Search

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. [ABSTRACT FROM AUTHOR]

Background: We aimed to evaluate the association between public media and trends in new presentations of acute coronary syndrome (ACS) during the first wave of the coronavirus disease 2019 (COVID‑19) in the Netherlands. Methods: New ACS presentations per week in 73 hospitals during the first half of 2019 and 2020 were retrieved from the national organisation Dutch Hospital Data and incidence rates were calculated. Stratified analyses were performed by region, type of ACS and patient characteristics. Results: After the first confirmed COVID‑19 case and during lockdown, numbers declined by up to 41% (95% confidence interval (CI): 36–47%) compared to 2019. This reduction was more pronounced for non-ST-segment elevation myocardial infarction (NSTEMI) (48%; 95% CI: 39–55%) and unstable angina (UA; 50%; 95% CI: 40–59%) than for STEMI (34%; 95% CI: 23–43%). There was no association between ACS and COVID‑19 incidence rate per region. After the steep decline, a public campaign encouraged patients not to postpone hospital visits. Numbers then increased, without a rebound effect. Trends were similar irrespective of sex, age or socio-economic status. During the outbreak, compared to coronary artery bypass graft procedures, relatively more (acute) percutaneous coronary interventions for NSTEMI and UA were performed. Conclusion: New ACS presentations decreased by up to 41%. Lockdown measures and public campaigns, rather than COVID‑19 incidence, were associated with significant changes in new ACS presentations. Even though causality cannot be established, this emphasises the role of the public media and healthcare organisations in informing patients to prevent underdiagnoses of ACS and associated health damage. [ABSTRACT FROM AUTHOR]

Abstract: Background: The focus of the diagnostic process in chest pain patients at the emergency department is to identify both low and high risk patients for an acute coronary syndrome (ACS). The HEART score was designed to facilitate this process. This study is a prospective validation of the HEART score. Methods: A total of 2440 unselected patients presented with chest pain at the cardiac emergency department of ten participating hospitals in The Netherlands. The HEART score was assessed as soon as the first lab results and ECG were obtained. Primary endpoint was the occurrence of major adverse cardiac events (MACE) within 6weeks. Secondary endpoints were (i) the occurrence of AMI and death, (ii) ACS and (iii) the performance of a coronary angiogram. The performance of the HEART score was compared with the TIMI and GRACE scores. Results: Low HEART scores (values 0–3) were calculated in 36.4% of the patients. MACE occurred in 1.7%. In patients with HEART scores 4–6, MACE was diagnosed in 16.6%. In patients with high HEART scores (values 7–10), MACE occurred in 50.1%. The c-statistic of the HEART score (0.83) is significantly higher than the c-statistic of TIMI (0.75)and GRACE (0.70) respectively (p<0.0001). Conclusion: The HEART score provides the clinician with a quick and reliable predictor of outcome, without computer-required calculating. Low HEART scores (0–3), exclude short-term MACE with >98% certainty. In these patients one might consider reserved policies. In patients with high HEART scores (7–10) the high risk of MACE may indicate more aggressive policies. [Copyright &y& Elsevier]