Combined ECG-AI high-risk classification

Combined ECG-AI high-risk classification predicts stroke incidence in humans (Concordant high-risk classification across disease-specific ECG-AI models in both cohorts).

“A similar gradient of disease incidence was observed for 10-year cumulative risk of HF and stroke”

HumansConcordant high-risk classification across disease-specific ECG-AI models in both cohorts10 years

Complementary Predictive Utility of Disease-Specific Electrocardiogram-Based Artificial Intelligence Models

AHA Scientific Sessions 2026 abstract·Nov 2, 2026

Combined ECG-AI high-risk classification predicts heart failure incidence in humans (Concordant high-risk classification across disease-specific ECG-AI models in both cohorts).

“A similar gradient of disease incidence was observed for 10-year cumulative risk of HF and stroke”

HumansConcordant high-risk classification across disease-specific ECG-AI models in both cohorts10 years

Complementary Predictive Utility of Disease-Specific Electrocardiogram-Based Artificial Intelligence Models

AHA Scientific Sessions 2026 abstract·Nov 2, 2026

Combined ECG-AI high-risk classification predicts atrial fibrillation incidence in humans (High risk by all three models versus not high risk by ECG2AF) (~5-fold higher risk; MGB: 20.4% versus 3.9%; BIDMC: 23.8% versus 4.2%).

“10-year cumulative risk of AF was ~5-fold higher among individuals classified as high-risk by all three models”

HumansHigh risk by all three models versus not high risk by ECG2AF10 years

Complementary Predictive Utility of Disease-Specific Electrocardiogram-Based Artificial Intelligence Models

AHA Scientific Sessions 2026 abstract·Nov 2, 2026