This project is a Flask-based web application designed to predict patient persistence in healthcare using a Random Forest model. The app leverages exploratory data analysis (EDA) and feature engineering to enhance prediction accuracy and provides a user-friendly interface for accessing machine learning insights.
Predictive Model: Uses a Random Forest algorithm to predict patient persistence based on provided data.
Data Analysis: Integrated exploratory data analysis to visualize trends and understand dataset characteristics.
Feature Engineering: Includes preprocessing techniques to prepare raw data for robust model performance.
Web Interface: Built with Flask, allowing users to input data and receive predictions in real-time.
Programming Language: Python
Frameworks: Flask
Libraries: Machine Learning: Scikit-learn, NumPy Visualization: Matplotlib, Seaborn Backend Utilities: Pandas
Python 3.8 or later Flask
Clone the repository:
bash
Copy code
git clone https://github.com/yourusername/healthcare-persistency-prediction.git
cd healthcare-persistency-prediction
Create a virtual environment and activate it:
bash
Copy code
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
Install the dependencies:
bash
Copy code
pip install -r requirements.txt
Run the Flask application:
bash
Copy code
flask run
Open your browser and navigate to:
arduino
Copy code
http://127.0.0.1:5000
Input patient data in the provided form on the web interface. Submit the form to generate a prediction for patient persistence. View the prediction result and related data insights.
app.py: Main Flask application file. model.pkl: Pre-trained Random Forest model for predictions. templates/: HTML templates for the web interface. static/: CSS and JS files for styling and functionality. requirements.txt: List of dependencies required to run the project.
Implement additional machine learning models for comparison. Add data visualization on the web interface for EDA insights. Integrate database support for storing patient data and predictions. License
Special thanks to the open-source community for providing the tools and resources that made this project possible. Feel free to contribute or provide feedback by opening an issue or pull request!
