🧠 GlucoRisk – Diabetes Risk Prediction System

A Machine Learning–based diabetes prediction system built using Python and Logistic Regression. The model analyzes clinical health parameters to classify whether a patient is likely to have diabetes.

🚀 Features

1. Exploratory Data Analysis (EDA) – Dataset inspection, target distribution, and correlation heatmap visualization.
2. Data Preprocessing – Feature scaling using StandardScaler.
3. Machine Learning Model – Logistic Regression classifier for binary outcome prediction.
4. Model Evaluation – Accuracy score, confusion matrix, and classification report.
5. Sample Prediction System – Predicts diabetes risk for a new patient input.

📂 Project Structure

GlycoRisk-Engine/
├── main.py
├── diabetes.csv
├── requirements.txt

💡 Technologies Used

• Python
• Pandas
• NumPy
• Scikit-learn
• Matplotlib
• Seaborn

🛠️ How to Run

1. Clone the repository:

git clone https://github.com/Agent-A345/GlycoRisk-Engine.git

2. Install the dependencies:

pip install -r requirements.txt

3. Run the application

python main.py

📊 Model Objective

To predict whether a patient is diabetic (1) or non-diabetic (0) using clinical features such as:

• Pregnancies
• Glucose
• Blood Pressure
• Skin Thickness
• Insulin
• BMI
• Diabetes Pedigree Function
• Age

The system applies feature scaling and Logistic Regression to perform binary classification.

📈 Evaluation Metrics

The model is evaluated using:

• Accuracy Score
• Confusion Matrix
• Precision, Recall, F1-score

🔄 Future Enhancements

• Model serialization using joblib
• Hyperparameter tuning
• Class imbalance handling
• Web-based deployment
• Explainable AI integration (SHAP / LIME)

📝 License

This project is licensed under the MIT License.