Artificial intelligence-enabled phenotyping of patients with severe aortic stenosis: on the recovery of extra-aortic valve cardiac damage after transcatheter aortic valve replacement

Abstract

ObjectiveA novel artificial intelligence-based phenotyping approach to stratify patients with severe aortic stenosis (AS) prior to transcatheter aortic valve replacement (TAVR) has been proposed, based on echocardiographic and haemodynamic data. This study aimed to analyse the recovery of extra-aortic valve cardiac damage in accordance with this novel stratification system following TAVR.MethodsThe proposed phenotyping approach was previously established employing data from 366 patients with severe AS from a bicentric registry. For this consecutive study, echocardiographic follow-up data, obtained on day 147±75.1 after TAVR, were available from 247 patients (67.5%).ResultsCorrection of severe AS by TAVR significantly reduced the proportion of patients suffering from concurrent severe mitral regurgitation (from 9.29% to 3.64%, p value: 0.0015). Moreover, pulmonary artery pressures were ameliorated (estimated systolic pulmonary artery pressure: from 47.2±15.8 to 43.3±15.1 mm Hg, p value: 0.0079). However, right heart dysfunction as well as the proportion of patients with severe tricuspid regurgitation remained unchanged. Clusters with persistent right heart dysfunction ultimately displayed 2-year survival rates of 69.2% (95% CI 56.6% to 84.7%) and 74.6% (95% CI 65.9% to 84.4%), which were significantly lower compared with clusters with little or no persistent cardiopulmonary impairment (88.3% (95% CI 83.3% to 93.5%) and 85.5% (95% CI 77.1% to 94.8%)).ConclusionsThis phenotyping approach preprocedurally identifies patients with severe AS, who will not recover from extra-aortic valve cardiac damage following TAVR and whose survival is therefore significantly reduced. Importantly, not the degree of pulmonary hypertension at initial presentation, but the irreversibility of right heart dysfunction determines prognosis.

Epiphenomenon or Prognostically Relevant Interventional Target? A Novel Proportionality Framework for Severe Tricuspid Regurgitation

“… 26 , 27 Moreover, it could be shown that not the disease‐defining severity of aortic stenosis at initial presentation but rather the (potentially irreversible) extra‐aortic valve cardiac damage determines prognosis after transcatheter aortic valve replacement. 28 , 29 , 30 Similarly, in patients with severe TR, the initial severity of TR expressed as TV EROA does not allow reliable prognostication for survival after TTVI as demonstrated by multivariable regression analysis (Table 5 ). A much better predictor for 2‐year mortality would be the residual TR severity grade (HR [increment per 1 grade]: 1.3 [95% CI, 1.0–1.6]; P =0.049 [as confirmed by multivariable regression analysis; Table 5 ]); however, this parameter is obviously not available ex ante to optimize patient selection.…”

Machine Learning-Based Predictive Model of Aortic Valve Replacement Modality Selection in Severe Aortic Stenosis Patients

“…Moreover, the assessment of preprocedural extra-aortic valve abnormality parameters and their subsequent measurements plays a crucial role in determining the long-term prognosis [ 15 ]. Notably, irreversible right ventricular (RV) dysfunction emerges as a defining factor delineating patients with a poorer long-term prognosis when juxtaposed with those devoid of RV dysfunction.…”

Artificial Intelligence in the Screening, Diagnosis, and Management of Aortic Stenosis

“…Lachmann et al . [ 94 ] found that the discriminative power of cluster analysis was based on identifying the inherent yet obscure irreversibility of cardiac dysfunction (and therefore poor prognosis), rather than the obvious characteristics at baseline. further studies support the use of risk stratification using unsupervised cluster analysis [ 18 , 19 , 27 , 95 , 96 ].…”