Background/Objectives: Traditional models like ordinary least squares (OLS) struggle to capture non-linear relationships in children’s subjective well-being (SWB), which is associated with physical activity. This study evaluated machine learning (ML) for predicting SWB, focusing on sports participation, and explored theoretical prediction limits using a global dataset. It addresses a gap in understanding complex patterns across diverse cultural contexts. Methods: We analyzed 128,184 records from the ISCWeB survey (ages 6–14, 35 countries), with self-reported data on sports frequency, emotional states, and family support. To ensure cross-country generalizability, we used GroupKFold CV (grouped by country) and leave-one-country-out (LOCO) validation, yielding mean R² = 0.45 ± 0.05, confirming robustness beyond cultural patterns, SHAP for interpretability, and bootstrapping for error estimation. No pre-registration was required for this secondary analysis. Results: XGBoost and LightGBM outperformed OLS, achieving R² up to 0.504 in restricted datasets (sensitivity excluding affective leakage: R² = 0.35), with sports-related variables (e.g., exercise frequency) associated positively with SWB predictions (SHAP values: +0.15–0.25; incremental ΔR² = 0.06 over demographics/family/school base). Using test–retest reliability from literature (r = 0.74), the estimated irreducible RMSE reached 0.941; XGBoost achieved RMSE = 1.323, approaching the predictability bound with 68.1% of explainable variance captured (after noise adjustment). Partial dependence plots showed linear associations with exercise without satiation and slight age decline. Conclusions: ML improves SWB prediction in children, highlighting associations with sports participation, and approaches predictable variance bounds. These findings suggest potential for data-driven tools to identify patterns, such as through physical literacy pathways, informing physical activity interventions. However, longitudinal studies are needed to explore causality and address cultural biases in self-reports.

RESUMO: Objetivo: Verificar as mudanças no deslocamento para o trabalho e na atividade física (AF) na população de três municípios da região de São Paulo nos anos 2000 e 2010. Métodos: Estudo de coorte transversal com amostra representativa de 602 adultos (62,3% homens), realizado nos municípios de Santo André, São Bernardo do Campo e São Caetano do Sul nos anos 2000 (n = 304; 66,1% homens) e 2010 (n = 298; 58,4% homens). A AF foi analisada pelo Questionário Internacional de Atividade Física e os participantes foram classificados em ativos (≥ 150 min/sem) e insuficientemente ativos (< 150 min/sem). O deslocamento para o trabalho foi rotulado em transporte ativo (a pé e bicicleta), privado (moto, carro, vans e ônibus) e público (ônibus, vans, trem ou metrô). Resultados: As médias (min/sem) de AF de caminhada (229,4 versus 190,6), moderada (449,1 versus 347,4), vigorosa (354,4 versus 317,4) e total (552,3 versus 442,5) dos participantes foram maiores em 2010 do que em 2000. A prevalência de ativos aumentou de 62,2 para 78,2%, respectivamente. Foi encontrada relação negativa entre transporte ativo e público com nível socioeconômico; transporte ativo e grau de escolaridade; transporte público e faixa etária. Relação positiva foi verificada somente entre transporte privado e nível socioeconômico. A média da AF total (min/sem) foi maior (p = 0,024; 32,2%) em 2010 do que em 2000 para o transporte ativo. Conclusão: Os dados de vigilância em AF total nos três municípios de São Paulo indicam que a média do transporte ativo para o trabalho aumentou após dez anos, enquanto o transporte público diminuiu.

This study examines the association between socioeconomic factors, gender, physical activity, and health satisfaction among Chilean adolescents. It aims to identify key disparities and their implications for public health policies. Cross-sectional study based on the third wave (2016-2019) of the international Children's Worlds survey. A total of 911 adolescents aged 12-13 years from Santiago, Chile, participated. Physical activity levels, socioeconomic indicators, and health satisfaction were assessed. Statistical analyses included t-tests, chi-square tests, ANOVA, and multiple linear regression models stratified by gender. Boys reported higher levels of electronic gaming (64.6 % vs. 35.4 %, p < 0.001), while girls engaged more in outdoor play at lower frequencies (52.8 % vs. 47.2 %, p = 0.045). Perceived safety was a stronger predictor of health satisfaction for girls (β = 0.252, p < 0.001) than for boys (β = 0.251, p < 0.001). Socioeconomic and environmental factors significantly influence adolescent health satisfaction, with gender-specific differences. Policies should focus on improving access to recreational spaces and addressing economic barriers, particularly for girls.

Introduction: The fitness industry continues adapting to customers' unique characteristics and needs across different regions. Studying fitness trends enables industry professionals to make informed decisions, seize new opportunities, and foster a culture of health and well-being. Objective: This observational and cross-sectional study aimed to determine the most relevant fitness trends in Ibero-America for the first time and examine any differences between global fitness trends for 2025. Methodology: A national online survey was conducted in two countries of the Iberian Peninsula (Spain and Portugal) and three countries in the Americas (Mexico, Brazil, and Chile), following the methodology used by the American College of Sports Medicine (ACSM) since 2006. An online questionnaire was sent to fitness professionals to assess the relevance of over 50 fitness trends. Discussion: A total of 5,262 responses were collected across the 5 national surveys, with an overall mean response rate of 13.44%. Some of the most relevant fitness trends in Ibero-America for 2025 include: exercise for weight loss, personal training, employing certified exercise professionals, fitness programs for older adults, and traditional strength training. Conclusions: The present findings highlight the similarities in the results of the Ibero-American surveys and their significant differences in global fitness trends. The results can help fitness professionals plan services and make strategic decisions based on the priorities of each Ibero-American region.

Physical inactivity remains a major modifiable risk factor for non-communicable diseases and continues to exhibit marked socioeconomic and gender disparities in Latin America. Identifying robust and interpretable predictors of inactivity in nationally representative datasets is essential for informing public health strategies. This study compared a survey-weighted logistic regression model and an explainable machine learning approach (XGBoost) to predict physical inactivity among Chilean adults using data from the 2024 National Physical Activity and Sports Survey (ENAFyD; n = 5248). Models were evaluated on a stratified held-out test set (n = 1050) using weighted and unweighted area under the ROC curve (AUC), Brier scores, and calibration curves. Survey-weighted logistic regression achieved a weighted AUC of 0.801, while XGBoost achieved 0.797, demonstrating comparable discrimination. XGBoost showed marginally lower Brier scores, indicating slightly improved probabilistic calibration. Low socioeconomic status, female sex, lower monthly physical activity expenditure, limited facility access, and lower engagement with digital resources were consistently associated with higher inactivity risk. SHAP-style contribution analysis provided additional insight into feature-level influence within the machine learning framework. Overall, both approaches demonstrated similar predictive capacity, supporting the complementary use of classical regression and explainable machine learning for population-level physical inactivity research.

El presente estudio tiene como objetivo analizar los motivos para practicar AF de los estudiantes universitarios en el contexto ecuatoriano, determinar las diferencias en función del sexo y la compatibilización estudio-trabajo, establecer la asociación entre los motivos para practicar AF y estimar el valor predictor del sexo, la edad y la compatibilización estudio-trabajo sobre los motivos para realizar AF. La muestra estuvo compuesta por 1412 estudiantes universitarios (21.2 ± 3.5 años), 513 hombres (36.3%) y 899 mujeres (63.7%). El instrumento utilizado para la recolección de los datos fue el Cuestionario de Contenido de los Objetivos en el Ejercicio. Para el análisis de resultados se empleó la prueba U de Mann-Whitney, el coeficiente de correlación de Spearman y un análisis de regresión lineal. Los principales hallazgos demuestran que hay diferencias estadísticamente significativas entre hombres y mujeres en los motivos de afiliación social, dirección de la salud, reconocimiento social y desarrollo de la habilidad. También, se observan diferencias estadísticas entre las mujeres que compatibilizan o no el estudio y el trabajo en los motivos de afiliación social, reconocimiento social y desarrollo de la habilidad. Por otro lado, se identifica que la principal motivación para realizar AF está direccionada a la salud, mientras que el motivo que menos incentiva la práctica de AF es el reconocimiento social. Por último, en el análisis de regresión el sexo presenta un valor predictor significativo en los motivos analizados. Por lo cual, se ponen de manifiesto los intereses de los estudiantes ecuatorianos y se obtiene información clave para mejorar e incrementar los niveles y la adherencia a la AF con el fin de contribuir a una vida físicamente más activa en la población universitaria. Palabras clave: motivos, actividad física, universitarios, motivación, Ecuador The aim of the present study was to analyze the reasons for practicing PA among university students in the Ecuadorian context, determine the differences according to sex and work-study compatibility, establish the association between the reasons for practicing PA, and estimate the predictive value of sex, age, and work-study compatibility on the reasons for practicing PA. The sample consisted of 1412 university students (21.2 ± 3.5 years), 513 men (36.3%) and 899 women (63.7%). The instrument used for data collection was the Goals in Exercise Content Questionnaire. The Mann-Whitney U test, Spearman's correlation coefficient and a linear regression analysis were used to analyze the results. The main findings show that there are statistically significant differences between men and women in the reasons of social affiliation, health direction, social recognition and skill development. Also, statistical differences are observed between women who do or do not combine study and work in the reasons of social affiliation, social recognition and skill development. On the other hand, the main motivation for PA is health, while the motive that least encourages the practice of PA is social recognition. Finally, in the regression analysis, sex presented a significant predictive value in the motives analyzed. Therefore, the interests of Ecuadorian students are revealed, and key information is obtained to improve and increase the levels and adherence to PA in order to contribute to a more physically active life in the university population. Keywords: Reasons, physical activity, university students, motivation, Ecuador