Analysis of Heart Disease Prediction Using Various Machine Learning Algorithms

Every year due to heart diseases around 12 million deaths have been confirmed by the World Health Organization. Cardiovascular disease is responsible for about one in every 4 deaths in the World, and the risk only rises with age. Even though this disease is very common, it can be reduced using smart predictions and diagnoses based on relevant medical data. This paper focuses on the relevant risk factors that are causing the heart diseases. There are two categories created from these risk factors. The patient’s age, sex, and family history make up the first group. The patient’s lifestyle-related risk factors are included in the second category. These factors include maximum blood pressure, smoking, a high level of cholesterol, and inactivity. We have used algorithms like Logistic Regression, Support Vector Classifier, and Random Forest to predict the risk level of heart diseases and we made a comparative study on these three algorithms.