ABSTRACT
BACKGROUND: New and more severe clinical manifestations associated with the coronavirus disease 2019 (COVID-19) are emerging constantly in the pediatric age group. Patients in this age group are also primary carriers of the influenza virus and are at a higher risk of developing severe infection. However, studies comparing influenza and COVID-19 to show which condition causes a more severe form of disease amongst the pediatric age group are scarce. AIM: To compare the laboratory results, clinical symptoms and clinical outcomes in pediatric patients with COVID-19 and influenza. METHODS: A systematic and comprehensive search was carried out in databases and search engines, including EMBASE, Cochrane, MEDLINE, ScienceDirect and Google Scholar from 1964 until January 2022. A meta-analysis was carried out using a random-effects model and pooled odds ratio (OR) or standardized mean difference (SMD) and 95%CI. RESULTS: A total of 16 studies satisfied the inclusion criteria. Pediatric COVID-19 patients had a significantly reduced risk of cough (pooled OR = 0.16; 95%CI: 0.09 to 0.27), fever (pooled OR = 0.23; 95%CI: 0.12 to 0.43), and dyspnea (pooled OR = 0.54; 95%CI: 0.33 to 0.88) compared to influenza patients. Furthermore, total hemoglobin levels (pooled SMD = 1.22; 95%CI: 0.29 to 2.14) in COVID-19 patients were significantly higher as compared to pediatric influenza patients. There was no significant difference in symptoms such as sore throat, white blood cell count, platelets, neutrophil and lymphocytes levels, and outcomes like mortality, intensive care unit admission, mechanical ventilation or length of hospital stay. CONCLUSION: COVID-19 is associated with a significantly lower rate of clinical symptoms and abnormal laboratory indexes compared to influenza in the pediatric age group. However, further longitudinal studies of the outcomes between influenza and COVID-19 pediatric patients are needed.
ABSTRACT
Objective: To assess the performance of a novel deep learning (DL)-based artificial intelligence (AI) system in classifying computed tomography (CT) scans of pneumonia patients into different groups, as well as to present an effective clinically relevant machine learning (ML) system based on medical image identification and clinical feature interpretation to assist radiologists in triage and diagnosis. Methods: The 3,463 CT images of pneumonia used in this multi-center retrospective study were divided into four categories: bacterial pneumonia (n = 507), fungal pneumonia (n = 126), common viral pneumonia (n = 777), and COVID-19 (n = 2,053). We used DL methods based on images to distinguish pulmonary infections. A machine learning (ML) model for risk interpretation was developed using key imaging (learned from the DL methods) and clinical features. The algorithms were evaluated using the areas under the receiver operating characteristic curves (AUCs). Results: The median AUC of DL models for differentiating pulmonary infection was 99.5% (COVID-19), 98.6% (viral pneumonia), 98.4% (bacterial pneumonia), 99.1% (fungal pneumonia), respectively. By combining chest CT results and clinical symptoms, the ML model performed well, with an AUC of 99.7% for SARS-CoV-2, 99.4% for common virus, 98.9% for bacteria, and 99.6% for fungus. Regarding clinical features interpreting, the model revealed distinctive CT characteristics associated with specific pneumonia: in COVID-19, ground-glass opacity (GGO) [92.5%; odds ratio (OR), 1.76; 95% confidence interval (CI): 1.71-1.86]; larger lesions in the right upper lung (75.0%; OR, 1.12; 95% CI: 1.03-1.25) with viral pneumonia; older age (57.0 years ± 14.2, OR, 1.84; 95% CI: 1.73-1.99) with bacterial pneumonia; and consolidation (95.8%, OR, 1.29; 95% CI: 1.05-1.40) with fungal pneumonia. Conclusion: For classifying common types of pneumonia and assessing the influential factors for triage, our AI system has shown promising results. Our ultimate goal is to assist clinicians in making quick and accurate diagnoses, resulting in the potential for early therapeutic intervention.