Clinical Research Directory

CMR-AI and Outcomes in AS

Sponsor: Medical University of Vienna

Summary

Background \& Aims: Artificial Intelligence (AI) in cardiac magnetic resonance (CMR) imaging has previously been shown to provide highly reproducible and accurate measures of myocardial structure and function, outperforming clinical experts. The prognostic value of more sensitive markers of early left (LV) and right ventricular (RV) function, such as global longitudinal shortening (GLS), mitral annular plane systolic excursion (MAPSE), and tricuspid annular plane systolic excursion (TAPSE) has not been established due to the lack of automated analysis. Thus, our aim is to evaluate whether AI-based measurements of these early markers of adverse cardiac remodeling convey relevant prognostic information in patients with severe aortic stenosis (AS) beyond LV and RV ejection fraction (EF). Materials \& Methods: In a current large-scale international, prospective, multi-center study \~1500 patients with severe AS underwent CMR imaging prior to aortic valve replacement (AVR). An AI-based algorithm, developed in the UK, was used for fully automated assessment of parameters of cardiac structure (end-diastolic volume, end-systolic volume, LV mass, maximum wall thickness) and function (EF, GLS, MAPSE, TAPSE). In this proposed follow-up project, we aim to associate these AI-based CMR parameters at baseline with mid-term clinical outcomes at 24-months post-AVR. A composite of all-cause mortality and heart failure hospitalization will serve as the primary endpoint. CMR-AI will be repeated at 24-months follow-up and trajectories from pre- to post-AVR will be assessed as a secondary endpoint. Future Outlook: In severe AS, a novel AI-based algorithm allows immediate and precise measurements of ventricular structure and function on CMR imaging. Our goal is to identify early markers of cardiac dysfunction indicating adverse mid-term prognosis post-AVR. This has guideline-forming potential as the optimal timepoint for AVR in patients with AS is currently a matter of debate.

Official title: Artificial Intelligence-based Risk Stratification and Mid-term Outcomes in Severe Aortic Stenosis: Insights from Cardiac Magnetic Resonance Imaging

Key Details

Conditions

Locations (7)