Heart failure & cardiomyopathiesCohort study
Artificial Intelligence-Based Echocardiographic Assessment for Monitoring Disease Progression in Transthyretin Cardiac Amyloidosis
- Retrospective cohort study
- landmark analysis
- multivariable Cox models
Authors' conclusion
A ≥5% decrease of AI-derived LVOT-VTI over 12 months, a simple indicator of SV loss, is independently associated with worse outcome in ATTR-CM.
Study context
- Population
- Consecutive patients with ATTR-CM with baseline and 12 ± 1 month transthoracic echocardiography, 2007–2021334 (44.4%) died
- Participants
- 752 patients
- Exposure
- ≥5% decrease vs <5% decrease
- ≥5% decreasen = 377
- Outcome
- All-cause mortality
- Follow-up
- Median 3.3 years
Main finding
As reported in the abstract
Adjusted hazard ratio (95% CI)P value
≥5% decrease vs <5% decrease
1.41(1.13–1.76)
P = 0.003- Left ventricular outflow tract velocity-time integral (LVOT-VTI) change per 1% decrease · only echocardiographic change independently prognostic
- adjusted HR 0.994; P = 0.025
- Integrated discrimination improvement
- 0.012
- Continuous net reclassification improvement
- 0.21
Observational data: associations, not effects.
Original publication
Artificial Intelligence-Based Echocardiographic Assessment for Monitoring Disease Progression in Transthyretin Cardiac Amyloidosis. Eur J Heart Fail. Published 16 October 2025. doi:10.1002/ejhf.70073
Summarised from the published abstract; every number is checked against it