Diagnosis of Cardiovascular Diseases Using Classification Algorithms

Heart diseases are the most common diseases in the world and will continue to be the number one cause of death for a long time. Each year 17.9 million people die due to cardiovascular diseases (CVDs), an estimated 32% of all deaths worldwide. However, many heart disease factors are preventable or treatable. If these factors are prevented or treated, it is an excellent opportunity to reduce the loss of life due to heart diseases. Nowadays, data science is actively used by people, and the importance of data science is increasing daily. It is vital for humanity that heart diseases and similar medical problems can be predicted using data science. For this reason, early disease detection aims to apply statistical methods in medicine. This research determines the relation between heart diseases and other human body characteristics to early diagnosis of heart diseases. In this research, data mining approaches specifically using different data science algorithms were applied to predict patients' heart diseases, namely Naïve Bayes, Logistic Regression, Multilayer Perceptron, and Random Forest algorithms for classification and diagnosis of cardiovascular diseases prediction. Results showed that the Naïve Bayes algorithm obtained an accuracy of 88.5% and was the best among all other algorithm.