Halwani Manal Ahmed, Merdad Ghada, Almasre Miada, Doman Ghadeer, AlSharif Shafiqa, Alshiakh Safinaz M, Mahboob Duaa Yousof, Halwani Marwah A, Faqerah Nojoud Adnan, Mosuily Mahmoud Talal
Pediatric Emergency Unit, Department of Emergency, College of Medicine, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia.
Emergency Department, College of Medicine, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia.
Int J Emerg Med. 2025 Mar 10;18(1):51. doi: 10.1186/s12245-025-00861-z.
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.
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.
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.
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.
急诊科（ED）的高效运作在很大程度上依赖于一个有效的分诊系统，该系统根据患者病情的严重程度对患者进行优先排序。传统的分诊系统，包括那些使用加拿大分诊与 acuity 量表（CTAS）的系统，可能涉及医疗服务提供者的主观评估，从而导致患者护理中潜在的不一致和延误。
本研究旨在评估六种机器学习（ML）模型——K 近邻（KNN）、支持向量机（SCM）、决策树（DT）、随机森林（RF）、高斯朴素贝叶斯（GNB）和轻量级梯度提升机（Light GBM）——在阿卜杜勒阿齐兹国王大学医院使用 CTAS 框架进行分诊预测的效果。
我们遵循了三个基本阶段：数据收集（7125 条急诊科患者记录）、数据探索与处理，以及为阿卜杜勒阿齐兹国王大学医院急诊科分诊开发机器学习预测模型。
使用 GNB 时，CTAS 的总体预测性能最高，准确率为 0.984。CTAS 级别模型的性能表明，SVM、RF 和 LGBM 在所有 CTAS 级别上的精度和召回值一致性方面表现出最高性能。
