Predicting VO2max in Children and Adolescents Aged between 6 and 17 Using Physiological Characteristics and Participation in Sport Activities: A Cross-Sectional Study Comparing Different Regression Models Stratified by Gender

Vilelmine Carayanni; Gregory C Bogdanis; Elpis Vlachopapadopoulou; Dimitra Koutsouki; Yannis Manios; Feneli Karachaliou; Theodora Psaltopoulou; Stefanos Michalacos

doi:10.3390/children9121935

Predicting VO₂max in Children and Adolescents Aged between 6 and 17 Using Physiological Characteristics and Participation in Sport Activities: A Cross-Sectional Study Comparing Different Regression Models Stratified by Gender

Children (Basel). 2022 Dec 9;9(12):1935. doi: 10.3390/children9121935.

Authors

Vilelmine Carayanni¹, Gregory C Bogdanis², Elpis Vlachopapadopoulou³, Dimitra Koutsouki², Yannis Manios⁴, Feneli Karachaliou³, Theodora Psaltopoulou⁵, Stefanos Michalacos³

Affiliations

¹ School of Administration Economics and Social Sciences, Department of Tourism Administration, University of West Attica, 28 Saint Spyridonos Str., 12243 Egaleo, Greece.
² School of Physical Education & Sports Science, National and Kapodistrian University of Athens, 41 Ethnikis Antistaseos Str., Daphne, 17237 Athens, Greece.
³ Department of Endocrinology-Growth and Development, Children's Hospital P. & A. Kyriakou, Thivon & Levadeias Str., Ampelokipoi T.K., 11527 Athens, Greece.
⁴ Department of Nutrition & Dietetics, School of Health Science & Education, Harokopio University, 70 El Venizelou Ave. Kallithea, 17671 Athens, Greece.
⁵ Department of Hygiene, Epidemiology and Medical Statistics, School of Medicine, National and Kapodistrian University of Athens, 75 Mikras Asias Str., 11527 Goudi, Greece.

Abstract

Background: The aim of this study is to use different regression models to capture the association between cardiorespiratory fitness VO2max (measured in mL/kg/min) and somatometric characteristics and sports activities and making better predictions. Methods: multiple linear regression (MLR), quantile regression (QR), ridge regression (RR), support vector regression (SVR) with three different kernels, artificial neural networks (ANNs), and boosted regression trees (RTs) were compared to explain and predict VO2max and to choose the best performance model. The sample consisted of 4908 children (2314 males and 2594 females) aged between 6 and 17. Cardiorespiratory fitness was assessed by the 20 m maximal multistage shuttle run test and maximal oxygen uptake (VO2max) was calculated. Welch t-tests, Mann−Whitney-U tests, X2 tests, and ANOVA tests were performed. The performance measures were root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). All analyses were stratified by gender. Results: A comparison of the statistical indices for both the predicted and actual data indicated that in boys, the MLR model outperformed all other models in all indices, followed by the linear SVR model. In girls, the MLR model performed better than the other models in R2 but was outperformed by SVR-RBF in terms of RMSE and MAE. The overweight and obesity categories in both sexes (p < 0.001) and maternal prepregnancy obesity in girls had a significant negative effect on VO2max. Age, weekly football training, track and field, basketball, and swimming had different positive effects based on gender. Conclusion: The MLR model showed remarkable performance against all other models and was competitive with the SVR models. In addition, this study’s data showed that changes in cardiorespiratory fitness were dependent, to a different extent based on gender, on BMI category, weight, height, age, and participation in some organized sports activities. Predictors that are not considered modifiable, such as gender, can be used to guide targeted interventions and policies.

Keywords: VO2max; adolescents; body mass Index (BMI) category; children; gender; machine learning; multiple linear regression; organized sports activity.

Grants and funding

This research was co-financed by the European Union (European Social Fund—ESF) and by Greek national funds through the National Strategic Reference Framework (NSRF). The funding body (funding number: MIS 301205) approved the design of the study and provided supervision to ensure that the methodology and timetable were followed as sampled. They had no involvement in the collection, analysis, and interpretation of data. or in writing of the manuscript.