Prediction of Obesity in adolescent and childhood using machine learning models

In many nations, the frequency of childhood and adolescent obesity is rising at a higher rate, given the correlation between these disorders and other comorbidities like metabolic syndrome, type 2 diabetes, and cardiovascular diseases, which will severely threaten the health system in the future. Machine learning models used for the prediction of obesity in adolescents and childhood due to the consequences are of utmost importance in order to build suitable prevention strategies and comprehend its causes. Obesity prediction among children and adolescents includes unique elements such as hormonal changes, metabolic, anthropometric, weaning, and pre-gestational changes experienced throughout this time. Machine learning is considered significant because it is more powerful and robust in future prediction. This is particularly critical in light of the recent emergence of sizable electronic health record repositories that enable the creation of models using datasets with many predictor variables and instances using deep learning technology for accurate prediction. The main scope of the study is to use the different types of machine learning models for forecasting adolescent and childhood obesity.