• Website Demo Video (Youtube link):

Technologies Used

Frontend

• HTML, CSS, Tailwind CSS - Styling and UI components.
• React.js - Dynamic frontend framework for an interactive UI.
• Deployed on Vercel.

Backend

• Node.js & Express.js - Server-side development.
• MongoDB (Atlas) - NoSQL database for storing user and appointment data.
• JWT - Secure authentication and session management.
• Deployed on Render.

Machine Learning

• Python & Flask - API integration for disease prediction.
• Scikit-learn - Used for training and implementing ML models.
• Models Implemented:
  • Logistic Regression: General disease prediction.
  • AdaBoost: Diabetes prediction for women.
  • Gradient Boosting: Stroke prediction.
• Deployed on Render.

How It Works

1. User Registration & Login

   • Sign up as a doctor or patient.
   • Authentication is handled using JWT for security.

2. Appointment Booking & Management

   • Patients browse and request appointments with doctors.
   • Doctors can accept or decline appointment requests.
   • Status updates (Pending, Confirmed, Completed, Canceled) are reflected in real time.
   • Calendar view displays appointment statuses for easy tracking.

3. Verification Appointment

   • Patients receive an email with the approval or cancellation status and a QR code.
   • When both the doctor and patient meet, the doctor scans the QR code to verify the appointment.

4. Disease Prediction

   • The main feature is disease prediction using symptoms.
   • Additionally, we have separate models for Diabetes Prediction (for women) and Stroke Prediction.

Installation & Setup (run locally)

1. Clone the repository:

   git clone https://github.com/ParamPS25/DoctorAppointmentSystem.git
   cd DoctorAppointmentSystem
   

2. Set up Environment variables

   VITE_ML_DOC_API = http://localhost:5000
   VITE_NODE_DOC_API = http://localhost:8080
   

   MONGO_URI = mongodb+srv://username:password@your-cluster.mongodb.net/your-database
   PORT = 8080
   JWT_ACCESS_SECRET = your_jwt_access_secret_key
   JWT_REFRESH_SECRET = your_jwt_refresh_secret_key
   JWT_EXPIRES_IN = 1h
   COOKIE_EXPIRES_IN = 24
   MAIL_PASS = your_email_app_password
   FRONTEND_URL=http://localhost:5173
   

3. Install dependencies for the frontend:

   cd frontend
   npm install
   npm run dev
   

4. Install dependencies for the backend:

   cd backend
   npm install
   npm run dev
   

5. Run the machine learning backend:

   cd ml-backend
   pip install -r requirements.txt
   python app.py
   

6. Using Conda for ML Backend (Alternative Setup):

    cd ml-backend
    conda create -n doc_env python=3.8 -y
    conda activate doc_env
    pip install -r requirements.txt
    python app.py
   

Contributors

• Param Bhavasar - Backend Development
• Purv Patel - Frontend Development
• Prit Patel - Frontend Development
• Prince Patel - Machine Learning

License

• This project is licensed under the MIT License.