Cargando…

Supervised Analysis for Phenotype Identification: The Case of Heart Failure Ejection Fraction Class

Artificial Intelligence is creating a paradigm shift in health care, with phenotyping patients through clustering techniques being one of the areas of interest. Objective: To develop a predictive model to classify heart failure (HF) patients according to their left ventricular ejection fraction (LVE...

Descripción completa

Detalles Bibliográficos
Autores principales: Lopez, Cristina, Holgado, Jose Luis, Cortes, Raquel, Sauri, Inma, Fernandez, Antonio, Calderon, Jose Miguel, Nuñez, Julio, Redon, Josep
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8233943/
https://www.ncbi.nlm.nih.gov/pubmed/34205745
http://dx.doi.org/10.3390/bioengineering8060085
_version_ 1783713967811592192
author Lopez, Cristina
Holgado, Jose Luis
Cortes, Raquel
Sauri, Inma
Fernandez, Antonio
Calderon, Jose Miguel
Nuñez, Julio
Redon, Josep
author_facet Lopez, Cristina
Holgado, Jose Luis
Cortes, Raquel
Sauri, Inma
Fernandez, Antonio
Calderon, Jose Miguel
Nuñez, Julio
Redon, Josep
author_sort Lopez, Cristina
collection PubMed
description Artificial Intelligence is creating a paradigm shift in health care, with phenotyping patients through clustering techniques being one of the areas of interest. Objective: To develop a predictive model to classify heart failure (HF) patients according to their left ventricular ejection fraction (LVEF), by using available data from Electronic Health Records (EHR). Subjects and methods: 2854 subjects over 25 years old with a diagnosis of HF and LVEF, measured by echocardiography, were selected to develop an algorithm to predict patients with reduced EF using supervised analysis. The performance of the developed algorithm was tested in heart failure patients from Primary Care. To select the most influentual variables, the LASSO algorithm setting was used, and to tackle the issue of one class exceeding the other one by a large amount, we used the Synthetic Minority Oversampling Technique (SMOTE). Finally, Random Forest (RF) and XGBoost models were constructed. Results: The full XGBoost model obtained the maximum accuracy, a high negative predictive value, and the highest positive predictive value. Gender, age, unstable angina, atrial fibrillation and acute myocardial infarct are the variables that most influence EF value. Applied in the EHR dataset, with a total of 25,594 patients with an ICD-code of HF and no regular follow-up in cardiology clinics, 6170 (21.1%) were identified as pertaining to the reduced EF group. Conclusion: The obtained algorithm was able to identify a number of HF patients with reduced ejection fraction, who could benefit from a protocol with a strong possibility of success. Furthermore, the methodology can be used for studies using data extracted from the Electronic Health Records.
format Online
Article
Text
id pubmed-8233943
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-82339432021-06-27 Supervised Analysis for Phenotype Identification: The Case of Heart Failure Ejection Fraction Class Lopez, Cristina Holgado, Jose Luis Cortes, Raquel Sauri, Inma Fernandez, Antonio Calderon, Jose Miguel Nuñez, Julio Redon, Josep Bioengineering (Basel) Article Artificial Intelligence is creating a paradigm shift in health care, with phenotyping patients through clustering techniques being one of the areas of interest. Objective: To develop a predictive model to classify heart failure (HF) patients according to their left ventricular ejection fraction (LVEF), by using available data from Electronic Health Records (EHR). Subjects and methods: 2854 subjects over 25 years old with a diagnosis of HF and LVEF, measured by echocardiography, were selected to develop an algorithm to predict patients with reduced EF using supervised analysis. The performance of the developed algorithm was tested in heart failure patients from Primary Care. To select the most influentual variables, the LASSO algorithm setting was used, and to tackle the issue of one class exceeding the other one by a large amount, we used the Synthetic Minority Oversampling Technique (SMOTE). Finally, Random Forest (RF) and XGBoost models were constructed. Results: The full XGBoost model obtained the maximum accuracy, a high negative predictive value, and the highest positive predictive value. Gender, age, unstable angina, atrial fibrillation and acute myocardial infarct are the variables that most influence EF value. Applied in the EHR dataset, with a total of 25,594 patients with an ICD-code of HF and no regular follow-up in cardiology clinics, 6170 (21.1%) were identified as pertaining to the reduced EF group. Conclusion: The obtained algorithm was able to identify a number of HF patients with reduced ejection fraction, who could benefit from a protocol with a strong possibility of success. Furthermore, the methodology can be used for studies using data extracted from the Electronic Health Records. MDPI 2021-06-21 /pmc/articles/PMC8233943/ /pubmed/34205745 http://dx.doi.org/10.3390/bioengineering8060085 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Lopez, Cristina
Holgado, Jose Luis
Cortes, Raquel
Sauri, Inma
Fernandez, Antonio
Calderon, Jose Miguel
Nuñez, Julio
Redon, Josep
Supervised Analysis for Phenotype Identification: The Case of Heart Failure Ejection Fraction Class
title Supervised Analysis for Phenotype Identification: The Case of Heart Failure Ejection Fraction Class
title_full Supervised Analysis for Phenotype Identification: The Case of Heart Failure Ejection Fraction Class
title_fullStr Supervised Analysis for Phenotype Identification: The Case of Heart Failure Ejection Fraction Class
title_full_unstemmed Supervised Analysis for Phenotype Identification: The Case of Heart Failure Ejection Fraction Class
title_short Supervised Analysis for Phenotype Identification: The Case of Heart Failure Ejection Fraction Class
title_sort supervised analysis for phenotype identification: the case of heart failure ejection fraction class
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8233943/
https://www.ncbi.nlm.nih.gov/pubmed/34205745
http://dx.doi.org/10.3390/bioengineering8060085
work_keys_str_mv AT lopezcristina supervisedanalysisforphenotypeidentificationthecaseofheartfailureejectionfractionclass
AT holgadojoseluis supervisedanalysisforphenotypeidentificationthecaseofheartfailureejectionfractionclass
AT cortesraquel supervisedanalysisforphenotypeidentificationthecaseofheartfailureejectionfractionclass
AT sauriinma supervisedanalysisforphenotypeidentificationthecaseofheartfailureejectionfractionclass
AT fernandezantonio supervisedanalysisforphenotypeidentificationthecaseofheartfailureejectionfractionclass
AT calderonjosemiguel supervisedanalysisforphenotypeidentificationthecaseofheartfailureejectionfractionclass
AT nunezjulio supervisedanalysisforphenotypeidentificationthecaseofheartfailureejectionfractionclass
AT redonjosep supervisedanalysisforphenotypeidentificationthecaseofheartfailureejectionfractionclass