Supervised Machine Learning Approach to Identify Early Predictors of Poor Outcome in Patients with COVID-19 Presenting to a Large Quaternary Care Hospital in New York City

Abstract

Background: The progression of clinical manifestations in patients with coronavirus disease 2019 (COVID-19) highlights the need to account for symptom duration at the time of hospital presentation in decision-making algorithms. Methods: We performed a nested case–control analysis of 4103 adult patients with COVID-19 and at least 28 days of follow-up who presented to a New York City medical center. Multivariable logistic regression and classification and regression tree (CART) analysis were used to identify predictors of poor outcome. Results: Patients presenting to the hospital earlier in their disease course were older, had more comorbidities, and a greater proportion decompensated (<4 days, 41%; 4–8 days, 31%; >8 days, 26%). The first recorded oxygen delivery method was the most important predictor of decompensation overall in CART analysis. In patients with symptoms for <4, 4–8, and >8 days, requiring at least non-rebreather, age ≥ 63 years, and neutrophil/lymphocyte ratio ≥ 5.1; requiring at least non-rebreather, IL-6 ≥ 24.7 pg/mL, and D-dimer ≥ 2.4 µg/mL; and IL-6 ≥ 64.3 pg/mL, requiring non-rebreather, and CRP ≥ 152.5 mg/mL in predictive models were independently associated with poor outcome, respectively. Conclusion: Symptom duration in tandem with initial clinical and laboratory markers can be used to identify patients with COVID-19 at increased risk for poor outcomes.

Cytokine Response Following SARS-CoV-2 Antigen Stimulation in Patients with Predominantly Antibody Deficiencies

“…During natural infection with SARS-CoV-2, it has been observed that along with traditional markers of inflammation, such as C-reactive protein (CRP) and serum amyloid A, there are higher levels of specific pro-inflammatory cytokines, including interleukin 6 (IL-6), IL-1β, IL-8, IL-10, interferon gamma (IFN-γ), and tumor necrosis factor alpha (TNF-α) [ 38 ]. In addition, several other cytokines and chemokines have been shown to have altered expression in COVID-19, and the levels of some of these cytokines have been linked to the prognosis of COVID-19 [ 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 , 59 ]. However, some have speculated that in patients with inborn errors of immunity, immunodeficiency might act as a protective factor against the cytokine storm, which is the main trigger for the severe course of COVID-19 [ 60 ].…”

Prognostic Role of Neutrophil-to-Lymphocyte Ratio in Patients with COVID-19

“…The NLR at admission to the emergency department had a capacity to predict disease severity (area under the curve (AUC), 0.59; cut-off value, 6.88; sensitivity, 48%; specificity, 66%) and disease mortality (AUC, 0.62; cut-off value, 8.23; sensitivity, 47%; specificity, 72%). Similarly, a large case–control study from the USA [ 9 ] analyzed 4103 COVID-19 patients and found that an elevated NLR (cut-off value, 5.1) was an early predictor of poor outcomes (mechanical ventilation, death or discharge to hospice). Another large retrospective cohort study from the USA [ 10 ] searched for factors associated with “care transitions” (i.e., transition from the emergency department to the inpatient floor and also to the ICU) by analyzing data from 11,406 COVID-19 patients.…”