Related Experiment Video
Updated: May 1, 2026
Catheter Ablation in Combination With Left Atrial Appendage Closure for Atrial Fibrillation
Published on: February 26, 2013
Performance of an AI prediction tool for new-onset atrial fibrillation after coronary artery bypass grafting
Hualong Ma1, Dalong Chen2, Weitao Lv3
1Jinan University School of Nursing, Guangzhou, Guangdong, China.
Insights
A new AI tool accurately predicts new-onset postoperative atrial fibrillation (NOAF) after coronary artery bypass grafting (CABG), outperforming existing methods. This bedside tool enhances NOAF risk assessment for better patient outcomes.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Informatics
Background:
- New-onset postoperative atrial fibrillation (NOAF) is a common complication after coronary artery bypass grafting (CABG).
- Existing predictive tools for NOAF after CABG lack sufficient accuracy and clinical utility.
- There is a critical need for advanced tools to predict NOAF in patients undergoing CABG.
Purpose of the Study:
- To develop and validate a novel artificial intelligence (AI)-based bedside tool for accurate prediction of NOAF after CABG.
- To compare the performance of the AI tool against established risk scores like CHA2DS2-VASc, HATCH, and POAF.
- To identify key clinical characteristics influencing NOAF prediction through explainable AI methods.
Main Methods:
- Retrospective analysis of data from 2994 patients who underwent CABG at two tertiary hospitals.
- Development of a stacking AI model integrating 11 base learners using a derivation cohort (n=2486).
- External validation of the AI model using a separate cohort (n=508) and evaluation with AUC, F1 score, Precision, and Recall. SHapley Additive exPlanations (SHAP) were used for model interpretability.
Main Results:
- The AI stacking model achieved a superior Area Under Curve (AUC) of 0.931 and F1 score of 0.797 in external validation.
- The AI tool significantly outperformed CHA2DS2-VASc (AUC 0.713), HATCH (AUC 0.708), and POAF (AUC 0.667) scores (p < 0.05).
- Key predictors identified by SHAP values include Brain natriuretic peptide, Left ventricular end-diastolic diameter, Ejection fraction, and BMI.
Conclusions:
- The developed AI-based bedside tool provides superior prediction of NOAF after CABG compared to existing clinical scores.
- The tool's interpretability using SHAP values allows for understanding the contribution of individual patient characteristics to NOAF risk.
- This AI tool has the potential to significantly improve preoperative risk stratification and patient management for NOAF following CABG.
Background:
There is lack of tools to predict new-onset postoperative atrial fibrillation (NOAF) after coronary artery bypass grafting (CABG). We aimed to develop and validate a novel AI-based bedside tool that accurately predicts predict NOAF after CABG.
Methods:
Data from 2994 patients who underwent CABG between March 2015 and July 2024 at two tertiary hospitals in China were retrospectively analyzed. 2486 patients from one hospital formed the derivation cohort, split 7:3 into training and test sets, while the 508 patients from a separate hospital formed the external validation cohort. A stacking model integrating 11 base learners was developed and evaluated using Accuracy, Precision, Recall, F1 score, and Area Under Curve (AUC). SHapley Additive exPlanations (SHAP) values were calculated and plotted to interpret the contributions of individual characteristics to the model's predictions.
Findings:
Seventy-seven predictive characteristics were analyzed. The stacking model achieved superior performance with AUCs 0·931 and F1 scores 0·797 in the independent external validation, outperforming CHA2DS2-VASc, HATCH, and POAF scores (AUC 0·931 vs. 0·713, 0·708, and 0·667; p < 0·05). SHAP value indicate that the importance of predictive features for NOAF, in descending order, include: Brain natriuretic peptide, Left ventricular end-diastolic diameter, Ejection fraction, BMI, β-receptor blockers, Duration of surgery, Age, Neutrophil percentage-to-albumin ratio, Myocardial infarction, Left atrial diameter, Hypertension, and smoking status. Subsequently, we constructed an easy-to-use bedside clinical tool for NOAF risk assessment leveraging these characteristics.
Interpretation:
The AI-based tool offers superior prediction of NOAF, outperforming three existing predictive tools. Future studies should further explore how various patient characteristics influence the timing of NOAF onset, whether early or late.
Funding:
This work was funded by Lingnan Nightingale Nursing Research Institute of Guangdong Province, and Guangdong Nursing Society (GDHLYJYZ202401).
More Related Videos
08:10Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
04:05Author Spotlight: Unveiling Prognostic Indicators in Heart Failure - The Role of Phase Angle and Bioelectrical Impedance Analysis
Published on: June 30, 2023
