Key result
Positive ECG-AI screening is linked to up to ~20-fold higher incident HF risk, improving PREVENT-HF classification.
Why the study?
To evaluate whether ECG-AI detecting systolic and diastolic dysfunction enhances the prediction of incident heart failure beyond clinical risk estimation using the PREVENT-HF equation.
Does the addition of ECG-AI to the PREVENT-HF equation improve the prediction of incident heart failure in a pooled cohort?
Cohort (n=14,126)
Yes
Does the addition of ECG-AI to the PREVENT-HF equation improve the prediction of incident heart failure in a pooled cohort?
Effect estimate: 10- to 20-fold higher risk
Adding AI-based ECG analysis to the PREVENT-HF clinical risk equation significantly improves the prediction and reclassification of incident heart failure risk.
BACKGROUND Artificial intelligence applied to electrocardiograms (ECG-AI) offers a scalable approach to identify individuals at risk for heart failure (HF) and guide preventive interventions. OBJECTIVE The purpose of this study was to assess whether ECG-AI designed to detect systolic and diastolic dysfunction enhances the prediction of incident HF over clinical risk estimation using the PREVENT-HF (Predicting Risk of Cardiovascular Disease EVENTs-Heart Failure) equation. METHODS Baseline clinical and electrocardiogram data were pooled from the Framingham Heart Study, Multi-Ethnic Study of Atherosclerosis, and Cardiovascular Health Study. Participants with data sufficient for both ECG-AI and PREVENT-HF assessment were included. Analyses were performed on the National Heart, Lung, and Blood Institute BioDataCatalyst from July to September 2025. Risk of incident HF was estimated using previously validated ECG-AI algorithms that detect systolic (ECG-AI LEF) and diastolic (ECG-AI DD) dysfunction. Discrimination and reclassification were evaluated using Harrell's C-statistic and net reclassification improvement. RESULTS Of 14,126 participants, positive screening rates were 2.9% for ECG-AI LEF, 11.1% for ECG-AI DD, 11.9% for the composite ECG-AI model, 25.1% for PREVENT-HF score ≥10%, and 5.8% for PREVENT-HF score ≥20%. Incident HF or death occurred in 7.7% and 15.1% of participants, respectively. Participants with positive composite ECG-AI screens at baseline had 10- to 20-fold higher risk of developing HF compared with those with negative screens. At 1, 3, 5, and 10 years, the addition of ECG-AI to PREVENT-HF yielded 1-directional net reclassification improvements ranging from 0.086 to 0.125 at a PREVENT-HF threshold of 10%, and 0.327 to 0.403 at a threshold of 20%. CONCLUSIONS The addition of ECG-AI to PREVENT-HF improved discrimination of near-term HF risk. ECG-AI may enable population-level HF risk stratification and facilitate targeted prevention strategies.
No takes yet. Share an insight, caveat, or question.
Desai et al. (2025) conducted a cohort in Heart failure (n=14,126). ECG-AI vs. PREVENT-HF clinical risk estimation alone was evaluated on Incident HF (10- to 20-fold higher risk). Positive composite ECG-AI screening was associated with a 10- to 20-fold higher risk of incident heart failure, and its addition to PREVENT-HF yielded net reclassification improvements up to 0.403.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: