Improving arrhythmic risk prediction using cardiac magnetic resonance within deep learning in ischemic heart disease.
Authors
Affiliations (9)
Affiliations (9)
- King's College London, School of Biomedical Engineering & Imaging Sciences, London, UK. [email protected].
- Imperial College London, National Heart and Lung Institute, London, UK.
- Cardiovascular Magnetic Resonance Unit, Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, UK.
- Anglia Ruskin School of Medicine & MTRC, Anglia Ruskin University, Chelmsford, UK.
- Mid and South Essex, NHS Foundation Trust, London, UK.
- King's College London, British Heart Foundation Centre of Research Excellence at the School of Cardiovascular and Metabolic Medicine & Sciences, London, UK.
- King's College London, School of Biomedical Engineering & Imaging Sciences, London, UK.
- Part of Guy's and St Thomas' NHS Foundation Trust, Royal Brompton and Harefield Hospitals, London, UK.
- NHS Foundation Trust, King's College Hospital, London, UK.
Abstract
Sudden arrhythmic death remains a major clinical risk in ischemic heart disease (IHD), underscoring the need for improved risk stratification. Late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) provides measures of scar burden and heterogeneity, but its incremental prognostic value beyond conventional markers such as left ventricular ejection fraction remains uncertain. We analysed two independent IHD cohorts (Dataset 1: n = 399, 54 events; National Research Ethics Service approvals 07/H0708/83 and 09/H0504/104+5; Dataset 2: n = 424, 50 events; derived from the prospectively registered REVIVED-BCIS2 trial, ISRCTN45979711, registered 20 November 2012)using clinical and LGE-CMR-derived variables to evaluate the contribution of LGE-CMR features, and compare machine learning-based survival modelling approaches. A brute-force feature-selection strategy identified optimal predictor subsets for Cox proportional hazards models, Random Survival Forests, and DeepSurv, evaluated using cross-cohort and pooled validation strategies. Scar entropy consistently emerged as a strong predictor of major arrhythmic events. Non-linear approaches outperformed Cox regression, with DeepSurv demonstrating superior generalization across cohorts and Random Survival Forests showing robust performance in pooled analyses. These findings support scar heterogeneity as an important prognostic marker and suggest that machine-learning survival models may improve arrhythmic risk prediction in patients with IHD.