Machine Learning Approaches to Predict Major Adverse Cardiovascular Events in Atrial Fibrillation

The increasing prevalence of atrial fibrillation (AF) and its association with Major Adverse Cardiovascular Events (MACE) presents challenges in early identification and treatment. Although existing risk factors, biomarkers, genetic variants, and imaging parameters predict MACE, emerging factors may...

Full description

Bibliographic Details
Main Authors: Pedro Moltó-Balado, Silvia Reverté-Villarroya, Victor Alonso-Barberán, Cinta Monclús-Arasa, Maria Teresa Balado-Albiol, Josep Clua-Queralt, Josep-Lluis Clua-Espuny
Format: Article
Language:English
Published: MDPI AG 2024-01-01
Series:Technologies
Subjects:
Online Access:https://www.mdpi.com/2227-7080/12/2/13
_version_ 1827342657311997952
author Pedro Moltó-Balado
Silvia Reverté-Villarroya
Victor Alonso-Barberán
Cinta Monclús-Arasa
Maria Teresa Balado-Albiol
Josep Clua-Queralt
Josep-Lluis Clua-Espuny
author_facet Pedro Moltó-Balado
Silvia Reverté-Villarroya
Victor Alonso-Barberán
Cinta Monclús-Arasa
Maria Teresa Balado-Albiol
Josep Clua-Queralt
Josep-Lluis Clua-Espuny
author_sort Pedro Moltó-Balado
collection DOAJ
description The increasing prevalence of atrial fibrillation (AF) and its association with Major Adverse Cardiovascular Events (MACE) presents challenges in early identification and treatment. Although existing risk factors, biomarkers, genetic variants, and imaging parameters predict MACE, emerging factors may be more decisive. Artificial intelligence and machine learning techniques (ML) offer a promising avenue for more effective AF evolution prediction. Five ML models were developed to obtain predictors of MACE in AF patients. Two-thirds of the data were used for training, employing diverse approaches and optimizing to minimize prediction errors, while the remaining third was reserved for testing and validation. AdaBoost emerged as the top-performing model (accuracy: 0.9999; recall: 1; F1 score: 0.9997). Noteworthy features influencing predictions included the Charlson Comorbidity Index (CCI), diabetes mellitus, cancer, the Wells scale, and CHA<sub>2</sub>DS<sub>2</sub>-VASc, with specific associations identified. Elevated MACE risk was observed, with a CCI score exceeding 2.67 ± 1.31 (<i>p</i> < 0.001), CHA2DS2-VASc score of 4.62 ± 1.02 (<i>p</i> < 0.001), and an intermediate-risk Wells scale classification. Overall, the AdaBoost ML offers an alternative predictive approach to facilitate the early identification of MACE risk in the assessment of patients with AF.
first_indexed 2024-03-07T22:11:40Z
format Article
id doaj.art-042a9db39edc491f9f821acd12e4b172
institution Directory Open Access Journal
issn 2227-7080
language English
last_indexed 2024-03-07T22:11:40Z
publishDate 2024-01-01
publisher MDPI AG
record_format Article
series Technologies
spelling doaj.art-042a9db39edc491f9f821acd12e4b1722024-02-23T15:36:13ZengMDPI AGTechnologies2227-70802024-01-011221310.3390/technologies12020013Machine Learning Approaches to Predict Major Adverse Cardiovascular Events in Atrial FibrillationPedro Moltó-Balado0Silvia Reverté-Villarroya1Victor Alonso-Barberán2Cinta Monclús-Arasa3Maria Teresa Balado-Albiol4Josep Clua-Queralt5Josep-Lluis Clua-Espuny6Primary Health-Care Center Tortosa Oest, Institut Català de la Salut, Primary Care Service (SAP) Terres de l’Ebre, CAP Baix Ebre Avda de Colom, 16-20, 43500 Tortosa, SpainNursing Department, Advanced Nursing Research Group at Rovira I Virgili University, Biomedicine Doctoral Programme Campus Terres de l’Ebre, Av. De Remolins, 13, 43500 Tortosa, SpainInstitut d’Educació Secundària El Caminàs, C/Pintor Soler Blasco, 3, Conselleria d’Educació, 12003 Castellón, SpainPrimary Health-Care Center Tortosa Oest, Institut Català de la Salut, Primary Care Service (SAP) Terres de l’Ebre, CAP Baix Ebre Avda de Colom, 16-20, 43500 Tortosa, SpainPrimary Health-Care Center CS Borriana I, Conselleria de Sanitat, Avinguda Nules, 31, 12530 Borriana, SpainPrimary Health-Care Center EAP Tortosa Est, Institut Català de la Salut, CAP El Temple Plaça Carrilet, s/n, 43500 Tortosa, SpainPrimary Health-Care Center EAP Tortosa Est, Institut Català de la Salut, CAP El Temple Plaça Carrilet, s/n, 43500 Tortosa, SpainThe increasing prevalence of atrial fibrillation (AF) and its association with Major Adverse Cardiovascular Events (MACE) presents challenges in early identification and treatment. Although existing risk factors, biomarkers, genetic variants, and imaging parameters predict MACE, emerging factors may be more decisive. Artificial intelligence and machine learning techniques (ML) offer a promising avenue for more effective AF evolution prediction. Five ML models were developed to obtain predictors of MACE in AF patients. Two-thirds of the data were used for training, employing diverse approaches and optimizing to minimize prediction errors, while the remaining third was reserved for testing and validation. AdaBoost emerged as the top-performing model (accuracy: 0.9999; recall: 1; F1 score: 0.9997). Noteworthy features influencing predictions included the Charlson Comorbidity Index (CCI), diabetes mellitus, cancer, the Wells scale, and CHA<sub>2</sub>DS<sub>2</sub>-VASc, with specific associations identified. Elevated MACE risk was observed, with a CCI score exceeding 2.67 ± 1.31 (<i>p</i> < 0.001), CHA2DS2-VASc score of 4.62 ± 1.02 (<i>p</i> < 0.001), and an intermediate-risk Wells scale classification. Overall, the AdaBoost ML offers an alternative predictive approach to facilitate the early identification of MACE risk in the assessment of patients with AF.https://www.mdpi.com/2227-7080/12/2/13atrial fibrillationmajor adverse cardiovascular events (MACE)machine learningartificial intelligence
spellingShingle Pedro Moltó-Balado
Silvia Reverté-Villarroya
Victor Alonso-Barberán
Cinta Monclús-Arasa
Maria Teresa Balado-Albiol
Josep Clua-Queralt
Josep-Lluis Clua-Espuny
Machine Learning Approaches to Predict Major Adverse Cardiovascular Events in Atrial Fibrillation
Technologies
atrial fibrillation
major adverse cardiovascular events (MACE)
machine learning
artificial intelligence
title Machine Learning Approaches to Predict Major Adverse Cardiovascular Events in Atrial Fibrillation
title_full Machine Learning Approaches to Predict Major Adverse Cardiovascular Events in Atrial Fibrillation
title_fullStr Machine Learning Approaches to Predict Major Adverse Cardiovascular Events in Atrial Fibrillation
title_full_unstemmed Machine Learning Approaches to Predict Major Adverse Cardiovascular Events in Atrial Fibrillation
title_short Machine Learning Approaches to Predict Major Adverse Cardiovascular Events in Atrial Fibrillation
title_sort machine learning approaches to predict major adverse cardiovascular events in atrial fibrillation
topic atrial fibrillation
major adverse cardiovascular events (MACE)
machine learning
artificial intelligence
url https://www.mdpi.com/2227-7080/12/2/13
work_keys_str_mv AT pedromoltobalado machinelearningapproachestopredictmajoradversecardiovasculareventsinatrialfibrillation
AT silviarevertevillarroya machinelearningapproachestopredictmajoradversecardiovasculareventsinatrialfibrillation
AT victoralonsobarberan machinelearningapproachestopredictmajoradversecardiovasculareventsinatrialfibrillation
AT cintamonclusarasa machinelearningapproachestopredictmajoradversecardiovasculareventsinatrialfibrillation
AT mariateresabaladoalbiol machinelearningapproachestopredictmajoradversecardiovasculareventsinatrialfibrillation
AT josepcluaqueralt machinelearningapproachestopredictmajoradversecardiovasculareventsinatrialfibrillation
AT joseplluiscluaespuny machinelearningapproachestopredictmajoradversecardiovasculareventsinatrialfibrillation