Implantable defibrillator therapy and mortality in patients with non-ischaemic dilated cardiomyopathy : An updated meta-analysis and effect on Dutch clinical practice by the Task Force of the Dutch Society of Cardiology.

BACKGROUND: Primary prophylactic implantable cardioverter-defibrillators (ICDs) in patients with non-ischaemic cardiomyopathy (NICMP) remains controversial. This study sought to assess the benefit of ICD therapy with or without cardiac resynchronisation therapy (CRT) in patients with NICMP. In addition, data were compared with real-world clinical data to perform a risk/benefit analysis. METHODS: Relevant randomised clinical trials (RCTs) published in meta-analyses since DANISH, and in PubMed, EMBASE and Cochrane databases from 2016 to 2020 were identified. The benefit of ICD therapy stratified by CRT use was assessed using random effects meta-analysis techniques. RESULTS: Six RCTs were included in the meta-analysis. Among patients without CRT, ICD use was associated with a 24% reduction in mortality (hazard ratio [HR]: 0.76; 95% confidence interval [CI]: 0.62-0.93; P = 0.008). In contrast, among patients with CRT, a CRT-defibrillator was not associated with reduced mortality (HR: 0.74, 95% CI 0.47-1.16; P = 0.19). For ICD therapy without CRT, absolute risk reduction at 3­years follow-up was 3.7% yielding a number needed to treat of 27. CONCLUSION: ICD use significantly improved survival among patients with NICMP who are not eligible for CRT. Considering CRT, the addition of defibrillator therapy was not significantly associated with mortality benefit compared with CRT pacemaker.

Electrocardiogram-based mortality prediction in patients with COVID-19 using machine learning.

BACKGROUND AND PURPOSE: The electrocardiogram (ECG) is frequently obtained in the work-up of COVID-19 patients. So far, no study has evaluated whether ECG-based machine learning models have added value to predict in-hospital mortality specifically in COVID-19 patients. METHODS: Using data from the CAPACITY-COVID registry, we studied 882 patients admitted with COVID-19 across seven hospitals in the Netherlands. Raw format 12-lead ECGs recorded within 72 h of admission were studied. With data from five hospitals (n = 634), three models were developed: (a) a logistic regression baseline model using age and sex, (b) a least absolute shrinkage and selection operator (LASSO) model using age, sex and human annotated ECG features, and (c) a pre-trained deep neural network (DNN) using age, sex and the raw ECG waveforms. Data from two hospitals (n = 248) was used for external validation. RESULTS: Performances for models a, b and c were comparable with an area under the receiver operating curve of 0.73 (95% confidence interval [CI] 0.65-0.79), 0.76 (95% CI 0.68-0.82) and 0.77 (95% CI 0.70-0.83) respectively. Predictors of mortality in the LASSO model were age, low QRS voltage, ST depression, premature atrial complexes, sex, increased ventricular rate, and right bundle branch block. CONCLUSION: This study shows that the ECG-based prediction models could be helpful for the initial risk stratification of patients diagnosed with COVID-19, and that several ECG abnormalities are associated with in-hospital all-cause mortality of COVID-19 patients. Moreover, this proof-of-principle study shows that the use of pre-trained DNNs for ECG analysis does not underperform compared with time-consuming manual annotation of ECG features.