Evaluating Obesity and Metabolic Syndrome Risk: A Cloud-Driven Logistic Regression Framework

Abstract

Worldwide, people are struggling with obesity and metabolic syndrome. For successful preventative interventions, it is necessary to predict and evaluate the risk factors linked to these illnesses. For the purpose of determining the potential of metabolic syndrome and obesity, this research presents a new cloud-driven logistic regression paradigm. Using the power of the cloud, we mined a massive dataset that included a wide range of demographic and clinical details. The cloud platform was used to build logistic regression models that analyzed intricate relationships among variables using powerful machine learning methods. A thorough assessment of risk variables is made possible by the framework's incorporation of data from many sources. Predicting the likelihood of obesity and metabolic syndrome was a strong suit of our cloud-based logistic regression methodology. Important factors, such as genetic susceptibility, lifestyle variables, and clinical biomarkers, were discovered by the model. The ability to efficiently handle parallel data sets on the cloud improved the model's predictive powers and made it possible to analyze massive datasets. an efficient and scalable method for large-scale evaluation of obesity and metabolic syndrome risk is provided by the suggested framework. The model may be easily adjusted to new trends and changing datasets using cloud-driven analytics, allowing real-time updates and enhancements. This study provides a powerful instrument for risk assessment and focused preventative actions, which advances public health initiatives and personalized treatment. © 2024 IEEE.