Research on Diabetes based on the Logistic Regression Model

Abstract

Diabetes, as a globally prevalent metabolic disease, poses a serious threat to public health. Due to the subtle early symptoms of diabetes, most patients have already developed complications by the time they are diagnosed. Therefore, risk prediction becomes crucial for disease prevention and control. This study employs a logistic regression model to conduct predictive analysis on a dataset from Kaggle and utilizes a confusion matrix to determine the accuracy of the model's predictions, while also performing comparative auxiliary analysis. The results showed that the model had a prediction accuracy of 74.500%, indicating good predictive performance. This study holds dual value. At the clinical practice level, the use of logistic regression models can assist in identifying high-risk populations and implementing early intervention to reduce the risk of disease, providing significant guidance for primary care. In terms of diabetes prevention, people can start by focusing on factors that affect diabetes, identifying which factors have a more significant impact on the development of diabetes, and thereby reducing the risk of developing diabetes.