Cargando…

A Machine Learning Model for the Prognosis of Pulseless Electrical Activity during Out-of-Hospital Cardiac Arrest

Pulseless electrical activity (PEA) is characterized by the disassociation of the mechanical and electrical activity of the heart and appears as the initial rhythm in 20–30% of out-of-hospital cardiac arrest (OHCA) cases. Predicting whether a patient in PEA will convert to return of spontaneous circ...

Descripción completa

Detalles Bibliográficos
Autores principales: Urteaga, Jon, Aramendi, Elisabete, Elola, Andoni, Irusta, Unai, Idris, Ahamed
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8307658/
https://www.ncbi.nlm.nih.gov/pubmed/34209405
http://dx.doi.org/10.3390/e23070847
_version_ 1783728099912843264
author Urteaga, Jon
Aramendi, Elisabete
Elola, Andoni
Irusta, Unai
Idris, Ahamed
author_facet Urteaga, Jon
Aramendi, Elisabete
Elola, Andoni
Irusta, Unai
Idris, Ahamed
author_sort Urteaga, Jon
collection PubMed
description Pulseless electrical activity (PEA) is characterized by the disassociation of the mechanical and electrical activity of the heart and appears as the initial rhythm in 20–30% of out-of-hospital cardiac arrest (OHCA) cases. Predicting whether a patient in PEA will convert to return of spontaneous circulation (ROSC) is important because different therapeutic strategies are needed depending on the type of PEA. The aim of this study was to develop a machine learning model to differentiate PEA with unfavorable (unPEA) and favorable (faPEA) evolution to ROSC. An OHCA dataset of 1921 [Formula: see text] PEA signal segments from defibrillator files was used, 703 faPEA segments from 107 patients with ROSC and 1218 unPEA segments from 153 patients with no ROSC. The solution consisted of a signal-processing stage of the ECG and the thoracic impedance (TI) and the extraction of the TI circulation component (ICC), which is associated with ventricular wall movement. Then, a set of 17 features was obtained from the ECG and ICC signals, and a random forest classifier was used to differentiate faPEA from unPEA. All models were trained and tested using patientwise and stratified 10-fold cross-validation partitions. The best model showed a median (interquartile range) area under the curve (AUC) of [Formula: see text] and a balance accuracy of [Formula: see text] , improving the previously available solutions at more than four points in the AUC and three points in balanced accuracy. It was demonstrated that the evolution of PEA can be predicted using the ECG and TI signals, opening the possibility of targeted PEA treatment in OHCA.
format Online
Article
Text
id pubmed-8307658
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83076582021-07-25 A Machine Learning Model for the Prognosis of Pulseless Electrical Activity during Out-of-Hospital Cardiac Arrest Urteaga, Jon Aramendi, Elisabete Elola, Andoni Irusta, Unai Idris, Ahamed Entropy (Basel) Article Pulseless electrical activity (PEA) is characterized by the disassociation of the mechanical and electrical activity of the heart and appears as the initial rhythm in 20–30% of out-of-hospital cardiac arrest (OHCA) cases. Predicting whether a patient in PEA will convert to return of spontaneous circulation (ROSC) is important because different therapeutic strategies are needed depending on the type of PEA. The aim of this study was to develop a machine learning model to differentiate PEA with unfavorable (unPEA) and favorable (faPEA) evolution to ROSC. An OHCA dataset of 1921 [Formula: see text] PEA signal segments from defibrillator files was used, 703 faPEA segments from 107 patients with ROSC and 1218 unPEA segments from 153 patients with no ROSC. The solution consisted of a signal-processing stage of the ECG and the thoracic impedance (TI) and the extraction of the TI circulation component (ICC), which is associated with ventricular wall movement. Then, a set of 17 features was obtained from the ECG and ICC signals, and a random forest classifier was used to differentiate faPEA from unPEA. All models were trained and tested using patientwise and stratified 10-fold cross-validation partitions. The best model showed a median (interquartile range) area under the curve (AUC) of [Formula: see text] and a balance accuracy of [Formula: see text] , improving the previously available solutions at more than four points in the AUC and three points in balanced accuracy. It was demonstrated that the evolution of PEA can be predicted using the ECG and TI signals, opening the possibility of targeted PEA treatment in OHCA. MDPI 2021-06-30 /pmc/articles/PMC8307658/ /pubmed/34209405 http://dx.doi.org/10.3390/e23070847 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
Urteaga, Jon
Aramendi, Elisabete
Elola, Andoni
Irusta, Unai
Idris, Ahamed
A Machine Learning Model for the Prognosis of Pulseless Electrical Activity during Out-of-Hospital Cardiac Arrest
title A Machine Learning Model for the Prognosis of Pulseless Electrical Activity during Out-of-Hospital Cardiac Arrest
title_full A Machine Learning Model for the Prognosis of Pulseless Electrical Activity during Out-of-Hospital Cardiac Arrest
title_fullStr A Machine Learning Model for the Prognosis of Pulseless Electrical Activity during Out-of-Hospital Cardiac Arrest
title_full_unstemmed A Machine Learning Model for the Prognosis of Pulseless Electrical Activity during Out-of-Hospital Cardiac Arrest
title_short A Machine Learning Model for the Prognosis of Pulseless Electrical Activity during Out-of-Hospital Cardiac Arrest
title_sort machine learning model for the prognosis of pulseless electrical activity during out-of-hospital cardiac arrest
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8307658/
https://www.ncbi.nlm.nih.gov/pubmed/34209405
http://dx.doi.org/10.3390/e23070847
work_keys_str_mv AT urteagajon amachinelearningmodelfortheprognosisofpulselesselectricalactivityduringoutofhospitalcardiacarrest
AT aramendielisabete amachinelearningmodelfortheprognosisofpulselesselectricalactivityduringoutofhospitalcardiacarrest
AT elolaandoni amachinelearningmodelfortheprognosisofpulselesselectricalactivityduringoutofhospitalcardiacarrest
AT irustaunai amachinelearningmodelfortheprognosisofpulselesselectricalactivityduringoutofhospitalcardiacarrest
AT idrisahamed amachinelearningmodelfortheprognosisofpulselesselectricalactivityduringoutofhospitalcardiacarrest
AT urteagajon machinelearningmodelfortheprognosisofpulselesselectricalactivityduringoutofhospitalcardiacarrest
AT aramendielisabete machinelearningmodelfortheprognosisofpulselesselectricalactivityduringoutofhospitalcardiacarrest
AT elolaandoni machinelearningmodelfortheprognosisofpulselesselectricalactivityduringoutofhospitalcardiacarrest
AT irustaunai machinelearningmodelfortheprognosisofpulselesselectricalactivityduringoutofhospitalcardiacarrest
AT idrisahamed machinelearningmodelfortheprognosisofpulselesselectricalactivityduringoutofhospitalcardiacarrest