Valvular & structural heart disease
A Multimodal Video-Based Artificial Intelligence (AI) Biomarker for Aortic Stenosis Development and Progression
Authors' conclusion
In this cohort study of patients without severe AS undergoing echocardiography or CMR imaging, a new AI-based video biomarker was independently associated with AS development and progression
Study context
- Population
- Patients without severe aortic stenosis (AS) undergoing echocardiography (Yale New Haven Health System (YNHHS) 2015–2021; Cedars-Sinai Medical Center (CSMC) 2018–2019) or cardiac magnetic resonance (CMR) (UK Biobank)echocardiographic study
- Participants
- 12,599 patients
- Exposure
- Higher vs lower baseline DASSi
- Outcome
- Annualized change in peak aortic valve velocity (AV-Vmax) and late (>6 months) aortic valve replacement (AVR)
Methodological detailsmulticohort (YNHHS, CSMC, UK Biobank)
- Multicohort (YNHHS, CSMC, UK Biobank)
Main finding
As reported in the abstract
DASSi ≥0.2 vs DASSi <0.2Adjusted hazard ratio (95% CI)
Late AVR, YNHHS (715 events)
4.97(2.71–5.82)
Late AVR, CSMC (56 events)
4.04(0.92–17.70)
M/s per year
- AV-Vmax progression per 0.1 DASSi increment, YNHHS (5483 participants)
- 0.033 (95% CI, 0.028-0.038)
- AV-Vmax progression per 0.1 DASSi increment, CSMC (1292 participants)
- 0.082 (95% CI, 0.053-0.111)
Observational data: associations, not effects.
Further findings
| Outcome | Adjusted HR (95% CI) | |
|---|---|---|
| AVR, UK Biobank CMR cohort (45 474 participants) · median follow-up 2.5 years | 11.38 (2.56–50.57) | |
| 0.050.21520Adjusted hazard ratio (log scale) |
Original publication
A Multimodal Video-Based AI Biomarker for Aortic Stenosis Development and Progression. JAMA Cardiol. Published 1 June 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →