How sharmeenshahid08/campus-health-detector works
Campus Health Detector is a Streamlit clinical decision-support dashboard. A user enters student and visit details, receives predictions for stress relation, diagnosis, treatment, and follow-up, and can inspect model results and campus health trends. The dashboard trains models at startup; a separate Python script also contains a data-generation, training, and prediction workflow. Evidence is partial, so the graph avoids assuming that the script supplies the dashboard or that the CSV is loaded by a particular code path.
Main entry points: streamlit_app.py Dashboard interface · full_dataset_5000.csv 5,000 health records
Components 9
Streamlit dashboard
- Dashboard interface
streamlit_app.py - Patient input
streamlit_app.py
Prediction and modeling
- Startup model training
streamlit_app.py - Patient prediction
streamlit_app.py - Standalone ML workflow
campus_health_detector.py
Results and insights
- Model results
streamlit_app.py - Data insights
streamlit_app.py
Health data
- 5,000 health records
full_dataset_5000.csv
Other components
- Medical staff
Connections 8
- Medical staff → Dashboard interface: uses
README.md - Dashboard interface → Patient input: collects
README.md - Dashboard interface → Startup model training: trains at startup
README.md - Patient input → Patient prediction: requests predictions
README.md - Startup model training → Patient prediction: supplies models
streamlit_app.py - Dashboard interface → Model results: displays
README.md - Dashboard interface → Data insights: displays
README.md - 5,000 health records → Startup model training: trains on