delirium-risk-predictor

An application to predict risk of delirium at time of admission.

This is a Next.js application that predicts the risk of delirium based on various clinical factors. It uses a React frontend with a clean, clinical interface.

Prerequisites

Before you begin, ensure you have the following installed:

• Node.js (version 14 or later)
• npm (usually comes with Node.js)

Getting Started

To get the application running on your local machine, follow these steps:

1. Clone the repository:

git clone git@github.com:VectorInstitute/delirium-risk-predictor.git

2. Navigate to the project directory:

cd delirium-risk-predictor

3. Install the dependencies:

npm install

4. Run the frontend server in development mode:

npm run dev -- -p <port>

5. Run the backend FastAPI server:

poetry install
cd api/
uvicorn api.main:app --reload --host 0.0.0.0 --port 8001

6. Open your browser and visit http://localhost:<port> to see the application.

Project Structure

• app/page.tsx: The main page component
• components/InputForm.tsx: The form for inputting patient data
• components/ResultsDisplay.tsx: Displays the risk prediction results
• api/: The backend API endpoints
• public/: Contains static assets like logos

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the Apache 2.0 license.

Acknowledgements

• Vector Institute
• GEMINI