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.

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

“…ML can improve the care of HF patients in various ways, e.g., by augmenting the prediction of readmission after HF hospitalization or by predicting the risk of mortality (16,17,19). In HF patients undergoing CRT implantation, our research group has previously confirmed the superiority of ML over pre-existing risk scores (24), and similar results have been reported by others as well (25,26). Underpinning these findings, we were able to predict the 1-and 3-year mortality of CRT patients with good discrimination and excellent calibration, even in subsets of patients divided by sex.…”

Comparison of Continuous Subcutaneous Insulin Infusion and Multiple Daily Injections in Pediatric Type 1 Diabetes: A Meta‐Analysis and Prospective Cohort Study

“…The individual demographic features of 188 TID cases were presented as mean ± SD for continuous variables (i.e., age, birthweight, and clinical laboratory parameter), frequency and percentages (i.e., gender, parity, delivery method, and Tanner stage) for categorical variables. Mean imputation method were imputed to replace missing values of laboratory assessments ( 23 ). T-test were used for continuous variables and chi-square test for categorical variables.…”

The year in cardiovascular medicine 2020: digital health and innovation

“…В настоящее время решение об имплантации дефибриллятора и/или применении сердечной ресинхронизирующей терапии (СРТ) у пациентов с СН зависит от четко определенных клинических, электрофизиологических и визуализационных характеристик [10,11]. Однако недавнее исследование, опубликованное в Европейском кардиологическом журнале (EHJ) в начале текущего года [12], напомнило нам, что прогнозирование реакции на СРТ, ориентированное на среднесрочные или долгосрочные результаты, должно быть ключевым фактором при принятии решений. Действительно, Tokodi M, et al [12] использовали машинное обучение, чтобы помочь построить оценку риска для прогнозирования смертности после СРТ.…”

“…Однако недавнее исследование, опубликованное в Европейском кардиологическом журнале (EHJ) в начале текущего года [12], напомнило нам, что прогнозирование реакции на СРТ, ориентированное на среднесрочные или долгосрочные результаты, должно быть ключевым фактором при принятии решений. Действительно, Tokodi M, et al [12] использовали машинное обучение, чтобы помочь построить оценку риска для прогнозирования смертности после СРТ. Оценка использовала информацию из анамнеза, клинического осмотра, медицинских карт, ЭКГ, эхокардиографических и лабораторных данных, обычно получаемых в рамках обычных посещений больниц пациентов с СН, и, после обучения на 1510 пациентах с использованием алгоритма под названием "случайный лес", она достигла замечательного прогностического значения по всем причинам смертности с площадью под ROC-кривой в диапазоне от 0,77 (при прогнозе на 1 год) до 0,8 (при прогнозе на 5 лет).…”