Heart failure & cardiomyopathies
Artificial Intelligence for Detection of Prognostically Significant Left Ventricular Dysfunction From Echocardiography
Authors' conclusion
A new AI-LVD algorithm using only echocardiographic measurements can reliably identify prognostically important LV dysfunction, including in preserved EF, even when key reporting parameters are missing. The AI-LVD can be used in real-time during routine echocardiography reporting.
Study context
- Population
- Cases from the National Echo Database of Australia with no mitral valve intervention or pacemakertest cohort, 41,796 men (51.3%) and 39,713 women · imputation cohort 126,136 · training cohort 254,735 · test cohort 81,509
- Participants
- 81,509 cases
- Comparison
- Highest vs lowest decile group
- Outcome
- Actual 5-year mortality across AI-LVD deciles
- Follow-up
- 5-year
Main finding
As reported in the abstract
Men, lowest to highest decile
5.7% to 66.3%
Women, lowest to highest decile
2.3% to 64.2%
Further findings
| Outcome | Adjusted hazard (95% CI) |
|---|---|
| All-cause mortality in preserved EF, adjusted for age, year of echo, and missing echo parameters · 1,541 (812-2,682) days follow-upHighest decile vs lowest decile · men | 4.93-fold (4.35–5.59) |
| All-cause mortality in preserved EF, adjusted for age, year of echo, and missing echo parameters · 1,541 (812-2,682) days follow-upHighest decile vs lowest decile · women | 7.11-fold (5.85–8.64) |
Ejection fraction (EF) and filling pressure status in test cohort
- Reduced EF
- 4,490 (5.5%)
- Mildly reduced EF
- 3,734 (4.6%)
- Preserved EF
- 59,297 (72.7%)
- No recorded EF
- 13,988 (17.2%)
- "indeterminate" filling pressures
- 39,940 (45.2%)
Original publication
Artificial Intelligence for Detection of Prognostically Significant Left Ventricular Dysfunction From Echocardiography. JACC Adv. Published 23 June 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →