English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

An outbreak of the 2019 novel Coronavirus epidemic (COVID-19) has rapidly spread worldwide. The coronavirus (COVID-19) has also spread among children, but it has been less severe than in adults. The characteristics of COVID-19 laboratory findings play a significant role in clinical manifestations, diagnosis, and treatment. Since the numbers of COVID-19 cases increased, it takes more time to interpret the lab outcomes and provide an accurate diagnosis. Little information about the clinical symptoms and epidemiological of COVID-19 is known. There is a need to investigate the characteristics of laboratory findings for the clinical decision-making system using predictive algorithms. This study aims to classify and validate machine learning approaches for detecting COVID-19 in children. The five well-known machine learning approaches: the artificial neural network (ANN); random forest (RF); support vector machines (SVM); decision trees (DT) which include classification and regression trees (CART); and gradient boosted trees (GBM) were used. All these approaches have been considered in the classification, and to determine the most suitable model. The performance of each model test was by conducted using a standard 10-fold cross-validation procedure. Given these results for classification performance and prediction of accuracy, CART is the best predictive model for classifications for children with COVID-19. The results of the study illustrate that the best classification performance was achieved with CART model to provide 92.5% accuracy for binary classes (positive vs. negative) based on laboratory findings. Leukocytes, Monocytes, Potassium, and Eosinophils, were among the most important predictors which indicate that those features may play a crucial role in COVID-19. Ultimately, our model may be helpful for medical experts to predict COVID-19 and can help invalidate their primary laboratory findings of children. ML methods can be a convenient tool for providing predictions for COVID-19 laboratory findings among Children.

Evaluation of Machine Learning Models to Forecast COVID-19 Relying on Laboratory Outcomes Characteristics in Children