![]() The first data-driven approach, tree-based analysis, allowed to identify profiles of patients with different risks of in-hospital death and severity respiratory distress, and to unravel the role of highly dependent covariates on risk stratification. To pursue these aims, two different advanced statistical approaches were performed, along with standard statistical methods such as Cox and logistic regression analyses. To this extent, our goal is to identify risk profiles of patients that might develop different severity of Covid-19 disease. ![]() Indeed, very often Covid-19 severity outcome has been evaluated by means of Intensive Care Unit (ICU) binary outcome which may be misleading being affected both by the epidemic wave strength as well as by the ICU regional health policies. The novelty of our approach is to consider as severity outcome the variable SOFA (Sequential Organ Failure Assessment) 6 defined on respiratory system according to 5 increasing levels of severity, a measure that accounts for the real individual Covid-19 evolution rather than for external factors. In this paper we aim at evaluating the effect of Covid-19 risk factors not only on in-hospital death but also on severity of respiratory distress. Moreover, fully understanding the characteristics of Covid-19-related severity of respiratory distress is also necessary for an early identification and precise treatment 5. Understanding the relationship between comorbidities, therapy, and Covid-19 mortality is needed to efficiently guide clinical and public health interventions. Older age, cardiovascular and kidney comorbidities, are among the most important risk factors influencing the virus–host interaction and the clinical outcome of Covid-19 3, 4. It has been reported that patients with underlying disease are more likely to contract Coronavirus disease 19 (Covid-19) and become critically ill 1, 2. ![]() This analysis confirmed the influence of creatinine and CRP on the severity of respiratory distress. Furthermore, to investigate the multivariate dependence structure among the demographic characteristics, the admission values, the comorbidities and the severity of respiratory distress, the Bayesian Network analysis was applied. Based on the CART analysis, the subgroups most at-risk of severity of respiratory distress were defined by patients with creatinine level \(\ge\) 1.2 mg/dL. ![]() The ST analysis identified as the most at-risk group for in-hospital death the patients with age > 65 years, creatinine \(\ge\) 1.2 mg/dL, CRP \(\ge\) 25 mg/L and anti-hypertensive treatment. First, the tree-based analysis allowed to identify profiles of patients with different risk of in-hospital death (by Survival Tree-ST analysis) and severity of respiratory distress (by Classification and Regression Tree-CART analysis), and to unravel the role on risk stratification of highly dependent covariates (i.e., demographic characteristics, admission values and comorbidities). ![]() In this paper, two different advanced data-driven statistical approaches along with standard statistical methods have been implemented to identify groups of patients most at-risk for death or severity of respiratory distress. A full understanding of the characteristics of Covid-19 patients with a better chance of experiencing poor vital outcomes is critical for implementing accurate and precise treatments. ![]()
0 Comments
Leave a Reply. |