Kane, G C

Background Tricuspid regurgitation (TR) is a common valvular disorder that can affect patients’ quality of life and survival. The impact of TR etiology on overall survival and the associated risk factors in each subgroup are not well studied. Methods Multisite, retrospective study evaluating survival based on TR etiology using Kaplan–Meier and Cox regression models. Stepwise approach was used to define TR etiology (≥moderate): primary (PTR; presence of a primary valvular pathology), lead associated (LTR; lead interfering with closure), and secondary TR (STR) in the setting of left‐sided valvular disease, left ventricular disease, other causes of pulmonary hypertension, right ventricular disease, and atrial secondary TR. Results A total of 12 899 patients were included (3% PTR, 90% STR, 7% LTR). The mean age was 68±14, 73±13, and 71±13 years, respectively (44%–55% female patients). Adjusting for age, sex, and TR severity, patients with PTR had better overall survival (PTR: reference; STR hazard ratio [HR], 1.4 [1.2–1.6], LTR HR, 1.5 [1.1–1.7]). On multivariable Cox regression, the Tricuspid Regurgitation Impact on Outcomes score was associated with mortality across all groups ( P <0.05 for all). In addition, other risk factors associated with worse outcomes included pulmonary hypertension and ≥moderate right ventricular enlargement in PTR; left‐sided valvular disease, pulmonary hypertension, and ≥moderate right ventricular dysfunction in STR; and left ventricular disease and ≥moderate right ventricular dysfunction in LTR. Conclusions Patients with PTR have better survival than STR and LTR. Tricuspid Regurgitation Impact on Outcomes score was associated with mortality across etiologies, whereas other risk factors are etiology specific. Improved risk profiling may enhance patient selection, treatment decisions, and outcomes.

Abstract Background Right ventricular (RV) systolic function is an independent predictor of outcome, but a robust automated method of quantitation is lacking. Purpose To develop and validate a deep learning model for quantifying RV systolic function from 2D echo clips and assess its prognostic value in various loading states and left-heart disease. Methods A deep learning convolutional neural network (CNN) was developed to quantitate RV systolic function using all available apical 4 chamber (A4C) views from 13,039 patients (61,187 A4C video clips) in a US institution. Videos were converted to frames of 256x256 grayscale pixels, with graphics, including the ECG, removed. The model used the S3D architecture, a 3D-CNN with many of the spatial and temporal convolutions separated. RV free wall longitudinal strain (RVFWLS) was used to define RV function: normal (≤-25%); mild (-20% to –24%); moderate (-15% to –19%) and severe RV dysfunction (0% to –14%). The AI-estimate was the average of multiple 32-frame segments for each clip identified as an A4C, including both standard and RV-focused variations. The model was validated in four distinct clinical cohorts from independent data sources: 1) 1365 patients referred to an external diagnostic echocardiography lab in a different US state; 2) 569 patients recruited prospectively with known or suspected pulmonary hypertension (PH); 3) 416 patients with moderate or greater tricuspid valve regurgitation (TR); 4) 872 patients imaged at an Eastern European University with left-sided cardiac diseases (valvular disease, cardiomyopathies, etc.), athletes, or healthy volunteers. Results Model output was strongly correlated with the presence of RV dysfunction by manual measurement [AUC 0.907 (95% CI: 0.888-0.926)] in the internal validation set. Results were similar in an external validation US cohort [N=1365; AUC 0.919 (95% CI: 0.899-0.939)]. When the model was applied to 569 patients with known or suspected PH, presence and severity of the AI measures of RV dysfunction were strongly associated with functional class, 6 min walk distance, NT-proBNP levels and right heart failure (p&lt;0.001). The presence and severity of RV dysfunction (as categorized by the AI model) was strongly associated with all-cause mortality in patients with PH (Figure 1A) and in patients with significant TR (Figure 1B). The European cohort was a geographically and institutionally distinct cohort with a low prevalence of &gt;mild TR (10.8%) or PH (6.4%). In this cohort the AI model predicted a reduced RVEF (&lt; 45%) with an AUC of 0.864 (95% CI: 0.831-0.898) and associated with both all-cause mortality (Figure 2A) and a composite endpoint of heart failure hospitalization or death (Figure 2B). Conclusions A fully automated, AI-based assessment of RV systolic function, using 2D apical 4 chamber echo views alone, is highly feasible and can accurately categorize disease severity and predict outcome across a wide spectrum of cardiovascular conditions.Figure 1 Figure 2