Heart Diagnosis Using Deep Neural Network

Abstract

Worldwide, heart disease is the leading cause of mortality. By providing proper therapy, early identification of heart disease can lower the likelihood of the illness advancing to a more severe level. It is possible to diagnose cardiac disease using decision support systems that are based on machine learning; these systems work by analyzing the clinical signs of a patient. The purpose of this study is to investigate several machine learning and deep learning methodologies that are used in the creation of a system for the diagnosis of heart diseases, with a particular focus on coronary artery disease. Feature selection is an essential phase in model development since reducing the amount of features reduces system complexity and improves performance. By using the wrapper method as correlation feature selection method for selecting feature. After it we applied three machine learning algorithm to optimize our dataset. In this paper we proposed a deep neural network Deep Neural Network (Region-CNN) that gives good result in comparison to the other machine learning algorithms.

Ähnliche Arbeiten