diabetes-risk-prediction-cnn

Diabetes Risk Prediction - End to End

This project provides an end-to-end solution for predicting diabetes risk based on various health metrics using a Random Forest Classifier.

Features

• Data Preprocessing: Handling categorical variables and feature scaling.
• Machine Learning: Random Forest model trained on patient health data.
• Web Interface: A premium, modern web dashboard built with Flask and Vanilla CSS/JS.
• Real-time Prediction: Instant risk assessment with confidence levels.

Tech Stack

• Backend: Python, Flask
• Machine Learning: Scikit-Learn, Pandas, NumPy
• Frontend: HTML5, Vanilla CSS (Glassmorphism), JavaScript

Project Structure

• train.py: Script to train the ML model and save preprocessors.
• app.py: Flask application to serve predictions.
• templates/: HTML templates for the web interface.
• static/: CSS and JS files.
• diabetes_risk_dataset.csv: The dataset used for training.
• model.pkl, scaler.pkl, etc.: Saved model and preprocessing artifacts.

How to Run

1. Install dependencies:

   pip install -r requirements.txt
   

2. Train the model (if model artifacts are missing):

   python train.py
   

3. Start the application:

   python app.py
   

4. Open your browser and navigate to http://127.0.0.1:5000

Author

Built with AI for Healthcare Analysis.