Skip to content

README.md

Latest commit

 

History

History
231 lines (181 loc) · 8.43 KB

README.md

File metadata and controls

231 lines (181 loc) · 8.43 KB
Raw

GitHub Stars Docker Pulls

🩺 AI-Powered Healthcare Intelligence Network

Revolutionizing Healthcare with AI-Driven Predictions, Recommendations, and Insights, Medibot(RAG)

DALL·E 2025-03-06 19 27 45 - A high-tech AI-driven healthcare system banner

📌 About This Project

The AI-Powered Healthcare Intelligence Network is a cutting-edge platform that leverages Machine Learning (ML) and Natural Language Processing (NLP) to provide accurate disease predictions, personalized medical recommendations, and AI-assisted drug suggestions. The system aims to enhance early diagnosis, reduce medical errors, and offer intelligent healthcare solutions.

AI.Powered.Healthcare.System.3.mp4

🚀 Features

💡 Disease Prediction & Medical Recommendation

This module uses Machine Learning to predict diseases based on symptoms and suggest the best medical recommendations.

  • ✅ Predicts diseases based on symptoms provided by the user.
  • ✅ Uses RandomForest Classifier for predictions.
  • ✅ Provides recommended treatments and precautions.
  • ✅ Provides medical descriptions, precautions, medication suggestions, and diet recommendations**.
Screenshot 1 Screenshot 2

💊 AI-Powered Drug Recommendation

Our AI system uses NLP & Cosine Similarity to recommend alternative medicines based on drug properties.

  • ✅ AI-powered alternative medicine finder.
  • ✅Utilizes **NLP & cosine similarity** for **accurate drug matching**
  • ✅ Matches medicines with similar ingredients.
  • ✅ Ensures safer and more effective drug prescriptions.
Screenshot 1 Screenshot 2

🪀 Heart Disease Risk Assessment

This module uses LightGBM & AI classifiers to assess heart disease risks based on patient history.

  • ✅ Evaluates heart disease risk based on lifestyle and medical history.
  • ✅ Uses machine learning models (LightGBM, EasyEnsemble) for predicting heart disease risk.
  • ✅ Takes inputs like age, BMI, smoking habits, medical history, etc.
  • ✅ Provides a **personalized heart risk score with AI-driven recommendations**
Screenshot 1 Screenshot 2

🤖 Medibot - AI Health Assistant

Our LLM-powered chatbot answers medical queries and provides instant healthcare insights using Hugging Face LLM (Mistral-7B-Instruct).

  • ✅ AI-powered medical chatbot based on Mistral-7B-Instruct.
  • ✅ Retrieves medical information from a FAISS vector database.
  • ✅ Retrieves reliable medical information using RAG (Retrieval Augmented Generation.
  • ✅ Provides fast, relevant, and fact-based healthcare responses.
  • ✅ Provides reliable AI-driven answers to health-related questions.
Screenshot 1 Screenshot 2

📂 Folder Structure

📦 AI-Powered Healthcare Intelligence Network
│── 📂 models/                         # Trained ML models
│── 📂 data/                           # Medical datasets (CSV)
│── 📂 vectorstore/db_faiss/           # FAISS vector database
│── 📂 utils/                          # Images, styles, and helper files
│── 📂 pages/                          # Individual module pages
│── 📜 home.py                         # Main homepage (Streamlit UI)
│── 📜 requirements.txt                 # Dependencies
│── 📜 README.md                        # Project Documentation
│── 📜 .gitignore                        # Ignored files
│── 📜 styles.css                        # Custom CSS for UI

⚙️ Installation & Setup

1️⃣ Clone the Repository

git clone https://github.com/AbhaySingh71/AI-Powered-Healthcare-Intelligence-System.git
cd AI-Powered-Healthcare-Intelligence-System

2️⃣ Set Up the Virtual Environment

python -m venv venv
source venv/bin/activate  # On macOS/Linux
venv\Scripts\activate  # On Windows

3️⃣ Install Dependencies

pip install -r requirements.txt

4️⃣ Set Up Environment Variables

Create a .env file and add:

HF_TOKEN=your_huggingface_api_token

Ensure it is added to GitHub Secrets when deploying.

5️⃣ Run the Application

streamlit run home.py

🚀 Deployment on Streamlit Cloud

1️⃣ Push code to GitHub

git add .
git commit -m "Initial commit"
git push origin main

2️⃣ Deploy on Streamlit

  • Go to Streamlit Cloud → Deploy a new app.
  • Set HF_TOKEN in Streamlit Secrets.
  • Click Deploy! 🎉

⚙️ Technologies Used

  • Machine Learning: RandomForest, LightGBM, NLP, Cosine Similarity
  • AI & NLP: Hugging Face Transformers, LangChain, FAISS
  • Data Handling: Pandas, NumPy, Pickle
  • Web Framework: Streamlit
  • Visualization: Plotly, SHAP for feature importance
  • Cloud Deployment: AWS, GCP

🔍 Why Use This App?

  • 🏥 AI-Powered Healthcare Insights: Get data-driven medical predictions.
  • ⚕️ Enhances Patient Care: Supports doctors and patients in making informed decisions.
  • 💡 Real-Time Recommendations: Provides immediate AI-assisted insights.
  • ⏳ Saves Time: Automates diagnosis and medical recommendations.
  • 🔬 Empowers Medical Research: Helps in early disease detection and prevention.

Docker Deployment

This project is Docker-first. Docker ensures that the model can run in any environment without worrying about Python versions, dependencies, or system settings.

docker pull abhaysingh71/ai-powered-healthcare-system
docker run -p 8501:8501 abhaysingh71/ai-powered-healthcare-system

✅ Why Docker?

  • Environment-independent deployments
  • Fast setup and teardown
  • Easy to host on cloud (AWS, GCP, Azure)
  • Reproducibility for teams and CI/CD pipelines

🌐 Docker hub

📜 License

This project is licensed under the MIT License. Feel free to use, modify, and contribute!

📬 Contact Us

Have questions or need support? Reach out to us at:

🌐 Connect With Me

🐙 GitHub | 🔗 LinkedIn | 🐦 Twitter