Related Experiment Video
Updated: Jun 29, 2025
Author Spotlight: Developing a Translational Model for Atrial Fibrillation Research Across Species
Published on: November 21, 2023
Prediction of atrial fibrillation and stroke using machine learning models in UK Biobank
Areti Papadopoulou1, Daniel Harding1, Greg Slabaugh2,3
1William Harvey Research Institute, Barts and the London School of Medicine and Dentistry, Queen Mary University of London, London, UK.
Insights
Machine learning models can predict atrial fibrillation (AF) and stroke risk in AF patients. XGBoost and LightGBM models show promise for clinical use, outperforming traditional risk scores.
Area of Science:
- Cardiology
- Medical Informatics
- Biomarker Research
Background:
- Atrial fibrillation (AF) is a common arrhythmia linked to underestimated ischemic stroke risk, often occurring asymptomatically.
- Accurate prediction of AF and subsequent stroke risk is crucial for effective patient management.
Purpose of the Study:
- To develop and compare machine learning (ML) models for predicting AF in the general population.
- To develop and compare ML models for predicting ischemic stroke in patients diagnosed with AF.
Main Methods:
- Utilized UK-Biobank data, including clinical, questionnaire, biochemical, and genetic information.
- Constructed and evaluated various ML models: XGBoost, LightGBM, Random Forest, Deep Neural Network, Support Vector Machine, and Lasso logistic regression.
- Assessed feature importance using SHapley Additive exPlanations (SHAP) and compared ML models against the CHA₂DS₂-VASc score for stroke prediction.
Main Results:
- LightGBM achieved the highest AUROC of 0.729 for AF prediction.
- XGBoost demonstrated superior performance for ischemic stroke prediction in AF patients with an AUROC of 0.631, significantly outperforming the CHA₂DS₂-VASc score.
- SHAP analysis identified key peripheral blood biomarkers (e.g., creatinine, glycated hemoglobin, monocytes) associated with ischemic stroke risk, not included in CHA₂DS₂-VASc.
Conclusions:
- The developed ML models show potential for clinical application in predicting AF and ischemic stroke, pending further validation.
- Incorporating routinely measured blood biomarkers into stroke risk prediction for AF patients is recommended.
- Machine learning offers a powerful approach to enhance cardiovascular risk prediction beyond traditional clinical scores.
Objective:
Atrial fibrillation (AF) is the most common cardiac arrythmia, and it is associated with increased risk for ischemic stroke, which is underestimated, as AF can be asymptomatic. The aim of this study was to develop optimal ML models for prediction of AF in the population, and secondly for ischemic stroke in AF patients.
Methods:
To develop ML models for prediction of 1) AF in the general population and 2) ischemic stroke in patients with AF we constructed XGBoost, LightGBM, Random Forest, Deep Neural Network, Support Vector Machine and Lasso penalised logistic regression models using UK-Biobank's extensive real-world clinical data, questionnaires, as well as biochemical and genetic data, and their predictive performances were compared. Ranking and contribution of the different features was assessed by SHapley Additive exPlanations (SHAP) analysis. The clinical tool CHA2DS2-VASc for prediction of ischemic stroke among AF patients, was used for comparison to the best performing ML model.
Findings:
The best performing model for AF prediction was LightGBM, with an area-under-the-roc-curve (AUROC) of 0.729 (95% confidence intervals (CI): 0.719, 0.738). The best performing model for ischemic stroke prediction in AF patients was XGBoost with AUROC of 0.631 (95% CI: 0.604, 0.657). The improved AUROC in the XGBoost model compared to CHA2DS2-VASc was statistically significant based on DeLong's test (p-value = 2.20E-06). In addition, the SHAP analysis showed that several peripheral blood biomarkers (e.g. creatinine, glycated haemoglobin, monocytes) were associated with ischemic stroke, which are not considered by CHA2DS2-VASc.
Implications:
The best performing ML models presented have the potential for clinical use, but further validation in independent studies is required. Our results endorse the incorporation of some routinely measured blood biomarkers for ischemic stroke prediction in AF patients.
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
28:13Catheter Ablation in Combination With Left Atrial Appendage Closure for Atrial Fibrillation
Published on: February 26, 2013