Exploring Bone Health Determinants in Youth Athletes Using Supervised and Unsupervised Machine Learning
Authors:
- Nikolaos-Orestis RetzepisNRNikolaos-Orestis Retzepis
- Alexandra AvlonitiAAAlexandra Avloniti
- Christos KokkotisChristos Kokkotis
- Theodoros StampoulisTSTheodoros Stampoulis
- Dimitrios BalampanosDBDimitrios Balampanos
- Dimitrios DraganidisDDDimitrios Draganidis
- Anastasia GkachtsouAGAnastasia Gkachtsou
- Marietta GrammenouMGMarietta Grammenou
- Anastasia Maria KaraiskouAKAnastasia Maria Karaiskou
- Danai KelarakiDanai Kelaraki
- Maria ProtopapaMPMaria Protopapa
- Dimitrios PantazisDimitrios Pantazis
Open Access
Abstract
Background: Bone health in youth is influenced by both modifiable factors, such as nutrition and physical activity, and non-modifiable factors, such as biological maturation and heredity. Understanding how these elements interact to predict body composition may enhance the effectiveness of early interventions. Importantly, the integration of both supervised and unsupervised machine learning models enables a data-driven exploration of complex relationships, allowing for accurate prediction and subgroup discovery. Methods: This cross-sectional study examined 94 male athletes during the developmental period. Anthropometric, performance, and nutritional data were collected, and bone parameters were assessed using dual-energy X-ray absorptiometry (DXA). Three supervised machine learning models (Random Forest, Gradient Boosting, and Support Vector Regression) were trained to predict Total Body-Less Head (TBLH) values. Nested cross-validation assessed model performance. Unsupervised clustering (K-Means) was also applied to identify dietary intake profiles (calcium, protein, vitamin D). SHAP analysis was used for model interpretability. Results: The Random Forest model yielded the best predictive performance (R2 = 0.71, RMSE = 0.057). Weight, height, and handgrip strength were the most influential predictors. Clustering analysis revealed two distinct nutritional profiles; however, t-tests showed no significant differences in TBLH or regional BMD between the clusters. Conclusions: Machine learning, both supervised for accurate prediction and unsupervised for nutritional subgroup discovery, provides a robust, interpretable framework for assessing adolescent bone health. While dietary intake clusters did not align with significant differences in bone parameters, this finding underscores the multifactorial nature of skeletal development and highlights areas for further exploration.Keywords
This publication has 74 references indexed in Scilit:
- Hand grip strength trajectories and the risk of low bone mineral density in 6–7-year-old children: a prospective studyEuropean Journal of Pediatrics, 2025
- The independent and interactive associations of physical activity intensity and vitamin D status with bone mineral density in prepubertal children: the PANIC StudyOsteoporosis International, 2021
- Bone metabolism markers and vitamin D in adolescent cyclistsArchives of Osteoporosis, 2018
- Tracking of Areal Bone Mineral Density From Age Eight to Young Adulthood and Factors Associated With Deviation From Tracking: A 17-Year Prospective Cohort StudyJournal of Bone and Mineral Research, 2017
- Vitamin D in European children—statement from the European Academy of Paediatrics (EAP)European Journal of Pediatrics, 2017
- Physical activity may be a potent regulator of bone turnover biomarkers in healthy girls during preadolescenceJournal of Bone and Mineral Metabolism, 2016
- The National Osteoporosis Foundation’s position statement on peak bone mass development and lifestyle factors: a systematic review and implementation recommendationsOsteoporosis International, 2016
- Vitamin D and Bone Health in Childhood and AdolescenceCalcified Tissue International, 2012
- Vitamin D: A Necessity for Children and Adolescents in GreeceCalcified Tissue International, 2005
- Are National Vitamin D Guidelines Sufficient to Maintain Adequate Blood Levels in Children?Canadian Journal of Public Health, 2005