Related Experiment Video
Updated: Jun 17, 2025
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Machine learning-based model to predict composite thromboembolic events among Chinese elderly patients with atrial
Jiefeng Ren1,2, Haijun Wang1, Song Lai3
1Department of Geriatric Cardiology, National Clinical Research Center for Geriatric Diseases, Second Medical Center of Chinese PLA General Hospital, Beijing, 100853, China.
Insights
This study developed a machine learning model to predict composite thromboembolic events (CTEs) in elderly patients with atrial fibrillation (AF). The random forest model accurately identified high-risk patients, aiding clinical decisions.
Area of Science:
- Cardiology
- Medical Informatics
- Geriatrics
Background:
- Accurate survival prognosis is crucial for clinical decision-making in elderly patients.
- Atrial fibrillation (AF) increases the risk of various thromboembolic events.
Purpose of the Study:
- To develop and validate a machine learning model for predicting composite thromboembolic events (CTEs) in elderly patients with AF.
- Identify key risk factors associated with CTEs in this population.
Main Methods:
- Retrospective study of 6,079 elderly patients (≥75 years) with AF.
- Utilized random forest imputation for missing data.
- Trained and validated four machine learning models (logistic regression, decision tree, random forest, XGBoost) on training and validation datasets.
Main Results:
- The incidence of CTEs was 19.53%.
- A random forest model achieved high performance (AUC: 0.927), outperforming other models.
- Key predictors identified included history of ischemic stroke, high triglycerides, high total cholesterol, elevated plasma D-dimer, and age.
Conclusions:
- A highly accurate random forest model can stratify elderly AF patients at high risk for CTEs.
- History of ischemic stroke, age, lipid profile, and D-dimer levels are significant correlates of CTEs.
Objective:
Accurate prediction of survival prognosis is helpful to guide clinical decision-making. The aim of this study was to develop a model using machine learning techniques to predict the occurrence of composite thromboembolic events (CTEs) in elderly patients with atrial fibrillation(AF). These events encompass newly diagnosed cerebral ischemia events, cardiovascular events, pulmonary embolism, and lower extremity arterial embolism.
Methods:
This retrospective study included 6,079 elderly hospitalized patients (≥ 75 years old) with AF admitted to the People's Liberation Army General Hospital in China from January 2010 to June 2022. Random forest imputation was used for handling missing data. In the descriptive statistics section, patients were divided into two groups based on the occurrence of CTEs, and differences between the two groups were analyzed using chi-square tests for categorical variables and rank-sum tests for continuous variables. In the machine learning section, the patients were randomly divided into a training dataset (n = 4,225) and a validation dataset (n = 1,824) in a 7:3 ratio. Four machine learning models (logistic regression, decision tree, random forest, XGBoost) were trained on the training dataset and validated on the validation dataset.
Results:
The incidence of composite thromboembolic events was 19.53%. The Least Absolute Shrinkage and Selection Operator (LASSO) method, using 5-fold cross-validation, was applied to the training dataset and identified a total of 18 features that exhibited a significant association with the occurrence of CTEs. The random forest model outperformed other models in terms of area under the curve (ACC: 0.9144, SEN: 0.7725, SPE: 0.9489, AUC: 0.927, 95% CI: 0.9105-0.9443). The random forest model also showed good clinical validity based on the clinical decision curve. The Shapley Additive exPlanations (SHAP) showed that the top five features associated with the model were history of ischemic stroke, high triglyceride (TG), high total cholesterol (TC), high plasma D-dimer, age.
Conclusions:
This study proposes an accurate model to stratify patients with a high risk of CTEs. The random forest model has good performance. History of ischemic stroke, age, high TG, high TC and high plasma D-Dimer may be correlated with CTEs.
More Related Videos
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018