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

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

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2023.1082778

DOI=10.3389/fcvm.2023.1082778

ISSN=2297-055X

ABSTRACT=Background: 
Machine learning analysis of complex myocardial scar patterns affords the potential to enhance risk prediction of life-threatening arrhythmia in stable 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 characterising 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 modelling. 

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:
ML 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.