Usefulness of regional right ventricular and right atrial strain for prediction of early and late right ventricular failure following a left ventricular assist device implant: A machine learning approach

Abstract

Background: Identifying candidates for left ventricular assist device surgery at risk of right ventricular failure remains difficult. The aim was to identify the most accurate predictors of right ventricular failure among clinical, biological, and imaging markers, assessed by agreement of different supervised machine learning algorithms. Methods: Seventy-four patients, referred to HeartWare left ventricular assist device since 2010 in two Italian centers, were recruited. Biomarkers, right ventricular standard, and strain echocardiography, as well as cath-lab measures, were compared among patients who did not develop right ventricular failure (N = 56), those with acute–right ventricular failure (N = 8, 11%) or chronic–right ventricular failure (N = 10, 14%). Logistic regression, penalized logistic regression, linear support vector machines, and naïve Bayes algorithms with leave-one-out validation were used to evaluate the efficiency of any combination of three collected variables in an “all-subsets” approach. Results: Michigan risk score combined with central venous pressure assessed invasively and apical longitudinal systolic strain of the right ventricular–free wall were the most significant predictors of acute–right ventricular failure (maximum receiver operating characteristic–area under the curve = 0.95, 95% confidence interval = 0.91–1.00, by the naïve Bayes), while the right ventricular–free wall systolic strain of the middle segment, right atrial strain (QRS-synced), and tricuspid annular plane systolic excursion were the most significant predictors of Chronic-RVF (receiver operating characteristic–area under the curve = 0.97, 95% confidence interval = 0.91–1.00, according to naïve Bayes). Conclusion: Apical right ventricular strain as well as right atrial strain provides complementary information, both critical to predict acute–right ventricular failure and chronic–right ventricular failure, respectively.

Assessment of right ventricular function following left ventricular assist device (LVAD) implantation—The role of speckle‐tracking echocardiography: A meta‐analysis

“…RVFWS was reported in 12 studies (9 TTE and 3 TEE). 8,19,21,22,[24][25][26][28][29][30]33,34 The RVFWS for the whole cohort (TEE and TTE) was found to be significantly lower preoperatively in patients who suf- Figure 3. The OR for RVF with percentage increase in FWS was reported in 3 studies, OR: 1.63, 95% CI 1.07-2.47…”

Assessment of Right Ventricular Function Following Left Ventricular Assist Device Implantation – The Role of Speckle-Tracking Echocardiography: A Meta-Analysis.

“…And upon adjustment of image sector to obtain a similar frame rate, the spatial resolution gets affected which in turn affects the accuracy of delineation of the endocardium. 31 Furthermore, mechanical ventilation increases the RV afterload due to increased intra-thoracic pressure, 44 hence decreasing the strain values. It is hard to draw accurate conclusion about TEE-derived strain given the small number in our analysis.…”

“…Beck, 2017 Adverse events: A composite of one or more of the following: death within 6 months, >14 days on inotropes, need for mechanical RV support, or device thrombosis requiring explant. Bellavia, 2019 The need for intravenous inotropes for >2 weeks; persistent RV stroke work index (RVSW) < 4.0 g/m2; or nitric oxide inhalation for > 48 h at any rotation speed or saline infusion; or presence of acute RVF when emergent/ urgent need for mechanical RV support was considered mandatory.…”

“…FWS was reported in 12 studies (9 TTE and 3 TEE). 8,18,31,19,20,23,24,26,[28][29][30] The FWS for the whole cohort (TEE and TTE) was found to be significantly worse (less negative) pre-operatively in patients who suffered RVF compared to non-RVF group; SMD: -2.75 (95% CI: -3.72 to -1.79; p-value <0.0001), I 2 =88.08%. Upon subgroup analysis based on modality, there was no statistically significant difference in the TEE-derived FWS between RVF and non-RVF groups; SMD of -1.81 (95% CI: -4.00 to 0.38; p-value= 0.07), I 2 =69.96%.…”

“…Five studies used EchoPac to analyze the GLS strain, 8,22,23,27,31 whereas, four studies used EchoPac to analyze the strain values for the FWS. 8,22,23,31 In the studies using EchoPac, the pooled SMD in GLS between RVF and non-RVF groups (figure 4) was -3.71 (95% CI: -5.64 to -1.77; p-value= 0.04), I 2 =61.69%. In EchoPac studies, the SMD in FWS between RVF and non-RVF groups (figure 5) was -4.48 (95% CI: -5.97 to -2.98; p-value <0.0001), I 2 = 0.00%.…”