Valvular & structural heart disease
Prediction of Aortic Stenosis Progression Using Artificial Intelligence: A Machine Learning Model
Authors' conclusion
Our novel, echocardiography-focused artificial intelligence model is a reliable tool for the early identification of patients at risk of progression to severe AS.
Study context
- Population
- Patients initially diagnosed with mild or moderate aortic stenosis (AS) on echocardiography, tertiary medical centre
- Participants
- 9,330 echocardiograms
- Outcome
- Prediction of progression from mild/moderate AS to severe AS (accuracy, AUC-ROC, calibration)
- Follow-up
- Within 5 years
Methodological detailssingle-centre, cross-validation
- Single-centre
- Cross-validation
Main finding
As reported in the abstract
AI model prediction of progression to severe AS
AUC-ROC
0.91
Accuracy
83%
Integrated Calibration Index
0.0576
Observational data: associations, not effects.
Further findings
Progression to severe AS during follow-up
- Patients who developed severe AS
- 1,625 (47%)
Original publication
Prediction of Aortic Stenosis Progression Using Artificial Intelligence: A Machine Learning Model. JACC Adv. Published 29 August 2025. doi:10.
Summarised from the published abstract; every number is checked against it