Decision tree in Obesity Level Classification of Northern Technical University Students

Abstract

The rising prevalence of overweight and obesity among youth and adolescents is a concerning trend in many countries. This poses a significant threat to current and future healthcare systems due to the associated risks of cardiovascular disease, type 2 diabetes, metabolic disorders, and even mortality. Developing effective strategies for preventing these conditions and understanding their origins are crucial. Creating predictive models for overweight and obesity in young individuals and their related outcomes holds immense value, and machine learning models have proven to be valuable tools for this purpose. The main objective of this study is to construct a data-driven model that can forecast the likelihood of overweight or obesity in youngsters. HTo achieve this, the researchers employed Decision tree analysis using the Rapid Miner program. This analysis aimed to determine the extent to which various human variables contribute to obesity and how accurately these factors can classify individuals into different obesity index categories based on their determined body mass(body weight in kg divided by the square of body length in meters). For this study, a body mass of <= 24.9 kg.m-2 was considered normal weight (obesity index = 0), while a body mass above 24.9 kg.m-2 indicated overweight (obesity index = 1), The attributes related to student activity and nutrition were utilized as inputs for the Decision tree models, and the outputs were the obesity index classifications. The results of the investigation demonstrated successful classification of obesity levels, with an efficiency rate of 94.16%. This indicates that the data attributes used in the study were highly accurate in determining the obesity index.