Machine learning-based prediction of 1-year all-cause mortality in patients undergoing CRT implantation: validation of the SEMMELWEIS-CRT score in the European CRT Survey I dataset.

Aims: We aimed to externally validate the SEMMELWEIS-CRT score for predicting 1-year all-cause mortality in the European Cardiac Resynchronization Therapy (CRT) Survey I dataset-a large multi-centre cohort of patients undergoing CRT implantation. Methods and results: The SEMMELWEIS-CRT score is a machine learning-based tool trained for predicting all-cause mortality in patients undergoing CRT implantation. This tool demonstrated impressive performance during internal validation but has not yet been validated externally. To this end, we applied it to the data of 1367 patients from the European CRT Survey I dataset. The SEMMELWEIS-CRT predicted 1-year mortality with an area under the receiver operating characteristic curve (AUC) of 0.729 (0.682-0.776), which concurred with the performance measured during internal validation [AUC: 0.768 (0.674-0.861), P = 0.466]. Moreover, the SEMMELWEIS-CRT score outperformed multiple conventional statistics-based risk scores, and we demonstrated that a higher predicted probability is not only associated with a higher risk of death [odds ratio (OR): 1.081 (1.061-1.101), P < 0.001] but also with an increased risk of hospitalizations for any cause [OR: 1.013 (1.002-1.025), P = 0.020] or for heart failure [OR: 1.033 (1.015-1.052), P < 0.001], a less than 5% improvement in left ventricular ejection fraction [OR: 1.033 (1.021-1.047), P < 0.001], and lack of improvement in New York Heart Association functional class compared with baseline [OR: 1.018 (1.006-1.029), P = 0.003]. Conclusion: In the European CRT Survey I dataset, the SEMMELWEIS-CRT score predicted 1-year all-cause mortality with good discriminatory power, which confirms the generalizability and demonstrates the potential clinical utility of this machine learning-based risk stratification tool.

The prevalence of frailty and its effect on the outcome in cardiac resynchronization therapy patients.

Frailty is a complex clinical syndrome associated with aging and comorbidities, which correlates with unfavorable outcomes. However, in heart failure patients, frailty is very common, data is scarce about those, who are eligible for Cardiac Resynchronization Therapy (CRT) implantation. We investigated the incidence of frailty and the association of Frailty Index (FI) with the outcome. Thirty baseline clinical parameters were used by the Rockwood cumulative deficit method to determine patients' FI in our single-center cohort. Based on previous studies, patients with FI ≤ 0.210 were considered as non-frail, those with FI 0.10-0.210 were classified in Frail-1, with FI > 0.10 in Frail-2 groups, respectively. Echocardiographic response after 12 months and all-cause mortality were investigated by frailty groups. Among 1004 included patients, 75 (7%) were considered Non-frail, 271 (27%) grouped in Frail-1, and 658 (66%) in Frail-2 with a median FI of 0.36 (0.28-0.43). Patients in Frail-2 group were older, with more comorbidities compared with non-frail patients or those in Group Frail-1. During the median follow-up time of 4.8 years, 29 (39%) patients died in the Non-frail, 140 (52%) in Frail-1, and 471 (72%) in the Frail-2 groups (log-rank p < 0.001). Group Frail-2 showed an unfavorable outcome compared to the non-frail (HR 2.49, 95%CI 1.92-3.22; p < 0.001) and the Frail-1 group (1.83, 95%CI 1.55-2.16; p < 0.001). In our HFrEF patients eligible for CRT implantation, patients were exceedingly vulnerable with a high prevalence of frailty. The calculated frailty index was associated with outcome and proved to be prevalent in individual risk stratification.

Phenogrouping and risk stratification of patients undergoing cardiac resynchronization therapy upgrade using topological data analysis.

Choosing the optimal device during cardiac resynchronization therapy (CRT) upgrade can be challenging. Therefore, we sought to provide a solution for identifying patients in whom upgrading to a CRT-defibrillator (CRT-D) is associated with better long-term survival than upgrading to a CRT-pacemaker (CRT-P). To this end, we first applied topological data analysis to create a patient similarity network using 16 clinical features of 326 patients without prior ventricular arrhythmias who underwent CRT upgrade. Then, in the generated circular network, we delineated three phenogroups exhibiting significant differences in clinical characteristics and risk of all-cause mortality. Importantly, only in the high-risk phenogroup was upgrading to a CRT-D associated with better survival than upgrading to a CRT-P (hazard ratio: 0.454 (0.228-0.907), p = 0.025). Finally, we assigned each patient to one of the three phenogroups based on their location in the network and used this labeled data to train multi-class classifiers to enable the risk stratification of new patients. During internal validation, an ensemble of 5 multi-layer perceptrons exhibited the best performance with a balanced accuracy of 0.898 (0.854-0.942) and a micro-averaged area under the receiver operating characteristic curve of 0.983 (0.980-0.986). To allow further validation, we made the proposed model publicly available ( https://github.com/tokmarton/crt-upgrade-risk-stratification ).

Topological data analysis to identify cardiac resynchronization therapy patients exhibiting benefit from an implantable cardioverter-defibrillator.

BACKGROUND: Current guidelines recommend considering multiple factors while deciding between cardiac resynchronization therapy with a defibrillator (CRT-D) or a pacemaker (CRT-P). Nevertheless, it is still challenging to pinpoint those candidates who will benefit from choosing a CRT-D device in terms of survival. OBJECTIVE: We aimed to use topological data analysis (TDA) to identify phenogroups of CRT patients in whom CRT-D is associated with better survival than CRT-P. METHODS: We included 2603 patients who underwent CRT-D (54%) or CRT-P (46%) implantation at Semmelweis University between 2000 and 2018. The primary endpoint was all-cause mortality. We applied TDA to create a patient similarity network using 25 clinical features. Then, we identified multiple phenogroups in the generated network and compared the groups' clinical characteristics and survival. RESULTS: Five- and 10-year mortality were 43 (40-46)% and 71 (67-74)% in patients with CRT-D and 48 (45-50)% and 71 (68-74)% in those with CRT-P, respectively. TDA created a circular network in which we could delineate five phenogroups showing distinct patterns of clinical characteristics and outcomes. Three phenogroups (1, 2, and 3) included almost exclusively patients with non-ischemic etiology, whereas the other two phenogroups (4 and 5) predominantly comprised ischemic patients. Interestingly, only in phenogroups 2 and 5 were CRT-D associated with better survival than CRT-P (adjusted hazard ratio 0.61 [0.47-0.80], p < 0.001 and adjusted hazard ratio 0.84 [0.71-0.99], p = 0.033, respectively). CONCLUSIONS: By simultaneously evaluating various clinical features, TDA may identify patients with either ischemic or non-ischemic etiology who will most likely benefit from the implantation of a CRT-D instead of a CRT-P. Topological data analysis to identify phenogroups of CRT patients in whom CRT-D is associated with better survival than CRT-P. AF atrial fibrillation, CRT cardiac resynchronization therapy, CRT-D cardiac resynchronization therapy defibrillator, CRT-P cardiac resynchronization therapy pacemaker, DM diabetes mellitus, HTN hypertension, LBBB left bundle branch block, LVEF left ventricular ejection fraction, MDS multidimensional scaling, MRA mineralocorticoid receptor antagonist, NYHA New York Heart Association.

Long-term outcome of cardiac resynchronization therapy patients in the elderly.

Heart failure (HF) is a leading cause of mortality and hospitalization in the elderly. However, data are scarce about their response to device treatment such as cardiac resynchronization therapy (CRT). We aimed to evaluate the age-related differences in the effectiveness of CRT, procedure-related complications, and long-term outcome. Between 2000 and 2020, 2656 patients undergoing CRT implantation were registered and analyzed retrospectively. Patients were divided into 3 groups according to their age: group I, < 65; group II, 65-75; and group III, > 75 years. The primary endpoint was the echocardiographic response defined as a relative increase > 15% in left ventricular ejection fraction (LVEF) within 6 months, and the secondary endpoint was the composite of all-cause mortality, heart transplantation, or left ventricular assist device implantation. Procedure-related complications were also assessed. After implantation, LVEF showed significant improvement both in the total cohort [28% (IQR 24/33) vs. 35% (IQR 28/40); p < 0.01)] and in each subgroup (27% vs. 34%; p < 0.01, 29% vs. 35%; p < 0.01, 30% vs. 35%; p < 0.01). Response rate was similar in the 3 groups (64% vs. 62% vs. 56%; p = 0.41). During the follow-up, 1574 (59%) patients died. Kaplan-Meier curves revealed a significantly lower survival rate in the older groups (log-rank p < 0.001). The cumulative complication rates were similar among the three age groups (27% vs. 28% vs. 24%; p = 0.15). Our results demonstrate that CRT is as effective and safe therapy in the elderly as for young ones. The present data suggest that patients with appropriate indications benefit from CRT in the long term, regardless of age.

Baseline clinical characteristics of heart failure patients with reduced ejection fraction enrolled in the BUDAPEST-CRT Upgrade trial.

AIMS: The BUDAPEST-CRT Upgrade study is the first prospective, randomized, multicentre clinical trial investigating the outcomes after cardiac resynchronization therapy (CRT) upgrade in heart failure (HF) patients with intermittent or permanent right ventricular (RV) pacing with wide paced QRS. This report describes the baseline clinical characteristics of the enrolled patients and compares them to cohorts from previous milestone CRT studies. METHODS AND RESULTS: This international multicentre randomized controlled trial investigates 360 patients having a pacemaker (PM) or implantable cardioverter defibrillator (ICD) device for at least 6 months prior to enrolment, reduced left ventricular ejection fraction (LVEF ≤35%), HF symptoms (New York Heart Association [NYHA] functional class II-IVa), wide paced QRS (>150 ms), and ≥20% of RV pacing burden without having a native left bundle branch block. At enrolment, the mean age of the patients was 73 ± 8 years; 89% were male, 97% were in NYHA class II/III functional class, and 56% had atrial fibrillation. Enrolled patients predominantly had conventional PM devices, with a mean RV pacing burden of 86%. Thus, this is a patient cohort with advanced HF, low baseline LVEF (25 ± 7%), high N-terminal pro-B-type natriuretic peptide (NT-proBNP) levels (2231 pg/ml [25th-75th percentile 1254-4309 pg/ml]), and frequent HF hospitalizations during the preceding 12 months (50%). CONCLUSION: When compared with prior CRT trial cohorts, the BUDAPEST-CRT Upgrade study includes older patients with a strong male predominance and a high burden of atrial fibrillation and other comorbidities. Moreover, this cohort represents an advanced HF population with low LVEF, high NT-proBNP, and frequent previous HF events. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov NCT02270840.

Effect of single ventricular premature contractions on response to cardiac resynchronization therapy.

BACKGROUND: We lack data on the effect of single premature ventricular contractions (PVCs) on the clinical and echocardiographic response after cardiac resynchronization therapy (CRT) device implantation. We aimed to assess the predictive value of PVCs at early, 1 month-follow up on echocardiographic response and all-cause mortality. METHODS: In our prospective, single-center study, 125 heart failure patients underwent CRT implantation based on the current guidelines. Echocardiographic reverse remodeling was defined as a ≥ 15% improvement in left ventricular ejection fraction (LVEF), end-systolic volume (LVESV), or left atrial volume (LAV) measured 6 months after CRT implantation. All-cause mortality was investigated by Wilcoxon analysis. RESULTS: The median number of PVCs was 11,401 in those 67 patients who attended the 1-month follow-up. Regarding echocardiographic endpoints, patients with less PVCs develop significantly larger LAV reverse remodeling compared to those with high number of PVCs. During the mean follow-up time of 2.1 years, 26 (21%) patients died. Patients with a higher number of PVCs than our median cut-off value showed a higher risk of early all-cause mortality (HR 0.97; 95% CI 0.38-2.48; P = 0.04). However, when patients were followed up to 9 years, its significance diminished (HR 0.78; 95% CI 0.42-1.46; P = 0.15). CONCLUSIONS: In patients undergoing CRT implantation, lower number of PVCs predicted atrial remodeling and showed a trend for a better mortality outcome. Our results suggest the importance of the early assessment of PVCs in cardiac resynchronization therapy and warrant further investigations.

The Prognostic Value of Anemia in Patients with Preserved, Mildly Reduced and Recovered Ejection Fraction.

Data on the relevance of anemia in heart failure (HF) patients with an ejection fraction (EF) > 40% by subgroup-preserved (HFpEF), mildly reduced (HFmrEF) and the newly defined recovered EF (HFrecEF)-are scarce. Patients with HF symptoms, elevated NT-proBNP, EF ≥ 40% and structural abnormalities were registered in the HFpEF-HFmrEF database. We described the outcome of our HFpEF-HFmrEF cohort by the presence of anemia. Additionally, HFrecEF patients were also selected from HFrEF patients who underwent resynchronization and, as responders, reached 40% EF. Using propensity score matching (PSM), 75 pairs from the HFpEF-HFmrEF and HFrecEF groups were matched by their clinical features. After PMS, we compared the survival of the HFpEF-HFmrEF and HFrecEF groups. Log-rank, uni-and multivariate regression analyses were performed. From 375 HFpEF-HFmrEF patients, 42 (11%) died during the median follow-up time of 1.4 years. Anemia (HR 2.77; 95%CI 1.47-5.23; p < 0.01) was one of the strongest mortality predictors, which was also confirmed by the multivariate analysis (aHR 2.33; 95%CI 1.21-4.52; p = 0.01). Through PSM, the outcomes for HFpEF-HFmrEF and HFrecEF patients with anemia were poor, exhibiting no significant difference. In HFpEF-HFmrEF, anemia was an independent mortality predictor. Its presence multiplied the mortality risk in those with EF ≥ 40%, regardless of HF etiology.

Long-term survival following upgrade compared with de novo cardiac resynchronization therapy implantation: a single-centre, high-volume experience.

AIMS: Patients with a pacemaker or implantable cardioverter-defibrillator are often considered for cardiac resynchronization therapy (CRT). However, limited comprehensive data are available regarding their long-term outcomes. METHODS AND RESULTS: Our retrospective registry included 2524 patients [1977 (78%) de novo, 547 (22%) upgrade patients] with mild to severe symptoms, left ventricular ejection fraction ≤35%, and QRS ≥ 130ms. The primary outcome was the composite of all-cause mortality, heart transplantation (HTX), or left ventricular assist device (LVAD) implantation; secondary endpoints were death from any cause and post-procedural complications. In our cohort, upgrade patients were older [71 (65-77) vs. 67 (59-73) years; P < 0.001], were less frequently females (20% vs. 27%; P = 0.002) and had more comorbidities than de novo patients. During the median follow-up time of 3.7 years, 1091 (55%) de novo and 342 (63%) upgrade patients reached the primary endpoint. In univariable analysis, upgrade patients exhibited a higher risk of mortality/HTX/LVAD than the de novo group [hazard ratio (HR): 1.41; 95% confidence interval (CI): 1.23-1.61; P < 0.001]. However, this difference disappeared after adjusting for covariates (adjusted HR: 1.12; 95% CI: 0.86-1.48; P = 0.402), or propensity score matching (propensity score-matched HR: 1.10; 95% CI: 0.95-1.29; P = 0.215). From device-related complications, lead dysfunction (3.1% vs. 1%; P < 0.001) and pocket infections (3.7% vs. 1.8%; P = 0.014) were more frequent in the upgrade group compared to de novo patients. CONCLUSION: In our retrospective analysis, upgrade patients had a higher risk of all-cause mortality than de novo patients, which might be attributable to their more significant comorbidity burden. The occurrence of lead dysfunction and pocket infections was more frequent in the upgrade group.

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

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.

Lateral left ventricular lead position is superior to posterior position in long-term outcome of patients who underwent cardiac resynchronization therapy.

AIMS: Preferring side branch of coronary sinus during cardiac resynchronization therapy (CRT) implantation has been empirical due to the limited data on the association of left ventricular (LV) lead position and long-term clinical outcome. We evaluated the long-term all-cause mortality by LV lead non-apical positions and further characterized them by interlead electrical delay (IED). METHODS AND RESULTS: In our retrospective database, 2087 patients who underwent CRT implantation were registered between 2000 and 2018. Those with non-apical LV lead locations were classified into anterior (n = 108), posterior (n = 643), and lateral (n = 1336) groups. All-cause mortality was assessed by Kaplan-Meier and Cox analyses. Echocardiographic response was measured 6 months after CRT implantation. During the median follow-up time of 3.7 years, 1150 (55.1%) patients died-710 (53.1%) with lateral, 78 (72.2%) with anterior, and 362 (56.3%) with posterior positions. When we investigated the risk of all-cause mortality, there was a significantly lower rate of death in patients with lateral LV lead location when compared with those with an anterior (P < 0.01) or posterior (P < 0.01) position. Multivariate analysis after adjustment for relevant clinical covariates such as age, sex, ischaemic aetiology, left bundle branch block morphology, atrial fibrillation, and device type revealed consistent results that lateral position is associated with a significant risk reduction of all-cause mortality when compared with anterior [hazard ratio 0.69; 95% confidence interval (CI) 0.55-0.87; P < 0.01] or posterior (hazard ratio 0.84; 95% CI 0.74-0.96; P < 0.01) position. When echocardiographic response was evaluated within the lateral group, patients with an IED longer than 110 ms (area under the receiver operating characteristic curve, 0.63; 95% CI 0.53-0.73; P = 0.012) showed 2.1 times higher odds of improvement in echocardiographic response 6 months after the implantation. CONCLUSIONS: In this study, we proved in a real-world patient population that after CRT implantation, lateral LV lead location was associated with long-term mortality benefit and is superior to both anterior and posterior positions. Moreover, patients with this position showed the greatest echocardiographic response over 110 ms IED.

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

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 < 0.001), 0.793 (95% CI: 0.718-0.867; P < 0.001), 0.785 (95% CI: 0.711-0.859; P < 0.001), 0.776 (95% CI: 0.703-0.849; P < 0.001), and 0.803 (95% CI: 0.733-0.872; P < 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.

De novo implantation vs. upgrade cardiac resynchronization therapy: a systematic review and meta-analysis.

Patients with conventional pacemakers or implanted defibrillators are often considered for cardiac resynchronization therapy (CRT). Our aim was to summarize the available evidences regarding the clinical benefits of upgrade procedures. A systematic literature search was performed from studies published between 2006 and 2017 in order to compare the outcome of CRT upgrade vs. de novo implantations. Outcome data on all-cause mortality, heart failure events, New York Heart Association (NYHA) Class, QRS narrowing and echocardiographic parameters were analysed. A total of 16 reports were analysed comprising 489,568 CRT recipients, of whom 468,205 patients underwent de novo and 21,363 upgrade procedures. All-cause mortality was similar after CRT upgrade compared to de novo implantations (RR 1.19, 95% CI 0.88-1.60, p = 0.27). The risk of heart failure was also similar in both groups (RR 0.96, 95% CI 0.70-1.32, p = 0.81). There was no significant difference in clinical response after CRT upgrade compared to de novo implantations in terms of improvement in left ventricular ejection fraction (ΔEF de novo - 6.85% vs. upgrade - 9.35%; p = 0.235), NYHA class (ΔNYHA de novo - 0.74 vs. upgrade - 0.70; p = 0.737) and QRS narrowing (ΔQRS de novo - 9.6 ms vs. upgrade - 29.5 ms; p = 0.485). Our systematic review and meta-analysis of currently available studies reports that CRT upgrade is associated with similar risk for all-cause mortality compared to de novo resynchronization therapy. Benefits on reverse remodelling and functional capacity improved similarly in both groups suggesting that CRT upgrade may be safely and effectively offered in routine practice. CLINICAL TRIAL REGISTRATION: Prospero Database-CRD42016043747.