Clinical Hematochemical Parameters in Differential Diagnosis between Pediatric SARS-CoV-2 and Influenza Virus Infection: An Automated Machine Learning Approach.

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.

Hemogram-based decision tree models for discriminating COVID-19 from RSV in infants.

OBJECTIVE: Decision trees are efficient and reliable decision-making algorithms, and medicine has reached its peak of interest in these methods during the current pandemic. Herein, we reported several decision tree algorithms for a rapid discrimination between coronavirus disease (COVID-19) and respiratory syncytial virus (RSV) infection in infants. METHODS: A cross-sectional study was conducted on 77 infants: 33 infants with novel betacoronavirus (SARS-CoV-2) infection and 44 infants with RSV infection. In total, 23 hemogram-based instances were used to construct the decision tree models via 10-fold cross-validation method. RESULTS: The Random forest model showed the highest accuracy (81.8%), while in terms of sensitivity (72.7%), specificity (88.6%), positive predictive value (82.8%), and negative predictive value (81.3%), the optimized forest model was the most superior one. CONCLUSION: Random forest and optimized forest models might have significant clinical applications, helping to speed up decision-making when SARS-CoV-2 and RSV are suspected, prior to molecular genome sequencing and/or antigen testing.

Could platelet indices have diagnostic properties in children with COVID-19?

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.

Incidence of Type 1 Diabetes Mellitus and Characteristics of Diabetic Ketoacidosis in Children and Adolescents during the First Two Years of the COVID-19 Pandemic in Vojvodina.

Background and Objectives: The COVID-19 pandemic has led to significant changes globally, which has also affected patients with type 1 diabetes mellitus (T1DM). This study aimed to determine the incidence of T1DM and the characteristics of diabetic ketoacidosis (DKA) during the pandemic comparing it to pre-pandemic period. Materials and Methods: Data from patients <19 years with newly diagnosed T1DM between 1st January 2017 and 31st December 2021 from four regional centers in Vojvodina were retrospectively collected and analyzed. Results: In 2021, the highest incidence of T1DM in the last five years was recorded, 17.3/100,000. During the pandemic period (2020-2021), there were 99 new-onset T1DM, of which 42.4% presented in DKA, which is significantly higher than in the pre-pandemic period (34.1%). During the pandemic, symptom duration of T1DM lasted significantly longer than before the COVID-19 period. At the age of 10-14 years, the highest incidence of T1DM and COVID-19, the highest frequency rate of DKA, and severe DKA were observed. Conclusions: The pandemic is associated with a high incidence rate of T1DM, longer duration of symptoms of T1DM, a high frequency of DKA, and a severe DKA at diagnosis. Patients aged 10-14 years are a risk group for the occurrence of T1DM with severe clinical presentation. Additional studies are needed with a longer study period and in a wider geographical area, with data on exposure to COVID-19 infection, the permanence of new-onset T1DM, and the psychosocial impact of the pandemic.