Heart failure & cardiomyopathiesDiagnostic or prognostic study
Artificial Intelligence Fully Automated Analysis of Handheld Echocardiography in Real-World Patients with Suspected Heart Failure
- Diagnostic accuracy study
- multicentre
- prospective
- observational
Authors' conclusion
Artificial intelligence-automated analysis of handheld echocardiography had good diagnostic accuracy for detecting LVEF ≤40%. AI-automated analysis of LVEF of handheld scans was interchangeable with cart-based expert human analysis.
Study context
- Population
- Real-world patients with suspected heart failure (HF)
- Participants
- 867 patients
- Comparison
- Artificial intelligence (AI) handheld vs Human cart-based
- Outcome
- Diagnostic accuracy of AI-automated analysis of handheld echocardiography to detect LVEF ≤40%
Performance
As reported in the abstract
Detection of LVEF ≤40% (vs human analysis of cart-based scans)
| Test or model | Diagnostic accuracy |
|---|---|
| AI handheld | 0.93 (95% CI 0.90, 0.95) |
Further findings
| Outcome | IEC (95% CI) |
|---|---|
| Interchangeability of AI handheld LVEF with cart-based LVEF by two expert humans · interchangeable | −0.40 (−0.60 to −0.16) |
Scans with an left ventricular ejection fraction (LVEF) produced
- AI, handheld scans
- 61%
- AI, cart-based scans
- 77%
- Human, handheld scans
- 76%
- Human, cart-based scans
- 77%
Original publication
Artificial Intelligence Fully Automated Analysis of Handheld Echocardiography in Real-World Patients with Suspected Heart Failure. Eur J Heart Fail. Published 24 July 2025. doi:10.1002/ejhf.3783
Summarised from the published abstract; every number is checked against it