Search

Anticoagulation during extracorporeal membrane oxygenation (ECMO) for Coronovirus Disease 2019 (COVID-19) can be performed by direct or indirect thrombin inhibitors but differences in outcomes with these agents are uncertain. A retrospective, multicenter study was conducted. All consecutive adult patients with COVID-19 placed on ECMO between March 1, 2020 and April 30, 2021 in participating centers, were included. Patients were divided in groups receiving either a direct thrombin inhibitor (DTI) or an indirect thrombin inhibitor such as unfractionated heparin (UFH). Overall, 455 patients with COVID-19 from 17 centers were placed on ECMO during the study period. Forty-four patients did not receive anticoagulation. Of the remaining 411 patients, DTI was used in 160 (39%) whereas 251 (61%) received UFH. At 90-days, in-hospital mortality was 50% (DTI) and 61% (UFH), adjusted hazard ratio: 0.81, 95% confidence interval (CI): 0.49-1.32. Deep vein thrombosis [adjusted odds ratio (aOR): 2.60, 95% CI: 0.90-6.65], ischemic (aOR: 1.58, 95% CI: 0.18-14.0), and hemorrhagic (aOR:1.22, 95% CI: 0.39-3.87) stroke were similar with DTI in comparison to UFH. Bleeding requiring transfusion was lower in patients receiving DTI (aOR: 0.40, 95% CI: 0.18-0.87). Anticoagulants that directly inhibit thrombin are associated with similar in-hospital mortality, stroke, and venous thrombosis and do not confer a higher risk of clinical bleeding in comparison to conventional heparin during ECMO for COVID-19., Competing Interests: Disclosure: The authors have no conflicts of interest to report., (Copyright © ASAIO 2022.)

Background: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has a variable clinical course with significant mortality. Early reports suggested higher rates of SARS-CoV-2 infection in patients with type A blood and enrichment of type A individuals among COVID-19 mortalities., Study Design and Methods: The study includes all patients hospitalized or with an emergency department (ED) visit who were tested for SARS-CoV-2 between March 10, 2020 and June 8, 2020 and had a positive test result by nucleic acid test (NAT) performed on a nasopharyngeal swab specimen. A total of 4968 patients met the study inclusion criteria, with a subsequent 23.1% (n = 1146/4968) all-cause mortality rate in the study cohort. To estimate overall risk by ABO type and account for the competing risks of in-hospital mortality and discharge, we calculated the cumulative incidence function (CIF) for each event. Cause-specific hazard ratios (csHRs) for in-hospital mortality and discharge were analyzed using multivariable Cox proportional hazards models., Results: Type A blood was associated with the increased cause-specific hazard of death among COVID-19 patients compared to type O (HR = 1.17, 1.02-1.33, p = .02) and type B (HR = 1.32,1.10-1.58, p = .003)., Conclusions: Our study shows that ABO histo-blood group type is associated with the risk of in-hospital death in COVID-19 patients, warranting additional inquiry. Elucidating the mechanism behind this association may reveal insights into the susceptibility and/or immunity to SARS-CoV-2., (© 2021 AABB.)

Background: During a pandemic, it is important for clinicians to stratify patients and decide who receives limited medical resources. Machine learning models have been proposed to accurately predict COVID-19 disease severity. Previous studies have typically tested only one machine learning algorithm and limited performance evaluation to area under the curve analysis. To obtain the best results possible, it may be important to test different machine learning algorithms to find the best prediction model., Objective: In this study, we aimed to use automated machine learning (autoML) to train various machine learning algorithms. We selected the model that best predicted patients' chances of surviving a SARS-CoV-2 infection. In addition, we identified which variables (ie, vital signs, biomarkers, comorbidities, etc) were the most influential in generating an accurate model., Methods: Data were retrospectively collected from all patients who tested positive for COVID-19 at our institution between March 1 and July 3, 2020. We collected 48 variables from each patient within 36 hours before or after the index time (ie, real-time polymerase chain reaction positivity). Patients were followed for 30 days or until death. Patients' data were used to build 20 machine learning models with various algorithms via autoML. The performance of machine learning models was measured by analyzing the area under the precision-recall curve (AUPCR). Subsequently, we established model interpretability via Shapley additive explanation and partial dependence plots to identify and rank variables that drove model predictions. Afterward, we conducted dimensionality reduction to extract the 10 most influential variables. AutoML models were retrained by only using these 10 variables, and the output models were evaluated against the model that used 48 variables., Results: Data from 4313 patients were used to develop the models. The best model that was generated by using autoML and 48 variables was the stacked ensemble model (AUPRC=0.807). The two best independent models were the gradient boost machine and extreme gradient boost models, which had an AUPRC of 0.803 and 0.793, respectively. The deep learning model (AUPRC=0.73) was substantially inferior to the other models. The 10 most influential variables for generating high-performing models were systolic and diastolic blood pressure, age, pulse oximetry level, blood urea nitrogen level, lactate dehydrogenase level, D-dimer level, troponin level, respiratory rate, and Charlson comorbidity score. After the autoML models were retrained with these 10 variables, the stacked ensemble model still had the best performance (AUPRC=0.791)., Conclusions: We used autoML to develop high-performing models that predicted the survival of patients with COVID-19. In addition, we identified important variables that correlated with mortality. This is proof of concept that autoML is an efficient, effective, and informative method for generating machine learning-based clinical decision support tools., (©Kenji Ikemura, Eran Bellin, Yukako Yagi, Henny Billett, Mahmoud Saada, Katelyn Simone, Lindsay Stahl, James Szymanski, D Y Goldstein, Morayma Reyes Gil. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 26.02.2021.)