Mostra el registre d'ítem simple

dc.contributor.authorRibas Ripoll, Vicent
dc.contributor.authorWojdel, Anna
dc.contributor.authorRamos, Pablo
dc.contributor.authorRomero Merino, Enrique
dc.contributor.authorBrugada Terradellas, Josep
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.date.accessioned2015-06-04T11:30:10Z
dc.date.available2015-06-04T11:30:10Z
dc.date.created2014
dc.date.issued2014
dc.identifier.citationRibas, V. [et al.]. Assessment of electrocardiograms with pretraining and shallow networks. A: Computing in Cardiology. "Computing in Cardiology, volume 41". Cambridge, Massachusetts: Computing in Cardiology, 2014, p. 1061-1064.
dc.identifier.isbn978-1-4799-4347-0
dc.identifier.urihttp://hdl.handle.net/2117/28178
dc.description.abstractObjective: Clinical Decision Support Systems normally resort to annotated signals for the automatic assessment of ECG signals. In this paper we put forward a new method for the assessment of normal/abnormal heart function from raw ECG signals (i.e. signals without annotation) based on shallow neural networks with pretraining. Methodology: this paper resorts to a prospective clinical study that took place at Hospital Cll´inic in Barcelona, Spain. This study took place in 2010-2012 and recruited 1390 patients. For each patient we recorded a 12-lead ECG and diagnosis was conducted by the Cardiology service at the same hospital. Two datasets were produced, the first contained the automatically annotated version of all input signals and the second contained the raw signals obtained from the ECG. Results: The new method was tested through crossvalidation with a cohort of 200 test patients. Performance was compared for both annotated and raw datasets. For the annotated dataset and a shallow network with pretraining we obtained an accuracy of 0.8639, a sensitivity of 0.9560 and specificity of 0.7143. The raw dataset yielded an accuracy of 0.8426, a sensitivity of 0.8977 and a specificity of 0.7785. Conclusion: Shallow networks with pretraining automatically obtain a representation of the input data without resorting to any annotation and thus simplify the process of assessing normality of ECG signals. Despite the fact that sensitivity has decreased, accuracy is not much lower than that obtained with standard methods. Specificity is improved with the new method. These results open up a promising line of research for the automatic assessment of ECG signals.
dc.format.extent4 p.
dc.language.isoeng
dc.publisherComputing in Cardiology
dc.rightsAttribution 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
dc.subject.lcshElectrocardiography
dc.subject.lcshDecision support systems
dc.subject.lcshMedical informatics
dc.titleAssessment of electrocardiograms with pretraining and shallow networks
dc.typeConference report
dc.subject.lemacElectrocardiografia
dc.subject.lemacSistemes d'ajuda a la decisió
dc.subject.lemacMedicina -- Informàtica
dc.contributor.groupUniversitat Politècnica de Catalunya. SOCO - Soft Computing
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://www.cinc.org/archives/2014/pdf/1061.pdf
dc.rights.accessOpen Access
local.identifier.drac15451070
dc.description.versionPostprint (published version)
local.citation.authorRibas, V.; Wojdel, A.Anna Wojdel; Ramos, P.; Romero, E.; Brugada, J.
local.citation.contributorComputing in Cardiology
local.citation.pubplaceCambridge, Massachusetts
local.citation.publicationNameComputing in Cardiology, volume 41
local.citation.startingPage1061
local.citation.endingPage1064


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple