StrokeShield is a web application that uses machine learning to predict the risk of heart strokes. The application is built on a Python server and utilizes the RandomForestClassifier algorithm to provide personalized risk assessments based on user input health data.
Check out live demo of the project in the description.
- StrokeShield uses the Stroke Prediction Dataset from Kaggle to train and test the RandomForestClassifier algorithm.
- This dataset includes 5110 records of
patient data, including demographic information, lifestyle factors, and medical history. - After preprocessing the data and training the model, StrokeShield achieved an accuracy of 94% on the test set.
- This high accuracy demonstrates the effectiveness of the RandomForestClassifier algorithm in predicting stroke risk based on individual risk factors.
- User-friendly interface for inputting health data
- Machine learning algorithm for predicting stroke risk
- Personalized risk assessments based on user data
- Proactive prevention strategies for improved heart health
- An accuracy of 94% prediction of required outcome with this approach.
- Clone the repository:
git clone https://github.com/spiderxp3/strokeshield.git - Install the required packages:
pip install -r requirements.txt - Run the server:
python server.py - Open the application in your web browser:
http://localhost:5000
- Input your health data into the application
- Click the "Predict" button to receive your personalized stroke risk assessment
- Follow the proactive prevention strategies provided by the application to improve your heart health
Contributions to StrokeShield are welcome! If you find a bug or have a feature request, please open an issue on the repository. If you would like to contribute code, please fork the repository and submit a pull request.
StrokeShield is licensed under the MIT License. See LICENSE for more information.
- RandomForestClassifier algorithm from scikit-learn
- Flask web framework
- Bootstrap CSS framework