The Essential Rule of Deep Learning and Machine Learning Technique for Diagnosis Childhood Obesity: A Comparative Analysis

Abstract

Obesity in children and adolescents is a serious health problem that is becoming more prevalent worldwide. In both industrialized and developing countries, morbid obesity is a significant public health concern. Specifically, this study intends to compare some approaches for childhood obesity diagnosis. Several diseases that formerly only affected adults, like heart disease, high blood pressure, and Type 2 diabetes, are now being found in young children. According to the New England Journal of Medicine, precision medicine is the capacity to predict the best treatment for an individual patient. In order to create obesity prediction models or identify important factors that contribute to obesity in order to create intervention tools, a number of studies based on machine learning and deep learning algorithms have been proposed. To create effective strategies for reducing childhood and teenage obesity, a thorough comprehension and critical evaluation of current deep learning and machine learning models are required. This study provides a critical review of the shortcomings of the current systems in order to present a logical perspective on the expanding corpus of recent research on machine learning and deep learning models for obesity prediction. For the analysis of the state-of-the-art, the taxonomy of the available literature on obesity prediction into methodologies utilized, predicted outcome, factors considered, kind of datasets, and the associated goal is explored. The objectives are to push the boundaries of this discipline and improve the quality of the conversations, and help identify the current gap between the most approaches. The results of this survey can be expanded upon by future research to create more accurate prediction models that incorporate data from other areas.