Classification of Death Related to Heart Failure by Machine Learning Algorithms

Authors : Remzi GÜRFİDAN, Mevlüt ERSOY

Pages : 13-18

View : 36 | Download : 9

Publication Date : 2021-01-15

Article Type : Research Paper

Abstract :The increase in the number of individuals with heart diseases and deaths associated with these diseases tops the list of causes of death. Early detection and treatment can reduce the risk of death of candidates with heart disease and people with heart disease. With the expansion of artificial intelligence technology in the field of health in recent years, artificial intelligence models with prediction and classification capability that will contribute positively to patients and health workers are being developed. In this study, the heart disease mortality status was classified according to the clinical data and life information of the patients included in the heart failure data set. The aim of this study is to evaluate the mortality associated with heart disease based on the clinical data and life information of the patients and to guide patients and doctors to early diagnosis or early treatment methods. Classification processes were performed with different machine learning algorithms and success rates were shown. Different algorithms have been tested to achieve success rates between 73% and 83%. Among the tried algorithms, the most successful classification process is provided by the Support Vector Machine (SVM) algorithm.
Keywords : Machine Learning, Healthcare, Hearth Failure, Support Vector Machine