Article citationsMore>>

Cooper, G.F., Aliferis, C.F., Ambrosino, R., Aronis, J., Buchanan, B.G., Caruana, R., Fine, M.J., Glymour, C., Gordon, G., Hanusa, B.H., Janosky, J.E., Meek, C., Mitchell, T., Richardson, T. and Spirtes, P. (1997) An Evaluation of Machine-Learning Methods for Predicting Pneumonia Mortality. Artificial Intelligence in Medicine, 9, 107-138. https://doi.org/10.1016/S0933-3657(96)00367-3

has been cited by the following article:

• TITLE: The Implementation of the Deep Neural Network in Predicting the Coronavirus 2019 (COVID-19) Based on Laboratory Findings in Children

  AUTHORS: Akpofure A. Enughwure, Rabia Al Mamlook

  KEYWORDS: COVID-19, SARS-CoV-2, Children, Artificial Intelligence, Laboratory Findings

  JOURNAL NAME: Open Access Library Journal, Vol.8 No.7, July 27, 2021

  ABSTRACT: The novel coronavirus (COVID-19) has considerably spread over the world. Whereas children infected with coronavirus (COVID-19) are less expected to develop serious infection compared with adults, children are even at the risk of increasing serious illness and problems from COVID-19. The risk factor of COVID-19 laboratory findings plays a major role in clinical symptoms, diagnosis, and medication. Because the number of COVID-19 cases increased, it takes extra time to explain the lab results and provide an accurate diagnosis. Laboratory findings in children have been only moderately described in some experimental studies. This study aimed to exploit a deep learning approach for detecting COVID-19 in children based on Laboratory findings. The dataset used in this research had 5664 patient samples (4927 negatives and 737 positives for COVID-19). The ANN model allowed the classification of negative and positive samples after the implementation of SMOTE to manage the severe data imbalance. To evaluate the predictive performance of our model, precision, F1-score, recall, AUC, and accuracy scores were calculated. The results of the study illustrate that our predictive model identifies patients that have COVID-19 disease at an accuracy of 93%, and recall and precision values were 76.47% respectively. Our analysis shows that the model could assist in the diagnosis and prediction of COVID-19 severity.