mj351/South-Africa-Heart-Disease

# South Africa Heart Disease Prediction A machine learning project that predicts the risk of coronary heart disease (CHD) using clinical and lifestyle risk factors from the Western Cape region of South Africa. Three classification algorithms are trained and compared to identify the most accurate predictive model. --- ## Project Overview Coronary heart disease (CHD) is one of the leading causes of death worldwide. This project applies supervised machine learning classification techniques to the South African Heart Disease dataset to predict whether a patient is likely to develop CHD based on a set of measurable risk factors. The dataset originates from the Coronary Risk-Factor Study (CORIS) baseline survey carried out in three rural communities of the Western Cape, South Africa (Rousseauw et al., 1983). It has since been widely used as a benchmark dataset in statistical learning literature, including Hastie, Tibshirani & Friedman's *The Elements of Statistical Learning* (2001). --- ## Dataset Description **Source:** Rousseauw et al. (1983), *South African Medical Journal*, 64: 430–436 **Subjects:** 462 males **Class distribution:** 160 CHD-positive cases, 302 controls (roughly 2 controls per case) | Feature | Description | | ----------- | -------------------------------------------------------- | | `sbp` | Systolic blood pressure (mmHg) | | `tobacco` | Cumulative tobacco use (kg, lifetime) | | `ldl` | Low-density lipoprotein (LDL) cholesterol | | `adiposity` | Measure of body fat / adiposity index | | `famhist` | Family history of heart disease (`Present` / `Absent`) | | `typea` | Type-A personality behaviour score | | `obesity` | Body mass index (BMI) | | `alcohol` | Current alcohol consumption | | `age` …