scholarly journals Exploring sex-specific patterns of mortality predictors among patients undergoing cardiac resynchronization therapy: a machine learning approach

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
M Tokodi ◽  
A Behon ◽  
E.D Merkel ◽  
A Kovacs ◽  
Z Toser ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sex Differences ◽  
Cardiac Resynchronization Therapy ◽  
Cardiac Resynchronization ◽  
Funding Source ◽  
Resynchronization Therapy ◽  
Test Set ◽  
All Cause Mortality ◽  
Mortality Predictors

Abstract Background The relative importance of variables explaining sex differences in outcomes is scarcely explored in patients undergoing cardiac resynchronization therapy (CRT). Purpose We sought to implement and evaluate machine learning (ML) algorithms for the prediction of 1- and 3-year all-cause mortality in patients undergoing CRT implantation. We also aimed to assess the sex-specific differences and similarities in the predictors of mortality using ML approaches. Methods A retrospective registry of 2191 CRT patients (75% males) was used in the current analysis. ML models were implemented in 6 partially overlapping patient subsets (all patients, females or males with 1- or 3-year follow-up data available). Each cohort was randomly split into a training (80%) and a test set (20%). After hyperparameter tuning with 10-fold cross-validation in the training set, the best performing algorithm was also evaluated in the test set. Model discrimination was quantified using the area under the receiver-operating characteristic curves (AUC) and the associated 95% confidence intervals. The most important predictors were identified using the permutation feature importances method. Results Conditional inference random forest exhibited the best performance with AUCs of 0.728 [0.645–0.802] and 0.732 [0.681–0.784] for the prediction of 1- and 3-year mortality, respectively. Etiology of heart failure, NYHA class, left ventricular ejection fraction and QRS morphology had higher predictive power in females, whereas hemoglobin was less important than in males. The importance of atrial fibrillation and age increased, whereas the relevance of serum creatinine decreased from 1- to 3-year follow-up in both sexes. Conclusions Using advanced ML techniques in combination with easily obtainable clinical features, our models effectively predicted 1- and 3-year all-cause mortality in patients undergoing CRT implantation. The in-depth analysis of features has revealed marked sex differences in mortality predictors. These results support the use of ML-based approaches for the risk stratification of patients undergoing CRT implantation. Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): National Research, Development and Innovation Office of Hungary

scholarly journals Sex-Specific Patterns of Mortality Predictors Among Patients Undergoing Cardiac Resynchronization Therapy: A Machine Learning Approach

2021 ◽  
Vol 8 ◽  
Author(s):  
Márton Tokodi ◽  
Anett Behon ◽  
Eperke Dóra Merkel ◽  
Attila Kovács ◽  
Zoltán Tősér ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cardiac Resynchronization Therapy ◽  
Left Ventricular ◽  
Conditional Inference ◽  
Cardiac Resynchronization ◽  
Left Ventricular Ejection ◽  
Resynchronization Therapy ◽  
All Cause Mortality ◽  
Test Sets

Background: The relative importance of variables explaining sex-related differences in outcomes is scarcely explored in patients undergoing cardiac resynchronization therapy (CRT). We sought to implement and evaluate machine learning (ML) algorithms for the prediction of 1- and 3-year all-cause mortality in CRT patients. We also aimed to assess the sex-specific differences in predictors of mortality utilizing ML.Methods: Using a retrospective registry of 2,191 CRT patients, ML models were implemented in 6 partially overlapping patient subsets (all patients, females, or males with 1- or 3-year follow-up). Each cohort was randomly split into training (80%) and test sets (20%). After hyperparameter tuning in the training sets, the best performing algorithm was evaluated in the test sets. Model discrimination was quantified using the area under the receiver-operating characteristic curves (AUC). The most important predictors were identified using the permutation feature importances method.Results: Conditional inference random forest exhibited the best performance with AUCs of 0.728 (0.645–0.802) and 0.732 (0.681–0.784) for the prediction of 1- and 3-year mortality, respectively. Etiology of heart failure, NYHA class, left ventricular ejection fraction, and QRS morphology had higher predictive power, whereas hemoglobin was less important in females compared to males. The importance of atrial fibrillation and age increased, while the importance of serum creatinine decreased from 1- to 3-year follow-up in both sexes.Conclusions: Using ML techniques in combination with easily obtainable clinical features, our models effectively predicted 1- and 3-year all-cause mortality in CRT patients. Sex-specific patterns of predictors were identified, showing a dynamic variation over time.

Abstract 13242: Insulin Treated Patients With Diabetes Derive Reduction in Mortality From Cardiac Resynchronization Therapy - Results From the Madit-Crt in Trial Experience

Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Barbara Szepietowska ◽  
Valentina Kutyifa ◽  
Martin H Ruwald ◽  
Scott D Solomon ◽  
Anne-Christine H Ruwald ◽  
...  
Keyword(s):  
Cardiac Resynchronization Therapy ◽  
Risk Reduction ◽  
Insulin Treatment ◽  
Cardiac Resynchronization ◽  
Reverse Remodeling ◽  
Diabetic Patients ◽  
Resynchronization Therapy ◽  
All Cause Mortality ◽  
Patients With Diabetes

Methods: We aimed to analyze the risk for death and HF and the effect of CRT on HF/death in diabetic patients with or without insulin treatment compared to none diabetic population. The study comprised 1278 patients with left bundle branch block in the MADIT-CRT trial with an average follow-up of 3.3y. We used time dependent survival analysis and Cox proportional hazards regression method. Results: In ICD arm patients with diabetes receiving insulin treatment had 2.4-fold higher risk of all-cause mortality (p=0.008), and 2.2-fold higher risk of HF (p<0.001) when compared to non diabetic patients, and 2.8-fold higher risk of death (p=0.01), and 1.6-fold higher risk of HF (p=0.06) when compared to patients with diabetes not treated with insulin. Treatment with CRT-D was associated with a significant 75% risk reduction in all-cause mortality (hazard ratio [HR ] 0.25; 95% confidence interval [CI]: 0.08-0.77; p=0.016) in patients with diabetes receiving insulin. Noteworthy, during the 3-year follow-up, reduction in all-cause mortality was not observed in patients not treated with insulin or in patients with no diabetes (interaction p-value=0.038). Significant risk reduction in HF and in HF/death after CRT treatment was observed across all three investigated groups. There were not significant differences in left ventricular reverse remodeling after CRT-D among diabetic patients with or without insulin treatment compared to the nondiabetic population. Conclusions: Patients with insulin treated diabetes derive significant reduction in mortality and heart failure after implantation of cardiac resynchronization therapy. Patients with diabetes and no insulin and patient without diabetes benefit from CRT by reduction of HF events.

P3805Mortality predictors and outcome in patients after upgrade from implantable cardioverter-defibrillator to cardiac resynchronization therapy in comparison to CRT-D de novo implantation

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
E Jedrzejczyk-Patej ◽  
M Mazurek ◽  
W Kowalska ◽  
M Bugajski ◽  
A Konieczny-Kozielska ◽  
...  
Keyword(s):  
Infective Endocarditis ◽  
Cardiac Resynchronization Therapy ◽  
Implantable Cardioverter Defibrillator ◽  
De Novo ◽  
Left Ventricular ◽  
Cardiac Resynchronization ◽  
Resynchronization Therapy ◽  
Cardioverter Defibrillator ◽  
Mortality Predictors

Abstract Background Over a quarter of all cardiac resynchronization therapy (CRT) implants are upgrades from previous devices, mainly from implantable cardioverter-defibrillator (ICD). In comparison to CRT with defibrillator (CRT-D) de novo implantation, upgrade from ICD to CRT-D carries higher risk of complications. Limited number of studies evaluated predictors of death in patients undergoing upgrade from ICD to CRT-D. Aim To determine mortality predictors and outcome in patients undergoing upgrade from ICD to CRT-D in comparison to subjects with CRT-D de novo implantation. Methods Study population consisted of 595 consecutive patients with CRT-D implanted between 2002 and 2015 in tertiary care university hospital, in a densely inhabited, urban region of Poland (480 subjects [84.3%] with CRT-D de novo implantation; 115 patients [15.7%] upgraded from ICD to CRT-D). Results The median follow-up was 1692 days (range: 457–3067). All-cause mortality in patients upgraded from ICD was significantly higher than in subjects with CRT-D implanted de novo (43.5% vs. 35.5%, P=0.045). On multivariable regression analysis, left ventricular end-systolic diameter (HR 1.07, 95% CI 1.02–1.11, P=0.002), creatinine level at baseline (HR 1.01, 95% CI 1.00–1.02, P=0.01), NYHA IV class at baseline (HR 2.36, 95% CI 1.00–5.53, P=0.049) and cardiac device-related infective endocarditis (CDRIE) during follow up (HR 2.42, 95% CI 1.02–5.75, P=0.046) were identified as independent predictors of higher mortality in patients with CRT-D upgraded from ICD. Conclusions Mortality rate in patients upgraded from ICD is higher in comparison to CRT-D de novo implanted subjects, and reaches almost 45% within 4.5 years. Left ventricular dimensions, creatinine level, high NYHA class at baseline and infective endocarditis during follow up are independent mortality predictors in patients with CRT-D upgraded from ICD.

scholarly journals Machine learning-based mortality prediction of patients undergoing cardiac resynchronization therapy: the SEMMELWEIS-CRT score

2020 ◽  
Vol 41 (18) ◽  
pp. 1747-1756 ◽  
Author(s):  
Márton Tokodi ◽  
Walter Richard Schwertner ◽  
Attila Kovács ◽  
Zoltán Tősér ◽  
Levente Staub ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cardiac Resynchronization Therapy ◽  
Mortality Prediction ◽  
Cardiac Resynchronization ◽  
Risk Scores ◽  
Resynchronization Therapy ◽  
Discriminative Ability ◽  
All Cause Mortality ◽  
Estimated Risk ◽  
Stratification System

Abstract Aims Our aim was to develop a machine learning (ML)-based risk stratification system to predict 1-, 2-, 3-, 4-, and 5-year all-cause mortality from pre-implant parameters of patients undergoing cardiac resynchronization therapy (CRT). Methods and results Multiple ML models were trained on a retrospective database of 1510 patients undergoing CRT implantation to predict 1- to 5-year all-cause mortality. Thirty-three pre-implant clinical features were selected to train the models. The best performing model [SEMMELWEIS-CRT score (perSonalizEd assessMent of estiMatEd risk of mortaLity With machinE learnIng in patientS undergoing CRT implantation)], along with pre-existing scores (Seattle Heart Failure Model, VALID-CRT, EAARN, ScREEN, and CRT-score), was tested on an independent cohort of 158 patients. There were 805 (53%) deaths in the training cohort and 80 (51%) deaths in the test cohort during the 5-year follow-up period. Among the trained classifiers, random forest demonstrated the best performance. For the prediction of 1-, 2-, 3-, 4-, and 5-year mortality, the areas under the receiver operating characteristic curves of the SEMMELWEIS-CRT score were 0.768 (95% CI: 0.674–0.861; P &lt; 0.001), 0.793 (95% CI: 0.718–0.867; P &lt; 0.001), 0.785 (95% CI: 0.711–0.859; P &lt; 0.001), 0.776 (95% CI: 0.703–0.849; P &lt; 0.001), and 0.803 (95% CI: 0.733–0.872; P &lt; 0.001), respectively. The discriminative ability of our model was superior to other evaluated scores. Conclusion The SEMMELWEIS-CRT score (available at semmelweiscrtscore.com) exhibited good discriminative capabilities for the prediction of all-cause death in CRT patients and outperformed the already existing risk scores. By capturing the non-linear association of predictors, the utilization of ML approaches may facilitate optimal candidate selection and prognostication of patients undergoing CRT implantation.

scholarly journals Cardiac changes after cardiac resynchronization therapy assessed using cardiac magnetic resonance imaging during biventricular pacing

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
C Czimbalmos ◽  
R Papp ◽  
L Szabo ◽  
A Toth ◽  
I Csecs ◽  
...  
Keyword(s):  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Cardiac Resynchronization Therapy ◽  
Biventricular Pacing ◽  
Radial Strain ◽  
Cardiac Resynchronization ◽  
Funding Source ◽  
Resynchronization Therapy ◽  
Left And Right

Abstract   Cardiac magnetic resonance (CMR) is a valuable tool in the assessment of left and right ventricular volumes and functions therefore establishing the effect of cardiac resynchronization therapy (CRT), but in majority of the devices MR safe mode does not include biventricular pacing as an option. We aimed to assess the effect of cardiac resynchronization using CMR with resynchronization on. NYHA class II-III patients with LVEF≤35% despite optimal medical therapy and complete LBBB with broad QRS (&gt;150 ms) were prospectively recruited (n=16, 65±7 years, 56% male, 69% nonischaemic). CMR examination was performed at baseline and at 6-month follow-up, applying both biventricular and AOO pacing. The following data were measured: conventional CMR parameters including left and right ventricular ejection fraction (LVEF), end-diastolic index (LVEDVi) and end-systolic volume index (LVESVi), stroke volume and mass, remodelling indices such as 3D sphericity and relative wall thickness (RWT: 2x end-diastolic wall thickness /end-diastolic long-axis diameter). Using feature tracking analysis global longitudinal, circumferential, radial strain, global dyssynchrony (mechanical dispersion (MD)) and regional dyssynchrony was measured. Comparing the baseline and follow-up CMR parameters measured during biventricular pacing, we found a significant increase in LVEF (27±7 vs 45±9%; p&lt;0.001) and decrease in LVEDVi and LVESVi (LVEDVi: 149±28 vs 91±20ml/m2; LVESVi: 108±31 vs 51±17ml/m2; p&lt;0.001). Based on decrease in LVESVi 14 patients were classified as super-responder (&gt;30%), one responder (&gt;15%) and one non-responder (&lt;15%). ProBNP levels significantly decreased (1186±83 vs 323±271 pg/ml, p&lt;0.05). LV remodelling indices (3D sphericity: 0.46±0.13 vs 0.61±0.11, RWT: 0.33±0.07 vs 0.43±0.10), global longitudinal, circumferential and radial strain values showed significant improvement. Circumferential MD decreased (18.3±6.7 vs 13.3±3.4, p&lt;0.01), while longitudinal MD did not change. Regional dyssynchrony drastically improved (358±108 vs 98±61ms, p&lt;0.001). Applying AOO pacing resulted in an immediate deterioration in LVEF (45±9 vs 38±9%), LVESVi (51±17 vs 58±19 ml/m2), global circumferential and radial strain and regional dyssynchrony. In conclusion CMR imaging during biventricular pacing is feasible and enables a more precise quantification of LV function, morphology and mechanics. As a result, it may contribute to a better understanding of the effects of resynchronization therapy and might improve responder rate in the future. Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): National Research, Development and Innovation Office of Hungary (NKFIA)

scholarly journals Optimized Implementation of cardiac resynchronization therapy – a call for action for referral and optimization of care

EP Europace ◽  
2021 ◽  
Author(s):  
Wilfried Mullens ◽  
Angelo Auricchio ◽  
Pieter Martens ◽  
Klaus Witte ◽  
Martin R Cowie ◽  
...  
Keyword(s):  
Cardiac Resynchronization Therapy ◽  
Care Pathway ◽  
Cardiac Resynchronization ◽  
Resynchronization Therapy ◽  
Reduced Ejection Fraction ◽  
Hospitalization Rates ◽  
All Cause Mortality ◽  
Post Implantation

Abstract Cardiac resynchronization therapy (CRT) is one of the most effective therapies for heart failure with reduced ejection fraction and leads to improved quality of life, reductions in heartfailure hospitalization rates and reduces all-cause mortality. Nevertheless, up to two-thirds ofeligible patients are not referred for CRT. Furthermore, post implantation follow-up is oftenfragmented and suboptimal, hampering the potential maximal treatment effect. This jointposition statement from three ESC Associations, HFA, EHRA and EACVI focuses onoptimized implementation of CRT. We offer theoretical and practical strategies to achievemore comprehensive CRT referral and post-procedural care by focusing on four actionabledomains; (I) overcoming CRT under-utilization, (II) better understanding of pre-implantcharacteristics, (III) abandoning the term ‘non-response’ and replacing this by the concept ofdisease modification, and (IV) implementing a dedicated post-implant CRT care pathway.

Abstract 13267: Age-Related Long-Term Benefit of Cardiac Resynchronization Therapy in LBBB Patients - a MADIT-CRT Long-Term Follow-Up Substudy

Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Sabu Thomas ◽  
Arthur J Moss ◽  
Wojciech Zareba ◽  
Scott McNitt ◽  
Alon Barsheshet ◽  
...  
Keyword(s):  
Heart Failure ◽  
Cardiac Resynchronization Therapy ◽  
Age Groups ◽  
Cardiac Resynchronization ◽  
Age Group ◽  
Resynchronization Therapy ◽  
All Cause Mortality ◽  
Long Term Follow Up

Background: Among patients with heart failure (HF), cardiac resynchronization therapy (CRT) combined with a defibrillator (CRT-D) reduces HF events and mortality compared with a defibrillator (ICD) alone. Whether these benefits extend to all age-groups during long-term follow-up is unclear. Hypothesis: We hypothesized that CRT-D would benefit all age groups with respect to reductions in HF events and all-cause mortality. Methods: We assessed the effect of age on HF events and death among patients in the MADIT-CRT long-term follow up study. 1281 patients with class I or II heart failure and left-bundle branch block (LBBB) were randomized to CRT-D or ICD alone. Patients were divided into 3 age groups: <60, 60-74 or ≥75 years and evaluated over 7 years for mortality and HF events. We compared cumulative events using the log-rank test and adjustments were made using a multivariate logistic regression model with various pre-specified covariates. Results: Overall 761 patients received CRT-D and 520 received ICD alone. The median age was 65 years. Among the three age groups, <60, 60-74 and ≥75 there were 399, 651 and 231 patients respectively. Multivariate analysis (Table) revealed that CRT-D compared to ICD alone significantly reduced the composite outcome of HF or death across all age groups: <60 years relative risk reduction (RRR)=39%, p=0.0236; 60-74 years RRR=59%, p<0.001; ≥75 years RRR=55%, p<0.001. CRT-D also significantly reduced HF events in all age groups <60 years RRR=52%, p=0.003; 60-74 years RRR=61%, p<0.001; ≥75 years RRR=73%, p<0.001. CRT-D was associated with significant mortality reduction only in the 60-74 year age group RRR 58%, p<0.001. Conclusion: Among patients with asymptomatic or mild heart failure, reduced LVEF and LBBB, CRT-D results in significant reduction of HF events and in the composite of all-cause mortality and HF events during long-term follow-up. All-cause mortality was significantly reduced with CRT-D only in the 60-74 year age group.

scholarly journals Impact of Depressive Symptoms on All-Cause Mortality in Patients with Congestive Heart Failure After Cardiac Resynchronization Therapy

Kardiologiia ◽  
2019 ◽  
Vol 59 (1) ◽  
pp. 5-11 ◽  
Author(s):  
G. S. Pushkarev ◽  
V. A. Kuznetsov ◽  
Y. A. Fisher ◽  
A. M. Soldatova ◽  
А. D. Sapozhnikova ◽  
...  
Keyword(s):  
Heart Failure ◽  
Congestive Heart Failure ◽  
Depressive Symptoms ◽  
Cardiac Resynchronization Therapy ◽  
Beck Depression Inventory ◽  
Cox Proportional Hazards ◽  
Cardiac Resynchronization ◽  
Resynchronization Therapy ◽  
All Cause Mortality

Purpose:to assess the association between depression and all-cause mortality in patients with congestive heart failure (CHF) after cardiac resynchronization therapy (CRT).Materials and Methods.We enrolled in this study 156 patients (mean age 55.3±9.6 years) with CHF and implanted devices for CRT. Mean duration of follow-up was 51.6±33.4 months. The Beck Depression Inventory (BDI) was used to evaluate depressive symptoms (DS); DS were considered absent for a score 0–9, mild to moderate – 10–18, severe – ≥19. For assessment of association of DS and mortality we used multivariate Cox proportional hazards regression model with estimation of hazard ratios (HR) with 95 % confidence intervals (95 %CI).Results. Average Beck Depression Inventory score was 12.4±8.3. In 66 patients (42.3 %) there were no DS, 57 patients (36.5 %) had mild, and 33 (21.2 %) – severe DS. These groups did not differ by main clinical-functional and laboratory indicators. Among individuals without DS prevailed men (90.9 vs. 69.7 % among those with severe DS, p=0.007). Hypercholesterolemia was more frequent in patients with DS (63.3 vs. 43.9 % in patients without DS, p=0.02). During follow-up 33 patients died (21.2 %). Adjusted HR of death from all-causes for DS score as continuous parameter was 1.05, 95 % CI 1.01–1.09, p=0.02. Patients without DS were used as reference (HR=1.0) in analysis of categorical indicator. HR was 1.08, 95 % CI 0.46–2.54, p=0.9 in patients with mild, and 2.92, 95 % CI 1.17–7.32, p=0.02 – with severe DS.Conclusion:DS were associated with gender and hypercholesterolemia. Severe DS were independently associated with all-cause mortality in patients with CHF and implanted CRT devices.

Fragmented QRS, a predictor of clinical events in patients on cardiac resynchronization therapy

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
J Martinez Milla ◽  
C Garcia-Talavera ◽  
B Arroyo ◽  
A Camblor ◽  
A Garcia-Ropero ◽  
...  
Keyword(s):  
Cardiac Resynchronization Therapy ◽  
Cardiovascular Events ◽  
Hospital Admissions ◽  
Multivariate Logistic Regression Analysis ◽  
Cardiac Resynchronization ◽  
Resynchronization Therapy ◽  
Coronary Syndrome ◽  
Clinical Events ◽  
Increased Risk

Abstract Introduction Cardiac resynchronization therapy with defrilator (CRT-D) has been shown to reduce mortality in HFrEF. The width and morphology of the QRS are essential when deciding on the implantation of these devices. QRS fragmentation (fQRS) has been shown to be a good predictor of cardiovascular events in certain patients, but its role in patients with CRT-D has not been studied. The aim of this study is to determine whether the presence of a fQRS at the time of CRT-D implantation can predict clinical events. Methods All patients who underwent CRT-D implantation from 2010 to 2017 were included. Patients' ECG were evaluated at the time of implantation, and the incidence of clinical events during follow-up was also assessed. fQRS was defined as the presence of an RSR' pattern with a notch in the R wave or in the ascending or descending branch of the S wave in two continuous leads on the ECG. Results We studied 131 patients (mean age 73 years, 76.5% male). The mean follow-up period was 37±26 months. No difference in baseline characteristics was found (Table 1); the proportion of fQRS was 48.9%. 25 patients (19.1%) had hospital admissions secondary to cardiovascular causes (heart failure, arrhythmic events, acute coronary syndrome, and death from other causes). We performed a multivariate logistic regression analysis aiming at an association between the presence of fQRS and the increased risk of hospital admissions due to cardiovascular causes OR 2.92 (95% CI: 1.04–8.21, P=0.04). Conclusion The presence of a fQRS at the time of implantation of a CRT-D is an independent predictor of hospital admissions due to cardiovascular causes. Therefore this could be a useful marker to identify the population at high risk of cardiovascular events, for this we consider necessary to conduct future studies and thus assess the value of the fQRS for the selection of patients requiring closer monitoring thus avoiding further hospital admissions. Funding Acknowledgement Type of funding source: None

Sign in / Sign up

Export Citation Format

Share Document