The association between therapeutic plasma exchange and the risk of mortality among patients critically ill with COVID-19: a meta-analysis

Application of Machine Learning in Hospitalized Patients with Severe COVID-19 Treated with Tocilizumab

Among the IL-6 inhibitors, tocilizumab is the most widely used therapeutic option in patients with SARS-CoV-2-associated severe respiratory failure (SRF). The aim of our study was to provide evidence on predictors of poor outcome in patients with COVID-19 treated with tocilizumab, using machine learning (ML) techniques. We conducted a retrospective study, analyzing the clinical, laboratory and sociodemographic data of patients admitted for severe COVID-19 with SRF, treated with tocilizumab. The extreme gradient boost (XGB) method had the highest balanced accuracy (93.16%). The factors associated with a worse outcome of tocilizumab use in terms of mortality were: baseline situation at the start of tocilizumab treatment requiring invasive mechanical ventilation (IMV), elevated ferritin, lactate dehydrogenase (LDH) and glutamate-pyruvate transaminase (GPT), lymphopenia, and low PaFi [ratio between arterial oxygen pressure and inspired oxygen fraction (PaO₂/FiO₂)] values. The factors associated with a worse outcome of tocilizumab use in terms of hospital stay were: baseline situation at the start of tocilizumab treatment requiring IMV or supplemental oxygen, elevated levels of ferritin, glutamate-oxaloacetate transaminase (GOT), GPT, C-reactive protein (CRP), LDH, lymphopenia, and low PaFi values. In our study focused on patients with severe COVID-19 treated with tocilizumab, the factors that were weighted most strongly in predicting worse clinical outcome were baseline status at the start of tocilizumab treatment requiring IMV and hyperferritinemia.

Efficacy of Red Blood Cell Exchange as Adjunctive Treatment for Hypoxemia and Survival Rate of Patients With Severe Coronavirus-2 Disease: An Open-Labeled Phase 2 Randomized Clinical Trial

Background

Severe acute respiratory syndrome (SARS) coronavirus-2 may infect red blood cells (RBCs) and impact oxygenation. We aimed to evaluate the efficacy of RBC exchange as an adjunctive treatment for hypoxemia and the survival rate of patients with severe coronavirus disease 2019 (COVID-19).

Methods

In a randomized clinical trial, we divided sixty patients with severe COVID-19 into two groups. The intervention group received the standard treatment of severe COVID-19 with RBC exchange three to four times in 2 days. The control group only received the standard treatment. Our primary outcomes were improving hypoxemia in 7 days, recovery or discharge, and death in 28 days. We conducted Chi-square test, independent samples t-test, and Fisher’s exact test to analyze the results. The ethical committee of Aja University of Medical Sciences approved the study (IR.AJAUMS.REC.1399.054), and the Iranian clinical trial registration organization registered it (IRCT20160316027081N2).

Results

Twenty-nine men and thirty-one women with a mean age of 67.5 years entered the study. The frequency of hypertension and diabetes mellitus was 86.7 and 68.3%, respectively. The most common symptoms of severe COVID-19 were dyspnea (91.6%), cough (75%), and fever (66.6%). Our results showed that hypoxemia improved in 21 of the 30 patients (70%) in the intervention group and 10 of the 30 patients (33.3%) in the control group (P < 0.004). The recovery and discharge rates were 19 of 30 patients (63.3%) in the intervention group and 2 of 30 patients (6.7%) in the control group (P < 0.001).

Conclusion

The RBC exchange improved the oxygenation and survival rate in patients with severe COVID-19.