Machine learning models combining ECG and clinical variables predicted non-arrhythmic mortality within 3 years of ICD implantation with an AUROC of 0.79 (95% CI 0.75-0.84) in an external cohort.
Cohort (n=1,010)
Sí
Does a machine learning model combining clinical variables and 12-lead ECG features predict non-arrhythmic mortality in patients receiving primary prevention ICDs?
A multimodal machine learning model combining ECG and clinical data can effectively predict non-arrhythmic mortality in primary prevention ICD candidates, potentially improving patient selection.
Estimación del efecto: AUROC 0.79 (95% CI 0.75-0.84)
Abstract Aims 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. Methods and results 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). Conclusions 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.
Kolk et al. (Wed,) conducted a cohort in Cardiomyopathy with LVEF ≤ 35% requiring primary prevention ICD (n=1,010). Machine learning models combining clinical variables and 12-lead ECG time-series features was evaluated on ICD non-arrhythmic mortality at three-year follow-up (AUROC 0.79, 95% CI 0.75-0.84). Machine learning models combining ECG and clinical variables predicted non-arrhythmic mortality within 3 years of ICD implantation with an AUROC of 0.79 (95% CI 0.75-0.84) in an external cohort.