Abstract
Background . Since the onset of the COVID -19 pandemic, interindividual variability in the course of the disease has been reported , indicating a wide range of factors influencing it. Factors most commonly associated with increased severity of COVID -19 disease include older age, obesity, and diabetes. The impact of the cytokine storm is complex, reflecting the complexity of the immunological processes triggered by SARS - CoV -2 infection. A modern problem such as a worldwide pandemic requires modern solutions, which in this case involve the use of machine learning to analyze differences in the clinical properties of populations affected by the disease and then assess its significance, which in turn leads to the creation of a tool that applicable to assess the individual risk of infection with SARS - CoV -2. Methods . Values of biochemical and morphological parameters of 781 patients ( Kazakhstan, Shymkent ) were collected and used for static analysis. The Spearman rank correlation coefficient formula was used to estimate the correlations between each of the traits in the population . Results . The highest correlation coefficients were shown by such parameters as , patient's age and sex , serum glucose, while the highest inverse correlation coefficient was estimated for serum red blood cell count. Conclusion . The current analysis indicates a range of parameters available for routine screening in clinical settings. A tool based on these parameters is also presented, useful for assessing the individual risk of developing COVID -19 in patients. A limitation of the study is the demographics of the study population, which may limit its general applicability.