Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model

[EN]Background: The integrated approach to electrical cardioversion (EC) in atrial fibrillation (AF) is complex; candidates can resolve spontaneously while waiting for EC, and post-cardioversion recurrence is high. Thus, it is especially interesting to avoid the programming of EC in patients who wou...

ver descrição completa

Detalhes bibliográficos
Autores: Núñez García, Jean Carlos, Sánchez-Puente, Antonio, Sampedro-Gómez, Jesús, Vicente-Palacios, Víctor, Jiménez-Navarro, Manuel, Oterino-Manzanas, Armando, Jiménez Candil, Francisco Javier, Dorado-Díaz, Pedro Ignacio, Sánchez Fernández, Pedro Luis
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Recursos:Universidad de Salamanca (USAL)
Repositorio:GREDOS. Repositorio Institucional de la Universidad de Salamanca
OAI Identifier:oai:gredos.usal.es:10366/161183
Acesso em linha:http://hdl.handle.net/10366/161183
Access Level:acceso abierto
Palavra-chave:Machine-learning
Electrical cardioversion
Atrial fibrillation
Rhythm control
Pharmaco- logic cardioversion
id ES_53eff016b6f7aeeda311cc332aefd64f
oai_identifier_str oai:gredos.usal.es:10366/161183
network_acronym_str ES
network_name_str España
repository_id_str
spelling Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic modelNúñez García, Jean CarlosSánchez-Puente, AntonioSampedro-Gómez, JesúsVicente-Palacios, VíctorJiménez-Navarro, ManuelOterino-Manzanas, ArmandoJiménez Candil, Francisco JavierDorado-Díaz, Pedro IgnacioSánchez Fernández, Pedro LuisMachine-learningElectrical cardioversionAtrial fibrillationRhythm controlPharmaco- logic cardioversion[EN]Background: The integrated approach to electrical cardioversion (EC) in atrial fibrillation (AF) is complex; candidates can resolve spontaneously while waiting for EC, and post-cardioversion recurrence is high. Thus, it is especially interesting to avoid the programming of EC in patients who would restore sinus rhythm (SR) spontaneously or present early recurrence. We have analyzed the whole elective EC of the AF process using machine-learning (ML) in order to enable a more realistic and detailed simulation of the patient flow for decision making purposes. Methods: The dataset consisted of electronic health records (EHRs) from 429 consecutive AF patients referred for EC. For analysis of the patient outcome, we considered five pathways according to restoring and maintaining SR: (i) spontaneous SR restoration, (ii) pharmacologic-cardioversion, (iii) direct-current cardioversion, (iv) 6-month AF recurrence, and (v) 6-month rhythm control. We applied ML classifiers for predicting outcomes at each pathway and compared them with the CHA2DS2-VASc and HATCH scores. Results: With the exception of pathway (iii), all ML models achieved improvements in comparison with CHA2DS2-VASc or HATCH scores (p < 0.01). Compared to the most competitive score, the area under the ROC curve (AUC-ROC) was: 0.80 vs. 0.66 for predicting (i); 0.71 vs. 0.55 for (ii); 0.64 vs. 0.52 for (iv); and 0.66 vs. 0.51 for (v). For a threshold considered optimal, the empirical net reclassification index was: +7.8%, +47.2%, +28.2%, and +34.3% in favor of our ML models for predicting outcomes for pathways (i), (ii), (iv), and (v), respectively. As an example tool of generalizability of ML models, we deployed our algorithms in an open-source calculator, where the model would personalize predictions. Conclusions: An ML model improves the accuracy of restoring and maintaining SR predictions over current discriminators. The proposed approach enables a detailed simulation of the patient flow through personalized predictions.MDPI202420242022info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://hdl.handle.net/10366/161183reponame:GREDOS. Repositorio Institucional de la Universidad de Salamancainstname:Universidad de Salamanca (USAL)InglésCC0 1.0 Universalhttp://creativecommons.org/publicdomain/zero/1.0/info:eu-repo/semantics/openAccessoai:gredos.usal.es:10366/1611832026-06-07T06:28:51Z
dc.title.none.fl_str_mv Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model
title Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model
spellingShingle Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model
Núñez García, Jean Carlos
Machine-learning
Electrical cardioversion
Atrial fibrillation
Rhythm control
Pharmaco- logic cardioversion
title_short Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model
title_full Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model
title_fullStr Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model
title_full_unstemmed Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model
title_sort Outcome analysis in elective electrical cardioversion of atrial fibrillation patients: development and validation of a machine learning prognostic model
dc.creator.none.fl_str_mv Núñez García, Jean Carlos
Sánchez-Puente, Antonio
Sampedro-Gómez, Jesús
Vicente-Palacios, Víctor
Jiménez-Navarro, Manuel
Oterino-Manzanas, Armando
Jiménez Candil, Francisco Javier
Dorado-Díaz, Pedro Ignacio
Sánchez Fernández, Pedro Luis
author Núñez García, Jean Carlos
author_facet Núñez García, Jean Carlos
Sánchez-Puente, Antonio
Sampedro-Gómez, Jesús
Vicente-Palacios, Víctor
Jiménez-Navarro, Manuel
Oterino-Manzanas, Armando
Jiménez Candil, Francisco Javier
Dorado-Díaz, Pedro Ignacio
Sánchez Fernández, Pedro Luis
author_role author
author2 Sánchez-Puente, Antonio
Sampedro-Gómez, Jesús
Vicente-Palacios, Víctor
Jiménez-Navarro, Manuel
Oterino-Manzanas, Armando
Jiménez Candil, Francisco Javier
Dorado-Díaz, Pedro Ignacio
Sánchez Fernández, Pedro Luis
author2_role author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Machine-learning
Electrical cardioversion
Atrial fibrillation
Rhythm control
Pharmaco- logic cardioversion
topic Machine-learning
Electrical cardioversion
Atrial fibrillation
Rhythm control
Pharmaco- logic cardioversion
description [EN]Background: The integrated approach to electrical cardioversion (EC) in atrial fibrillation (AF) is complex; candidates can resolve spontaneously while waiting for EC, and post-cardioversion recurrence is high. Thus, it is especially interesting to avoid the programming of EC in patients who would restore sinus rhythm (SR) spontaneously or present early recurrence. We have analyzed the whole elective EC of the AF process using machine-learning (ML) in order to enable a more realistic and detailed simulation of the patient flow for decision making purposes. Methods: The dataset consisted of electronic health records (EHRs) from 429 consecutive AF patients referred for EC. For analysis of the patient outcome, we considered five pathways according to restoring and maintaining SR: (i) spontaneous SR restoration, (ii) pharmacologic-cardioversion, (iii) direct-current cardioversion, (iv) 6-month AF recurrence, and (v) 6-month rhythm control. We applied ML classifiers for predicting outcomes at each pathway and compared them with the CHA2DS2-VASc and HATCH scores. Results: With the exception of pathway (iii), all ML models achieved improvements in comparison with CHA2DS2-VASc or HATCH scores (p < 0.01). Compared to the most competitive score, the area under the ROC curve (AUC-ROC) was: 0.80 vs. 0.66 for predicting (i); 0.71 vs. 0.55 for (ii); 0.64 vs. 0.52 for (iv); and 0.66 vs. 0.51 for (v). For a threshold considered optimal, the empirical net reclassification index was: +7.8%, +47.2%, +28.2%, and +34.3% in favor of our ML models for predicting outcomes for pathways (i), (ii), (iv), and (v), respectively. As an example tool of generalizability of ML models, we deployed our algorithms in an open-source calculator, where the model would personalize predictions. Conclusions: An ML model improves the accuracy of restoring and maintaining SR predictions over current discriminators. The proposed approach enables a detailed simulation of the patient flow through personalized predictions.
publishDate 2022
dc.date.none.fl_str_mv 2022
2024
2024
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10366/161183
url http://hdl.handle.net/10366/161183
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv CC0 1.0 Universal
http://creativecommons.org/publicdomain/zero/1.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv CC0 1.0 Universal
http://creativecommons.org/publicdomain/zero/1.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:GREDOS. Repositorio Institucional de la Universidad de Salamanca
instname:Universidad de Salamanca (USAL)
instname_str Universidad de Salamanca (USAL)
reponame_str GREDOS. Repositorio Institucional de la Universidad de Salamanca
collection GREDOS. Repositorio Institucional de la Universidad de Salamanca
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408150867673088
score 15.81155

Registos relacionados