Key result
ECG-based AI model predicts 10-year incident HFrEF with ~0.88 AUROC, outperforming PREVENT-HF.
Why the study?
Does an electrocardiogram-based artificial intelligence model (ECG2HF-Subtype) accurately predict the 10-year risk of incident HFrEF and HFpEF compared to age, sex, and PREVENT-HF variables in individuals without prior heart failure?
Cohort (n=220,257)
Yes
Does an electrocardiogram-based artificial intelligence model (ECG2HF-Subtype) accurately predict the 10-year risk of incident HFrEF and HFpEF compared to age, sex, and PREVENT-HF variables in individuals without prior heart failure?
Answers are grounded in this paper and cite their sources.
An AI-enabled ECG model accurately discriminates 10-year risk of both incident HFrEF and HFpEF across multiple centers, outperforming standard clinical variables for HFrEF prediction and potentially enabling subtype-specific preventive strategies.
BACKGROUND: Heart failure is classically divided into two subtypes based on the ejection fraction (EF): HF with reduced ejection fraction (HFrEF) and HF with preserved ejection fraction (HFpEF), each with varying risk mitigation strategies. Electrocardiogram-based artificial intelligence (AI) may facilitate HF subtype-specific risk prediction, to enable tailored prevention. METHODS AND RESULTS: Based on a previously validated HF prediction architecture, we developed an ECG-based AI model to predict 10-year risk of incident HFrEF (LVEF <50%) versus HFpEF (LVEF ≥50%) (Electrocardiogram to Heart Failure Subtype, "ECG2HF-Subtype"). ECG2HF-Subtype was developed in 98,190 individuals in Massachusetts General Hospital (MGH), and validated in three test sets: MGH, Brigham and Women's Hospital (BWH), and Beth Israel Deaconess Medical Center (BIDMC), among individuals without prior HF. HF was identified using a validated natural language processing model, and subtypes were classified by LVEF proximate to incident HF. Discrimination was quantified using time-dependent area under the receiver operating characteristic curve (AUROC) and average precision (AP), with comparisons to age and sex, and a multinomial logistic regression classifier including PREVENT-HF variables. In aggregate, models were evaluated in MGH (n=16,739, age 56±17, 54% women), BWH (n=75,195, 56±16, 59%) and BIDMC (n=30,133, 56±17, 54%). ECG2HF-Subtype consistently discriminated incident HFrEF (MGH 10-year AUROC 0.89 [0.86-0.91], 10-year AP: 0.11 [95%CI 0.09-0.15], cumulative incidence 1.73%; BWH: 0.88 [0.87-0.89], 0.13 [0.11-0.14], 2.23% BIDMC: 0.88 [0.86-0.89], 0.14 [0.12-0.17], 2.19%) and HFpEF events (MGH 10-year AUROC 0.83 [0.81-0.85], 10-year AP: 0.10 [95% CI 0.09-0.13], cumulative incidence 3.17%; BWH: 0.79 [0.77-0.80], 0.06 [0.06-0.07], 2.75%), BIDMC: 0.81 [0.80-0.82], 0.10 [0.09-0.12], 3.49%), with consistently greater AUROC versus age and sex. When compared to PREVENT-HF variables, ECG2HF-Subtypes had favorable discrimination of HFrEF (e.g., 10-year AUROC in MGH+BWH 0.86 [0.84-0.88] vs. 0.78 [0.76-0.80]), and modestly lower for HFpEF (10-year AUROC in MGH+BWH 0.78 [0.76-0.80] vs. 0.81 [0.79-0.82]). CONCLUSIONS: By predicting risk of HFpEF and HFrEF, AI-enabled ECG analysis may enable targeted prevention to reduce HF-related morbidity.
No takes yet. Share an insight, caveat, or question.
Khurshid et al. (2026) conducted a cohort in Risk of incident heart failure with reduced (HFrEF) or preserved ejection fraction (HFpEF) (n=220,257). Electrocardiogram to Heart Failure Subtype AI model (ECG2HF-Subtype) vs. Age and sex, and a multinomial logistic regression classifier including PREVENT-HF variables was evaluated on 10-year incident HFrEF (LVEF <50%) and HFpEF (LVEF >=50%) (AUROC 0.88-0.89 for HFrEF; AUROC 0.79-0.83 for HFpEF). The ECG2HF-Subtype AI model discriminated 10-year incident HFrEF (AUROC 0.88-0.89) and HFpEF (AUROC 0.79-0.83), outperforming PREVENT-HF variables for HFrEF (AUROC 0.86 vs 0.78).
Synapse has enriched 10 related papers. Consider them for comparative context: