Early cardiac disease detection using neural networks

Hugo D. Calderon-Vilca; Kevin E.Chagua Callupe; Richard J.Inga Aliaga; Jair Barzola Cuba; Flor C. Marino-Cardenas

doi:10.1109/IESTEC46403.2019.00106

Early cardiac disease detection using neural networks

Hugo D. Calderon-Vilca, Kevin E.Chagua Callupe, Richard J.Inga Aliaga, Jair Barzola Cuba, Flor C. Marino-Cardenas

Research output: Contribution to conference › Paper

8 Scopus citations

Abstract

© 2019 IEEE. Heart disease is one of the biggest problems in the world that will continue to be research. We have made an overview of the research related to heart disease. We verify that algorithms have been used for the classification of cardiac diseases: Apriori, decision tree, naive Bayesian. Neural network, SVM, ANN, KN and others. In this research, we have designed three architectures of neural networks to evaluate which of them adapts and predicts better the presence of heart diseases, we have determined that the architecture that best adapts is a neural network Backpropagation with quadratic error 0.01788 with a 99.26% accuracy. In addition, we have designed a web application tool to detect heart disease, this tool has been designed with the steps of software engineering.

Original language	American English
Pages	562-567
Number of pages	6
DOIs	https://doi.org/10.1109/IESTEC46403.2019.00106
State	Published - 1 Oct 2019
Event	Proceedings - 2019 7th International Engineering, Sciences and Technology Conference, IESTEC 2019 - Duration: 1 Oct 2019 → …

Conference

Conference	Proceedings - 2019 7th International Engineering, Sciences and Technology Conference, IESTEC 2019
Period	1/10/19 → …

Access to Document

10.1109/IESTEC46403.2019.00106

Cite this

@conference{fe806180951e436dac44f82c45c9d2bb,

title = "Early cardiac disease detection using neural networks",

abstract = "{\textcopyright} 2019 IEEE. Heart disease is one of the biggest problems in the world that will continue to be research. We have made an overview of the research related to heart disease. We verify that algorithms have been used for the classification of cardiac diseases: Apriori, decision tree, naive Bayesian. Neural network, SVM, ANN, KN and others. In this research, we have designed three architectures of neural networks to evaluate which of them adapts and predicts better the presence of heart diseases, we have determined that the architecture that best adapts is a neural network Backpropagation with quadratic error 0.01788 with a 99.26% accuracy. In addition, we have designed a web application tool to detect heart disease, this tool has been designed with the steps of software engineering.",

author = "Calderon-Vilca, {Hugo D.} and Callupe, {Kevin E.Chagua} and Aliaga, {Richard J.Inga} and Cuba, {Jair Barzola} and Marino-Cardenas, {Flor C.}",

year = "2019",

month = oct,

day = "1",

doi = "10.1109/IESTEC46403.2019.00106",

language = "American English",

pages = "562--567",

note = "Proceedings - 2019 7th International Engineering, Sciences and Technology Conference, IESTEC 2019 ; Conference date: 01-10-2019",

}

TY - CONF

T1 - Early cardiac disease detection using neural networks

AU - Calderon-Vilca, Hugo D.

AU - Callupe, Kevin E.Chagua

AU - Aliaga, Richard J.Inga

AU - Cuba, Jair Barzola

AU - Marino-Cardenas, Flor C.

PY - 2019/10/1

Y1 - 2019/10/1

N2 - © 2019 IEEE. Heart disease is one of the biggest problems in the world that will continue to be research. We have made an overview of the research related to heart disease. We verify that algorithms have been used for the classification of cardiac diseases: Apriori, decision tree, naive Bayesian. Neural network, SVM, ANN, KN and others. In this research, we have designed three architectures of neural networks to evaluate which of them adapts and predicts better the presence of heart diseases, we have determined that the architecture that best adapts is a neural network Backpropagation with quadratic error 0.01788 with a 99.26% accuracy. In addition, we have designed a web application tool to detect heart disease, this tool has been designed with the steps of software engineering.

AB - © 2019 IEEE. Heart disease is one of the biggest problems in the world that will continue to be research. We have made an overview of the research related to heart disease. We verify that algorithms have been used for the classification of cardiac diseases: Apriori, decision tree, naive Bayesian. Neural network, SVM, ANN, KN and others. In this research, we have designed three architectures of neural networks to evaluate which of them adapts and predicts better the presence of heart diseases, we have determined that the architecture that best adapts is a neural network Backpropagation with quadratic error 0.01788 with a 99.26% accuracy. In addition, we have designed a web application tool to detect heart disease, this tool has been designed with the steps of software engineering.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85078169449&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85078169449&origin=inward

U2 - 10.1109/IESTEC46403.2019.00106

DO - 10.1109/IESTEC46403.2019.00106

M3 - Paper

SP - 562

EP - 567

T2 - Proceedings - 2019 7th International Engineering, Sciences and Technology Conference, IESTEC 2019

Y2 - 1 October 2019

ER -

Early cardiac disease detection using neural networks

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this