Advancing stroke prevention in atrial fibrillation: a systematic review of machine learning–based risk prediction models

Key Points

• The aim is to review and assess the effectiveness of machine learning models in predicting stroke risk for patients with atrial fibrillation.
• Conducted a systematic review of existing studies on machine learning-based risk prediction models.
• Evaluated model performance metrics, including accuracy, sensitivity, and specificity.
• Included studies focusing on atrial fibrillation populations and stroke outcomes.
• Multiple machine learning models demonstrated improved accuracy in stroke risk prediction compared to traditional methods.
• Some models achieved up to 85% accuracy with a positive predictive value of 75% for high-risk patients.
• The utilization of AI-based tools can enhance risk stratification, indicating a significant improvement in clinical outcomes.