Classification of Cardiovascular Disease Based on Lifestyle Using Random Forest and Logistic Regression Methods

Abstract

Cardiovascular disease is a non-communicable disease caused by a disturbance in the function of the heart or blood vessels. This study aims to classify cardiovascular disease based on lifestyle using the Random Forest and Logistic Regression methods. In the classification process with the Random Forest and Logistic Regression machine learning methods, a combination of parameters from each machine learning method will be tested to see which parameter combination is the best for processing and classifying cardiovascular disease datasets. The dataset used in this research is obtained from Kaggle called Cardiovascular Disease. The dataset was processed through several pre-processing stages, namely missing value imputation, outlier detection, and extreme data checking. After going through the pre-processing process, the amount of data that entered the classification process was 62478 rows of data with 13 attributes or columns, namely age, height, weight, gender, systolic blood pressure, diastolic blood pressure, cholesterol, glucose, smoking, alcohol intake, physical activity, and cardiovascular disease. Dividing the dataset into different percentage distributions of training data and testing data was also tested to see the difference in classification performance of the two methods. The division of training data was 90% and testing data is 10%. The results obtained from this study were the Logistic Regression method had better accuracy results of 73.07% compared to Random Forest with an accuracy result of 71.87%.