Introduction Viral infections are often accompanied by reactive thrombocytosis, that is, increased activity of platelets, which is especially common in infants and children. Objective This study aimed to test the diagnostic properties of platelet indices, plateletcrit (PCT), mean platelet volume (MPV) and platelet distribution width (PDW), in children with beta corona virus 2 (SARS‐CoV‐2) infection. Methods The study included 232 patients below the age of 18 admitted to the coronavirus disease (COVID‐19) isolation wards at the Institute for Child and Youth Health Care of Vojvodina. PCT, MPV and PDW values on the day of admission were recorded. In total, 245 controls were selected from those treated for SARS‐CoV‐2 negative respiratory infections. Descriptive and inferential statistical analyses were performed. Results MPV and PDW were found important as independent predictors for COVID‐19 in children. Furthermore, the joint effect of MPV and PDW for predicting COVID‐19 was confirmed. The parameters showed better sensitivity than specificity. Conclusion Our study showed that PCT is not clinically significant, while MPV and PDW have diagnostic value in predicting COVID‐19 in children. In perspective, these parameters could be implemented in the various learning algorithms in order to achieve earlier diagnosis and treatment.

BACKGROUND: Clinical judgment of initial baseline laboratory tests plays an important role in triage and preliminary diagnosis among coronavirus disease 2019 (COVID-19) patients. OBJECTIVES: To determine the differences in laboratory parameters between COVID-19 and COVID-like patients, and between COVID-19 and healthy children. Additionally, to ascertain whether healthy children or patients with COVID-like symptoms would form a better control group. DESIGN AND SETTING: Cross-sectional study at the Institute for Child and Youth Health Care of Vojvodina, Novi Sad, Serbia. METHODS: A retrospective study was conducted on 42 pediatric patients of both sexes with COVID-19. Hematological parameters (white blood cell count, absolute lymphocyte count and platelet count) and biochemical parameters (natremia, kalemia, chloremia, aspartate aminotransferase [AST], alanine aminotransferase [ALT], lactate dehydrogenase [LDH] and C-reactive protein [CRP]) were collected. The first control group was formed by 80 healthy children and the second control group was formed by 55 pediatric patients with COVID-like symptoms. RESULTS: Leukocytosis, lymphopenia, thrombocytosis, elevated systemic inflammatory index and neutrophil-lymphocyte ratio, hyponatremia, hypochloremia and elevated levels of AST, ALT, LDH and CRP were present in COVID patients, in comparison with healthy controls, while in comparison with COVID-like controls only lymphopenia was determined. CONCLUSIONS: The presence of leukocytosis, lymphopenia, thrombocytosis, elevated systemic inflammatory index and neutrophil-lymphocyte ratio, hyponatremia, hypochloremia and elevated levels of AST, ALT, LDH and CRP may help healthcare providers in early identification of COVID-19 patients. Healthy controls were superior to COVID-like controls since they provided better insight into the laboratory characteristics of children with novel betacoronavirus (SARS-CoV-2) infection.

Background: The influenza virus and the novel beta coronavirus (SARS-CoV-2) have similar transmission characteristics, and it is very difficult to distinguish them clinically. With the development of information technologies, novel opportunities have arisen for the application of intelligent software systems in disease diagnosis and patient triage. Methods: A cross-sectional study was conducted on 268 infants: 133 infants with a SARS-CoV-2 infection and 135 infants with an influenza virus infection. In total, 10 hematochemical variables were used to construct an automated machine learning model. Results: An accuracy range from 53.8% to 60.7% was obtained by applying support vector machine, random forest, k-nearest neighbors, logistic regression, and neural network models. Alternatively, an automated model convincingly outperformed other models with an accuracy of 98.4%. The proposed automated algorithm recommended a random tree model, a randomization-based ensemble method, as the most appropriate for the given dataset. Conclusions: The application of automated machine learning in clinical practice can contribute to more objective, accurate, and rapid diagnosis of SARS-CoV-2 and influenza virus infections in children.