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

Abstract

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.