Support Vector Machine for Cardiac Catheterization

Disorders of the heart and blood vessels are referred to as cardiovascular disease (CVD), which can lead to a heart attack, chest pain (angina), or stroke. CVDs are the main reasons for morbidity and mortality worldwide. Cardiac catheterization is a tool for both diagnosis and therapy of CVDs. Machine learning can be used in the modeling of cardiac catheterization for binary classification. This work investigates the application of linear and non-linear support vector machines for classifying patients who need to be monitored. Using a dataset obtained from the Benghazi Heart Disease Center, involving about 814 patients, we apply principal component analysis to display the dataset in a 3D space, providing insight into the dataset. The aim of the research is to construct a binary classifier to predict whether a patient is required to be followed by a doctor or not after a catheterization procedure. We find that the linear support vector machine identifies crucial patients with an accuracy of 90.3%, with slight effects on recall.