Sex-Specific Patterns of Mortality Predictors Among Patients Undergoing Cardiac Resynchronization Therapy: A Machine
Márton Tokodi1, Anett Behon1, Eperke Dóra Merkel1
1Heart and Vascular Center, Semmelweis University, Budapest, Hungary.
Insights
Machine learning models accurately predict mortality in cardiac resynchronization therapy (CRT) patients. Analysis revealed distinct sex-specific predictors of mortality that change over time.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Sex-related differences in outcomes after cardiac resynchronization therapy (CRT) are not well understood.
- Predicting mortality in CRT patients requires further investigation into variable importance.
Purpose of the Study:
- To develop and validate machine learning (ML) models for predicting 1- and 3-year all-cause mortality in CRT patients.
- To identify sex-specific predictors of mortality using ML and analyze their temporal dynamics.
Main Methods:
- Retrospective analysis of 2,191 CRT patients using ML algorithms.
- Models were trained and tested on patient subsets, with performance evaluated using area under the receiver-operating characteristic curves (AUC).
- Permutation feature importance was used to identify key predictors.
Main Results:
- A conditional inference random forest model achieved AUCs of 0.728 and 0.732 for 1- and 3-year mortality prediction, respectively.
- Key predictors included heart failure etiology, NYHA class, ejection fraction, and QRS morphology.
- Sex-specific differences in predictor importance were observed (e.g., hemoglobin less important in females), with varying importance of atrial fibrillation, age, and creatinine over time.
Conclusions:
- ML models effectively predict all-cause mortality in CRT patients using accessible clinical data.
- Identified sex-specific predictor patterns demonstrate dynamic changes over the 1- to 3-year follow-up period.
Abstract:
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.
