Machine Learning-Based Diabetic Risk Prediction Model for Early Detection

Abstract

Diabetes is a chronic disease that affects millions of people worldwide. Early detection and effective management of diabetes can significantly reduce the risk of complications and improve the quality of life of individuals with diabetes. In recent years, machine learning techniques have been applied to predict the risk of diabetes and to develop personalized treatment plans. In this study, we propose a machine learning-based diabetic risk prediction model for early detection and management. The proposed model uses various clinical and demographic variables such as age, gender, BMI, blood pressure, and fasting blood glucose levels to predict the risk of developing diabetes. We evaluated the performance of the proposed models using a dataset of patients with diabetes and non-diabetic individuals. Machine learning techniques including Logistic Regression, Support Vector Machine, K-Nearest Neighbors, and Random Forest are evaluated using the confusion matrices. The experimental results show that the Random Forest classifier achieved an accuracy of 80%, sensitivity of 82%, specificity of 80% in predicting the risk of diabetes. However, Increasing the accuracy rates of machine learning algorithms to 90% to 100% will be the challenging part of this study.