cvd-risk-prediction

Cardiovascular Risk Prediction

This project implements a full end‑to‑end machine learning pipeline for cardiovascular risk prediction using structured clinical data.
It includes rigorous data cleaning, feature engineering, robust preprocessing, model benchmarking, probability calibration, interpretability, fairness analysis, and a fully documented final model.


🔍 Project Overview

The goal of this project is to build a reliable and interpretable machine learning system capable of predicting cardiovascular disease (CVD) using clinical variables.
The pipeline is designed to be modular, reproducible, and deployment‑ready, following best practices in clinical ML.


🧠 Key Features


📊 Final Model Performance


📁 Repository Structure