Performance Evaluation Of Ensembled Learning Algorithms for Aged-Based Risk Factor Analysis Based on Hypertension and Obesity

The worldwide public health issues of obesity and hypertension have far-reaching effects. In this paper, the proposed three ensembled Boosting algorithms, which are CATBoost, XGBoost, and LightGBM, used to predict and gain insights into these critical health conditions. Remarkably, models achieved high accuracy, with CATBoost, XGBoost, and LightGBM delivering impressive results, including obesity and hypertension accuracies of 100% and 91.6%, 100% and 91.07%, and 100% and 91.49%, respectively. Including these results, the Identification of seven key theoretical conclusions regarding the risk factors associated with hypertension and obesity has been done. This approach contributes to a comprehensive understanding of these health issues and informs effective preventive and intervention strategies.