Dpredicto-An-Disease-Prediction-System

D-predicto is an end-to-end application designed to predict diseases like diabetes, heart disease, and Parkinson's disease with respective accuracies of 77%, 82%, and 87%. Leveraging SVM and Logistic Regression models, this project aims to provide accurate predictions for these ailments. Additionally, it integrates an NLP-driven chatbot into the website, enhancing user interaction and information accessibility.

Description

This project encompasses machine learning models for disease prediction and a chatbot feature using NLP techniques. The models are trained and deployed using Python's SK Learn library. Flask is utilized to develop the web application, providing a user-friendly interface for disease prediction and interaction with the chatbot.

Key Features

• Disease Prediction -D-predicto offers accurate predictions for diabetes, heart disease, and Parkinson's disease, leveraging sophisticated models tailored for each ailment.

• Advanced Models - The integration of Support Vector Machines (SVM) and Logistic Regression models ensures precision and reliability in disease prognosis, achieving accuracy rates of 77%, 82%, and 87% respectively.

• NLP-Driven Chatbot - Enhancing user interaction, the application integrates a Natural Language Processing (NLP) powered chatbot, providing an intuitive and accessible interface for users to access information and engage effectively.

Technologies Used

• Python : The core programming language used for the entire project, facilitating code development and execution.
• SK Learn (Scikit-learn) : Employed for implementing machine learning models such as Support Vector Machines (SVM) and Logistic Regression for disease prediction tasks.
• Machine Learning (ML) : Utilized extensively to train, validate, and deploy the predictive models for diseases like diabetes, heart disease, and Parkinson's disease.
• NumPy : Played a crucial role in handling numerical data and performing computations, enhancing efficiency in data manipulation and model operations.
• Pandas : Used for data manipulation and analysis, particularly for managing and preprocessing datasets required for training the machine learning models.
• NLP (Natural Language Processing) : Integrated for developing a chatbot interface, enabling natural language understanding and interaction for users accessing the application.
• Flask : Utilized as the web framework to develop the user interface, providing a seamless platform for disease prediction and chatbot interaction.
• GitHub : Served as the version control system, hosting the project repository and enabling collaborative development, tracking changes, and managing project iterations.

Requirements

To run this project locally, ensure you have Python installed along with the necessary libraries mentioned in the requirements.txt file. You can install these dependencies using:

  pip install -r requirements.txt

Deployment

Accessing the project involves a few steps:

Step 1 : Clone the Repository :

  git clone https://github.com/shubham-murtadak/dpredictoflask.git

Step 2 : Set Up Environment and Dependencies

• Install Python : Ensure Python (preferably Python 3.x) is installed on your system.

• Install Required Libraries : Navigate to the project directory and install the necessary Python libraries by running -

  pip install -r requirements.txt

If there's a requirements.txt file in the project, this command installs all the dependencies needed for the project to run.

Step 3 : Configure and Run the Project

• Dataset Setup : Ensure the datasets are placed in the appropriate directory (Datasets/) within the project structure as required by the code.

• Adjust Configuration (if required) : Modify any configuration parameters in the code if needed, such as file paths or model hyperparameters.

• Run the Application : Launch the Flask application that powers the disease prediction and chatbot features -

  python app.py

• Accessing the Application : Once the Flask application is running, access it through your web browser using the provided address (usually http://127.0.0.1:5000/ or http://localhost:5000/). Navigate through the user interface to utilize the disease prediction functionality and interact with the chatbot.

Conclusion

D-predicto offers a comprehensive solution for disease prediction, incorporating machine learning models and an interactive chatbot. Its accuracy rates demonstrate its reliability in predicting these critical ailments, aiming to assist users in early diagnosis and information retrieval.

=======