scholarly journals Importance of systematic right ventricular assessment in cardiac resynchronization therapy candidates: a machine-learning approach

2021 ◽  
Vol 22 (Supplement_1) ◽  
Author(s):  
E Galli ◽  
V Le Rolle ◽  
OA Smiseth ◽  
J Duchenne ◽  
JM Aalen ◽  
...  

Abstract Funding Acknowledgements Type of funding sources: None. Background Despite having all a systolic heart failure and broad QRS, patients proposed for cardiac resynchronization therapy (CRT) are highly heterogeneous and it remains extremely complicated to predict the impact of the device on left ventricular (LV) function and outcomes. Objectives We sought to evaluate the relative impact of clinical, electrocardiographic, and echocardiographic data on the left ventricular (LV) remodeling and prognosis of CRT-candidates by the application of machine learning (ML) approaches. Methods 193 patients with systolic heart failure undergoing CRT according to current recommendations were prospectively included in this multicentre study. We used a combination of the Boruta algorithm and random forest methods to identify features predicting both CRT volumetric response and prognosis (Figure 1). The model performance was tested by the area under the receiver operating curve (AUC). We also applied the K-medoid method to identify clusters of phenotypically-similar patients. Results From 28 clinical, electrocardiographic, and echocardiographic-derived variables, 16 features were predictive of CRT-response; 11 features were predictive of prognosis. Among the predictors of CRT-response, 7 variables (44%) pertained to right ventricular (RV) size or function. Tricuspid annular plane systolic excursion was the main feature associated with prognosis. The selected features were associated with a very good prediction of both CRT response (AUC 0.81, 95% CI: 0.74-0.87) and outcomes (AUC 0.84, 95% CI: 0.75-0.93) (Figure 1, Supervised Machine Learning Panel). An unsupervised ML approach allowed the identifications of two phenogroups of patients who differed significantly in clinical and parameters, biventricular size and RV function. The two phenogroups had significant different prognosis (HR 4.70, 95% CI: 2.1-10.0, p < 0.0001; log –rank p < 0.0001; Figure 1, Unsupervised Machine Learning Panel). Conclusions Machine learning can reliably identify clinical and echocardiographic features associated with CRT-response and prognosis. The evaluation of both RV-size and function parameters has pivotal importance for the risk stratification of CRT-candidates and should be systematically assessed in patients undergoing CRT. Abstract Figure 1

2020 ◽  
Vol 4 (3) ◽  
pp. 1-5
Author(s):  
David Aouate ◽  
Aymeric Menet ◽  
Dimitri Bellevre ◽  
Thibaud Damy ◽  
Sylvestre Marechaux

Abstract Background Cardiac amyloidosis involvement is associated with a detrimental outcome including frequent arrhythmias, heart failure, and conduction disturbances which may need permanent pacing. Cases summary We report two cases of patients with transthyretin amyloidosis (ATTR) who developed heart failure and depressed left ventricular ejection fraction (LVEF) following permanent right ventricular (RV) pacing but highly responded to cardiac resynchronization therapy (CRT). Discussion The impact of RV pacing and CRT in cardiac amyloidosis is not known. In our cases, the detrimental effect of permanent RV pacing on left ventricular (LV) systolic function and heart failure symptoms was suggested by both permanent RV pacing mediated functional and LV function decline and LV systolic dysfunction reversal following CRT along with QRS width reduction. Whether cardiac resynchronization should be readily recommended in ATTR patients who need ventricular pacing whatever the LVEF deserves further investigation.


Author(s):  
Stacey Howell ◽  
Tim Stivland ◽  
Kenneth Stein ◽  
Kenneth Ellenbogen ◽  
Larisa Tereshchenko

Introduction—We aimed to apply machine learning (ML) to develop a prediction model for cardiac resynchronization therapy (CRT) response. Methods and Results—Participants from the SmartDelay Determined AV Optimization (SMART-AV) trial (n=741; age, 66 ±11 yrs; 33% female; 100% NYHA III-IV; 100% EF≤35%) were randomly split into training & testing (80%; n=593), and validation (20%; n=148) samples. Baseline clinical, ECG, echocardiographic and biomarker characteristics, and left ventricular (LV) lead position (43 variables) were included in 6 ML models (random forests, convolutional neural network, lasso, adaptive lasso, plugin lasso, elastic net, ridge, and logistic regression). A composite of freedom from death and heart failure hospitalization and a >15% reduction in LV end-systolic volume index at 6-months post-CRT was the endpoint. The primary endpoint was met by 337 patients (45.5%). The adaptive lasso model was more accurate than class I ACC/AHA guidelines criteria (AUC 0.759; 95%CI 0.678-0.840 versus 0.639; 95%CI 0.554-0.722; P<0.0001), well-calibrated, and parsimonious (19 predictors; nearly half are potentially modifiable). The model predicted CRT response with 70% accuracy, 70% sensitivity, and 70% specificity, and should be further validated in prospective studies. Conclusions—ML predicts short-term CRT response and thus may help with CRT procedure planning.


2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
M V Kostyukevich ◽  
P Van Der Bijl ◽  
N M Vo ◽  
N Ajmone Marsan ◽  
V Delgado ◽  
...  

Abstract Background Myocardial work, assessed by speckle tracking echocardiography, reflects mechanical efficiency of the left ventricle. In heart failure patients, characterization of acute changes in regional (septal and lateral) left ventricular (LV) myocardial walls after cardiac resynchronization therapy (CRT) may enhance understanding of CRT response. Objective To evaluate the interaction between CRT response and components of myocardial work of the lateral wall and septum in patients with heart failure. Methods Regional LV myocardial work was calculated by integrating non-invasive blood pressure measurements, timing of mitral and aortic valve opening and closure and speckle tracking-derived LV longitudinal strain. From pressure-strain loops, constructive work (CW) and wasted work (WW) were calculated. CRT response was defined as a decrease in LV end-systolic volume ≥15% at 6 months follow-up. Changes in CW and WW of the septal and lateral walls prior to (baseline) and within the first 5 days after CRT implantation were compared between CRT responders and non-responders. Results At baseline, measurement of regional CW and WW was performed in 168 patients treated with CRT (71% men, 66±10 years). At 6 months, 59% of patients were CRT responders. CRT responders more frequently had non-ischemic heart failure than non-responders (54% vs 36%; p=0.027). At baseline, CRT responders were characterized by a significantly higher septal WW (270.5 [160.0; 451.5] mmHg% vs. 210.5 [106.3; 336.5] mmHg%; p=0.038) and lateral CW (989.5 [574.0; 1439.0] mmHg% vs. 689.0 [463,3; 1140.0] mmHg%; p=0.005). On multivariable analysis, only CW of the lateral wall at baseline was independently associated with CRT response (HR 1.001; 95% CI, 1.000–1.001; p=0.048). Immediately after CRT implantation, measurement of regional CW and WW was feasible in 115 patients. CRT responders showed improvement in CW (433.0 [254.5; 686.5] mmHg% to 664.5 [424.5; 977.8] mmHg%; p<0.001) and WW (305.0 [169.0; 461.3] mmHg% to 145.0 [80.0; 306.3] mmHg%; p=0.005) of the septum whereas the lateral wall demonstrated a significant decrease in CW (1036.5 [561.0; 1402.0] to 818.0 [491.0; 1154.3] mmHg%; p=0.005) and increase in WW (132.5 [80.3; 269.3] to 198.5 [107.5; 331.0] mmHg%; p=0.025). Non-responders showed only a decrease in WW of the septum (202.8 [102.9; 332.5] to 168.5 [67.6; 258.4] mmHg%; p=0.049). Conclusion CRT responders are characterized by increased WW of the septum and CW of the lateral wall at baseline, which are corrected immediately after CRT implantation. Constructive work of the LV lateral wall at baseline is independently associated with CRT response. Acknowledgement/Funding Study was supported by ESC Research grant 2018


2017 ◽  
Vol 3 (2) ◽  
pp. 245-248
Author(s):  
Matthias Heinke ◽  
Gudrun Dannberg ◽  
Tobias Heinke ◽  
Johannes Hörth ◽  
Helmut Kühnert

AbstractCardiac resynchronization therapy with biventricular pacing is an established therapy for heart failure patients with sinus rhythm, reduced left ventricular ejection fraction and electrical ventricular desynchronization. The aim of the study was to evaluate electrical interventricular delay and left ventricular delay in right ventricular pacemaker pacing before upgrading to cardiac resynchronization therapy. Heart failure patients with right ventricular pacing, DDD pacemaker, DDD defibrillator and 24.5 ± 4.9 % left ventricular ejection fraction were measured by surface ECG and transesophageal bipolar left ventricular ECG before upgrading to cardiac resynchronization therapy. Interventricular and intraventricular desynchronization in right ventricular pacemaker pacing were 228.2 ± 44.8ms QRS duration, 86.5 ± 32.8ms interventricular delay and 94.4 ± 23.8ms left ventricular delay. Cardiac resynchronization therapy was optimized by impedance cardiography. Transesophageal electrical interventricular delay and left ventricular delay in right ventricular pacemaker pacing may be additional useful ventricular desynchronization parameters to improve patient selection for upgrading right ventricular pacemaker pacing to cardiac resynchronization therapy.


EP Europace ◽  
2021 ◽  
Vol 23 (Supplement_3) ◽  
Author(s):  
M Kerekanic ◽  
M Hudak ◽  
M Jakubova ◽  
D Kucerova ◽  
S Misikova ◽  
...  

Abstract Funding Acknowledgements Type of funding sources: Public Institution(s). Main funding source(s): The present study was supported by a grant from Slovak Hearth Rhythm Association (Prognostic value of MR-proANP and MR-proADM in patients undergoing cardiac resynchronization therapy). Background Chronic heart failure (CHF) is a complex syndrome characterized by an abnormal neurohormonal activation, including arginine vasopressin (AVP). Copeptin is an indicator of AVP activation, which levels are elevated in CHF and have prognostic importance. Cardiac resynchronization therapy (CRT) is an important device therapy for patients with advanced CHF, left ventricular (LV) systolic dysfunction and evidence of electromechanical dyssynchrony. The aim of the present study was to determine the possible relationship between CRT and serum copeptin levels. Methods We have included CRT patients with ischemic as well as nonischemic etiology of CHF. The levels of copeptin were measured at baseline and 12 months respectively after CRT implantation. Echocardiography was also performed pre and 12 months post CRT implantation. A CRT response was defined as a ≥ 15 % reduction in LV end-systolic volume (LVESV). Results The study population consisted of 41 patients. The mean copeptin level was 20.50 ± 15.77 pmol/l. Copeptin levels positively correlated with New York Heart Association class, left atrial diameter, creatinine levels and NT-proBNP levels. CRT responders have significant reduction in copeptin levels from baseline to 12 months (from 16.96 ± 12.80 pmol/l to 6.20 ± 6.44 pmol/l, p &lt; 0.001). No significant changes in copeptin levels were observed in CRT nonresponders. Reduction &gt; 45 % in copeptin levels was predictor of CRT-response (OR 6.72, 95 % CI 1.01 - 18.11, p = 0.045). Conclusion The copeptin serum levels can be a useful biomarker in the evaluation of the CRT response.


2020 ◽  
Vol 26 (3) ◽  
pp. 5-14
Author(s):  
M. D. Utsumueva ◽  
N. A. Mironova ◽  
O. V. Stukalova ◽  
E. M. Gupalo ◽  
S. Yu. Kashtanova ◽  
...  

Introduction. As a significant number of patients with heart failure (HF) does not respond to cardiac resynchronization therapy (CRT), a lot of research has deservedly focused on optimization, and better patient selection. The ideal resynchronization depends on different factors, from device programming to heart features and left ventricle (LV) lead position. Analysis of the 12-lead electrocardiogram (ECG) is the most simple method which can provide important information on LV lead location, presence of scar at LV pacing site, and fusion of intrinsic activation or RV pacing with LV pacing.Purpose. To analyze the electrophysiological and structural heart features and their correlation with the ECG pattern during biventricular (BV) pacing in patients with HF and CRT devices.Methods. The study included 47 patients (mean age 62.3±8.9 years) with LBBB, QRS duration ≥ 130 ms, left ventricular ejection fraction (LVEF) ≤ 35%, heart failure (HF) NYHA II-IV despite optimal pharmacological therapy during months. All patients had undergone CRT-D implantation. Late-gadolinium enhancement-cardiovascular magnetic resonance (LGE-CMR), 12-lead ECG, non-invasive cardiac mapping (NICM) (with obtaining the zone of late LV activation (ZLA)) were undertaken prior to CRT devices implantation. NICM with cardiac CT and evaluation of LV lead position, ECG pattern during BV pacing (#1 - fusion complex with increased or dominant R wave, independent of QRS duration, #2- QS pattern with QRS duration normalization, and #3- QS pattern with increased QRS duration) were undertaken after CRT devices implantation. Response to CRT was estimated by echo and was defined as decrease in LV end-systolic volume by > 15% after 6 months of follow-up.Results. CRT was effective in 28 patients (59.5%). According to the results of NICM, zone of late LV activation more often was located at 5,6,11,12 segments, and LV pacing site - at 6,7,12 segments of LV. In the “response” group overlap of scar zone and zone of late LV activation was observed (p=0.005). The presence of scar tissue in the LV pacing site was associated with CRT non-response (p<0.001), and the pacing zone of late LV activation resulted in the best CRT response (p<0.001). The distance from the LV electrode to the zone of late LV activation was less in the “CRT response” group (33 [20;42] mm vs 83 [55;100] mm, p<0.001). The most beneficial ECG pattern during BV pacing was #2, and #3 was more often observed in the group “CRT non-response”; configuration #1 was intermediate between ECG patterns #2 and #3.Conclusions. A comprehensive examination, including the study of the structural and electrophysiological heart features is important for the optimal positioning the LV lead and subsequent CRT device programming. The simple analysis of the QRS pattern during BV pacing can show whether biventricular pacing is adequately performed and can reveal inadequate CRT programming and LV lead positioning.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Beata Zaborska ◽  
Ewa Pilichowska-Paszkiet ◽  
Ewa Makowska ◽  
Grażyna Sygitowicz ◽  
Tomasz Słomski ◽  
...  

AbstractRecently, associations between the biomarker galectin-3 and numerous pathological processes involved in heart failure (HF) and right ventricular (RV) function have been observed. We aimed to assess the long-term prognostic ability of galectin-3 and RV function parameters for all-cause mortality in HF patients treated with cardiac resynchronization therapy (CRT). We prospectively studied 63 symptomatic HF patients with a left ventricular (LV) ejection fraction (EF) ≤ 35%. The median serum galectin-3 concentration was 13.4 ng/mL (IQR 11.05, 17.15). A detailed assessment of LV and RV geometry and function was performed with echocardiography. CRT defibrillator implantation was achieved in all patients without major complications. The follow-up lasted 5 years. In the multivariable Cox regression model, independent predictors for all-cause mortality were log baseline galectin-3 and baseline RV function expressed as tricuspid annular plane systolic excursion with HR 2.96 (p = 0.037) and HR 0.88 (p = 0.023), respectively. Analysis of subgroups defined by galectin-3 concentration and CRT response showed that patients with high baseline galectin-3 concentrations and a lack of response to CRT had a significantly lower probability of survival. In our patient cohort, the baseline galectin-3 concentration and RV function were independent predictors of long-term all-cause mortality in HFrEF patients following CRT implantation.


2020 ◽  
Vol 103 (10) ◽  
pp. 1091-1098

Background: Despite contemporary restrictive clinical and electrocardiographic selection criteria, up to one-third of chronic heart failure patients with implanted cardiac resynchronization therapy (CRT) are non-responders. Previous studies reported that some electrocardiographic patterns, such as the longer the intrinsicoid deflection (ID) in lead I, the higher the R wave amplitude in V₆, and other patterns may be helpful for CRT response prediction. Objective: To establish a simplified model using electrocardiographic parameters as predictors of CRT response among chronic heart failure patients. Materials and Methods: Eighty chronic heart failure patients meeting the current guideline recommendation for CRT implantation were enrolled in the present retrospective cohort study. The patients’ clinical and electrocardiographic parameters at the time of CRT implantation and during follow-up were analyzed. The response to CRT was evaluated after six months of implantation, defined as a decrease in the left ventricular end systolic volume (LVESV) of 15% or more or an increase in the left ventricular ejection fraction (LVEF) of 10% or more. Results: During a median follow-up period of 34 months, there were 45 (56.3%) responders. In multivariate analysis, the independent predictors for CRT response were the greater the reduction of the QRS complex duration after implantation (QRS post – QRS pre), the higher the time to ID in the lead I/QRS ratio (ID I/QRS), and the higher the difference in the amplitude of the R and S waves in lead V₁ and V₆ [(S1+R6) – (S6+R1)] (QRS post – QRS pre: adjusted odds ratio [OR] 0.97, 95% CI 0.94 to 0.99, p=0.004; ID I/QRS: OR 18.65, 95% CI 1.02 to 342.64, p=0.049; (S1+R6) – (S6+R1): OR 1.1, 95% CI 1.04 to 1.17, p=0.002). The new equation for calculating the predictive CRT response model, generated from multiple logistic regression analysis, was –3.414 – 0.035(QRS post – QRS pre) + 2.926(ID I/QRS) + 0.097[(S1+R6) – (S6+R1)]. The area under the receiver operating characteristic (ROC) curve for the new model for predicting CRT response was 0.853 (95% CI 0.767 to 0.939). A model score of more than 0.3 showed a sensitivity of 85.7% and specificity of 80% for the prediction of CRT response. Conclusion: The new electrocardiographic model achieved a high sensitivity and specificity for the prediction of CRT response among chronic heart failure patients, who met the current guideline recommendation for CRT implantation. Keywords: Cardiac resynchronization therapy, Electrocardiography, Heart failure, Responders, Model


Sign in / Sign up

Export Citation Format

Share Document