Electrocardiogram-based deep learning improves outcome prediction following cardiac resynchronization therapy.
Philippe C WoutersRutger R van de LeurMelle B VessiesAntonius M W van StipdonkMohammed A GhosseinRutger J HassinkPieter A M DoevendansPim van der HarstAlexander H MaassFrits W PrinzenKevin VernooyMathias MeineRené van EsPublished in: European heart journal (2022)
Requiring only a standard 12-lead ECG, FactorECG held superior discriminative ability for the prediction of clinical outcome when compared with guideline criteria and QRSAREA, without requiring additional clinical variables. End-to-end automated visualization of ECG features allows for an explainable algorithm, which may facilitate rapid uptake of this personalized decision-making tool in CRT.