Background: Severe tricuspid regurgitation (TR) translates into distressing mortality under conservative treatment. Transcatheter tricuspid valve intervention (TTVI) is therefore emerging as a novel treatment option, promising to prolong survival. Predictors for procedural success in patients treated with Cardioband system, targeting tricuspid annulus dilatation, are largely elusive.

Purpose: This study aims to refine prediction of procedural success in patients with severe TR undergoing TTVI with Cardioband system by employing a random forest algorithm.

Methods: 72 patients were enrolled at two tertiary centers in Germany between 2018 and 2020. Key inclusion criterion was TR≥III/V°. Procedural success was defined as technically successful Cardioband implantation, and TR reduction of at least II/V° as assessed on transthoracic echocardiography before discharge. Since 66.7% of patients were classified as “success”, a synthetic minority over-sampling technique was applied in order to train the random forest algorithm on a balanced data set.

Results: Procedural success was predicted with an accuracy of 85.4% (AUC: 0.923) by using a random forest algorithm. Therefore, eight parameters from pre-procedural echocardiography served as input variables (tricuspid valve (TV) effective regurgitant orifice area (EROA), basal right ventricular diameter, TV anteroseptal diameter, vena cava inferior diameter, TV coaptation depth, systolic pulmonary artery pressure (sPAP), left ventricular stroke volume index, tricuspid annular plane systolic excursion (TAPSE)). Partial dependence analysis revealed that enlargement of the TV anteroseptal diameter was most important for model accuracy. Applied to the real-world data set (24 patients classified as “failure” and 48 patients classified as “success”), the now trained random forest algorithm predicted procedural success with high sensitivity (70.8%) and specificity (100.0%), significantly outperforming the no information rate (p-value: 0.0069). Patients with low probability for success were characterized by impaired right ventricular function (TAPSE: 15.5 ± 3.63 mm) and enlarged right sided cardiac diameters (basal right ventricular diameter: 51.6 ± 3.79 mm; TV anteroseptal diameter: 45.0 ± 5.10 mm). Notably, sPAP and TV EROA were negatively correlated (R: -0.3004, p-value: 0.0322), and elevation in sPAP was attenuated in patients with low probability for procedural success (sPAP: 34.0 ± 11.7 mmHg). Survival analysis further revealed that any amelioration in TR upon Cardioband implantation was associated with reduction in mortality (hazard ratio: 0.19 [95% confidence interval: 0.051-0.7], p-value: 0.013).

Conclusion: The random forest algorithm enables precise prediction of procedural success in patients treated with Cardioband system. TR reduction ≥ II/V° appears less achievable in patients with advanced stages of right heart failure. Subsequently, adequate patient selection and timing of intervention is of great importance.