EP News: Basic and Translational

Abstract

In the current study, Popescu et al (Nat Cardiovasc Res 2022;1:334; PMID: 35464150) develop a novel deep learning (DL) approach that combines neural networks and survival analysis to predict patient-specific survival curves using contrast-enhanced cardiac magnetic resonance images and clinical covariates for patients with ischemic heart disease. The DL-predicted survival curves provide accurate predictions up to 10 years and allow for estimation of uncertainty in predictions. The performance of the DL approach was evaluated on multi-center internal validation data and tested on an independent test set, achieving concordance index of 0.83 and 0.74. The DL approach with only raw cardiac images as input outperforms standard survival models constructed using clinical covariates. The authors conclude that DL approach has the potential to transform clinical decision-making by offering accurate and generalizable predictions of patient-specific survival probabilities of arrhythmic death over time.