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

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 < 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.

Download Full-text

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

European Heart Journal ◽

10.1093/ehjci/ehaa946.0996 ◽

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

Download Full-text

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

Frontiers in Cardiovascular Medicine ◽

10.3389/fcvm.2021.611055 ◽

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.

Download Full-text

5107Survival prediction in patients undergoing cardiac resynchronization therapy: a machine learning based risk stratification system

European Heart Journal ◽

10.1093/eurheartj/ehz746.0043 ◽

2019 ◽

Vol 40 (Supplement_1) ◽

Author(s):

M Tokodi ◽

Z Toser ◽

A M Boros ◽

W Schwertner ◽

A Kovacs ◽

...

Keyword(s):

Machine Learning ◽

Heart Failure ◽

Risk Stratification ◽

Cardiac Resynchronization Therapy ◽

Cardiac Resynchronization ◽

Resynchronization Therapy ◽

Training Cohort ◽

Non Linear ◽

Stratification System ◽

Risk Stratification System

Abstract Background Cardiac Resynchronization Therapy (CRT) has well-known beneficial effects in patients with advanced heart failure, reduced ejection fraction and wide QRS complex. However, mortality rates still remain high in this patient population. Therefore, precise risk stratification would be essential, nonetheless, the currently available risk scores have several shortcomings which hamper their utilization in the everyday clinical practice. Purpose Accordingly, our objective was to design and validate a machine learning based risk stratification system to predict 2-year and 5-year mortality from pre-implant parameters of patients undergoing CRT implantation. Methods We trained two models separately to predict 2-year (model 1) and 5-year mortality (model 2). As training cohort of model 1 we used 1678 patients (67±10 years, 1251 [75%] males) undergoing CRT implantation. From this population, 1320 patients (66±10 years, 1005 [76%] males) also completed 5-year follow-up and they served as the training cohort for model 2. Forty-seven pre-implant parameters (demographics, cardiovascular risk factors and clinical characteristics) were used to train the models. Our models were designed in a way to tolerate missing values. Among non-linear classifiers, random forest demonstrated the best performance. We validated our models, along with the Seattle Heart Failure Model (SHFM), VALID-CRT risk score and EAARN score on an independent cohort of 136 patients (66±10 years, 110 [81%] males). Based on the predicted probability of survival, patients were split into quartiles and survival was plotted via Kaplan-Meier (KM) curves. Results There were 358 (21%) deaths in the 2-year, 697 (53%) deaths in the 5-year training cohort. In the validation cohort, there were 30 (22%) deaths at 2 years and 58 (43%) deaths at 5 years after CRT implantation. For the prediction of 2-year mortality, the Area Under the Receiver-Operating Characteristic Curve (AUC) for model 1 was 0.77 (95% CI: 0.67–0.87; p=0.002), for SHFM was 0.54 (95% CI: 0.39–0.69; p=0.006), for EAARN was 0.57 (95% CI: 0.46–0.68, p=0.002), and for VALID-CRT was 0.62 (95% CI: 0.52–0.71; p=0.002). To predict 5-year mortality, the AUC for model 2 was 0.85 (95% CI: 0.78–0.91; p=0.001), for SHFM was 0.62 (95% CI: 0.51–0.74; p=0.003), for EAARN was 0.61 (95% CI: 0.51–0.70, p=0.002), for VALID-CRT was 0.65 (95% CI: 0.56–0.74; p=0.002). The AUCs of the machine learning based models were significantly higher than the AUCs of the pre-existing scores (DeLong test, all p<0.05). The KM curves of the quartiles were significantly separating in both models (Log-rank test, both p<0.001). Conclusion Our results indicate that machine learning algorithms can outperform the already existing linear model based scores. By capturing the non-linear association of predictors, the utilization of these state-of-the-art approaches may facilitate optimal candidate selection and prognostication of patients undergoing CRT implantation.

Download Full-text

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

European Heart Journal - Cardiovascular Imaging ◽

10.1093/ehjci/jeaa356.044 ◽

2021 ◽

Vol 22 (Supplement_1) ◽

Author(s):

E Galli ◽

V Le Rolle ◽

OA Smiseth ◽

J Duchenne ◽

JM Aalen ◽

...

Keyword(s):

Machine Learning ◽

Heart Failure ◽

Cardiac Resynchronization Therapy ◽

Right Ventricular ◽

Systolic Heart Failure ◽

Left Ventricular ◽

Supervised Machine Learning ◽

Cardiac Resynchronization ◽

Resynchronization Therapy ◽

Crt Response

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

Download Full-text

Outcomes of Cardiac Resynchronization Therapy in Patients with Hypothyroidism and Heart Failure

10.21203/rs.3.rs-23073/v2 ◽

2020 ◽

Author(s):

MEI YANG ◽

Xuping Li ◽

John C. Morris III ◽

Jinjun Liang ◽

Abhishek J. Deshmukh ◽

...

Keyword(s):

Heart Failure ◽

Cardiac Resynchronization Therapy ◽

Implantable Cardioverter Defibrillator ◽

Hazard Ratio ◽

Cardiac Resynchronization ◽

Resynchronization Therapy ◽

Therapy Outcomes ◽

Implantable Cardioverter Defibrillator Therapy ◽

Cardioverter Defibrillator ◽

All Cause Mortality

Abstract Background Hypothyroidism is known to be associated with adverse clinical outcomes in heart failure. The association between hypothyroidism and cardiac resynchronization therapy outcomes in patients with severe heart failure is not clear. Methods The study included 1,316 patients who received cardiac resynchronization therapy between 2002 and 2015. Baseline demographics and cardiac resynchronization therapy outcomes, including left ventricular ejection fraction, New York Heart Association class, appropriate implantable cardioverter-defibrillator therapy, and all-cause mortality, were collected from the electronic health record. Results Of the study cohort, 350 patients (26.6%) were classified as the hypothyroidism group. The median duration of follow-up was 3.6 years (interquartile range, 1.7-6.2). Hypothyroidism was not associated with a higher risk of all-cause mortality in patients receiving CRT for heart failure. The risk of appropriate implantable cardioverter-defibrillator therapy significantly increased in association with increased baseline thyroid -stimulating hormone level in the entire cohort (hazard ratio, 1.23 per 5mIU/L increase; 95% CI, 1.01-1.5; P=0.04) as well as in the hypothyroid group (hazard ratio, 1.44 per 5mIU/L increase; 95% CI, 1.13-1.84; P=0.004). Conclusions CRT improves cardiac function in hypothyroid patients. The ventricular arrhythmic events requiring ICD therapies are associated with baseline TSH level, which might be considered as an important biomarker to stratify the risk of sudden death for patients with heart failure and hypothyroidism.

Download Full-text

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

Circulation ◽

10.1161/circ.130.suppl_2.13242 ◽

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.

Download Full-text

56-61: A Clinical Risk Score to Predict All-Cause Mortality in Patients Receiving Cardiac Resynchronization Therapy: A Retrospective Cohort Study

EP Europace ◽

10.1093/europace/18.suppl_1.i48 ◽

2016 ◽

Vol 18 (suppl_1) ◽

pp. i48-i48

Author(s):

Ghanshyam Palamaner Subash Shantha ◽

Hardik Doshi ◽

Ward Chad ◽

Musab Alqasrawi ◽

Alexander Bolton ◽

...

Keyword(s):

Cohort Study ◽

Cardiac Resynchronization Therapy ◽

Risk Score ◽

Retrospective Cohort Study ◽

Retrospective Cohort ◽

Cardiac Resynchronization ◽

Clinical Risk Score ◽

Resynchronization Therapy ◽

Clinical Risk ◽

All Cause Mortality

Download Full-text

All-cause mortality and cardiac resynchronization therapy with or without defibrillation in primary prevention

European Heart Journal ◽

10.1093/ehjci/ehaa946.0405 ◽

2020 ◽

Vol 41 (Supplement_2) ◽

Author(s):

A Bisson

Keyword(s):

Primary Prevention ◽

Cardiac Resynchronization Therapy ◽

Ischemic Cardiomyopathy ◽

Real Life ◽

Cardiac Resynchronization ◽

Resynchronization Therapy ◽

Total Study Population ◽

Life Study ◽

All Cause Mortality ◽

Study Population

Abstract Aims Cardiac resynchronization therapy with (CRTD) or without (CRTP) defibrillator is recommended in selected patient with systolic chronic heart failure and wide QRS. There is no guideline firmly indicating choice between CRTP and CRTD in primary prevention, particularly in older patients. Methods Based on the French administrative hospital-discharge database, information was collected from 2010 to 2017 for all patients implanted with CRTP or CRTD in primary prevention. Outcomes analyses were undertaken in the total study population and in propensity-matched samples. Results A total of 45,697 patients were analyzed (19,266 with CRTP and 26,431 with CRTD). The nationwide numbers of implantations increased between 2010 and 2017 (+29.6% for CRTD, +28.8% for CRTP). Proportion of CRTP implantation over CRTD remained similar over these years. During follow up (913 days, SD 841, median 701, IQR 151–1493), incidence rate (%patient/year) of all-cause mortality was higher in CRTP (11.6%) than in CRTD patients (6.8%) (Hazard Ratio [HR] 1.70, 95% CI 1.63–1.76, p<0.001). After propensity-matched analyses, mortality of patients over 75 years-old with non-ischemic cardiomyopathy (NICM) was not different with CRTP and CRTD (HR 0.93, 95% CI 0.80–1.09, p=0.39). CRTP patients under 75 yo with NICM had a higher mortality than CRTD patients (HR 1.22, 95% CI 1.08–1.37, p=0.01). Mortality rate was also higher with CRTP than with CRTD irrespectively of age in patients with ischemic cardiomyopathy (ICM) (<75 yo: HR 1.13, 95% CI 1.04–1.33, p<0.01; ≥75 yo: HR 1.22, 95% CI 1.08–1.37, p=0.01). Conclusion This real-life study gives up-to-date information about unselected patients implanted with CRTP and CRTD in primary prevention, and provides additional data which may help physicians choosing between CRTP and CRTD at the time of implantation. Benefit of CRTD seemed clear for all-cause mortality in patients with ICM and in patients with NICM under 75 yo. Patients over 75 yo with NICM seemed less likely to benefit from primary prevention CRTD implantation. Event free curves for mortality outcomes Funding Acknowledgement Type of funding source: None

Download Full-text

Outcomes of Cardiac Resynchronization Therapy in Patients with Hypothyroidism and Heart Failure

10.21203/rs.3.rs-23073/v1 ◽

2020 ◽

Author(s):

MEI YANG ◽

Xuping Li ◽

John C. Morris III ◽

Jinjun Liang ◽

Abhishek J. Deshmukh ◽

...

Keyword(s):

Heart Failure ◽

Cardiac Resynchronization Therapy ◽

Implantable Cardioverter Defibrillator ◽

Hazard Ratio ◽

Cardiac Resynchronization ◽

Resynchronization Therapy ◽

Therapy Outcomes ◽

Implantable Cardioverter Defibrillator Therapy ◽

Cardioverter Defibrillator ◽

All Cause Mortality

Abstract Background Hypothyroidism is known to be associated with adverse clinical outcomes in heart failure. The association between hypothyroidism and cardiac resynchronization therapy outcomes in patients with severe heart failure is not clear. Methods The study included 1,316 patients who received cardiac resynchronization therapy between 2002 and 2015. Baseline demographics and cardiac resynchronization therapy outcomes, including left ventricular ejection fraction, New York Heart Association class, appropriate implantable cardioverter-defibrillator therapy, and all-cause mortality, were collected from the electronic health record. Results Of the study cohort, 349 patients (26.5%) were classified as the hypothyroidism group. The median duration of follow-up was 3.6 years (interquartile range, 1.7-6.2). Hypothyroidism was associated with a greater all-cause mortality than euthyroidism (hazard ratio, 1.19; 95% CI, 1.01-1.38; P=0.04). In this group, the risk of appropriate implantable cardioverter-defibrillator therapy significantly increased in association with increased baseline thyroid-stimulating hormone level (hazard ratio, 1.27 per 5 mIU/L increase, 95% CI, 1.00-1.53, P=0.04). Conclusions Cardiac resynchronization therapy improves cardiac function in hypothyroid patients. Hypothyroidism has adverse effects on cardiac resynchronization therapy outcomes with reduced survival and increased implantable cardioverter-defibrillator therapies for ventricular arrhythmic events.

Download Full-text