Arrhythmias & electrophysiology
Efficient feature fusion network (EFFNet): Efficient feature fusion network for left ventricular hypertrophy identification based on 12-lead electrocardiogram signals
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
- Participants with 12-lead electrocardiogram (ECG) signals in the UK Biobank data set and an external cohort, the Qinghai data setUK Biobank data set (cardiovascular magnetic resonance reference standard) 38,289 · Qinghai data set (echocardiography standard) 142,777
- Index test or model
- EFFNet based on 12-lead ECG signals vs cardiovascular magnetic resonance measurement (UK Biobank) or echocardiography (Qinghai) as the reference standard
- Target condition
- Left ventricular hypertrophy (LVH)
Methodological details5-fold cross-validation with external validation, external cohort
- 5-fold cross-validation with external validation
- External cohort
Performance
As reported in the abstract
| Test or model | AUROC |
|---|---|
| UK Biobank data set (cross-validation, average) | 0.933 |
| External Qinghai validation set | 0.654 |
AUROC
UK Biobank data set (cross-validation, average)0.933
External Qinghai validation set0.654
Further findings
Association of EFFNet-predicted left ventricular hypertrophy (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.
Composed by AI from the published abstract and checked against it. How Briefs are made →