Mechanical dispersion of left ventricle and left atrial reservoir strain are both superior to global longitudinal strain to predict exercise capacity in heart failure with preserved ejection fraction

Abstract Funding Acknowledgements Type of funding sources: Public hospital(s). Main funding source(s): Fundação Adib Jatene Background/Introduction: Peak oxygen uptake (peak VO2) measures cardiovascular fitness and is a valuable diagnostic and prognostic marker in patients with heart failure with preserved ejection fraction (HFpEF). Measurement of peak VO2, however, requires specialized equipment and expert supervision, limiting its routine use by practicing clinicians. Strain curves obtained by speckle tracking echocardiography (STE) can provide different parameters of myocardial mechanics such as the Global Longitudinal Strain (GLS), which is the most robust STE feature for clinical practice. Notwithstanding, there is conflicting data on whether the GLS is associated with peak VO2 in HFpEF subjects. Moreover, few studies have addressed the relationship between peak VO2 and other interesting deformation parameters such as the left atrial (LA) reservoir strain or the left ventricular mechanical dispersion (MD). Purpose The present study aimed to examine the utility of the myocardial mechanics as assessed by STE in predicting peak VO2 in patients with HFpEF. Methods From an ongoing prospective cohort of 189 subjects, we sampled subjects with different HFpEF stages. All patients underwent cardiopulmonary exercise testing (CPX) and a 2D-STE (LV GLS, MD, LA reservoir strain, LA conduit strain, and LA contraction strain) obtained by a blinded examinator. The missing data was handled by complete case analysis approach. We excluded subjects who had atrial fibrillation/flutter, severe COPD, STE with poor tracking quality, CPX with respiratory exchange rate (RER) < 1. The Spearman"s correlation was calculated, and the 95% CI were estimated. Finally, an estimative of the STE features importance to predict peak VO2 < 20mL/Kg/min was done using the function "xgb.importance()" from machine learning model XGBoost in R software. XGBoost is a variant of Gradient Boosting Method that uses ensembles of decision trees. Results We obtained 74 subjects (23 without evidence of heart disease, 23 with pre-heart failure and 28 with HFpEF). The MD presented the highest correlation with peak VO2 (Rho=-0.48; p-value < 0.001) followed by LA reservoir strain (Rho = 0.40; p-value < 0.001), LA conduit strain (Rho= –0.36; p-value < 0.001) and LA contraction (Rho= –0.30 p-value < 0.004) as shown in Figure 1. However, no correlation was found between GLS and peak VO2 (Rho= –0.07 p-value < 0.5) (Figure 2A). The feature importance score (Figure 2B) showed the MD as the best relative contribution for VO2 prediction (gain= 0.34) superior to LA reservoir strain (gain = 0.25). GLS presented contribution (gain = 20) superior to LA conduit strain (gain =10) and LA contraction strain (gain = 0.08). Conclusion Left ventricular mechanical dispersion and left atrial reservoir strain obtained with STE were better predictors of peak VO2 than GLS in patients with different HFpEF stages and may be helpful in risk stratification and diagnosis. Abstract Figure 1 Abstract Figure 2