Background: Up to 30–50% of chronic heart failure patients who underwent cardiac resynchronization therapy (CRT) do not respond to the treatment. Therefore, patient stratification for CRT and optimization of CRT device settings remain a challenge.Objective: The main goal of our study is to develop a predictive model of CRT outcome using a combination of clinical data recorded in patients before CRT and simulations of the response to biventricular (BiV) pacing in personalized computational models of the cardiac electrophysiology.Materials and Methods: Retrospective data from 57 patients who underwent CRT device implantation was utilized. Positive response to CRT was defined by a 10% increase in the left ventricular ejection fraction in a year after implantation. For each patient, an anatomical model of the heart and torso was reconstructed from MRI and CT images and tailored to ECG recorded in the participant. The models were used to compute ventricular activation time, ECG duration and electrical dyssynchrony indices during intrinsic rhythm and BiV pacing from the sites of implanted leads. For building a predictive model of CRT response, we used clinical data recorded before CRT device implantation together with model-derived biomarkers of ventricular excitation in the left bundle branch block mode of activation and under BiV stimulation. Several Machine Learning (ML) classifiers and feature selection algorithms were tested on the hybrid dataset, and the quality of predictors was assessed using the area under receiver operating curve (ROC AUC). The classifiers on the hybrid data were compared with ML models built on clinical data only.Results: The best ML classifier utilizing a hybrid set of clinical and model-driven data demonstrated ROC AUC of 0.82, an accuracy of 0.82, sensitivity of 0.85, and specificity of 0.78, improving quality over that of ML predictors built on clinical data from much larger datasets by more than 0.1. Distance from the LV pacing site to the post-infarction zone and ventricular activation characteristics under BiV pacing were shown as the most relevant model-driven features for CRT response classification.Conclusion: Our results suggest that combination of clinical and model-driven data increases the accuracy of classification models for CRT outcomes.

No abstract

No abstract

We revealed some features of the left ventricular functional geometry in patients with myocardial diseases with different degrees of left ventricular systolic dysfunction. A negative correlation was found between the spatio-temporal heterogeneity of the kinetics of the left ventricular wall during systole and ejection fraction in normal heart and in systolic dysfunction. The differences in the quantitative characteristics of the functional geometry between patients and normal subjects and between different groups of patients depended on the severityof left-ventricular systolic dysfunction. In particular, spatial heterogeneity index that characterizes heterogeneity of systolic movement of the wall segments and end-systolic Fourier shape-power index characterizing complexity of the left ventricle shape during systole differed significantly in the examined groups of patients and have the greatest diagnostic power.

No abstract

Cardiac resynchronization therapy (CRT) has been shown as an essential treatment of patients with heart failure, leading to improvements in symptoms, left ventricular (LV) function, and survival. However, up to 30% of appropriately selected patients remain nonresponders to CRT. The aim of our study was to test a hypothesis on the impact of lead positioning in the ventricular walls on CRT response in patients with advanced chronic heart failure with and without pre-operative inter and intraventricular myocardial dyssynchrony. We examined 53 guideline-selected CRT candidates. Response to CRT was defined in 6 months after implantation of CRT devices. All patients underwent standard and Doppler echocardiography for assessment of LV function and mechanical dyssynchrony. Individual right ventricular (RV) and LV lead tip position, inter-lead distance, and the horizontal and vertical components were measured on the radiograph images with using an automated custom made software Our results showed that the RLV inter-lead distance is an essential parameter correlated with the CRT outcomes. A logistic model comprising the RLV inter-lead distance with parameters of dyssynchrony demonstrated a high predictive power for odds of CRT success.

Aim. To assess the association between changes in interventricular delay (IVD) and response to cardiac resynchronization therapy (CRT) during 24-month postoperative period in patients with quadripolar left ventricular leads.Material and methods. This retrospective non-randomized study included data from 48 patients with implanted CRT devices with quadripolar left ventricular (LV) leads, examined 3, 6, 12, 24 months after operation. CRT responders were considered patients with a decrease in end-systolic volume (ESV) by more than 10% compared with preoperative. To test the hypothesis about the rationale for choosing the maximum IVD when installing the LV lead, the group of patients was divided into two subgroups as follows: one with the maximum IVD (IVDmax, n=24), the other — without this condition (n=24).Results. A correlation was found between changes in IVD and ESV, as well as ejection fraction (EF) in the period of 6, 12 and 24 months after implantation compared to baseline. In the subgroup with IVDmax, the shortening of IVD in the postoperative period is higher at each considered period compared to the second subgroup, and in general, there is a more pronounced decrease in IVD over 24 months. At the same time, 3, 6, 12 months after surgery, patients with IVDmax show a significantly greater decrease in ESV and, accordingly, a greater increase in EF. Prognostic models of CRT response in the long term after implantation were created. Significant predictors were the initial IVD, changes in IVD in the early postoperative period and IVDmax selection. At the same time, not a single factor, taken separately, made it possible to separate responders and non-responders.Conclusion. A greater shortening of the IVD corresponds to a greater decrease in LV ESV and EDV, as well as a greater increase in EF in the long-term postoperative period. The choice of quadripolar LV lead in accordance with the maximum IVD is accompanied by a decrease in the proportion of non-responders, a more pronounced decrease in electrical ventricular dyssynchrony and an improvement in systolic function.

No abstract