Skip to content

Latest commit

 

History

History
72 lines (50 loc) · 3.27 KB

README.md

File metadata and controls

72 lines (50 loc) · 3.27 KB

🩺 Medical Chatbot for Symptom Analysis and Disease Guidance

📜 Summary

This project develops a local, AI-driven medical chatbot designed to assist users with symptom analysis and provide preliminary health guidance. The chatbot employs a pre-trained GPT-2 model for natural language understanding and integrates with MongoDB to store user interactions.

Key features include:

  • Symptom-based analysis: Extract relevant medical conditions and offer follow-up questions.
  • Medical recommendations: Provide tailored guidance based on a pre-programmed symptom questionnaire.
  • Emergency response: Direct users to nearby medical facilities in urgent cases.

The chatbot includes a Graphical User Interface (GUI) built with PyQt5, enabling easy interaction with users. The project demonstrates the integration of machine learning for conversational AI, symptom classification, and basic medical guidance, while focusing on a user-friendly interface.

🎯 Objective

To develop a medical chatbot that helps users by analyzing symptoms and providing tailored health-related recommendations and emergency guidance.

🛠 Skills Required

Technical Skills

Python NLP GPT-2 PyQt5 MongoDB Torch

  • Python programming
  • Natural Language Processing (NLP) using GPT-2
  • PyQt5 for GUI development
  • MongoDB for data storage and retrieval
  • Torch for machine learning model execution
  • Basic understanding of medical terminologies

Soft Skills

  • 🧠 Problem-solving
  • 🎯 Attention to Detail
  • 🎨 User Interface Design
  • 🗣️ Communication for handling user input effectively

📊 Deliverables

Key Outputs

  • 🤖 A functional chatbot application with:
    • Symptom-based conversation flow
    • Dynamic question generation based on user input
    • Real-time medical recommendations
    • A fully operational GUI for user interaction
  • 🧠 Pre-trained NLP model integration for text generation and intent recognition
  • 🗂 Stored conversation logs in MongoDB for future analysis or improvements
  • 🚨 Emergency handling system with integrated browser redirection for urgent care

🔍 Additional Information

  • Model Used: GPT-2 for generating dynamic responses.
  • Conversation Flow: Customized using a keyword-based intent extraction system.
  • Data Storage: MongoDB is used to maintain user-specific context and manage multiple symptoms.
  • GUI Development: PyQt5 ensures ease of use and a professional interface.
  • Environment: Built locally to provide quick access and ensure user privacy during conversations.