Related Experiment Video
Updated: Oct 5, 2025
A Pediatric Concussion Model in Mice: Closed Head Injury with Long-Term Disorders (CHILD)
Published on: February 7, 2025
Symptom-Based Predictive Model of COVID-19 Disease in Children
Jesús M Antoñanzas1, Aida Perramon2, Cayetana López1
1Barcelona School of Informatics, Universitat Politècnica de Catalunya (UPC⋅BarcelonaTech), 08034 Barcelona, Spain.
Insights
Machine learning models can help assess the need for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) testing in children based on symptoms. This approach aids diagnosis when exposure data is unavailable.
Area of Science:
- Pediatric infectious diseases
- Medical informatics
- Machine learning in healthcare
Background:
- Testing for SARS-CoV-2 in children presents accessibility and ease-of-use challenges.
- A need exists for efficient methods to determine SARS-CoV-2 testing requirements in pediatric populations.
Purpose of the Study:
- To develop and evaluate a machine learning (ML) model for assessing the necessity of SARS-CoV-2 testing in children under 16 years old.
- To identify key clinical symptoms that predict the likelihood of SARS-CoV-2 infection in pediatric patients.
Main Methods:
- Utilized epidemiological and clinical data from 4434 symptomatic children tested between November 2020 and March 2021.
- Pre-processed data, balanced positive-negative rates, and created age-specific subsets for ML model training.
- Trained and selected multiple ML models based on performance for each age subset.
Main Results:
- The ML models achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.65 for predicting COVID-19 diagnosis in children.
- Absence of high-grade fever was a primary predictor in younger children.
- Loss of taste or smell emerged as the most significant symptom for older children.
Conclusions:
- While model accuracy was below expectations, the ML approach offers a valuable tool for guiding SARS-CoV-2 testing decisions.
- These models can assist in diagnosis when information regarding COVID-19 exposure risk is uncertain.
Background:
Testing for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection is neither always accessible nor easy to perform in children. We aimed to propose a machine learning model to assess the need for a SARS-CoV-2 test in children (<16 years old), depending on their clinical symptoms.
Methods:
Epidemiological and clinical data were obtained from the REDCap® registry. Overall, 4434 SARS-CoV-2 tests were performed in symptomatic children between 1 November 2020 and 31 March 2021, 784 were positive (17.68%). We pre-processed the data to be suitable for a machine learning (ML) algorithm, balancing the positive-negative rate and preparing subsets of data by age. We trained several models and chose those with the best performance for each subset.
Results:
The use of ML demonstrated an AUROC of 0.65 to predict a COVID-19 diagnosis in children. The absence of high-grade fever was the major predictor of COVID-19 in younger children, whereas loss of taste or smell was the most determinant symptom in older children.
Conclusions:
Although the accuracy of the models was lower than expected, they can be used to provide a diagnosis when epidemiological data on the risk of exposure to COVID-19 is unknown.
More Related Videos
12:21A Mouse Model for the Transition of Streptococcus pneumoniae from Colonizer to Pathogen upon Viral Co-Infection Recapitulates Age-Exacerbated Illness
Published on: September 28, 2022
06:19Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
Related Concept Videos
01:18Steps in Outbreak Investigation
01:05Single Nucleotide Polymorphisms-SNPs
01:13Sensitivity, Specificity, and Predicted Value
Sensitivity is the...