Arrhythmias & electrophysiology
Integrating AI-ECG and point-of-care cardiac ultrasound for screening structural heart disease: A proof-of-concept study
Authors' conclusion
The integration of AI-ECG and POCCUS holds promise as a potentially effective screening method for SHD, facilitating improved patient selection for formal echocardiography.
Study context
- Population
- Outpatients undergoing ECG at the Mayo Clinic ECG laboratory, November 2023–February 2024286 with formal echocardiography
- Participants
- 486 outpatients
- Comparison
- AI-ECG + point-of-care cardiac-ultrasonography (POCCUS) vs AI-ECG alone for structural heart disease (SHD) screening
- Outcome
- Detection of any SHD (LV systolic dysfunction [EF<50%], AS, increased LV wall thickness suggestive of cardiac amyloidosis or hypertrophic cardiomyopathy)
Methodological detailsproof-of-concept, pragmatic, novice operators, expert review, operators blinded
- Proof-of-concept
- Pragmatic
- Novice operators, expert review
- Operators blinded
Performance
As reported in the abstract
Detection of any SHD
| Test or model | PPV | NPV |
|---|---|---|
| AI-ECG | 32% | 94% |
AI-ECG
PPV32%
NPV94%
- Adding POCCUS: overall PPV
- 64%
- Adding POCCUS: NPV
- 93%
- Adding POCCUS: diagnostic accuracy increased from 67% to
- 88%
Further findings
- False positives of AI-ECG + POCCUS with less-than-moderate SHD — AI-ECG + POCCUS
- 89.5%
- Number-needed-to-screen to identify 1 patient requiring formal echocardiography (entire cohort) — AI-ECG + POCCUS
- 8
- False positives of AI-ECG + POCCUS with less-than-moderate SHD: 17/19 false positives
Original publication
Integrating AI-ECG and point-of-care cardiac ultrasound for screening structural heart disease: A proof-of-concept study. Am Heart J. Published 31 December 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →