🩺 AI-Powered Multi-Disease Prediction System

🏥 An AI-powered healthcare web app that predicts the risk of 5 diseases using trained ML models. Integrates multiple predictive models into a single intelligent dashboard for fast, efficient health risk analysis.

⚠️ The app may take a few seconds to load due to free hosting.

---

🧠 Supported Predictions

🩸 Diabetes Prediction Model: Support Vector Machine Accuracy: ~77%	❤️ Heart Disease Prediction Model: Random Forest Accuracy: ~85%	🍺 Liver Disease Prediction Model: Gradient Boosting Accuracy: ~87%
🧬 Kidney Disease Prediction Model: Random Forest Accuracy: 100%	🎗️ Breast Cancer Detection Model: Random Forest Accuracy: ~95%	☁️ Cloud Deployed Platform: Streamlit Cloud Always accessible

---

📊 Model Performance

Disease	Model Used	Accuracy
🩸 Diabetes	Support Vector Machine	~77%
❤️ Heart Disease	Random Forest	~85%
🍺 Liver Disease	Gradient Boosting	~87%
🧬 Kidney Disease	Random Forest	100%
🎗️ Breast Cancer	Random Forest	~95%

---

✨ Key Features

🧠 Multi-Disease Platform 5 diseases in one dashboard Single unified interface Seamless model switching	⚡ Real-Time Predictions Instant ML inference Preprocessing pipeline Pickle model persistence
📊 Interactive UI Clean Streamlit interface Feature input validation Visual result display	🏗️ Scalable Architecture Modular model structure Easy to extend Cloud deployment ready

---

🏗️ System Architecture

User Input (Streamlit UI)
        │
        ▼
Data Preprocessing
(Scaling + Feature Alignment)
        │
        ▼
Machine Learning Model
(SVM / Random Forest / Gradient Boosting)
        │
        ▼
Prediction Output
        │
        ▼
UI Display (Risk Result)

---

📂 Project Structure

Multi_Disease_Prediction_System/
│
├── 📄 app.py                         # Main Streamlit application
│
├── 🏋️ train_diabetes_model.py        # Diabetes model training
├── 🏋️ train_heart_model.py           # Heart disease model training
├── 🏋️ train_liver_model.py           # Liver disease model training
├── 🏋️ train_kidney_model.py          # Kidney disease model training
├── 🏋️ train_breast_cancer_model.py   # Breast cancer model training
│
├── 📁 datasets/                      # Raw training datasets
├── 🧠 models/                        # Saved Pickle model files
│
├── 📋 requirements.txt               # Python dependencies
└── 📖 README.md

---

🛠️ Tech Stack

Layer	Technology
🐍 Language	Python 3.10
📊 Data	NumPy · Pandas
🤖 ML Models	Scikit-learn · XGBoost
🌐 Frontend	Streamlit
💾 Persistence	Pickle
🔧 Tools	Git · GitHub

---

🚀 Getting Started

1️⃣ Clone the Repository

git clone https://github.com/yashrajagawane/Multi-Disease-Prediction-System.git
cd Multi-Disease-Prediction-System

2️⃣ Create & Activate Virtual Environment

# Create
python -m venv venv

# Activate — Windows
venv\Scripts\activate

# Activate — macOS / Linux
source venv/bin/activate

3️⃣ Install Dependencies

pip install -r requirements.txt

4️⃣ Run the Application

streamlit run app.py

---

🎯 Use Cases

• 🏥 Healthcare risk analysis — quick screening for patients
• 🧪 Medical research — support and data exploration
• 📊 Early detection — flag disease risk before symptoms
• 🤖 Clinical decision support — AI-assisted diagnosis aid

---

🔮 Roadmap

• 🚀 API-based deployment with FastAPI
• 🔐 User authentication system
• 📋 Patient history tracking
• 📈 Prediction confidence visualization
• 📱 Mobile-responsive UI improvements
• 🧬 Deep learning model integration

---

👨‍💻 Author

Yashraj Agawane

🎓 B.Tech Student  |  💡 Machine Learning Enthusiast

Passionate about building scalable AI-driven applications and solving real-world problems using Machine Learning & Data Structures.

---

⭐ Found this helpful?

Star the repo — it takes one click and means a lot!

Built with ❤️ to make healthcare more accessible