Optimising Patient Selection for Primary Prevention ICD Implantation: Utilising Multimodal Machine Learning to Assess Risk of ICD Non-Benefit.
Maarten Z H KolkSamuel Ruipérez-CampilloBrototo DebE BekkersC P AllaartAlbert J RogersAnne-Lotte C J van der LingenL Alvarez FlorezIvana IšgumBob D de VosPaul CloptonArthur A M WildeReinoud E KnopsSanjiv M NarayanFleur V Y TjongPublished in: Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology (2023)
ML models combining ECG time-series features and clinical variables were able to predict non-arrhythmic mortality within 3 years after device implantation in a primary prevention population, with robust performance in an independent cohort.