000170009 001__ 170009
000170009 005__ 20260316092629.0
000170009 0247_ $$2doi$$a10.1093/europace/euag015
000170009 0248_ $$2sideral$$a148620
000170009 037__ $$aART-2026-148620
000170009 041__ $$aeng
000170009 100__ $$aNaderi, Hafiz
000170009 245__ $$aDeep learning to predict left ventricular hypertrophy from the electrocardiogram
000170009 260__ $$c2026
000170009 5060_ $$aAccess copy available to the general public$$fUnrestricted
000170009 5203_ $$aAims: Left ventricular hypertrophy (LVH) is a strong predictor of cardiovascular disease. We previously compared supervised machine learning techniques to classify cardiac magnetic resonance (CMR)-derived LVH using electrocardiogram (ECG) and clinical variables in 37 534 UK Biobank participants, obtaining an area under the receiving operating curve (AUROC) of 0.85, but with limited specificity and requiring external validation. In this study, we develop a deep learning (DL) model to improve classification with external evaluation in the Study of Health in Pomerania (SHIP). Methods and results: We analysed 12-lead ECGs of 48 835 participants from the UK Biobank imaging study. The dataset was split into a training set (70%), validation set (15%), and test set (15%) for performance evaluation. The model architecture was a fully convolutional network, for which the input was the participants’ median ECG and clinical variables and the predicted indexed left ventricular mass (iLVM) as the output. A subsequent logistic regression model was used to recalibrate iLVM predictions. In UK Biobank, 717 (1.5%) participants had CMR-derived LVH and the AUROC for the DL model was 0.97. The ECG components most predictive of LVH were the QRS complex and ventricular rate. The DL model outperformed our supervised algorithms, previous DL modelling efforts and clinical ECG benchmarks. There was modest generalizability of the DL model to 1423 participants in SHIP (AUROC 0.78), with differences in clinical profile, ECG acquisition, and CMR labelling as important factors. Conclusion: Our findings support the feasibility of scalable DL-based screening tools for the prediction of LVH from the ECG, whilst highlighting the need for model development using larger datasets with greater diversity to ensure generalizability.
000170009 536__ $$9info:eu-repo/grantAgreement/ES/AEI/PID2023-148975OB-I00$$9info:eu-repo/grantAgreement/EC/H2020/825903 /EU/An EU-Canada joint infrastructure for next-generation multi-Study Heart research/euCanSHare$$9This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 825903 -euCanSHare$$9info:eu-repo/grantAgreement/ES/MICINN/RYC2021-031413-I
000170009 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es
000170009 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000170009 700__ $$aKaplan, Thomas
000170009 700__ $$avan Duijvenboden, Stefan
000170009 700__ $$aPujadas, Esmeralda Ruiz
000170009 700__ $$aAung, Nay
000170009 700__ $$aAnwar A Chahal, C
000170009 700__ $$aLekadir, Karim
000170009 700__ $$aChamling, Bishwas
000170009 700__ $$aDörr, Marcus
000170009 700__ $$aMarkus, Marcello R P
000170009 700__ $$aPetersen, Steffen E
000170009 700__ $$0(orcid)0000-0003-4130-5866$$aRamírez, Julia$$uUniversidad de Zaragoza
000170009 700__ $$aMunroe, Patricia B
000170009 7102_ $$15008$$2800$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Teoría Señal y Comunicac.
000170009 773__ $$g28, 2 (2026), [15 pp.]$$pEuropace$$tEuropace$$x1099-5129
000170009 8564_ $$s2354774$$uhttps://zaguan.unizar.es/record/170009/files/texto_completo.pdf$$yVersión publicada
000170009 8564_ $$s2688992$$uhttps://zaguan.unizar.es/record/170009/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000170009 909CO $$ooai:zaguan.unizar.es:170009$$particulos$$pdriver
000170009 951__ $$a2026-03-16-08:16:45
000170009 980__ $$aARTICLE