Related Experiment Video
Updated: Apr 1, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Machine learning to predict hospital admission at triage in paediatric emergency care: A meta-analysis
Blanca Paola Pérez1, Octavio Galindo Osorio2, Mónica Arias-Colinas3,4
1School of Medicine, Department of Preventive Medicine and Public Health, University of Navarra, 31008, Pamplona, Spain.
Insights
Machine learning models show strong potential for predicting hospital admissions in paediatric emergency departments. Top models utilize random forest algorithms with vital signs and triage data for accurate risk stratification.
Area of Science:
- Pediatric Emergency Medicine
- Health Informatics
- Artificial Intelligence in Healthcare
Background:
- Traditional paediatric emergency department (ED) triage has limitations in accurately predicting hospital admissions.
- Machine learning (ML) is increasingly used to enhance risk stratification in clinical settings.
Purpose of the Study:
- To evaluate the diagnostic performance of ML models in predicting hospital admissions from paediatric ED triage data.
- To identify key variables and algorithms that improve prediction accuracy.
Main Methods:
- Systematic review of studies using ML for paediatric ED admission prediction.
- Searches conducted in PubMed, Ovid, Scopus, and Web of Science.
- Data extraction included population characteristics, ML methods, and diagnostic metrics (AUC, sensitivity, specificity).
Main Results:
- ML models demonstrated high diagnostic performance, with Area Under the Curve (AUC) ranging from 0.78 to 0.97.
- Random forest algorithms using variables like age, heart rate, and triage level achieved the highest performance (AUC ≥ 0.94).
- Meta-analysis of six studies showed a pooled AUC of 0.84 (sensitivity 0.78, specificity 0.76) with high heterogeneity.
Conclusions:
- ML models hold significant potential for improving paediatric ED triage and risk stratification.
- Standardized methodologies, explainable AI, and prospective validation are crucial for clinical implementation.
Abstract:
Machine learning (ML) models have shown promise improving outcome prediction and early risk stratification in paediatric emergency department (ED) triage. This review aims to evaluate the diagnostic performance of ML in predicting hospital admissions from the data collected at triage in paediatric emergency departments (EDs). Searches were conducted in PubMed, Ovid, Scopus, and Web of Science. Two reviewers screened 264 abstracts after duplicate removal, excluding 239 not meeting inclusion criteria. Of the 25 full-texts assessed, 15 were excluded for outcome mismatch, leaving 10 for data extraction. Data were thereafter extracted including population characteristics, ML methods, and diagnostic metrics: area under the curve (AUC), sensitivity, and specificity. Most studies used retrospective cohorts from electronic records or national databases. Sample sizes ranged from 9,069 to over 2.9 million. AUCs ranged from 0.78 to 0.97, with top-performing models (AUC ≥ 0.94) using random forest algorithms and variables like age, heart rate, triage level. Meta-analysis of six studies showed pooled sensitivity of 0.78 and specificity of 0.76 (AUC = 0.84), though heterogeneity was high (I2 = 100%).
Conclusion:
ML models have potential for paediatric ED triage. Standardized methods, explainable AI, and prospective validation are essential for clinical use.
What Is Known:
• Traditional triage in paediatric emergency departments may have limitations in accurately predicting hospital admissions. • Machine learning models are increasingly applied to improve risk stratification in clinical settings.
What Is New:
• This review shows ML models can predict paediatric ED admissions with high AUCs (up to 0.97). • Random forest algorithms using vital signs and triage data performed best.