Predicting COVID-19 severity in pediatric patients using machine learning: a comparative analysis of algorithms and ensemble methods

Abstract COVID-19 has posed a significant global health challenge, affecting individuals across all age groups. While extensive research has focused on adults, pediatric patients exhibit distinct clinical characteristics that necessitate specialized predictive models for disease severity. Machine le...

Full description

Saved in:
Bibliographic Details
Main Authors: Babak Pourakbari, Setareh Mamishi, Sepideh Keshavarz Valian, Shima Mahmoudi, Reihaneh Hosseinpour Sadeghi, Mohammad Reza Abdolsalehi, Mahmoud Khodabandeh, Mohammad Farahmand
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-15366-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235404589367296
author Babak Pourakbari
Setareh Mamishi
Sepideh Keshavarz Valian
Shima Mahmoudi
Reihaneh Hosseinpour Sadeghi
Mohammad Reza Abdolsalehi
Mahmoud Khodabandeh
Mohammad Farahmand
author_facet Babak Pourakbari
Setareh Mamishi
Sepideh Keshavarz Valian
Shima Mahmoudi
Reihaneh Hosseinpour Sadeghi
Mohammad Reza Abdolsalehi
Mahmoud Khodabandeh
Mohammad Farahmand
author_sort Babak Pourakbari
collection DOAJ
description Abstract COVID-19 has posed a significant global health challenge, affecting individuals across all age groups. While extensive research has focused on adults, pediatric patients exhibit distinct clinical characteristics that necessitate specialized predictive models for disease severity. Machine learning offers a powerful approach to analyzing complex datasets and predicting outcomes, yet its application in pediatric COVID-19 remains limited. This study evaluates the performance of machine learning algorithms in predicting disease severity among pediatrics. A retrospective analysis was conducted on a dataset of 588 pediatric with confirmed COVID-19, incorporating demographic, clinical, and laboratory variables. Various machine learning models were trained and assessed, with a SuperLearner ensemble model implemented to enhance predictive accuracy. Among the models, Random Forest exhibited the highest performance, achieving an accuracy of 90.1%, sensitivity of 90.2%, and specificity of 90.1%. The SuperLearner ensemble further improved predictive performance, demonstrating the lowest mean risk estimate. Key predictors, including oxygen saturation, respiratory parameters, and specific laboratory markers, played a crucial role in distinguishing severe from non-severe cases. These findings emphasize the potential of machine learning, particularly ensemble methods, in improving risk stratification for pediatric COVID-19. Integrating these predictive models into clinical practice could support early identification of high-risk patients and optimize clinical decision-making.
format Article
id doaj-art-ca8c59ab384c4f8799fbc29edcdbeb40
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ca8c59ab384c4f8799fbc29edcdbeb402025-08-20T04:02:46ZengNature PortfolioScientific Reports2045-23222025-08-0115111510.1038/s41598-025-15366-1Predicting COVID-19 severity in pediatric patients using machine learning: a comparative analysis of algorithms and ensemble methodsBabak Pourakbari0Setareh Mamishi1Sepideh Keshavarz Valian2Shima Mahmoudi3Reihaneh Hosseinpour Sadeghi4Mohammad Reza Abdolsalehi5Mahmoud Khodabandeh6Mohammad Farahmand7Pediatric Infectious Disease Research Center, Tehran University of Medical SciencesPediatric Infectious Disease Research Center, Tehran University of Medical SciencesSchool of Medicine, Tehran University of Medical SciencesBiotechnology Centre, Silesian University of TechnologyPediatric Infectious Disease Research Center, Tehran University of Medical SciencesDepartment of Infectious Diseases, Pediatrics Center of Excellence, Children’s Medical Center, Tehran University of Medical SciencesDepartment of Infectious Diseases, Pediatrics Center of Excellence, Children’s Medical Center, Tehran University of Medical SciencesPediatric Infectious Disease Research Center, Tehran University of Medical SciencesAbstract COVID-19 has posed a significant global health challenge, affecting individuals across all age groups. While extensive research has focused on adults, pediatric patients exhibit distinct clinical characteristics that necessitate specialized predictive models for disease severity. Machine learning offers a powerful approach to analyzing complex datasets and predicting outcomes, yet its application in pediatric COVID-19 remains limited. This study evaluates the performance of machine learning algorithms in predicting disease severity among pediatrics. A retrospective analysis was conducted on a dataset of 588 pediatric with confirmed COVID-19, incorporating demographic, clinical, and laboratory variables. Various machine learning models were trained and assessed, with a SuperLearner ensemble model implemented to enhance predictive accuracy. Among the models, Random Forest exhibited the highest performance, achieving an accuracy of 90.1%, sensitivity of 90.2%, and specificity of 90.1%. The SuperLearner ensemble further improved predictive performance, demonstrating the lowest mean risk estimate. Key predictors, including oxygen saturation, respiratory parameters, and specific laboratory markers, played a crucial role in distinguishing severe from non-severe cases. These findings emphasize the potential of machine learning, particularly ensemble methods, in improving risk stratification for pediatric COVID-19. Integrating these predictive models into clinical practice could support early identification of high-risk patients and optimize clinical decision-making.https://doi.org/10.1038/s41598-025-15366-1COVID-19Pediatric patientsMachine learningSeverity predictionRandom forestEnsemble model
spellingShingle Babak Pourakbari
Setareh Mamishi
Sepideh Keshavarz Valian
Shima Mahmoudi
Reihaneh Hosseinpour Sadeghi
Mohammad Reza Abdolsalehi
Mahmoud Khodabandeh
Mohammad Farahmand
Predicting COVID-19 severity in pediatric patients using machine learning: a comparative analysis of algorithms and ensemble methods
Scientific Reports
COVID-19
Pediatric patients
Machine learning
Severity prediction
Random forest
Ensemble model
title Predicting COVID-19 severity in pediatric patients using machine learning: a comparative analysis of algorithms and ensemble methods
title_full Predicting COVID-19 severity in pediatric patients using machine learning: a comparative analysis of algorithms and ensemble methods
title_fullStr Predicting COVID-19 severity in pediatric patients using machine learning: a comparative analysis of algorithms and ensemble methods
title_full_unstemmed Predicting COVID-19 severity in pediatric patients using machine learning: a comparative analysis of algorithms and ensemble methods
title_short Predicting COVID-19 severity in pediatric patients using machine learning: a comparative analysis of algorithms and ensemble methods
title_sort predicting covid 19 severity in pediatric patients using machine learning a comparative analysis of algorithms and ensemble methods
topic COVID-19
Pediatric patients
Machine learning
Severity prediction
Random forest
Ensemble model
url https://doi.org/10.1038/s41598-025-15366-1
work_keys_str_mv AT babakpourakbari predictingcovid19severityinpediatricpatientsusingmachinelearningacomparativeanalysisofalgorithmsandensemblemethods
AT setarehmamishi predictingcovid19severityinpediatricpatientsusingmachinelearningacomparativeanalysisofalgorithmsandensemblemethods
AT sepidehkeshavarzvalian predictingcovid19severityinpediatricpatientsusingmachinelearningacomparativeanalysisofalgorithmsandensemblemethods
AT shimamahmoudi predictingcovid19severityinpediatricpatientsusingmachinelearningacomparativeanalysisofalgorithmsandensemblemethods
AT reihanehhosseinpoursadeghi predictingcovid19severityinpediatricpatientsusingmachinelearningacomparativeanalysisofalgorithmsandensemblemethods
AT mohammadrezaabdolsalehi predictingcovid19severityinpediatricpatientsusingmachinelearningacomparativeanalysisofalgorithmsandensemblemethods
AT mahmoudkhodabandeh predictingcovid19severityinpediatricpatientsusingmachinelearningacomparativeanalysisofalgorithmsandensemblemethods
AT mohammadfarahmand predictingcovid19severityinpediatricpatientsusingmachinelearningacomparativeanalysisofalgorithmsandensemblemethods