Heart failure & cardiomyopathies
Noninvasive assessment of left ventricular end-diastolic pressure using machine learning–derived phasic left atrial strain
Authors' conclusion
LASi allows the detection of elevated LVEDP using invasive measurements as a reference, at least as accurately as peak LAS and current diastolic function guideline algorithm, with the advantage of no indeterminate classifications in patients with measurable LAS.
Study context
- Population
- Patients undergoing left heart catheterization and TTE within 24 h; reference standard invasive left ventricular end-diastolic pressure (LVEDP)194 in validation cohort
- Participants
- 294 patients
- Comparison
- LAS index (LASi) vs peak left atrial strain (LAS) vs ASE/EACVI algorithm for detecting elevated LVEDP
- Outcome
- Accuracy for detecting LVEDP ≥ 15 mmHg against invasive filling pressures
Methodological detailsretrospective, machine learning-derived parameter, derivation (100) and validation (194) cohorts
- Retrospective
- Machine learning-derived parameter
- Derivation (100) and validation (194) cohorts
Performance
As reported in the abstract
Overall accuracy (validation cohort, excluding 37 ASE/EACVI-indeterminate)
| Test or model | Accuracy |
|---|---|
| LASi | 79% |
| Peak LAS | 75% |
| ASE/EACVI | 76% |
Accuracy
LASi79%
Peak LAS75%
ASE/EACVI76%
Further findings
| Outcome | LASi | Peak LAS |
|---|---|---|
| Accuracy of LASi with indeterminates matched to ASE/EACVI (n = 37)LASi indeterminates defined by near-zero LASi values | ||
| Accuracy | 87% | — not stated in the abstract |
| Accuracy in ASE/EACVI-indeterminate diastolic function (subgroup, n = 37) | ||
| Accuracy | 81% | 76% |
— not stated in the abstract
Original publication
Noninvasive assessment of left ventricular end-diastolic pressure using machine learning–derived phasic left atrial strain. Eur Heart J Cardiovasc Imaging. Published 14 September 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →