`pip install -r requirements.txt` installs all Python dependencies for the Clinical AI Decision Support System.
`cp .env.example .env` creates a local environment file that I then edit to add my `GROQ_API_KEY`.
`uvicorn api.main:app --reload` starts the FastAPI backend with live reload.
`streamlit run app.py` launches the Streamlit front‑end UI.
All predictions include SHAP explanations so clinicians can understand which clinical features influence the model output.
LLM explanations are supported by retrieved clinical guideline evidence, helping reduce hallucinations and improve reliability.
Clinicians remain responsible for reviewing predictions and explanations through a human‑in‑the‑loop decision process.
Generated reasoning passes through validation layers that enforce safety checks and clinical disclaimers.
- The system monitors:
This project is a research and educational implementation of an AI‑powered clinical decision support system.
I use these steps whenever I need to spin up the CDSS locally for experimentation or demo purposes.
- Prediction confidence
- Model calibration
- Data drift
- Pipeline reliability
The repository started 2025-12 and was last updated 2026-10.
Topics: ai, ai-system, clinicaldecisionsupport, explainable-ai, fastapi, generative-ai, healthcare-ai, llm, machine-learning, rag, shap, streamlit.