Predicting mortality after transcatheter aortic valve replacement using AI-based fully automated left atrioventricular coupling index.

Abstract

Background: This study aimed to determine whether artificial intelligence (AI)-based automated assessment of left atrioventricular coupling index (LACI) can provide incremental value above other traditional risk factors for predicting mortality among patients with severe aortic stenosis (AS) undergoing coronary CT angiography (CCTA) before transcatheter aortic valve replacement (TAVR).

Methods: This retrospective study evaluated patients with severe AS who underwent CCTA examination before TAVR between September 2014 and December 2020. An AI-prototype software fully automatically calculated left atrial and left ventricular end-diastolic volumes and LACI was defined by the ratio between them. Uni- and multivariate Cox proportional hazard methods were used to identify the predictors of mortality in models adjusting for relevant significant parameters and Society of Thoracic Surgeons Predicted Risk of Mortality (STS-PROM) score.

Results: A total of 656 patients (77 years [IQR, 71-84 years]; 387 [59.0 ​%] male) were included in the final cohort. The all-cause mortality rate was 21.6 ​% over a median follow-up time of 24 (10-40) months. When adjusting for clinical confounders, LACI ≥43.7 ​% independently predicted mortality (adjusted HR, 1.52, [95 ​% CI: 1.03, 2.22]; p ​= ​0.032). After adjusting for the STS-PROM score in a separate model, LACI ≥43.7 ​% remained an independent prognostic parameter (adjusted HR, 1.47, [95 ​% CI: 1.03-2.08]; p ​= ​0.031). In a sub-analysis of patients with preserved left ventricular ejection fraction, LACI remained a significant predictor (adjusted HR, 1.72 [95 ​% CI: 1.02, 2.89]; p ​= ​0.042).

Conclusions: AI-based fully automated assessment of LACI can be used independently to predict mortality in patients undergoing TAVR, including those with preserved LVEF.