Heart Attack Risk Prediction Using Machine Learning & SHAP Explainability

!!This is the GitHub repository for my first research paper! This project focuses on predicting heart attack risk using advanced machine learning models and explainability techniques like SHAP analysis.
📖 About the Research

1. This study uses XGBoost and Random Forest to predict heart attack risks based on the data.
   
2. SHAP explainability helps interpret the model’s decision-making process for transparency.
   
3. The goal is to contribute to trustworthy AI-driven healthcare.
   

-->Features

1. Machine Learning Models – XGBoost, Random Forest, and Logistic Regression for risk prediction.
   
2. Explainability with SHAP – Helps understand feature importance in predictions.
   
3. Data Processing & Analysis – Uses Pandas, NumPy, Matplotlib and Seaborn for visualization.
   
4. Preprint & Publication – Hosted on ResearchGate & Zenodo for open access.
   

📖 Read the Full Paper:
🔗 ResearchGate: https://www.researchgate.net/publication/392693726_Heart_Attack_Risk_Prediction_Using_Machine_Learning_and_SHAP_Explainability
🔗 Zenodo DOI: https://zenodo.org/records/15663652

🤝 Contributions & Feedback
--Have feedback on the paper? Please comment on ResearchGate or submit an issue here!
--Want to collaborate? Reach out via LinkedIn or GitHub Discussions!