This project involves the development of a machine learning model for early diabetes detection. We used a dataset of patient health records containing features such as BMI, blood pressure, glucose levels, age, insulin levels, and skin thickness.
The model was trained using Scikit-learn with algorithms like Logistic Regression and Random Forest. After preprocessing and feature scaling with Pandas and NumPy, we evaluated the model using accuracy, precision, recall, and ROC-AUC score.
The goal was to assist healthcare professionals in identifying high-risk individuals through a simple, automated system.
Technologies: Python, Pandas, Scikit-learn, NumPy, Matplotlib