Artificial intelligence-enabled echocardiography as a surrogate for multi-modality aortic stenosis imaging: post-hoc analysis of a clinical trial

BackgroundAccurate aortic stenosis (AS) phenotyping requires access to multimodality imaging which has limited availability. The Digital Aortic Stenosis Severity Index (DASSi), an AI biomarker of AS-related remodeling on 2D echocardiography, predicts AS progression independent of Doppler measurements. Whether DASSi-enhanced echocardiography provides a scalable alternative to multimodality AS imaging remains unknown. We sought to evaluate the ability of DASSi to define personalized AS progression profiles and validate its performance against multimodality imaging features of functional, structural, and biological disease severity. MethodsIn the SALTIRE-2 trial of participants with mild-or-moderate AS, we performed blinded DASSi measurements (probability of severe AS, 0-to-1) on baseline transthoracic echocardiograms. We evaluated the association between baseline DASSi and (i) disease severity by hemodynamic (peak aortic valve velocity [AV-Vmax]), structural (CT-derived aortic valve calcium score [AVCS]) and biological features ([18F]sodium fluoride [NaF] uptake on Positron Emission Tomography-CT), (ii) disease progression (change in AV-Vmax and AVCS), and (iii) incident aortic valve replacement (AVR). We used generalized linear mixed, or Cox models adjusted for risk factors and aortic valve area, as appropriate. ResultsWe analyzed 134 participants (72 [IQR: 69-78] years, 27 [20.1%] women) with a mean baseline DASSi of 0.51 (standard deviation [SD]: 0.19). DASSi was independently associated with disease severity: each SD increase was associated with higher AV-Vmax (+0.21 [95%CI: 0.12-0.30] m/sec), AVCS (+284 [95%CI: 101-467] AU) and [18F]NaF TBRmax (+0.17 [95%CI: 0.04-0.31]). Higher DASSi was also associated with disease progression by Doppler (AV-Vmax) and CT (AVCS) at 24 months (pinteraction for DASSi (x) time<0.001), and future AVR (75 events over 5.5 [IQR: 2.4-7.2] years, adj.HR 1.47 [95%CI: 1.12-1.94] per SD). ConclusionsDASSi is associated with functional, structural and biological features of AS severity as well as disease progression and outcomes. DASSi-enhanced echocardiography provides a readily accessible alternative to multimodality imaging of AS which has potential value both in clinical practice and as a clinical trial biomarker.