Simple record

dc.rights.licenseAttribution 4.0 International*
dc.contributor.authorAyala Fernández, Unai
dc.contributor.otherPicon, Artzai
dc.contributor.otherIrusta, Unai
dc.contributor.otherÁlvarez-Gila, Aitor
dc.contributor.otherAramendi, Elisabete
dc.contributor.otherAlonso-Atienza, Felipe
dc.contributor.otherFiguera, Carlos
dc.contributor.otherGarrote, Estibaliz
dc.contributor.otherWik, Lars
dc.contributor.otherKramer-Johansen, Jo
dc.contributor.otherEftestøl, Trygve
dc.date.accessioned2020-03-26T15:58:15Z
dc.date.available2020-03-26T15:58:15Z
dc.date.issued2019
dc.identifier.issn1932-6203en
dc.identifier.otherhttps://katalogoa.mondragon.edu/janium-bin/janium_login_opac.pl?find&ficha_no=153458en
dc.identifier.urihttp://hdl.handle.net/20.500.11984/1601
dc.description.abstractEarly defibrillation by an automated external defibrillator (AED) is key for the survival of out-of-hospital cardiac arrest (OHCA) patients. ECG feature extraction and machine learning have been successfully used to detect ventricular fibrillation (VF) in AED shock decision algorithms. Recently, deep learning architectures based on 1D Convolutional Neural Networks (CNN) have been proposed for this task. This study introduces a deep learning architecture based on 1D-CNN layers and a Long Short-Term Memory (LSTM) network for the detection of VF. Two datasets were used, one from public repositories of Holter recordings captured at the onset of the arrhythmia, and a second from OHCA patients obtained minutes after the onset of the arrest. Data was partitioned patient-wise into training (80%) to design the classifiers, and test (20%) to report the results. The proposed architecture was compared to 1D-CNN only deep learners, and to a classical approach based on VF-detection features and a support vector machine (SVM) classifier. The algorithms were evaluated in terms of balanced accuracy (BAC), the unweighted mean of the sensitivity (Se) and specificity (Sp). The BAC, Se, and Sp of the architecture for 4-s ECG segments was 99.3%, 99.7%, and 98.9% for the public data, and 98.0%, 99.2%, and 96.7% for OHCA data. The proposed architecture outperformed all other classifiers by at least 0.3-points in BAC in the public data, and by 2.2-points in the OHCA data. The architecture met the 95% Sp and 90% Se requirements of the American Heart Association in both datasets for segment lengths as short as 3-s. This is, to the best of our knowledge, the most accurate VF detection algorithm to date, especially on OHCA data, and it would enable an accurate shock no shock diagnosis in a very short time.en
dc.language.isoengen
dc.rights© 2019 Picon et al.en
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.titleMixed convolutional and long short-term memory network for the detection of lethal ventricular arrhythmiaen
dc.typeinfo:eu-repo/semantics/articleen
dcterms.accessRightsinfo:eu-repo/semantics/openAccessen
dcterms.sourcePLoS ONEen
dc.description.versioninfo:eu-repo/semantics/publishedVersionen
local.contributor.groupTeoría de la señal y comunicacioneses
local.description.peerreviewedtrueen
local.identifier.doihttps://doi.org/10.1371/journal.pone.0216756en
local.rights.publicationfeeAPC
local.rights.publicationfeeamount1695 USD
local.contributor.otherinstitutionFundación Tecnaliaes
local.contributor.otherinstitutionEuskal Herriko Unibertsitatea (EHUes
local.contributor.otherinstitutionUniversidad Rey Juan Carloses
local.contributor.otherinstitutionBanco Bilbao Vizcaya Argentaria (BBVA)es
local.contributor.otherinstitutionUniversity of Stavangeres
local.contributor.otherinstitutionUniversity of Osloes
local.source.detailsVol. 14. Nº 5. May, 2019eu_ES


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Simple record

Attribution 4.0 International
Except where otherwise noted, this item's license is described as Attribution 4.0 International