Heart Disease Prediction Using Tree-based Models

It has become increasingly difficult in recent years to predict heart disease. A person dies from heart disease approximately once a minute in the modern era. Health care uses data science to process enormous amounts of data. In order to avoid risks associated with heart disease prediction and alert patients well in advance, the prediction process needs to be automated. An analysis of heart disease data is conducted in this paper. We propose to use Decision Trees, Random Forests, Bagging Trees, XGboost, and LightGBMs to predict Heart Disease and classify patients' risk levels. Because it is critical to diagnose people with heart disease, it is preferable to use the Recall criteria to find the model that can better diagnose people with heart disease. In the trial results, XGboost has a Recall of ۹۵.۸%, which is higher than other ML algorithms implemented.