Data-driven discovery of a clinical route for severity detection of COVID-19 pediatric cases

Abstract

The outbreak of COVID-19 epidemic has caused worldwide health concerns since Nov., 2019. A previous study described the demographic, epidemiologic, and clinical features for infected infants. However, compared with adult cases, little attention has been paid to the infected pediatric cases. Severity detection is challenging for children since most of children patients have mild symptoms no matter they are moderately or critically ill therein.

Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal

“…Of 2696 titles, 85 studies were retained for abstract and full text screening. Twenty seven studies describing 31 prediction models met the inclusion criteria and were selected for data extraction and critical appraisal 789101112181920212223242526272829303132333435363738…”

Systematic review and critical appraisal of prediction models for diagnosis and prognosis of COVID-19 infection

“…One study used U.S. Medicare claims data from 2015 to 2016 to estimate COVID-19 vulnerability, 8 two studies used control CT scans from the USA or Switzerland, 11 25 and one study used simulated data. 18 All but one study 24 developed prediction models for use in adults. The median age varied between studies (from 34 to 65 years, see Supplementary Table 1), as did the percentage of men (from 41% to 61%).…”

“…One study developed a model to detect COVID-19 pneumonia in fever clinic patients (estimated C-index 0.94), 10 one to diagnose COVID-19 in suspected cases (estimated C-index 0.97), 30 one to diagnose COVID-19 in suspected and asymptomatic cases (estimated C-index 0.87), 12 one to diagnose COVID-19 using deep learning of genomic sequences (estimated Cindex 0.98), 35 and one to diagnose severe disease in symptomatic paediatric inpatients based on direct bilirubin and alaninetransaminase (reporting an F1 score of 1.00 , indicating 100% observed sensitivity and specificity). 24 Only one study reported assessing calibration, but it was unclear how this was done. 12 Predictors used in more than one model were age (n=3), body temperature or fever (n=2), and signs and symptoms (such as shortness of breath, headache, shiver, sore throat, fatigue) (n=2) (see Table 1).…”

“…30 A decision tree to detect severe disease for pediatric COVID-19 confirmed patients is also available in an article. 24 Diagnostic models based on CT imaging. Three of the seven AI models to assist with diagnosis based on CT results, are available via web applications.…”

“…The guarantors had full access to all the data in the study, take responsibility for the integrity of the data and the accuracy of the data analysis, and had final responsibility for the decision to submit for publication. 35 unclear low low high Meng, Wang, et al 12 high low high high Song, Xu, et al 30 high unclear low high Yu, Shao, et al 24 unclear unclear unclear high…”