Multiple Disease Prediction System

This project is a web-based multiple disease prediction system built with Python, Machine Learning, and Streamlit (Spyder). It provides a simple and interactive interface where users can input medical parameters to obtain disease predictions.

Table of Contents

• Overview
• Features
• Technologies Used
• Installation
• Usage
• Project Structure
• Requirements

---

Overview

The Multiple Disease Prediction System leverages state-of-the-art machine learning algorithms to predict several diseases based on user-inputted medical parameters in real-time. The user interface is powered by Streamlit for easy interaction.

Features

• Predicts multiple diseases based on various health parameters.
• Intuitive and interactive web-based interface.
• Instant results: The UI displays outcomes within seconds, indicating whether the person has the disease or not.
• Visualization of input data and results.
• Built with modular, extensible code.

Technologies Used

• Jupyter Notebook (100%): Main development and exploratory environment.
• Python: Core programming language for ML models and backend.
• Streamlit: Web application framework for building the UI.
• Machine Learning Libraries: scikit-learn, pandas, numpy, etc.

Installation

1. Clone the repository

   git clone https://github.com/AnanyaGubba/Multiple-Disease-Prediction-System.git
   cd Multiple-Disease-Prediction-System

Requirements

Copy and use the following in requirements.txt:

streamlit
scikit-learn
pandas
numpy
joblib
matplotlib
seaborn

Add additional libraries as needed if you use extra packages in your notebooks or scripts.

2. Install dependencies

   # Create and activate a virtual environment (optional)
   python -m venv venv
   source venv/bin/activate   # For Linux/macOS
   venv\Scripts\activate      # For Windows
   
   # Install required packages
   pip install -r requirements.txt
   

   Note: If requirements.txt is not present, ensure you have Jupyter, Streamlit, scikit-learn, pandas, numpy installed.

Usage

1. Run Jupyter Notebook for exploration

   jupyter notebook

2. Run the Streamlit app

   streamlit run app.py

   Replace app.py with the Streamlit script name if different.

3. Navigate to the provided local URL in your browser and use the web interface to enter medical parameters and view predictions.

4. Get instant outcomes:

   • After submitting parameters, the system delivers results within seconds.
   • The result clearly states whether the person has the disease or not for the selected prediction.

Project Structure

├── README.md
├── requirements.txt
├── multiple_disease_pred.py
├── MDPS_Diabetes.ipynb                  # Jupyter Notebook for ML workflow
├── MDPS_Heart_Disease.ipynb      # Jupyter Notebook for diabetes model
├── MDPS_Breast_Cancer.ipynb # Jupyter Notebook for heart disease model
├── MDPS_Parkinsons.ipynb
│
├── models/
│   ├── bc_trained_model.sav               # Trained breast cancer prediction model
│   ├── diabetes_trained_model.sav                  # Trained heart disease prediction model
|   ├── hd_trained_model.sav                 # Trained heart disease prediction model
|   ├── parkinsons_trained_model.sav            # Trained parkinsons prediction model
│
├── data/
│   ├── diabetes.csv                     # Diabetes dataset
│   ├── heart_disease_data.csv                    # Heart disease dataset
│   |── parkinsons.csv                     # parkinsons dataset
|   |── breast_cancer_data.csv              # breast cancer dataset
|
├── utils/
│   └── helper_functions.py              # Utility scripts
│
└── ...

Feel free to open an issue for questions, feedback, or suggestions!