Valvular & structural heart disease
Artificial Intelligence-Enabled Echocardiography as a Surrogate for Multimodality Aortic Stenosis Imaging: Post Hoc Analysis of a Clinical Trial
Authors' conclusion
DASSi is associated with functional, structural and biological features of AS severity and predicts disease progression and adverse outcomes.
Study context
- Population
- Participants with mild or moderate aortic stenosis (AS) in the SALTIRE-2 trialanalysed
- Participants
- 134 participants
- Primary endpoint
- Association of baseline DASSi (AI echocardiography biomarker, probability of severe AS 0-1) with cross-sectional AS severity (peak aortic valve velocity, CT aortic valve calcium score, [18F]sodium fluoride uptake on PET-CT)
- Follow-up
- Mean baseline
Methodological detailspost hoc analysis, blinded digital aortic stenosis severity index (DASSi) measurements
- Post hoc analysis
- Blinded DASSi measurements
Primary result
As reported in the abstract
Cross-sectional AS severity per SD increase in DASSi
Peak aortic valve velocity per SD DASSi increase
+0.21 m/s
95% CI 0.12–0.30
Aortic valve calcium score per SD DASSi increase
+284 Agatston units
95% CI 101–467
[18F]sodium fluoride target-to-background ratiomax per SD DASSi increase
+0.17
95% CI 0.04–0.31
Mean baseline DASSi (SD, 0.19)
0.51
Further findings
| Outcome | Adjusted HR (95% CI) | |
|---|---|---|
| Aortic valve replacement · 5.5 [interquartile range, 2.4-7.2] years · 75 events | 1.42 (1.11–1.84) | |
| 0.512Adjusted hazard ratio (log scale) |
Disease progression (peak aortic valve velocity, aortic valve calcium score) · 24 months
- Higher DASSi associated with progression by Doppler and CT
- P interaction for DASSi × time<0.001
Original publication
Artificial Intelligence-Enabled Echocardiography as a Surrogate for Multimodality Aortic Stenosis Imaging: Post Hoc Analysis of a Clinical Trial. Circ Cardiovasc Imaging. Published 31 December 2025. doi:10.
Summarised from the published abstract; every number is checked against it