Comparative Machine-Learning Approach: Study for Heart Diseases

2022

Closed access Metadata (CSL-JSON)
DOI 10.1109/sist54437.2022.9945705
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 heart is important as the most important organ in the human body. Through the heart, blood circulates in the human body, and through this circulation, oxygen, hormones, various cells and compounds necessary for human life are distributed. When the heart stops working, all functions in the human body fail. In this context, machine learning methods demonstrate a significant ability to make predictions. In recent years, the pace of application of machine learning methods to medicine has been increasing. Given that the scope of application is in demand, we can see that the accuracy of the machine learning method is quite high. In this paper, which we used to predict heart disease, classification algorithms were used, resulting in a high predictive ability. Data consisting of 304 columns was taken as a database. In order to achieve better results through algorithms, the data was standardized according to the result, the data that could not be standardized was trained through the best parameters.