What is the clinical evidence from this study?

Study design: Observational. Population: Coronary artery disease (n=199). Intervention: Combined machine learning model (myocardial synchrony and strain) vs. Strain-only model. Primary outcome: Detection of myocardial dysfunction of coronary artery disease (AUC) (AUC, 95% CI 0.89-1.00, p=0.037).

What question did this study set out to answer?

The aim was to develop a new CMR-based method to quantify myocardial synchrony and assess its diagnostic effectiveness in coronary artery disease.

February 28, 2026

Novel insights into myocardial synchrony: A CMR-based approach for improving the detection of coronary artery disease at rest

Key Result

Integrating CMR-derived myocardial synchrony with strain significantly enhanced CAD myocardial dysfunction detection relative to strain alone (AUC 0.94 vs 0.84; p=0.037).

Key Points

The aim was to develop a new CMR-based method to quantify myocardial synchrony and assess its diagnostic effectiveness in coronary artery disease.
Enrolled 112 participants with obstructive coronary artery disease and 87 healthy participants for CMR imaging.
Analyzed myocardial strain using feature-tracking and quantified synchrony with Pearson correlation coefficients.
Developed and validated machine learning models using strain-only, synchrony-only, and combined approaches in an external cohort.
Healthy participants showed significantly higher myocardial synchrony than those with CAD across all measured strains (p < 0.001).
The combined machine learning model achieved an AUC of 0.94, outperforming strain-only (AUC: 0.84) and synchrony-only models (AUC: 0.79).
Diagnostic superiority persisted in CAD participants with preserved LVEF, showing an AUC of 0.91.

Study Design

Type

Observational (n=199)

Multicenter

Yes

Structured PICO

Does a combined CMR-based model integrating myocardial synchrony and strain improve the detection of coronary artery disease compared to strain or synchrony alone?

Population

199 participants (112 with anatomically/angiographically obstructive coronary artery disease and 87 healthy participants) undergoing cardiac magnetic resonance (CMR) imaging, plus an independent external validation cohort.

Intervention

Combined machine learning model integrating CMR-derived myocardial synchrony and strain

Comparator

Strain-only model and synchrony-only model

Outcome

Diagnostic performance (Area Under the Curve [AUC]) for detecting myocardial dysfunction of coronary artery diseasesurrogate

Integrating CMR-derived myocardial synchrony with strain significantly enhances the detection of coronary artery disease at rest, including in patients with preserved left ventricular ejection fraction.

Main Result

Effect estimate: AUC (95% CI 0.89-1.00)

Absolute Event Rate: 0.94% vs 0.84%

p-value: p=0.037

Abstract

BACKGROUND We aimed to develop a novel cardiac magnetic resonance (CMR)-based method for quantifying myocardial synchrony and evaluate its diagnostic value in detecting myocardial dysfunction of coronary artery disease (CAD). METHODS Consecutive participants with anatomically/angiographically obstructive CAD (n = 112) and healthy participants (n = 87) undergoing CMR imaging were prospectively enrolled. Myocardial strain was analyzed using feature-tracking, and myocardial synchrony was quantified via Pearson correlation coefficients of segmental strain time series across the cardiac cycle. Machine learning models (strain-only, synchrony-only, combined) were developed and validated in an independent external cohort. RESULTS Healthy participants exhibited high left ventricular myocardial synchrony (radial: 0.91 IQR: 0.88, 0.93; circumferential: 0.90 ± 0.04; longitudinal: 0.97 ± 0.02), significantly reduced in participants with CAD (radial: 0.84 IQR: 0.75, 0.89; circumferential: 0.81 ± 0.12; longitudinal: 0.90 ± 0.08), including those with preserved left ventricular ejection fraction (LVEF ≥50%) (radial: 0.86 IQR: 0.82, 0.90; circumferential: 0.86 ± 0.07; longitudinal: 0.91 ± 0.07), all p < 0.001. In model analysis, the combined model significantly outperformed individual models (AUC: 0.94 95% CI: 0.89-1.00 vs. 0.84 0.75-0.94 for strain model, p = 0.037; vs. 0.79 0.68-0.90 for synchrony model, p = 0.001). Superiority persisted in CAD with preserved LVEF (AUC: 0.91 95% CI: 0.83-1.00) and external validation (AUC: 0.93 95% CI: 0.84-1.00). CONCLUSIONS This CMR-derived approach demonstrated the high degree of left ventricular synchrony in healthy populations and significant dyssynchrony in CAD, even in those with preserved LVEF. Integrating myocardial synchrony with strain significantly enhanced CAD myocardial dysfunction detection relative to strain alone, with robust diagnostic performance maintained in CAD with preserved LVEF.

Ask AI

Helpful

Bookmark