Importance of Systematic Right Ventricular Assessment in Cardiac Resynchronization Therapy Candidates: A Machine Learning Approach.

BACKGROUND: Despite all having systolic heart failure and broad QRS intervals, patients screened for cardiac resynchronization therapy (CRT) are highly heterogeneous, and it remains extremely challenging to predict the impact of CRT devices on left ventricular function and outcomes. The aim of this study was to evaluate the relative impact of clinical, electrocardiographic, and echocardiographic data on the left ventricular remodeling and prognosis of CRT candidates by the application of machine learning approaches. METHODS: One hundred ninety-three patients with systolic heart failure receiving CRT according to current recommendations were prospectively included in this multicenter study. A combination of the Boruta algorithm and random forest methods was used to identify features predicting both CRT volumetric response and prognosis. Model performance was tested using the area under the receiver operating characteristic curve. The k-medoid method was also applied to identify clusters of phenotypically similar patients. RESULTS: From 28 clinical, electrocardiographic, and echocardiographic variables, 16 features were predictive of CRT response, and 11 features were predictive of prognosis. Among the predictors of CRT response, eight variables (50%) pertained to right ventricular size or function. Tricuspid annular plane systolic excursion was the main feature associated with prognosis. The selected features were associated with particularly good prediction of both CRT response (area under the curve, 0.81; 95% CI, 0.74-0.87) and outcomes (area under the curve, 0.84; 95% CI, 0.75-0.93). An unsupervised machine learning approach allowed the identification of two phenogroups of patients who differed significantly in clinical variables and parameters of biventricular size and right ventricular function. The two phenogroups had significantly different prognosis (hazard ratio, 4.70; 95% CI, 2.1-10.0; P < .0001; log-rank P < .0001). CONCLUSIONS: Machine learning can reliably identify clinical and echocardiographic features associated with CRT response and prognosis. The evaluation of both right ventricular size and functional parameters has pivotal importance for the risk stratification of CRT candidates and should be systematically performed in patients undergoing CRT.

New expectations for diastolic function assessment in transthoracic echocardiography based on a semi-automated computing of strain-volume loops.

AIMS: Early diagnosis of heart failure with preserved ejection fraction (HFpEF) by determination of diastolic dysfunction is challenging. Strain-volume loop (SVL) is a new tool to analyse left ventricular function. We propose a new semi-automated method to calculate SVL area and explore the added value of this index for diastolic function assessment. METHOD AND RESULTS: Fifty patients (25 amyloidosis, 25 HFpEF) were included in the study and compared with 25 healthy control subjects. Left ventricular ejection fraction was preserved and similar between groups. Classical indices of diastolic function were pathological in HFpEF and amyloidosis groups with greater left atrial volume index, greater mitral average E/e' ratio, faster tricuspid regurgitation (P < 0.0001 compared with controls). SVL analysis demonstrated a significant difference of the global area between groups, with the smaller area in amyloidosis group, the greater in controls and a mid-range value in HFpEF group (37 vs. 120 vs. 72 mL.%, respectively, P < 0.0001). Applying a linear discriminant analysis (LDA) classifier, results show a mean area under the curve of 0.91 for the comparison between HFpEF and amyloidosis groups. CONCLUSION: SVLs area is efficient to identify patients with a diastolic dysfunction. This new semi-automated tool is very promising for future development of automated diagnosis with machine-learning algorithms.

Model-based estimation of left ventricular pressure and myocardial work in aortic stenosis.

This paper proposes a model-based estimation of left ventricular (LV) pressure for the evaluation of constructive and wasted myocardial work of patients with aortic stenosis (AS). A model of the cardiovascular system is proposed, including descriptions of i) cardiac electrical activity, ii) elastance-based cardiac cavities, iii) systemic and pulmonary circulations and iv) heart valves. After a sensitivity analysis of model parameters, an identification strategy was implemented using a Monte-Carlo cross-validation approach. Parameter identification procedure consists in two steps for the estimation of LV pressures: step 1) from invasive, intraventricular measurements and step 2) from non-invasive data. The proposed approach was validated on data obtained from 12 patients with AS. The total relative errors between estimated and measured pressures were on average 11.9% and 12.27% and mean R2 were equal to 0.96 and 0.91, respectively for steps 1 and 2 of parameter identification strategy. Using LV pressures obtained from non-invasive measurements (step 2) and patient-specific simulations, Global Constructive (GCW), Wasted (GWW) myocardial Work and Global Work Efficiency (GWE) parameters were calculated. Correlations between measures and model-based estimations were 0.88, 0.80, 0.91 respectively for GCW, GWW and GWE. The main contributions concern the proposal of the parameter identification procedure, applied on an integrated cardiovascular model, able to reproduce LV pressure specifically to each AS patient, by non-invasive procedures, as well as a new method for the non-invasive estimation of constructive, wasted myocardial work and work efficiency in AS.