000131594 001__ 131594
000131594 005__ 20250829134152.0
000131594 0247_ $$2doi$$a10.22489/CinC.2023.342
000131594 0248_ $$2sideral$$a136865
000131594 037__ $$aART-2023-136865
000131594 041__ $$aeng
000131594 100__ $$0(orcid)0000-0003-4130-5866$$aRamírez, Julia$$uUniversidad de Zaragoza
000131594 245__ $$aA Multi-layer CNN Using the ECG, Age and Sex Predicts Ventricular Arrhythmias in the General Population
000131594 260__ $$c2023
000131594 5060_ $$aAccess copy available to the general public$$fUnrestricted
000131594 5203_ $$aLife-threatening ventricular arrhythmias (LTVA) prediction in individuals without cardiovascular disease remains a major challenge. We tested the performance of a multilayer convolutional neural network (CNN) using ECG signals, age and sex. We split 86,603 individuals from the UK Biobank study into a training (90%) and a test (10%) set. In the training set, we trained a multilayer CNN using 15-second ECGs at rest from lead I, age and sex as inputs. The output was the probability of LTVA within a 12-year follow-up. The CNN model consisted of a four-layer CNN (128, 128, 256 and 256 channels, kernel sizes of 3) and a single attention layer. Age and sex were included as external inputs to the final layer. In the test set (0.9% LTVA events), the CNN's prediction led to a median AUC of 0.601, and a specificity of 0.287 for a sensitivity of 0.750. We set a threshold at the CNN's prediction value maximising the sum of specificity and sensitivity in the training set. Survival analyses showed a hazard ratio (HR) of 1.396(P=0.021) for individuals with a CNN's prediction value > threshold, versus those with a CNN's prediction value < threshold. A multilayer CNN model using 10-second ECG data from lead I, together with information on age and sex, can stratify individuals at risk of LTVA. Our findings support the potential utility of wearables for accessible screening in the general population.
000131594 536__ $$9info:eu-repo/grantAgreement/ES/AEI/PID2021-128972OA-I00$$9info:eu-repo/grantAgreement/ES/MICINN/PID2022-140556OB-I00$$9info:eu-repo/grantAgreement/ES/MICINN/RYC2021-031413-I$$9info:eu-repo/grantAgreement/EUR/MICINN/TED2021-130459B-I00
000131594 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000131594 592__ $$a0.227$$b2023
000131594 593__ $$aComputer Science (miscellaneous)$$c2023
000131594 593__ $$aCardiology and Cardiovascular Medicine$$c2023
000131594 594__ $$a1.1$$b2023
000131594 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000131594 700__ $$0(orcid)0000-0001-5803-4316$$aMiguel, Antonio$$uUniversidad de Zaragoza
000131594 700__ $$avan Duijvenboden, Stefan
000131594 700__ $$aOrini, Michele
000131594 700__ $$aYoung, William J.
000131594 700__ $$aTinker, Andrew
000131594 700__ $$aLambiase, Pier D.
000131594 700__ $$aMunroe, Patricia B.
000131594 700__ $$0(orcid)0000-0002-7503-3339$$aMartínez, Juan Pablo$$uUniversidad de Zaragoza
000131594 7102_ $$15008$$2800$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Teoría Señal y Comunicac.
000131594 773__ $$g50 (2023), [4 pp.]$$pComput. cardiol.$$tComputing in Cardiology$$x2325-8861
000131594 8564_ $$s190471$$uhttps://zaguan.unizar.es/record/131594/files/texto_completo.pdf$$yVersión publicada
000131594 8564_ $$s2640792$$uhttps://zaguan.unizar.es/record/131594/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000131594 909CO $$ooai:zaguan.unizar.es:131594$$particulos$$pdriver
000131594 951__ $$a2025-08-29-13:39:57
000131594 980__ $$aARTICLE