Predicting paediatric asthma exacerbations with machine learning: a systematic review with meta-analysis

Background Asthma exacerbations in children pose a significant burden on healthcare systems and families. While traditional risk assessment tools exist, artificial intelligence (AI) offers the potential for enhanced prediction models. Objective This study aims to systematically evaluate and quantify...

Full description

Saved in:
Bibliographic Details
Main Authors: Martina Votto, Annalisa De Silvestri, Lorenzo Postiglione, Maria De Filippo, Sara Manti, Stefania La Grutta, Gian Luigi Marseglia, Amelia Licari
Format: Article
Language:English
Published: European Respiratory Society 2024-11-01
Series:European Respiratory Review
Online Access:http://err.ersjournals.com/content/33/174/240118.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850088681940975616
author Martina Votto
Annalisa De Silvestri
Lorenzo Postiglione
Maria De Filippo
Sara Manti
Stefania La Grutta
Gian Luigi Marseglia
Amelia Licari
author_facet Martina Votto
Annalisa De Silvestri
Lorenzo Postiglione
Maria De Filippo
Sara Manti
Stefania La Grutta
Gian Luigi Marseglia
Amelia Licari
author_sort Martina Votto
collection DOAJ
description Background Asthma exacerbations in children pose a significant burden on healthcare systems and families. While traditional risk assessment tools exist, artificial intelligence (AI) offers the potential for enhanced prediction models. Objective This study aims to systematically evaluate and quantify the performance of machine learning (ML) algorithms in predicting the risk of hospitalisation and emergency department (ED) admission for acute asthma exacerbations in children. Methods We performed a systematic review with meta-analysis, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The risk of bias and applicability for eligible studies was assessed according to the prediction model study risk of bias assessment tool (PROBAST). The protocol of our systematic review was registered in the International Prospective Register of Systematic Reviews. Results Our meta-analysis included seven articles encompassing a total of 17 ML-based prediction models. We found a pooled area under the curve (AUC) of 0.67 (95% CI 0.61–0.73; I2=99%; p<0.0001 for heterogeneity) for models predicting ED admission, indicating moderate accuracy. Notably, models predicting child hospitalisation demonstrated a higher pooled AUC of 0.79 (95% CI 0.76–0.82; I2=95%; p<0.0001 for heterogeneity), suggesting good discriminatory power. Conclusion This study provides the most comprehensive assessment of AI-based algorithms in predicting paediatric asthma exacerbations to date. While these models show promise and ML-based hospitalisation prediction models, in particular, demonstrate good accuracy, further external validation is needed before these models can be reliably implemented in real-life clinical practice.
format Article
id doaj-art-b535aede6c424db79e26890b9280437d
institution DOAJ
issn 0905-9180
1600-0617
language English
publishDate 2024-11-01
publisher European Respiratory Society
record_format Article
series European Respiratory Review
spelling doaj-art-b535aede6c424db79e26890b9280437d2025-08-20T02:42:57ZengEuropean Respiratory SocietyEuropean Respiratory Review0905-91801600-06172024-11-013317410.1183/16000617.0118-20240118-2024Predicting paediatric asthma exacerbations with machine learning: a systematic review with meta-analysisMartina Votto0Annalisa De Silvestri1Lorenzo Postiglione2Maria De Filippo3Sara Manti4Stefania La Grutta5Gian Luigi Marseglia6Amelia Licari7 Pediatric Unit, Department of Clinical, Surgical, Diagnostic and Pediatric Sciences, University of Pavia, Pavia, Italy Biometry and Clinical Epidemiology, Scientific Direction, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy Pediatric Unit, Department of Clinical, Surgical, Diagnostic and Pediatric Sciences, University of Pavia, Pavia, Italy Pediatric Unit, Department of Clinical, Surgical, Diagnostic and Pediatric Sciences, University of Pavia, Pavia, Italy Pediatric Unit, Department of Human Pathology in Adult and Developmental Age “Gaetano Barresi”, University of Messina, Messina, Italy Institute of Translational Pharmacology (IFT), National Research Council of Italy (CNR), Palermo, Italy Pediatric Unit, Department of Clinical, Surgical, Diagnostic and Pediatric Sciences, University of Pavia, Pavia, Italy Pediatric Unit, Department of Clinical, Surgical, Diagnostic and Pediatric Sciences, University of Pavia, Pavia, Italy Background Asthma exacerbations in children pose a significant burden on healthcare systems and families. While traditional risk assessment tools exist, artificial intelligence (AI) offers the potential for enhanced prediction models. Objective This study aims to systematically evaluate and quantify the performance of machine learning (ML) algorithms in predicting the risk of hospitalisation and emergency department (ED) admission for acute asthma exacerbations in children. Methods We performed a systematic review with meta-analysis, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The risk of bias and applicability for eligible studies was assessed according to the prediction model study risk of bias assessment tool (PROBAST). The protocol of our systematic review was registered in the International Prospective Register of Systematic Reviews. Results Our meta-analysis included seven articles encompassing a total of 17 ML-based prediction models. We found a pooled area under the curve (AUC) of 0.67 (95% CI 0.61–0.73; I2=99%; p<0.0001 for heterogeneity) for models predicting ED admission, indicating moderate accuracy. Notably, models predicting child hospitalisation demonstrated a higher pooled AUC of 0.79 (95% CI 0.76–0.82; I2=95%; p<0.0001 for heterogeneity), suggesting good discriminatory power. Conclusion This study provides the most comprehensive assessment of AI-based algorithms in predicting paediatric asthma exacerbations to date. While these models show promise and ML-based hospitalisation prediction models, in particular, demonstrate good accuracy, further external validation is needed before these models can be reliably implemented in real-life clinical practice.http://err.ersjournals.com/content/33/174/240118.full
spellingShingle Martina Votto
Annalisa De Silvestri
Lorenzo Postiglione
Maria De Filippo
Sara Manti
Stefania La Grutta
Gian Luigi Marseglia
Amelia Licari
Predicting paediatric asthma exacerbations with machine learning: a systematic review with meta-analysis
European Respiratory Review
title Predicting paediatric asthma exacerbations with machine learning: a systematic review with meta-analysis
title_full Predicting paediatric asthma exacerbations with machine learning: a systematic review with meta-analysis
title_fullStr Predicting paediatric asthma exacerbations with machine learning: a systematic review with meta-analysis
title_full_unstemmed Predicting paediatric asthma exacerbations with machine learning: a systematic review with meta-analysis
title_short Predicting paediatric asthma exacerbations with machine learning: a systematic review with meta-analysis
title_sort predicting paediatric asthma exacerbations with machine learning a systematic review with meta analysis
url http://err.ersjournals.com/content/33/174/240118.full
work_keys_str_mv AT martinavotto predictingpaediatricasthmaexacerbationswithmachinelearningasystematicreviewwithmetaanalysis
AT annalisadesilvestri predictingpaediatricasthmaexacerbationswithmachinelearningasystematicreviewwithmetaanalysis
AT lorenzopostiglione predictingpaediatricasthmaexacerbationswithmachinelearningasystematicreviewwithmetaanalysis
AT mariadefilippo predictingpaediatricasthmaexacerbationswithmachinelearningasystematicreviewwithmetaanalysis
AT saramanti predictingpaediatricasthmaexacerbationswithmachinelearningasystematicreviewwithmetaanalysis
AT stefanialagrutta predictingpaediatricasthmaexacerbationswithmachinelearningasystematicreviewwithmetaanalysis
AT gianluigimarseglia predictingpaediatricasthmaexacerbationswithmachinelearningasystematicreviewwithmetaanalysis
AT amelialicari predictingpaediatricasthmaexacerbationswithmachinelearningasystematicreviewwithmetaanalysis