Arrhythmias & electrophysiologyDiagnostic or prognostic study
Efficient feature fusion network (EFFNet): Efficient feature fusion network for left ventricular hypertrophy identification based on 12-lead electrocardiogram signals
- development and validation of a deep learning model
- 5-fold cross-validation
- external cohort
Authors' conclusion
EFFNet significantly improves ECG-based LVH detection and introduces a novel deep learning framework for LVH risk prediction, advancing intelligent ECG-based screening and early identification of LVH.
Study context
- Population
- Individuals with 12-lead electrocardiogram (ECG) signals in the UK Biobank data set and the Qinghai data setUK Biobank data set 38,289 · Qinghai data set 142,777
- Comparison
- EFFNet left ventricular hypertrophy (LVH) classification against cardiovascular magnetic resonance measurement (UK Biobank) and echocardiography (Qinghai) as the reference standard
Further findings
| Outcome | EFFNet | conventional ECG-based diagnostic methods | comparative deep learning methods |
|---|---|---|---|
| Area under the receiver operating characteristic curve, cross-validation on UK Biobank · on average | area under the receiver operating characteristic curve 0.933 | Not reported in the abstract | Not reported in the abstract |
| Area under the receiver operating characteristic curve, external Qinghai validation set | area under the receiver operating characteristic curve 0.654 | Not reported in the abstract | Not reported in the abstract |
Area under the receiver operating characteristic curve, cross-validation on UK Biobank
- outperformed conventional ECG-based diagnostic methods and comparative deep learning methods
Association of EFFNet-predicted LVH with cardiovascular rhythm abnormalities
- EFFNet-predicted LVH was associated with atrial fibrillation, ventricular premature beats, and atrial premature beats
Original publication
EFFNet: Efficient feature fusion network for left ventricular hypertrophy identification based on 12-lead electrocardiogram signals. Heart Rhythm. Published 4 March 2026. doi:10.1016/j.hrthm.2026.02.046
Summarised from the published abstract; every number is checked against it