Related Experiment Video
Updated: Aug 10, 2025
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Medical record data-enabled machine learning can enhance prediction of left atrial appendage thrombosis in
Yue Zhao1, Li-Ya Cao1, Ying-Xin Zhao2
1Department of Pharmacy, the First Affiliated Hospital of Army Medical University (Third Military Medical University)，Chongqing, China.
Insights
A new machine learning model (RXTP-NVAF) accurately predicts left atrial appendage (LAA) thrombosis in non-valvular atrial fibrillation (NVAF) patients. This model outperforms traditional scoring systems, identifying key risk factors to prevent strokes.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning
Background:
- Left atrial appendage (LAA) thrombosis is a major complication of non-valvular atrial fibrillation (NVAF), leading to ischemic strokes.
- Current risk assessment methods for LAA thrombosis are limited in their ability to incorporate diverse risk factors.
- There is a need for improved predictive models for LAA thrombosis in NVAF patients.
Purpose of the Study:
- To develop and validate a clinical data-driven machine learning model for predicting LAA thrombosis risk in NVAF patients.
- To identify key clinical variables associated with LAA thrombosis.
- To compare the performance of the developed model against existing scoring systems (CHADS2 and CHA2DS2-VASc).
Main Methods:
- A cohort of 713 NVAF patients was retrospectively analyzed.
- Forty variables including demographics, medical history, lab results, and LAA structure were collected.
- Three machine learning algorithms were employed, with Random Forest and eXtreme Gradient Boosting (RXTP) models showing the best performance.
Main Results:
- The RXTP-NVAF model achieved a high accuracy of 0.865, significantly outperforming CHADS2 (0.757) and CHA2DS2-VASc (0.754) scores.
- Key predictors identified by SHapley Addictive exPlanations (SHAP) included B-type natriuretic peptide, LAA width, C-reactive protein, Fibrinogen, and estimated glomerular filtration rate.
- The model demonstrated superior ROC value and recall rate compared to existing scores.
Conclusions:
- The RXTP-NVAF model is highly effective for predicting LAA thrombosis in NVAF patients.
- Identifying and understanding these risk factors can help optimize treatment strategies.
- This approach aids in preventing thromboembolism and cardiogenic ischemic stroke in NVAF patients.
Background:
As a major complication of non-valvular atrial fibrillation (NVAF), left atrial appendage (LAA) thrombosis is associated with cerebral ischemic strokes, as well as high morbidity. Due to insufficient incorporation of risk factors, most current scoring methods are limited to the analysis of relationships between clinical characteristics and LAA thrombosis rather than detecting potential risk. Therefore, this study proposes a clinical data-driven machine learning method to predict LAA thrombosis of NVAF.
Methods:
Patients with NVAF from January 2014 to June 2022 were enrolled from Southwest Hospital. We selected 40 variables for analysis, including demographic data, medical history records, laboratory results, and the structure of LAA. Three machine learning algorithms were adopted to construct classifiers for the prediction of LAA thrombosis risk. The most important variables related to LAA thrombosis and their influences were recognized by SHapley Addictive exPlanations method. In addition, we compared our model with CHADS2 and CHADS2-VASc scoring methods.
Results:
A total of 713 participants were recruited, including 127 patients with LAA thrombosis and 586 patients with no obvious thrombosis. The consensus models based on Random Forest and eXtreme Gradient Boosting LAA thrombosis prediction (RXTP) achieved the best accuracy of 0.865, significantly outperforming CHADS2 score and CHA2DS2-VASc score (0.757 and 0.754, respectively). The SHAP results showed that B-type natriuretic peptide, left atrial appendage width, C-reactive protein, Fibrinogen and estimated glomerular filtration rate are closely related to the risk of LAA thrombosis in nonvalvular atrial fibrillation.
Conclusions:
The RXTP-NVAF model is the most effective model with the greatest ROC value and recall rate. The summarized risk factors obtained from SHAP enable the optimization of the treatment strategy, thereby preventing thromboembolism events and the occurrence of cardiogenic ischemic stroke.
