How keysarenull/heart-disease-predictor works
This is a small Streamlit health-risk prediction app. A user enters patient features, the app encodes them in the model’s expected order, and the loaded classifier produces a risk label and confidence estimate. The sampled app source supports the form, model-loading, inference, and display flow; the README provides no additional product capabilities.
Main entry points: app.py Risk inference · random_forest_heart_disease_model.joblib Trained classifier
Components 7
User interface
- Feature form
app.py - Input encoding
app.py - Risk and confidence
app.py
Prediction
- Model loading
app.py - Trained classifier
random_forest_heart_disease_model.joblib - Risk inference
app.py
Other components
- Patient / user
Connections 7
- Patient / user → Feature form: enters features
- Feature form → Input encoding: collects values
- Model loading → Trained classifier: loads model
- Input encoding → Risk inference: provides array
- Trained classifier → Risk inference: supplies classifier
- Risk inference → Risk and confidence: returns prediction
- Patient / user → Risk inference: requests prediction