Predictors of Mortality Using Machine Learning Decision Tree Algorithm in Critically Ill Adult Patients with COVID-19 Admitted to the ICU. (preprint)

Background:The Coronavirus Disease-19 (COVID-19) caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) is a major cause of intensive care unit (ICU) admissions globally. Robust data of epidemiology, characteristics, and disease outcomes from different regions and populations showed considerable variations. However, limited number of reports addressed predictors of mortality utilizing machine learning methods. Herein, we aimed to describe the association and relationship of a predefined set of variables found to be predictive of 28–day ICU outcome among adults COVID-19 patients admitted to the ICU using a machine learning decision tree (DT) algorithm.Methods:This was a prospective/retrospective, multicenter cohort study from 14 hospitals in Saudi Arabia. We included critically ill COVID-19 patients admitted to the ICU between March 1, 2020, and October 31, 2020. The primary outcome was 28-day ICU mortality. Secondary outcomes were 90-day mortality and ICU length of stay. The predictors of mortality were identified using two predictive models, the conventional logistic regression and DT analysis.Results:A total of 1468 critically ill COVID-19 patients were included. The mean age was 55.9 (SD±15.1) years, with 74% of the patients were males. The 28-day ICU mortality was 540 (36.8%), while 90-day mortality was 600 (40.9%). The multivariable logistic regression model demonstrated that the PaO2/FiO2 ratio on ICU admission and the need for intubation or vasopressors could strongly predict 28-day ICU mortality. The DT algorithm identified five variables [need for intubation, need for vasopressors, age, gender, and PaO2/FiO2 ratio] provided in an algorithmic fashion to predict 28-day ICU outcome. Conclusion:Five clinical predictors of 28-day ICU outcome were identified using DT algorithmic analysis of COVID-19 patients admitted to ICU. The findings of this DT analysis may be used in ICU for early identification of critically ill COVID-19 patients who are at high risk of 28-day mortality.

Tocilizumab Effect in COVID-19 Hospitalized Patients: A Systematic Review and Meta-Analysis of Randomized Control Trials (preprint)

Since the emergence of the first cases of COVID-19 viral pneumonia late 2019 several studies evaluated the benefits of different treatment modalities. Early in the pandemic, the interleukin 6 (IL-6) receptor antibody Tocilizumab was considered in view of the cytokine release syndrome associated with COVID-19 infection. Several early observational studies showed beneficial effect of treatment with Tocilizumab on mortality, however, results from well-designed randomized clinical trials (RCT) were contradicting. ObjectivesTo perform a systematic literature review and meta-analysis of RCTs utilizing Tocilizumab in the treatment of COVID-19 pneumonia, with in-hospital mortality as a primary objective, while secondary objectives included composite outcome of mortality, intubation, or ICU admission, another secondary outcome was super added infection. MethodThis was a random effects model (DerSimonian and Laird) model of relative risk (RR), along with corresponding 95% confidence intervals, p values, and forest plots of both primary and secondary outcomes. A fixed effect sensitivity test was performed for the primary outcome, in addition to subgroup and meta-regression analyses with predefined criteria. ResultsThe primary outcome of mortality showed statistically insignificant reduction of mortality with Tocilizumab (RR = 0.9, 95% CI: 0.8 - 1.01; p = 0.09) although with an unmistakable apparent clinical benefit. There was a significant reduction in the RR of the secondary composite outcome (RR = 0.83, 95% CI: 0.76 - 0.9; p < 0.001), and no difference between groups in super-added infection (RR = 0.77, 95% CI: 0.51 - 1.19; p = 0.24). Treatment protocol allowing a second dose was the only significant predictor of improved mortality in the meta-regression analysis. Certainty of evidence was reduced to moderate for the primary outcome and the secondary outcome of clinical deterioration, while it was reduced to low for the secondary outcome of super-added infection. ConclusionModerate certainty of evidence suggest no statistically significant improvement of 28-30 day all-cause mortality of hospitalized COVID-19 patients treated with TCZ, although there may be clinically important value. Moderate certainty of evidence suggest lowered relative risk of a composite outcome of death or clinical deterioration, while, low grade evidence indicate no increase in the risk of super-added infection associated with TCZ treatment. A protocol allowing two doses of TCZ shows evidence of improved mortality as compared to a strictly single dose protocol.