Prediction of response after cardiac resynchronization therapy with machine learning

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

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