ECG-Based Stroke Risk Prediction

Key Points

• To evaluate the effectiveness of ECG-based algorithms in predicting stroke risk.
• ECG data was analyzed using machine learning algorithms to identify risk factors for stroke.
• Participants included individuals with varying cardiac health status.
• Statistical analysis was performed to assess the predictive power of the models.
• The ECG-based model predicted stroke risk with an accuracy of 85%, HR 2.5 (95% CI 1.8-3.2), p<0.001.
• Identified specific cardiac arrhythmias associated with higher stroke risk, including atrial fibrillation.
• Improved risk stratification compared to traditional methods.