📑 Instructors

HealthPredictor: A Healthcare Machine Learning Application

Welcome to the HealthPredictor Project guide!

This document outlines the framework for delivering the HealthPredictor project, designed for students to develop a comprehensive full-stack healthcare application.

This project combines machine learning, FastAPI for the backend, and a modern frontend framework. Through this experience, students will gain valuable insights and hands-on skills relevant to real-world healthcare challenges.

Project Objectives

By the end of this project, students will be able to:

1. Develop a FastAPI application with machine learning capabilities to predict health risks based on user input.
2. Create a responsive frontend using a JavaScript framework (React, Vue.js, or Angular) that interacts seamlessly with the backend.
3. Implement RESTful API endpoints for data management and predictions.
4. Deploy the application using Docker and set up Continuous Integration/Continuous Deployment (CI/CD) pipelines for automated deployment.
5. Apply best practices in software development, including code organization, documentation, and testing methodologies.

Project Structure and Phases

The FastAPI FullStack template

Phase 1: Research and Planning (1 week)

• Activities:
  • Students select a healthcare dataset (e.g., heart disease, diabetes, or other relevant datasets).
  • Outline the features and functionalities of the application, including user input forms and prediction results.
  • Design the database schema, ensuring it meets the application’s requirements.
• Deliverables:
  • Dataset Selection Document: Justification for the chosen dataset and its relevance to the project.
  • Project Feature List: A comprehensive list of features and functionalities.
  • Initial Wireframe Designs: Mockups of the user interface and user experience.
  • Database Schema Diagram: Visual representation of the database structure.

Phase 2: Backend Development (2 weeks)

• Activities:
  • Develop the FastAPI application to handle backend logic.
  • Create scripts for building and training machine learning models using libraries like scikit-learn or TensorFlow.
  • Implement SQLAlchemy for database management, ensuring proper connections to the selected relational database (e.g., PostgreSQL or SQLite).
• Deliverables:
  • FastAPI Application Code: Codebase for the backend with endpoints for model training, predictions, and CRUD operations.
  • API Documentation: Auto-generated documentation using Swagger, including endpoint specifications.
  • Database Migration Scripts: Scripts to set up the database schema and tables.

Phase 3: Frontend Development (2 weeks)

• Activities:
  • Build the user interface using Streamlit, React, Vue.js, or Angular, ensuring it is intuitive and user-friendly.
  • Integrate the frontend with the FastAPI backend using Axios or Fetch API for data transmission.
  • Implement data visualization components to present prediction results and insights.
• Deliverables:
  • Frontend Codebase: Complete code for the user interface.
  • User Interface Designs: Documentation on UI components and their functionalities.
  • API Integration Documentation: Guidelines on how the frontend interacts with the backend.

Phase 4: Testing and Deployment (1 week)

• Activities:
  • Conduct thorough testing of the application for functionality, usability, and performance.
  • Containerize both backend and frontend applications using Docker to simplify deployment.
  • Deploy the applications to cloud platforms (e.g., AWS, Heroku, or Azure) and set up CI/CD pipelines using GitHub Actions or similar tools.
• Deliverables:
  • Test Cases and Results: Documentation of testing strategies and results obtained.
  • Dockerfiles: Configuration files for containerizing both applications.
  • Deployment Instructions: Comprehensive guidelines for deploying the application, including CI/CD pipeline configurations.

Assessment Criteria

1. Functionality (30%)
   • Does the application perform the required predictions accurately?
   • Are all specified features implemented correctly?
2. Code Quality (25%)
   • Is the code well-structured, organized, and documented?
   • Are best practices followed in both backend and frontend development?
3. User Experience (20%)
   • Is the user interface intuitive, responsive, and aesthetically pleasing?
   • Are the visualizations clear, meaningful, and useful for end-users?
4. Deployment (15%)
   • Is the application deployed successfully with proper accessibility and performance?
   • Are CI/CD pipelines functioning correctly and efficiently?
5. Presentation and Documentation (10%)
   • Is the project documentation clear, comprehensive, and well-structured?
   • Did the team effectively present their project and findings, demonstrating an understanding of the technologies used?

Supporting Materials

• Datasets:
  • UCI Machine Learning Repository: Heart Disease Dataset
  • Kaggle: Diabetes Dataset
• FastAPI Documentation:
  • FastAPI Official Documentation
• Frontend Framework Documentation:
  • React Documentation
  • Vue.js Documentation
  • Angular Documentation
• Docker Documentation:
  • Docker Official Documentation
• CI/CD Resources:
  • GitHub Actions Documentation

Feel free to adapt the timeline and assessment criteria to best fit your course structure and learning objectives!

Let’s inspire the next generation of developers to innovate in healthcare technology!