During the last years, a disease with a higher incidence in children and adolescents has been observed, being this the bone weakness, which can be the beginning of chronic bone diseases and future bone cancer, that is why our objective is to detect bone weakness in children and adolescents through anthropometric indicators in the high Andean areas of Peru, specifically in the city of Arequipa. Applying various data mining techniques that allow a deep analysis and prediction that these algorithms indicate after training. We worked with data from 1511 people between children and adolescents. The Knowledge Discovery in Databases methodology was used to perform data pre-training. When applying the classification algorithms, it was obtained that 2 out of 5 people among children and adolescents suffer from bone weakness, with an accuracy of 97% and an AUROC of 0.934, this value being reached by the Support Vector Machine algorithm.