Multi-marker risk assessment in patients hospitalized with COVID-19: Results from the American Heart Association COVID-19 Cardiovascular Disease Registry

Impact of COVID-19 in patients with heart failure with mildly reduced or preserved ejection fraction enrolled in the DELIVER trial

AIM

COVID-19 may affect clinical risk in patients with heart failure. DELIVER began before and was conducted during the COVID-19 pandemic. This study aimed to evaluate the association between COVID-19 and clinical outcomes among DELIVER participants.

METHODS AND RESULTS

Participants with chronic heart failure with mildly reduced or preserved ejection fraction (HFmrEF/HFpEF) were randomized to dapagliflozin or placebo across 350 sites in 20 countries. COVID-19 was investigator-reported and the contribution of COVID-19 to death was centrally adjudicated. We assessed (i) the incidence of COVID-19, (ii) event rates before/during the pandemic, and (iii) risks of death after COVID-19 diagnosis compared to risks of death in participants without COVID-19. Further, we performed a sensitivity analysis assessing treatment effects of dapagliflozin vs. placebo censored at pandemic onset. Of 6263 participants, 589 (9.4%) developed COVID-19, of whom 307 (52%) required/prolonged hospitalization. A total of 155 deaths (15% of all deaths) were adjudicated as definitely/possibly COVID-19-related. COVID-19 cases and deaths did not differ by randomized assignment. Death rate in the 12 months following diagnosis was 56.1 (95% confidence interval [CI] 48.0-65.6) versus 6.4 (95% CI 6.0-6.8)/100 participant-years among trial participants with versus without COVID-19 (adjusted hazard ratio [aHR] 8.60, 95% CI 7.18-10.30). Risk was highest 0-3 months following diagnosis (153.5, 95% CI 130.3-180.8) and remained elevated at 3-6 months (12.6, 95% CI 6.6-24.3/100 participant-years). After excluding investigator-reported fatal COVID-19 events, all-cause death rates in the 12 months following diagnosis among COVID-19 survivors (n = 458) remained higher (aHR 2.46, 95% CI 1.83-3.33) than rates for all trial participants from randomization, with censoring of participants who developed COVID-19 at the time of diagnosis. Dapagliflozin reduced cardiovascular death/worsening HF events when censoring participants at COVID-19 diagnosis (HR 0.81, 95% CI 0.72-0.91) and pandemic onset (HR 0.72, 95% CI 0.58-0.89). There were no diabetic ketoacidosis or major hypoglycaemic events within 30 days of COVID-19.

CONCLUSION

DELIVER is one of the most extensive experiences with COVID-19 of any cardiovascular trial, with >75% of follow-up time occurring during the pandemic. COVID-19 was common, with >50% of cases leading to hospitalization or death. Treatment benefits of dapagliflozin persisted when censoring at COVID-19 diagnosis and pandemic onset. Patients surviving COVID-19 had a high early residual risk.

CLINICAL TRIAL REGISTRATION

ClinicalTrials.gov Identifier NCT03619213.

Hyperparameter optimization for cardiovascular disease data-driven prognostic system

Prediction and diagnosis of cardiovascular diseases (CVDs) based, among other things, on medical examinations and patient symptoms are the biggest challenges in medicine. About 17.9 million people die from CVDs annually, accounting for 31% of all deaths worldwide. With a timely prognosis and thorough consideration of the patient's medical history and lifestyle, it is possible to predict CVDs and take preventive measures to eliminate or control this life-threatening disease. In this study, we used various patient datasets from a major hospital in the United States as prognostic factors for CVD. The data was obtained by monitoring a total of 918 patients whose criteria for adults were 28-77 years old. In this study, we present a data mining modeling approach to analyze the performance, classification accuracy and number of clusters on Cardiovascular Disease Prognostic datasets in unsupervised machine learning (ML) using the Orange data mining software. Various techniques are then used to classify the model parameters, such as k-nearest neighbors, support vector machine, random forest, artificial neural network (ANN), naïve bayes, logistic regression, stochastic gradient descent (SGD), and AdaBoost. To determine the number of clusters, various unsupervised ML clustering methods were used, such as k-means, hierarchical, and density-based spatial clustering of applications with noise clustering. The results showed that the best model performance analysis and classification accuracy were SGD and ANN, both of which had a high score of 0.900 on Cardiovascular Disease Prognostic datasets. Based on the results of most clustering methods, such as k-means and hierarchical clustering, Cardiovascular Disease Prognostic datasets can be divided into two clusters. The prognostic accuracy of CVD depends on the accuracy of the proposed model in determining the diagnostic model. The more accurate the model, the better it can predict which patients are at risk for CVD.

Echocardiography in Coronavirus Disease 2019 Era: A Single Tool for Diagnosis and Prognosis

Coronavirus disease 2019 (COVID-19) is characterized by multi-organ involvement, including respiratory and cardiac events. Echocardiography is widely considered the first-choice tool for the evaluation of cardiac structures and function because of its reproducibility, feasibility, easy to use at bedside, and for good cost-effectiveness. The aim of our literature review is to define the utility of echocardiography in the prediction of prognosis and mortality in COVID-19 patients with mild to critical respiratory illness, with or without known cardiovascular disease. Moreover, we focused our attention on classical echocardiographic parameters and the use of speckle tracking to predict the evolution of respiratory involvement. Finally, we tried to explore the possible relationship between pulmonary disease and cardiac manifestations.