A low ejection fraction AI-ECG algorithm predicted incident heart failure with EF ≤35% in patients with atrial fibrillation (highest vs lowest risk tertile: HR 5.20; 95% CI 3.03-8.91).
Cohort
Does a low ejection fraction artificial intelligence electrocardiogram (AI-ECG) algorithm predict incident heart failure with reduced ejection fraction (HFrEF) in patients with atrial fibrillation?
An AI-ECG algorithm can identify patients with atrial fibrillation at high risk of developing incident HFrEF, outperforming current clinical models.
Effect estimate: HR 5.20 (95% CI 3.03-8.91)
p-value: p=0.019
Objective: To determine whether a low ejection fraction artificial intelligence electrocardiogram (AI-ECG) algorithm predicts incident heart failure with reduced ejection fraction (HFrEF) in patients with atrial fibrillation (AF) independently of known HF risk factors. Patients and Methods: -statistic estimates derived from Cox proportional hazard regression models. Results: =.019). Similar results were observed for HF with EF of 35% or less (highest vs lowest risk AI-ECG tertile: HR, 5.20; 95% CI, 3.03-8.91). Conclusion: Incorporation of the AI-ECG algorithm into routine clinical care may provide enhanced ability to identify patients with AF at risk of developing HFrEF with predictive performance that is superior to current clinical models.
Shropshire et al. (Sat,) conducted a cohort in Atrial fibrillation. Low ejection fraction artificial intelligence electrocardiogram (AI-ECG) algorithm vs. Lowest risk AI-ECG tertile / known HF risk factors was evaluated on Incident heart failure with reduced ejection fraction (HFrEF) (HR 5.20, 95% CI 3.03-8.91, p=0.019). A low ejection fraction AI-ECG algorithm predicted incident heart failure with EF ≤35% in patients with atrial fibrillation (highest vs lowest risk tertile: HR 5.20; 95% CI 3.03-8.91).