Skip to content
Open access

Associations between echocardiographic traits and artificial intelligence-enabled electrocardiography predictions of heart failure

May 2026 · European Heart Journal - Digital Health · Vol 7 · 0 citations · 30 references
Computer Science Medicine

TL;DR

Echocardiographic trait characterization showed that the AI–ECG HF prediction score aligned primarily with measures of systolic function, particularly GLS, while also being associated with diastolic-related abnormalities in patients with preserved LVEF.

Abstract

Abstract Aims Artificial intelligence-enabled electrocardiography (AI–ECG) can detect heart failure (HF), including disease not captured by left ventricular ejection fraction (LVEF), but the cardiac phenotypes underlying AI–ECG HF prediction remain unclear. We therefore investigated whether an AI–ECG HF prediction score aligns with established echocardiographic measures of myocardial dysfunction, remodelling, and filling pressures. Methods and results We retrospectively analysed ECG and echocardiography data from 8147 patients who underwent both examinations within 3 days at Akershus University Hospital between 1 January 2023 and 1 June 2025. A previously developed AI–ECG model, pragmatically trained using ICD-10 HF codes and N-terminal pro-B-type natriuretic peptide thresholds, was applied to all electrocardiograms. Spearman’s rank correlation ρ quantified associations between echocardiographic parameters and the AI–ECG HF prediction score. Subgroup analyses were performed by sex and LVEF. External replication of shared echocardiographic associations included 36 286 ECG–echocardiography pairs from Columbia University Irving Medical Center. Global longitudinal strain (GLS) showed the strongest correlation (ρ = 0.57), followed by mitral annular plane systolic excursion (MAPSE; ρ = −0.49) and LVEF (ρ = −0.45). In patients with LVEF ≥50%, correlations remained substantial for GLS, MAPSE, and diastolic-related parameters. Volumetric left ventricular indices correlated less strongly in women, whereas diastolic indices showed stronger correlations in women than in men. Conclusion Echocardiographic trait characterization showed that the AI–ECG HF prediction score aligned primarily with measures of systolic function, particularly GLS, while also being associated with diastolic-related abnormalities in patients with preserved LVEF. This approach may inform future studies of model interpretability and refinement.

Read PDF

Similar papers

Open access Oct 2026

Artificial intelligence-enabled electrocardiography for estimating left ventricular filling pressure

Elevated left ventricular filling pressure (LVFP) is a hallmark of heart failure with preserved ejection fraction (HFpEF), yet its non-invasive assessment remains challenging. AI-enabled ECG (AI-ECG) has shown potential for detecting cardiac dysfunction, but its utility for identifying elevated LVFP has not been...

M. Kim, J. Seo, Seng-Chan You · 0 citations
Oct 2026

Left Ventricular Filling Pressure Classification by Electrocardiogram, Echocardiography, and Catheterization: Prognostic Implications.

Despite moderate agreement with PAWP, echocardiography and AI-ECG showed stronger associations with clinical outcomes, suggesting they capture prognostically relevant myocardial information beyond resting hemodynamic status.

G. Tsaban, E. Lee, Francisco López-Jiménez et al. · 0 citations
Oct 2026

Diastolic Function From Artificial Intelligence-Derived Electrocardiography in Mitral Annulus Calcification.

OBJECTIVE To evaluate whether a validated artificial intelligence-enabled electrocardiography (AI-ECG) model for left ventricular diastolic function (LVDF) can provide prognostic risk stratification in patients with significant mitral annulus calcification (MAC). METHODS We included patients who underwent transthorac...

G. Tsaban, E. Lee, Y. Wong et al. · 0 citations

Prediction of Systolic Heart Failure from Real-World ECG Data

It is suggested that ECG models for systolic HF can be developed using ICD-based labels from routine clinical data, with model output associated with echo-derived LVEF, however, the performance decrease in external evaluation underscores the importance of careful interpretation and validation against imaging-derived en...

L. Graf, G. Riedemann, N. Spicher et al. · 0 citations
Open access Oct 2026

Grading left ventricular diastolic function and filling pressure using artificial intelligence-enabled echocardiography

Assessment of left ventricular diastolic dysfunction (LVDD) and filling pressure is standard in echocardiography but remains time- and expertise-dependent. We evaluated the performance and prognostic significance of an artificial intelligence (AI)-enabled echocardiography for LVDD grading. An AI model was...

R. Loutati, M. Fiman, A. Amshalom et al. · 0 citations
Open access Sep 2026

Artificial Intelligence-Enabled Electrocardiography Model for Left Ventricular Systolic and Diastolic Dysfunction Predict Incident Atrial Fibrillation in Patients with Sinus Rhythm: A Time-Dependent Analysis

Structural AI-ECG LVSD and LVDD scores from a single sinus-rhythm ECG predict incident AF in a time-dependent manner, with the strongest performance shortly after acquisition and more durable discrimination for LVDD.

Kyung Su Kim, J. Son, Hak-Seung Lee et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.