Optimizing patient selection for primary prevention implantable cardioverter-defibrillator implantation: utilizing multimodal machine learning to assess risk of implantable cardioverter-defibrillator non-benefit
Authors:
- Maarten Z H KolkMKMaarten Z H Kolk
- Samuel Ruipérez-CampilloSRSamuel Ruipérez-Campillo
- Brototo DebBDBrototo Deb
- Erik J BekkersEBErik J Bekkers
- Albert J RogersARAlbert J Rogers
- Anne-Lotte C J Van Der LingenALAnne-Lotte C J Van Der Lingen
- Laura Alvarez FlorezLFLaura Alvarez Florez
- Ivana IsgumIIIvana Isgum
- Bob D De VosBVBob D De Vos
- Paul CloptonPCPaul Clopton
- Arthur A M WildeAWArthur A M Wilde
Open Access
- 2 August 2023
- journal article
- research article
- Published by Oxford University Press (OUP) in EP Europace
- Vol. 25 (9)
Abstract
Left ventricular ejection fraction (LVEF) is suboptimal as a sole marker for predicting sudden cardiac death (SCD). Machine learning (ML) provides new opportunities for personalized predictions using complex, multimodal data. This study aimed to determine if risk stratification for implantable cardioverter-defibrillator (ICD) implantation can be improved by ML models that combine clinical variables with 12-lead electrocardiograms (ECG) time-series features. A multicentre study of 1010 patients (64.9 ± 10.8 years, 26.8% female) with ischaemic, dilated, or non-ischaemic cardiomyopathy, and LVEF ≤ 35% implanted with an ICD between 2007 and 2021 for primary prevention of SCD in two academic hospitals was performed. For each patient, a raw 12-lead, 10-s ECG was obtained within 90 days before ICD implantation, and clinical details were collected. Supervised ML models were trained and validated on a development cohort (n = 550) from Hospital A to predict ICD non-arrhythmic mortality at three-year follow-up (i.e. mortality without prior appropriate ICD-therapy). Model performance was evaluated on an external patient cohort from Hospital B (n = 460). At three-year follow-up, 16.0% of patients had died, with 72.8% meeting criteria for non-arrhythmic mortality. Extreme gradient boosting models identified patients with non-arrhythmic mortality with an area under the receiver operating characteristic curve (AUROC) of 0.90 [95% confidence intervals (CI) 0.80–1.00] during internal validation. In the external cohort, the AUROC was 0.79 (95% CI 0.75–0.84). ML models combining ECG time-series features and clinical variables were able to predict non-arrhythmic mortality within three years after device implantation in a primary prevention population, with robust performance in an independent cohort.Keywords
Funding Information
- DEEP RISK ICD (452019308)
- F.V.Y.T.
- Rubicon
- Dutch Research Council
- Amsterdam Cardiovascular Sciences
- F.V.Y.T
This publication has 47 references indexed in Scilit:
- 2014 ESC Guidelines on diagnosis and management of hypertrophic cardiomyopathyEuropean Heart Journal, 2014
- Risk stratification for sudden cardiac death: current status and challenges for the futureEuropean Heart Journal, 2014
- Prognostic Role of CMR in Patients Presenting With Ventricular ArrhythmiasJACC: Cardiovascular Imaging, 2013
- Clinical prediction model for death prior to appropriate therapy in primary prevention implantable cardioverter defibrillator patients with ischaemic heart disease: the FADES risk scoreHeart, 2012
- MissForest—non-parametric missing value imputation for mixed-type dataBioinformatics, 2011
- Maximizing Survival Benefit With Primary Prevention Implantable Cardioverter-Defibrillator Therapy in a Heart Failure PopulationCirculation, 2009
- A Critical Appraisal of Implantable Cardioverter-Defibrillator Therapy for the Prevention of Sudden Cardiac DeathJACC, 2008
- Risk Stratification for Primary Implantation of a Cardioverter-Defibrillator in Patients With Ischemic Left Ventricular DysfunctionJACC, 2008
- T-Wave Alternans and the Susceptibility to Ventricular ArrhythmiasJACC, 2006
- Prospective Study of Heart Rate Variability and Mortality in Chronic Heart FailureCirculation, 1998