Related Experiment Video
Updated: Jun 2, 2025
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Development and validation of an interpretable machine learning model for predicting left atrial thrombus or
Chaoqun Huang1, Shangzhi Shu1, Miaomiao Zhou1
1Department of Cardiovascular Medicine, The First Bethune Hospital of Jilin University, Changchun, Jilin Province, China.
Insights
Machine learning accurately predicts left atrial thrombus/spontaneous echo contrast (LAT/SEC) in non-valvular atrial fibrillation (NVAF) patients. A developed logistic regression model offers personalized risk assessment for targeted interventions.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Left atrial thrombus or spontaneous echo contrast (LAT/SEC) are significant causes of cardiogenic embolism in non-valvular atrial fibrillation (NVAF).
- Accurate risk prediction of LAT/SEC is crucial for preventing embolic events in NVAF patients.
- Current risk stratification tools may not fully capture the complexity of LAT/SEC development.
Purpose of the Study:
- To develop and validate an interpretable machine learning (ML) model for predicting LAT/SEC risk in NVAF patients.
- To identify key predictors of LAT/SEC using ML techniques.
- To compare the performance of the ML model against the established CHA2DS2-VASc scoring system.
Main Methods:
- A retrospective analysis of 1,078 NVAF patients' electronic medical records was conducted.
- Nine ML algorithms were employed, with feature selection via LASSO and logistic regression.
- Shapley Additive exPlanations (SHAP) were used for model interpretability and personalized risk assessment.
Main Results:
- The logistic classification model achieved an AUC of 0.850, accuracy of 0.812, sensitivity of 0.818, and specificity of 0.780.
- Six independent predictors identified: age, non-paroxysmal AF, diabetes, ischemic stroke/thromboembolism, hyperuricemia, and left atrial diameter.
- The ML-based logistic regression model significantly outperformed the CHA2DS2-VASc score (AUC 0.831 vs. 0.650).
Conclusions:
- Machine learning provides a reliable method for predicting LAT/SEC risk in NVAF patients.
- The developed logistic regression model with SHAP interpretation can identify high-risk individuals.
- This tool facilitates personalized treatment strategies and targeted diagnostic evaluations for NVAF patients.
Purpose:
Left atrial thrombus or spontaneous echo contrast (LAT/SEC) are widely recognized as significant contributors to cardiogenic embolism in non-valvular atrial fibrillation (NVAF). This study aimed to construct and validate an interpretable predictive model of LAT/SEC risk in NVAF patients using machine learning (ML) methods.
Methods:
Electronic medical records (EMR) data of consecutive NVAF patients scheduled for catheter ablation at the First Hospital of Jilin University from October 1, 2022, to February 1, 2024, were analyzed. A retrospective study of 1,222 NVAF patients was conducted. Nine ML algorithms combined with demographic, clinical, and laboratory data were applied to develop prediction models for LAT/SEC in NVAF patients. Feature selection was performed using the least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression. Multiple ML classification models were integrated to identify the optimal model, and Shapley Additive exPlanations (SHAP) interpretation was utilized for personalized risk assessment. Diagnostic performances of the optimal model and the CHA2DS2-VASc scoring system for predicting LAT/SEC risk in NVAF were compared.
Results:
Among 1,078 patients included, the incidence of LAT/SEC was 10.02%. Six independent predictors, including age, non-paroxysmal AF, diabetes, ischemic stroke or thromboembolism (IS/TE), hyperuricemia, and left atrial diameter (LAD), were identified as the most valuable features. The logistic classification model exhibited the best performance with an area under the receiver operating characteristic curve (AUC) of 0.850, accuracy of 0.812, sensitivity of 0.818, and specificity of 0.780 in the test set. SHAP analysis revealed the contribution of explanatory variables to the model and their relationship with LAT/SEC occurrence. The logistic regression model significantly outperformed the CHA2DS2-VASc scoring system, with AUCs of 0.831 and 0.650, respectively (Z = 7.175, P < 0.001).
Conclusions:
ML proves to be a reliable tool for predicting LAT/SEC risk in NVAF patients. The constructed logistic regression model, along with SHAP interpretation, may serve as a clinically useful tool for identifying high-risk NVAF patients. This enables targeted diagnostic evaluations and the development of personalized treatment strategies based on the findings.
