Predicting triage of pediatric patients in the emergency department using machine learning approach

Predicting triage of pediatric patients in the emergency department using machine learning approach

Canadian triage and acuity scale, K-Nearest neighbours, Support vector machine, Gaussian Naive Bayes,
Decision tree, Random forest, Light GBM

Abstract
Background The efficient performance of an Emergency Department (ED) relies heavily on an effective triage
system that prioritizes patients based on the severity of their medical conditions. Traditional triage systems, including
those using the Canadian Triage and Acuity Scale (CTAS), may involve subjective assessments by healthcare providers,
leading to potential inconsistencies and delays in patient care.
Objective This study aimed to evaluate six Machine Learning (ML) models K-Nearest Neighbors (KNN), Support
Vector Machine (SCM), Decision Tree (DT), Random Forest (RF), Gaussian Naïve Bayes (GNB), and Light GBM (Light
Gradient Boosting Machine) for triage prediction in the King Abdulaziz University Hospital using the CTAS framework.
Methodology We followed three essential phases: data collection (7125 records of ED patients), data exploration and
processing, and the development of machine learning predictive models for ED triage at King Abdulaziz University
Hospital.
Results and conclusion The overall predictive performance of CTAS was the highest using GNB=0.984 accuracy.
The CTAS-level model performance indicated that SVM, RF, and LGBM achieved the highest performance regarding
the consistency of precision and recall values across all CTAS levels.
Plain Language summary
A study used a dataset of records of ED patients to improve triage prediction accuracy using six machine learning
models. The Gaussian-naive Bayes model was the most accurate, predicting triage levels at 98.4% of the time.
However, SVM, Random Forest, and Light GBM outperformed each other in precision and recall, demonstrating that
these models can enhance the consistency and accuracy of triage judgments in the ED.
Keywords Canadian triage and acuity scale, K-Nearest neighbours, Support vector machine, Gaussian Naive Bayes,
Decision tree, Random forest, Light GBM

Manal Ahmed Halwani1* , Ghada Merdad3

, Miada Almasre2 , Ghadeer Doman3 , Shafiqa AlSharif1 ,
Safinaz M. Alshiakh3 , Duaa Yousof Mahboob3 , Marwah A. Halwani4 , Nojoud Adnan Faqerah5 and
Mahmoud Talal Mosuily2

https://doi.org/10.1186/s12245-025-00861-z

2025

Peri Irawan

pdf

english

text