Comparison of Multi-class Classification Algorithms on Early Diagnosis of Heart Diseases

Creative Commons License

Akkaya B. , Çolakoğlu N.

y-BIS Conference 2019: Recent Advances in Data Science and Business Analytics, İstanbul, Turkey, 25 - 28 September 2019, pp.162-172

  • Publication Type: Conference Paper / Full Text
  • City: İstanbul
  • Country: Turkey
  • Page Numbers: pp.162-172


In recent years, one of the most common problems in estimation and classification problems has been multi-class classification problems, leading to that several machine learning algorithms have been used to solve such problems.

Today, heart diseases are the cause of the most deaths in the world. Since the early diagnosis of heart diseases plays an important role for the survival of the individual, this study focuses on classification algorithms which are capable of to do multi-class classification like Logistic Regression, Gaussian Naïve Bayes, k-Nearest Neighbors, Support Vector Machines, Multilayer Perceptron, CART, Random Forest, Gradient Boosting Machine, Extreme Gradient Boosting. Those algorithms have been applied to a dataset containing 2126 CTG (Cardiotocogram) reports which are divided into three classes as "Normal", "Suspect" and "Pathological". The classification success of these multi-class classification algorithms has been compared.