Prediction of Metabolic Disease using Various Multilevel Classification Algorithms and Their Analysis

In recent years, multilevel classification algorithms have gained much attention due to their ability to handle complex classification problems. This study provides a metabolic syndrome prediction model using multi-layer classification algorithms. The proposed model is based on a dataset containing medical records of patients. In order to determine which multi-level classification algorithms performed best at detecting the existence or absence of a metabolic syndrome, the study examined SVM, decision trees, and random forests. The suggested approach has potential applications in the early identification and prevention of metabolic syndrome, a substantial risk factor for cardiovascular disease and diabetes.