Key result
A deep learning model integrating 12-lead ECG and clinical data predicted CMR-derived left ventricular hypertrophy with an AUROC of 0.97, outperforming supervised models and conventional ECG criteria.
Why the study?
Does a deep learning model utilizing 12-lead ECG and clinical variables improve the detection of CMR-derived left ventricular hypertrophy compared to conventional ECG criteria and supervised machine learning methods?
Cross-Sectional (n=50,258)
Yes
Does a deep learning model utilizing 12-lead ECG and clinical variables improve the detection of CMR-derived left ventricular hypertrophy compared to conventional ECG criteria and supervised machine learning methods?
A fully convolutional deep learning model can accurately predict CMR-derived left ventricular hypertrophy from 12-lead ECGs and clinical variables, greatly outperforming conventional clinical criteria, though domain shift remains a challenge for external generalizability.
AIMS: 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.
No takes yet. Share an insight, caveat, or question.
Naderi et al. (2026) conducted a cross-sectional in Left ventricular hypertrophy (LVH) (n=50,258). Deep learning model (FCN LVM + LR) integrating 12-lead ECG and clinical data vs. Supervised machine learning (SVM) and conventional ECG criteria (Sokolow-Lyon, Cornell) was evaluated on Prediction of CMR-derived left ventricular hypertrophy (AUROC) (AUROC 0.97, 95% CI 0.95-0.99, p=<0.001). A deep learning model integrating 12-lead ECG and clinical data predicted CMR-derived left ventricular hypertrophy with an AUROC of 0.97, outperforming supervised models and conventional ECG criteria.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: