🧠 Hepatitis Prediction using Machine Learning

This project predicts the likelihood of survival in hepatitis patients using a Machine Learning model trained on real medical data. It is built using Python, Jupyter Notebook, and Scikit-learn.

📁 Files in this Repository

• hepatitis.csv - Dataset containing medical records of hepatitis patients.
• hepatitis_prediction_project.ipynb - Jupyter Notebook with data cleaning, exploration, model training, and evaluation.
• 02_model_hapitits.pkl - Trained ML model saved using pickle.

🧪 Tech Stack

• Python
• Pandas, NumPy
• Scikit-learn
• Jupyter Notebook
• Pickle (for model serialization)

✅ What this Project Covers

• Data preprocessing (handling missing values, encoding, etc.)
• Exploratory Data Analysis (EDA)
• Model training using Logistic Regression
• Model evaluation using accuracy score
• Model export for future use

📊 Dataset Info

The dataset contains several features like:

• Age
• Sex
• Steroid
• Liver size
• Bilirubin level
• And other medical indicators

The target is to predict whether the patient lives (1) or dies (2).

📈 Model Performance

• Model Used: Logistic Regression
• Accuracy: ~85% (can vary depending on preprocessing)

🚀 How to Run

1. Clone the repository
2. Install dependencies:

   pip install pandas numpy scikit-learn jupyter

3. Open the notebook:

   jupyter notebook hepatitis_prediction_project.ipynb

🔮 Future Improvements

• Use more advanced models (e.g., Random Forest, XGBoost)
• Deploy the model using Flask or FastAPI
• Build a small frontend interface

---

👨‍💻 Author

Fahad Ali – Full Stack Developer | Python | Django | React | DRF | Exploring AI/ML
GitHub Linkedin

---

📌 This project is a part of my learning journey into Data Science and Machine Learning.