keyboard_arrow_up
Predicting Diabetes with Machine Learning Analysis of Income and Health Factors Detection

Authors

Fariba Jafari Horestani and M. Mehdi Owrang O, American University, USA

Abstract

This study, explores the intricate interplay between diabetes risk and a plethora of health indicators, with a special emphasis on the economic dimension of income, leveraging data from the 2015 Behavioral Risk Factor Surveillance System (BRFSS). We examine the influence of various health factors-such as blood pressure, cholesterol, BMI, and lifestyle choices like smoking-on diabetes prevalence, with a novel focus on the role of income. Through comprehensive statistical and machine learning analyses, we delineate how socio-economic status correlates with diabetes, revealing that lower income groups exhibit a higher risk of the disease. Notably, our findings underscore the significant predictive power of income, alongside traditional health metrics, in diabetes incidence. The inclusion of income as a variable provides new insights into the socioeconomic gradients affecting health outcomes and highlights the potential for tailored public health interventions. Our research contributes to the growing body of evidence that socioeconomic factors, particularly income, are critical in managing and understanding diabetes risk, offering a broader perspective for public health strategies aimed at mitigating diabetes prevalence.

Keywords

Full Text  Volume 14, Number 7