Related Experiment Videos
Development and validation of an interpretable machine learning model for predicting atrial fibrillation risk in
1Department of Cardiology, Affiliated Banan Hospital of Chongqing Medical University, Chongqing, China.
Insights
A new machine learning model accurately predicts atrial fibrillation (AF) risk in coronary heart disease (CHD) patients using electronic health records. This interpretable tool aids early detection and personalized interventions for AF in CHD.
Area of Science:
- Cardiology
- Medical Informatics
- Machine Learning in Healthcare
Background:
- Coronary heart disease (CHD) and atrial fibrillation (AF) frequently coexist.
- Current risk stratification tools inadequately predict AF in CHD patients.
- Need for advanced models to capture complex determinants of AF in this population.
Purpose of the Study:
- Develop and validate an interpretable machine learning (ML) model for AF risk prediction.
- Leverage electronic medical records (EMR) data for model development.
- Improve risk stratification for middle-aged and older CHD patients.
Main Methods:
- Retrospective cohort analysis of 47,617 hospitalized CHD patients.
- Utilized random forest imputation and LASSO screening for feature selection.
- Trained and validated eight ML algorithms, evaluating performance with AUC, calibration curves, and DCA.
- Applied SHAP and LIME for model interpretability.
Main Results:
- LASSO identified 16 predictors; pulse rate, total cholesterol, systolic blood pressure, creatinine, and triglycerides were key.
- XGBoost model achieved AUCs of 0.867 (training) and 0.813 (validation).
- Nonlinear relationships and individualized feature contributions were identified via spline analysis and SHAP/LIME.
Conclusions:
- An interpretable XGBoost model provides accurate, individualized AF risk assessment in CHD patients.
- The model facilitates early identification and targeted interventions.
- Offers a practical clinical tool for managing AF risk in this cohort.
Background:
Coronary heart disease (CHD) and atrial fibrillation (AF) frequently coexist, yet existing risk stratification tools inadequately capture the nonlinear, multidimensional determinants of AF in middle-aged and older CHD patients. This study aimed to develop and validate an interpretable machine learning-based prediction model leveraging electronic medical records (EMR) data.
Methods:
A retrospective cohort of 47,617 hospitalized CHD patients (January 2020-December 2025) was analyzed. After random forest imputation and least absolute shrinkage and selection operator (LASSO) screening, eight machine learning algorithms were trained and validated (7:3 split). Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA), with Shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) applied for interpretability.
Results:
LASSO regression identified 16 predictors, with pulse rate, total cholesterol, systolic blood pressure, creatinine, and triglycerides emerging as the top five contributors. XGBoost outperformed competing models, achieving AUCs of 0.867 (95% CI: 0.862-0.872) in the training set and 0.813 (95% CI: 0.802-0.823) in the validation set. Restricted cubic spline analysis revealed nonlinear dose-response relationships for multiple continuous variables. SHAP visualization quantified individualized feature contributions. LIME explanations demonstrated consistent local feature contributions at the individual level.
Conclusions:
This data-driven, interpretable XGBoost model enables individualized AF risk assessment in middle-aged and older CHD patients, offering a practical tool for early identification and targeted intervention in clinical practice.