PROCESSING OF ISCHEMIC HEART DISEASE DATA USING ENSEMBLE CLASSIFICATION METHODS OF MACHINE LEARNING

2023

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.26577/jpcsit.2023.v1.i2.06
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The WHO 2019 statistics provide evidence that cardiovascular diseases are among the prevailing causes of death globally [1]. In this study, a combined dataset of coronary artery disease (CAD), also known as ischemic heart disease, was used as the dataset for analysis. To influence the outcome of the occurrence of cardiovascular diseases, it is important to find significant features that contribute to the presence of this disease. This article demonstrated that important features can be obtained through classification and their visualization in Tableau. Three classification models were built, and important features were identified for each model. Then, the top 10 important features were selected from each model, and through comparison, the 5 most important features were identified that may influence the disease outcome. The classification models achieved the following f1-score results: LGBM (93.2%), XGB (92.0%), and RF (89.1%).