Classification of Heart Failure Using Machine Learning: A Comparative Study

Several machine learning classification algorithms were evaluated using a dataset focused on heart failure. Results obtained from logistic regression, random forest, decision tree, K-nearest neighbors, and multilayer perceptron (MLP) were compared to obtain the best model. The random forest method o...

Full description

Saved in:
Bibliographic Details
Main Authors: Bryan Chulde-Fernández, Denisse Enríquez-Ortega, Cesar Guevara, Paulo Navas, Andrés Tirado-Espín, Paulina Vizcaíno-Imacaña, Fernando Villalba-Meneses, Carolina Cadena-Morejon, Diego Almeida-Galarraga, Patricia Acosta-Vargas
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Life
Subjects:
Online Access:https://www.mdpi.com/2075-1729/15/3/496
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850279759383101440
author Bryan Chulde-Fernández
Denisse Enríquez-Ortega
Cesar Guevara
Paulo Navas
Andrés Tirado-Espín
Paulina Vizcaíno-Imacaña
Fernando Villalba-Meneses
Carolina Cadena-Morejon
Diego Almeida-Galarraga
Patricia Acosta-Vargas
author_facet Bryan Chulde-Fernández
Denisse Enríquez-Ortega
Cesar Guevara
Paulo Navas
Andrés Tirado-Espín
Paulina Vizcaíno-Imacaña
Fernando Villalba-Meneses
Carolina Cadena-Morejon
Diego Almeida-Galarraga
Patricia Acosta-Vargas
author_sort Bryan Chulde-Fernández
collection DOAJ
description Several machine learning classification algorithms were evaluated using a dataset focused on heart failure. Results obtained from logistic regression, random forest, decision tree, K-nearest neighbors, and multilayer perceptron (MLP) were compared to obtain the best model. The random forest method obtained specificity = 0.93, AUC = 0.97, and Matthews correlation coefficient (MCC) = 0.83. The accuracy was high; therefore, it was considered the best model. On the other hand, K-nearest neighbors and MLP (multi-layer perceptron) showed lower accuracy rates. These results confirm the effectiveness of the random forest method in identifying heart failure cases. This study underlines that the number of features, feature selection and quality, model type, and hyperparameter fit are also critical in these studies, as well as the importance of using machine learning techniques.
format Article
id doaj-art-2fb018b43bb3471a8430799863acf9d3
institution OA Journals
issn 2075-1729
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Life
spelling doaj-art-2fb018b43bb3471a8430799863acf9d32025-08-20T01:49:00ZengMDPI AGLife2075-17292025-03-0115349610.3390/life15030496Classification of Heart Failure Using Machine Learning: A Comparative StudyBryan Chulde-Fernández0Denisse Enríquez-Ortega1Cesar Guevara2Paulo Navas3Andrés Tirado-Espín4Paulina Vizcaíno-Imacaña5Fernando Villalba-Meneses6Carolina Cadena-Morejon7Diego Almeida-Galarraga8Patricia Acosta-Vargas9School of Biological Sciences and Engineering, Yachay Tech University, Hacienda San José s/n, San Miguel de Urcuquí 100119, EcuadorSchool of Biological Sciences and Engineering, Yachay Tech University, Hacienda San José s/n, San Miguel de Urcuquí 100119, EcuadorQuantitative Methods Department, CUNEF University, 28040 Madrid, SpainSchool of Biological Sciences and Engineering, Yachay Tech University, Hacienda San José s/n, San Miguel de Urcuquí 100119, EcuadorSchool of Mathematical and Computational Sciences, Universidad Yachay Tech, San Miguel de Urcuquí 100119, EcuadorFaculty of Technical Sciences, School of Computer Science, UIDE-International University of Ecuador, Quito 170501, EcuadorSchool of Biological Sciences and Engineering, Yachay Tech University, Hacienda San José s/n, San Miguel de Urcuquí 100119, EcuadorSchool of Mathematical and Computational Sciences, Universidad Yachay Tech, San Miguel de Urcuquí 100119, EcuadorSchool of Biological Sciences and Engineering, Yachay Tech University, Hacienda San José s/n, San Miguel de Urcuquí 100119, EcuadorIntelligent and Interactive Systems Laboratory, Universidad de Las Américas, Quito 170125, EcuadorSeveral machine learning classification algorithms were evaluated using a dataset focused on heart failure. Results obtained from logistic regression, random forest, decision tree, K-nearest neighbors, and multilayer perceptron (MLP) were compared to obtain the best model. The random forest method obtained specificity = 0.93, AUC = 0.97, and Matthews correlation coefficient (MCC) = 0.83. The accuracy was high; therefore, it was considered the best model. On the other hand, K-nearest neighbors and MLP (multi-layer perceptron) showed lower accuracy rates. These results confirm the effectiveness of the random forest method in identifying heart failure cases. This study underlines that the number of features, feature selection and quality, model type, and hyperparameter fit are also critical in these studies, as well as the importance of using machine learning techniques.https://www.mdpi.com/2075-1729/15/3/496heart failuremachine learningclassificationfeature extractiondiagnosis
spellingShingle Bryan Chulde-Fernández
Denisse Enríquez-Ortega
Cesar Guevara
Paulo Navas
Andrés Tirado-Espín
Paulina Vizcaíno-Imacaña
Fernando Villalba-Meneses
Carolina Cadena-Morejon
Diego Almeida-Galarraga
Patricia Acosta-Vargas
Classification of Heart Failure Using Machine Learning: A Comparative Study
Life
heart failure
machine learning
classification
feature extraction
diagnosis
title Classification of Heart Failure Using Machine Learning: A Comparative Study
title_full Classification of Heart Failure Using Machine Learning: A Comparative Study
title_fullStr Classification of Heart Failure Using Machine Learning: A Comparative Study
title_full_unstemmed Classification of Heart Failure Using Machine Learning: A Comparative Study
title_short Classification of Heart Failure Using Machine Learning: A Comparative Study
title_sort classification of heart failure using machine learning a comparative study
topic heart failure
machine learning
classification
feature extraction
diagnosis
url https://www.mdpi.com/2075-1729/15/3/496
work_keys_str_mv AT bryanchuldefernandez classificationofheartfailureusingmachinelearningacomparativestudy
AT denisseenriquezortega classificationofheartfailureusingmachinelearningacomparativestudy
AT cesarguevara classificationofheartfailureusingmachinelearningacomparativestudy
AT paulonavas classificationofheartfailureusingmachinelearningacomparativestudy
AT andrestiradoespin classificationofheartfailureusingmachinelearningacomparativestudy
AT paulinavizcainoimacana classificationofheartfailureusingmachinelearningacomparativestudy
AT fernandovillalbameneses classificationofheartfailureusingmachinelearningacomparativestudy
AT carolinacadenamorejon classificationofheartfailureusingmachinelearningacomparativestudy
AT diegoalmeidagalarraga classificationofheartfailureusingmachinelearningacomparativestudy
AT patriciaacostavargas classificationofheartfailureusingmachinelearningacomparativestudy