Health Monitoring System

Description

The Health Monitoring System is a web-based machine learning application designed to predict diseases based on user-provided symptoms. The application utilizes a Multi-Layer Perceptron (MLP Classifier) machine learning model, achieving an accuracy of 94.42% and an f1-score of 94.30%.

This system enables users to select from 376 symptoms and predicts up to 41 diseases with a confidence score threshold of 50%, ensuring reliable and data-driven health assessments. Once a disease is predicted, the application provides detailed information including:

1. Disease Description
2. Precautions
3. Recommended Diet
4. Medications
5. Doctor to be Consulted

Additionally, users can download a neatly formatted PDF prescription for their records. The frontend is built using React.js, providing a seamless and interactive user experience, while the backend is powered by Flask, ensuring robust and efficient data handling.

#### [!NOTE]
Checkout the screenshots of the web app in the HMS-Interface Preview folder.

Dataset

The dataset used in this project is a combination of two publicly available datasets:
1. Disease-Symptom Dataset (Kaggle)
2. Symptom-Disease Prediction Dataset (Mendeley)

After integrating these datasets, extensive processing - including symptom mapping, disease mapping, elimination of redundant features, and removal of duplicate records... was performed. The final dataset consists of:

• 19,012 records
• 376 unique symptoms
• 41 disease labels

For additional disease-related information such as description, precautions, diet, medications, and consulted doctor, the following resource was used:
Disease-Prediction-and-Medical-Recommendation-System

Installation Guide

Follow these steps to set up and run the Health Monitoring System on your local machine.

Prerequisites

Ensure you have the following installed:

Step 1: Clone the Repository to your local machine

    1. Run the following command to clone the repository:
        git clone https://github.com/BharathKanuri/health-monitoring-system.git

    2. Navigate to the project directory:
        cd health-monitoring-system

Step 2: Set Up the Backend

    1. Navigate to the backend folder:
        cd backend

    2. Create a virtual environment (optional but recommended):
        python -m venv venv

    3. Activate the virtual environment:
        • On Windows:
            venv\Scripts\activate

        • On macOS/Linux:
            source venv/bin/activate

    4. Install the required Python packages:
        pip install -r requirements.txt

    5. Run the Flask backend server:
        python app.py

[!NOTE]

Before proceeding, please visit /frontend/README.md for detailed instructions on setting up the React app.

Step 3: Set Up the Frontend

    1. Open a new terminal window and navigate to the frontend folder:
        cd ../frontend

    2. Install the required Node.js packages:
        npm install

    3. Start the React development server:
        npm start

Step 4: Access the Application

    Once both the backend and frontend servers are running, open your browser and
    navigate to: https://localhost:3000 to access the Health Monitoring System.

Project Directory Structure

Usage

Technologies Used

1. Frontend: React.js
2. Backend: Flask (Python)
3. Machine Learning: Multi-Layer Perceptron Model (scikit-learn library)
4. PDF Generation: jspdf & jspdf-autotable libraries
5. Styling: CSS