A Comprehensive Analysis of Diabetes Risk Prediction Using Logistic Regression

This study aimed to develop a predictive model for diabetes risk using a combination of demographic, examination, diet, and laboratory data. The dataset was processed through ETL (Extract, Transform, Load) and EDA (Exploratory Data Analysis) to identify potential correlations. A logistic regression model was built and evaluated using various metrics, achieving an accuracy of approximately 93%. The results indicate that the model can accurately predict diabetes risk, making it a valuable tool for healthcare professionals. The study demonstrates a comprehensive approach to building a predictive model for diabetes risk using a multidimensional dataset with potential applications in healthcare.