Dynamic prediction of malignant ventricular arrhythmias using neural networks in patients with an implantable cardioverter-defibrillatorResearch in context
Maarten Z.H. Kolk,
Samuel Ruipérez-Campillo,
Laura Alvarez-Florez,
Brototo Deb,
Erik J. Bekkers,
Cornelis P. Allaart,
Anne-Lotte C.J. Van Der Lingen,
Paul Clopton,
Ivana Išgum,
Arthur A.M. Wilde,
Reinoud E. Knops,
Sanjiv M. Narayan,
Fleur V.Y. Tjong
Affiliations
Maarten Z.H. Kolk
Department of Clinical and Experimental Cardiology, Amsterdam UMC Location University of Amsterdam, Heart Center, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Cardiovascular Sciences, Heart Failure & Arrhythmias, Amsterdam, the Netherlands
Samuel Ruipérez-Campillo
Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA; Department of Information Technology and Electrical Engineering, Swiss Federal Institute of Technology Zurich (ETHz), Gloriastrasse 35, Zurich, Switzerland; ITACA Institute, Universtitat Politècnica de València, Camino de Vera S/n, Valencia, Spain
Laura Alvarez-Florez
Department of Biomedical Engineering and Physics, Amsterdam University Medical Center Location University of Amsterdam, Meibergdreef 9, Amsterdam, the Netherlands
Brototo Deb
Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA
Erik J. Bekkers
Faculty of Science, University of Amsterdam, Science Park 904, Amsterdam, the Netherlands
Cornelis P. Allaart
Department of Cardiology, Amsterdam UMC, Location VU Medical Center, De Boelelaan 1118, Amsterdam, the Netherlands
Anne-Lotte C.J. Van Der Lingen
Department of Cardiology, Amsterdam UMC, Location VU Medical Center, De Boelelaan 1118, Amsterdam, the Netherlands
Paul Clopton
Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA
Ivana Išgum
Department of Biomedical Engineering and Physics, Amsterdam University Medical Center Location University of Amsterdam, Meibergdreef 9, Amsterdam, the Netherlands; Faculty of Science, University of Amsterdam, Science Park 904, Amsterdam, the Netherlands; Department of Radiology and Nuclear Medicine, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, the Netherlands
Arthur A.M. Wilde
Department of Clinical and Experimental Cardiology, Amsterdam UMC Location University of Amsterdam, Heart Center, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Cardiovascular Sciences, Heart Failure & Arrhythmias, Amsterdam, the Netherlands
Reinoud E. Knops
Department of Clinical and Experimental Cardiology, Amsterdam UMC Location University of Amsterdam, Heart Center, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Cardiovascular Sciences, Heart Failure & Arrhythmias, Amsterdam, the Netherlands
Sanjiv M. Narayan
Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA
Fleur V.Y. Tjong
Department of Clinical and Experimental Cardiology, Amsterdam UMC Location University of Amsterdam, Heart Center, Meibergdreef 9, Amsterdam, the Netherlands; Department of Medicine and Cardiovascular Institute, Stanford University, Stanford, CA, USA; Amsterdam Cardiovascular Sciences, Heart Failure & Arrhythmias, Amsterdam, the Netherlands; Corresponding author. Heart Center, University of Amsterdam, Amsterdam, 1105 AZ, the Netherlands.
Summary: Background: Risk stratification for ventricular arrhythmias currently relies on static measurements that fail to adequately capture dynamic interactions between arrhythmic substrate and triggers over time. We trained and internally validated a dynamic machine learning (ML) model and neural network that extracted features from longitudinally collected electrocardiograms (ECG), and used these to predict the risk of malignant ventricular arrhythmias. Methods: A multicentre study in patients implanted with an implantable cardioverter-defibrillator (ICD) between 2007 and 2021 in two academic hospitals was performed. Variational autoencoders (VAEs), which combine neural networks with variational inference principles, and can learn patterns and structure in data without explicit labelling, were trained to encode the mean ECG waveforms from the limb leads into 16 variables. Supervised dynamic ML models using these latent ECG representations and clinical baseline information were trained to predict malignant ventricular arrhythmias treated by the ICD. Model performance was evaluated on a hold-out set, using time-dependent receiver operating characteristic (ROC) and calibration curves. Findings: 2942 patients (61.7 ± 13.9 years, 25.5% female) were included, with a total of 32,129 ECG recordings during a mean follow-up of 43.9 ± 35.9 months. The mean time-varying area under the ROC curve for the dynamic model was 0.738 ± 0.07, compared to 0.639 ± 0.03 for a static (i.e. baseline-only model). Feature analyses indicated dynamic changes in latent ECG representations, particularly those affecting the T-wave morphology, were of highest importance for model predictions. Interpretation: Dynamic ML models and neural networks effectively leverage routinely collected longitudinal ECG recordings for personalised and updated predictions of malignant ventricular arrhythmias, outperforming static models. Funding: This publication is part of the project DEEP RISK ICD (with project number 452019308) of the research programme Rubicon which is (partly) financed by the Dutch Research Council (NWO). This research is partly funded by the Amsterdam Cardiovascular Sciences (personal grant F.V.Y.T).
