Machine learning analysis of complex late gadolinium enhancement patterns to improve risk prediction of major arrhythmic events

Hassan A Zaidi; Richard E Jones; Daniel J Hammersley; Suzan Hatipoglu; Gabriel Balaban; Lukas Mach; Brian P Halliday; Pablo Lamata; Sanjay K Prasad; Martin J Bishop

doi:10.3389/fcvm.2023.1082778

Machine learning analysis of complex late gadolinium enhancement patterns to improve risk prediction of major arrhythmic events

Front Cardiovasc Med. 2023 Feb 7:10:1082778. doi: 10.3389/fcvm.2023.1082778. eCollection 2023.

Authors

Hassan A Zaidi¹, Richard E Jones^{2

3}, Daniel J Hammersley^{2

3}, Suzan Hatipoglu³, Gabriel Balaban^{1

4}, Lukas Mach^{2

3}, Brian P Halliday^{2

3}, Pablo Lamata¹, Sanjay K Prasad^{2

3}, Martin J Bishop¹

Affiliations

¹ Department of Biomedical Engineering, School of Biomedical and Imaging Sciences, King's College London, London, United Kingdom.
² National Heart and Lung Institute, Imperial College London, London, United Kingdom.
³ Cardiovascular Magnetic Resonance Unit, Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, United Kingdom.
⁴ Department of Computational Physiology, Simula Research Laboratory, Oslo, Norway.

Abstract

Background: Machine learning analysis of complex myocardial scar patterns affords the potential to enhance risk prediction of life-threatening arrhythmia in stable coronary artery disease (CAD).

Objective: To assess the utility of computational image analysis, alongside a machine learning (ML) approach, to identify scar microstructure features on late gadolinium enhancement cardiovascular magnetic resonance (LGE-CMR) that predict major arrhythmic events in patients with CAD.

Methods: Patients with stable CAD were prospectively recruited into a CMR registry. Shape-based scar microstructure features characterizing heterogeneous ('peri-infarct') and homogeneous ('core') fibrosis were extracted. An ensemble of machine learning approaches were used for risk stratification, in addition to conventional analysis using Cox modeling.

Results: Of 397 patients (mean LVEF 45.4 ± 16.0) followed for a median of 6 years, 55 patients (14%) experienced a major arrhythmic event. When applied within an ML model for binary classification, peri-infarct zone (PIZ) entropy, peri-infarct components and core interface area outperformed a model representative of the current standard of care (LVEF<35% and NYHA>Class I): AUROC (95%CI) 0.81 (0.81-0.82) vs. 0.64 (0.63-0.65), p = 0.002. In multivariate cox regression analysis, these features again remained significant after adjusting for LVEF<35% and NYHA>Class I: PIZ entropy hazard ratio (HR) 1.88, 95% confidence interval (CI) 1.38-2.56, p < 0.001; number of PIZ components HR 1.34, 95% CI 1.08-1.67, p = 0.009; core interface area HR 1.6, 95% CI 1.29-1.99, p = <0.001.

Conclusion: Machine learning models using LGE-CMR scar microstructure improved arrhythmic risk stratification as compared to guideline-based clinical parameters; highlighting a potential novel approach to identifying candidates for implantable cardioverter defibrillators in stable CAD.

Keywords: arrhythmic risk stratification; cardiovascular magnetic resonance; coronary artery disease; entropy; fibrosis; late gadolinium enhanced; scar heterogeneity; sudden cardiac death.

Abstract

Grants and funding