Heart failure & cardiomyopathies
Predicting decline in left ventricular function after new-onset left bundle branch block
Authors' conclusion
Artificial intelligence-derived ECG markers of LV systolic and diastolic dysfunction independently predicted future LVEF decline in patients with new-onset LBBB.
Study context
- Population
- Patients with newly diagnosed left bundle branch block (LBBB) and preserved left ventricular ejection fraction (LVEF) (≥50%)
- Participants
- 769 patients
- Outcome
- ≥20% LVEF decline on follow-up echocardiography
Main finding
As reported in the abstract
LVEF decline ≥20% · median follow-up 4.9 years (IQR 2.3-8.4)
Patients with LVEF decline ≥20%
242
31.5%
AI-ECG score for low LVEF, HR per 1% probability increase (multivariable)
1.01
P = .005
AI-ECG predicted diastolic dysfunction grade, HR per grade (multivariable)
1.25
P = .005
Observational data: associations, not effects.
Further findings
Model discrimination (C-index)
- Final model
- 0.615
- After adjusting for baseline LVEF
- 0.65
- Landmark analysis of 1-year follow-up
- 0.70
Original publication
Predicting decline in left ventricular function after new-onset left bundle branch block. Heart Rhythm. Published 19 November 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →