Mortality and Complications of COVID-19 Among Adult Congenital Heart Disease Patients: A Retrospective Cohort Study Using the National Inpatient Sample Database.

This study examines in-hospital mortality and complicated COVID-19 infection among adult congenital heart disease (ACHD) patients admitted with COVID-19, using the National Inpatient Sample (NIS). A total of 4219 COVID-19 patients with ACHD were included. We demonstrated that COVID-19 patients with ACHD were more likely to experience in-hospital mortality (OR 1.04, 95% CI 1.04-1.04, P < 0.01) and complicated COVID-19 infection (OR: 1.30, 95% CI: 1.11-1.53, P < 0.01). In our sub-group analysis, COVID-19 patients with tetralogy of Fallot (TOF) had higher mortality and COVID-19 patients with atrial septal defects (ASD) had a higher incidence of complicated infection when compared to COVID-19 patients with all other ACHDs. Risk factors for mortality among COVID-19 patients with ACHD include advanced age, lower income, unrepaired ACHD, malnutrition, and chronic liver disease. Accordingly, we recommend aggressive preventive care with vaccination and non-pharmacologic measures in order to improve survival for ACHD patients.

Population Risk Factors for Severe Disease and Mortality in COVID-19 in the United States during the Pre-Vaccine Era: A Retrospective Cohort Study of National Inpatient Sample.

Background-Previous studies on coronavirus disease 2019 (COVID-19) were limited to specific geographical locations and small sample sizes. Therefore, we used the National Inpatient Sample (NIS) 2020 database to determine the risk factors for severe outcomes and mortality in COVID-19. Methods-We included adult patients with COVID-19. Univariate and multivariate logistic regression was performed to determine the predictors of severe outcomes and mortality in COVID-19. Results-1,608,980 (95% CI 1,570,803-1,647,156) hospitalizations with COVID-19 were included. Severe complications occurred in 78.3% of COVID-19 acute respiratory distress syndrome (ARDS) and 25% of COVID-19 pneumonia patients. The mortality rate for COVID-19 ARDS was 54% and for COVID-19 pneumonia was 16.6%. On multivariate analysis, age > 65 years, male sex, government insurance or no insurance, residence in low-income areas, non-white races, stroke, chronic kidney disease, heart failure, malnutrition, primary immunodeficiency, long-term steroid/immunomodulatory use, complicated diabetes mellitus, and liver disease were associated with COVID-19 related complications and mortality. Cardiac arrest, septic shock, and intubation had the highest odds of mortality. Conclusions-Socioeconomic disparities and medical comorbidities were significant determinants of mortality in the US in the pre-vaccine era. Therefore, aggressive vaccination of high-risk patients and healthcare policies to address socioeconomic disparities are necessary to reduce death rates in future pandemics.

Novel ensemble of optimized CNN and dynamic selection techniques for accurate Covid-19 screening using chest CT images.

The world is significantly affected by infectious coronavirus disease (covid-19). Timely prognosis and treatment are important to control the spread of this infection. Unreliable screening systems and limited number of clinical facilities are the major hurdles in controlling the spread of covid-19. Nowadays, many automated detection systems based on deep learning techniques using computed tomography (CT) images have been proposed to detect covid-19. However, these systems have the following drawbacks: (i) limited data problem poses a major hindrance to train the deep neural network model to provide accurate diagnosis, (ii) random choice of hyperparameters of Convolutional Neural Network (CNN) significantly affects the classification performance, since the hyperparameters have to be application dependent and, (iii) the generalization ability using CNN classification is usually not validated. To address the aforementioned issues, we propose two models: (i) based on a transfer learning approach, and (ii) using novel strategy to optimize the CNN hyperparameters using Whale optimization-based BAT algorithm + AdaBoost classifier built using dynamic ensemble selection techniques. According to our second method depending on the characteristics of test sample, the classifier is chosen, thereby reducing the risk of overfitting and simultaneously produced promising results. Our proposed methodologies are developed using 746 CT images. Our method obtained a sensitivity, specificity, accuracy, F-1 score, and precision of 0.98, 0.97, 0.98, 0.98, and 0.98, respectively with five-fold cross-validation strategy. Our developed prototype is ready to be tested with huge chest CT images database before its real-world application.