021-01551-5.
[22] M. M. Afsar et al., (2023) “Body-Worn Sensors for Recognizing Physical Sports Activities in Exergaming via Deep Learning Model" IEEE Access 11: 12460–12473. DOI: 10.1109/ACCESS.2023.3239692.
[23] M. A. Mc Narry et al., (2022) “Inspiratory muscle training enhances recovery post-COVID-19: a randomised controlled trial" European Respiratory Journal 60(4): 2103101. DOI: 10.1183/13993003.03101-2021.
[24] E. W. Koevoets et al., (2022) “Effect of physical exercise on cognitive function after chemotherapy in patients with breast cancer: a randomized controlled trial (PAM study)" Breast Cancer Research 24(1): 36. DOI: 10.1186/s13058-022-01530-2.
[25] R. K. Gudivaka, R. L. Gudivaka, B. R. Gudivaka, D. K. R. Basani, S. H. Grandhi, and F. Khan, (2025) “Diabetic foot ulcer classification assessment employing an improved machine learning algorithm" Technology and Health Care 0(0): DOI: 10.1177/09287329241296417.
[26] F.B.Ortegaetal., (2023) “European fitness landscape for children and adolescents: updated reference values, fitness maps and country rankings based on nearly 8 million test results from 34 countries gathered by the Fit Back network" British Journal of Sports Medicine 57(5): 299–310. DOI: 10.1136/bjsports-2022-106176.
[27] J. Granero-Jiménez, M. M. López-Rodríguez, I. Dobarrio-Sanz, and A. E. Cortés-Rodríguez, (2022) “Influence of physical exercise on psychological well-being of young adults: a quantitative study" International Journal of Environmental Research and Public Health 19(7): 4282. DOI: 10.3390/ijerph19074282.
[28] Z. Hu, Z. Liu, and Y. Su, (2024) “AI-driven smart transformation in physical education: Current trends and future research directions" Applied Sciences 14(22): 10616.
[29] A. Smiley and J. Finkelstein, (2024) “Dynamic Pre diction of Physical Exertion: Leveraging AI Models and Wearable Sensor Data During Cycling Exercise" Diagnostics 15(1): 52.
[30] Y. Liu, V. Sathishkumar, and A. Manickam, (2022) “Augmented reality technology based on school physical education training" Computers and Electrical Engineering 99: 107807. DOI: 10.1016/j.compeleceng.2022.107807.
[31] A. E. M. Berkel et al., (2022) “Effects of community based exercise prehabilitation for patients scheduled for colorectal surgery with high risk for postoperative com plications: results of a randomized clinical trial" Annals of Surgery 275(2): e299–e306. DOI: 10.1097/SLA.0000000000004702.
[32] M.Hayes,(2022)“Social media and in spiring physical activity during COVID-19 and beyond" Managing Sport and Leisure 27(1–2): 14–21. DOI: 10.1080/23750472.2020.1794939.
[33] Z. Liu et al., (2022) “Effectiveness of a multifaceted intervention for prevention of obesity in primary school children in China: a cluster randomized clinical trial" JAMA Pediatrics 176(1): e214375. DOI: 10.1001/jamapediatrics.2021.4375.
[34] A. Martín-Rodríguez et al., (2024) “Sporting mind: the interplay of physical activity and psychological health" Sports 12(1): 37. DOI: 10.3390/sports12010037.
[35] V. J. Clemente-Suárez et al., (2022) “Physical activity and COVID-19: the basis for an efficient intervention in times of COVID-19 pandemic" Physiology & Behavior 244: 113667. DOI: 10.1016/j.physbeh.2021.113667.