Explainable machine learning analysis of factors associated with emergency nurses’ triage competency following CTAS training in Saudi Arabia

Abstract A systematic and straightforward triage system is significant for the proper and timely care of patients within the emergency department (ED). The Canadian Triage and Acuity Scale (CTAS) is a well-recognized and validated triage system that gives priority to patient care with respect to severity of illness. This study aimed to evaluate the impact of a CTAS educational intervention on emergency nurses’ triage knowledge, skills, and attitudes in a tertiary hospital in Saudi Arabia, while identifying demographic predictors of workforce competency using explainable machine learning approaches. Among 110 eligible nurses, 85 emergency nurses participated, who were selected by convenience sampling. The study used a one-group pre-posttest design methodology, and a triage-training workshop was presented on CTAS by face-to-face education through PowerPoint slides and a video projector. At the end of each session, questions and answers on practical examples were asked. We analyzed the data using paired t-tests and multiple machine learning (ML) models with SHAP interpretation to identify key predictive demographic factors. We observed significant improvements in knowledge (12.6 ± 3.2 vs. 7.2 ± 4.1, p < 0.001), skills (85.9 ± 9.5 vs. 61.9 ± 13.2, p < 0.001), and attitude (65.8 ± 7.2 vs. 46.5 ± 8.9, p < 0.001). The neural network slightly achieved better performance in predicting Triage Knowledge (TAK) and Triage Skills (TAS), while the random forest model showed slightly closer fit for Triage Attitude (TAA). These models yielded the lowest RMSE values of 3.03 for TAK, 14.32 for TAS, and 8.44 for TAA, respectively. Within the trained neural network, higher years of experience were associated with increased predicted skill and attitude scores (SHAP values + 4.53 and + 4.36, respectively), while showing a slight negative association with predicted knowledge (–0.29). Similarly, a higher educational level had a positive association with predicted skill scores (SHAP + 12.02). The study showed that the triage education program improved the emergency nurses’ triage CTAS knowledge, attitude, and skills in the short term, with a potential role in strengthening emergency care preparedness. We suggest having more and regular standardized triage training programs should be integrated into emergency nursing professional development and national healthcare quality strategies.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-09-19
DOI
https://doi.org/10.1038/s41598-026-72575-y
Primary Topic
Emergency and Acute Care Studies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Explainable machine learning analysis of factors associated with emergency nurses’ triage competency following CTAS training in Saudi Arabia

Hanan Alyami, Muhammad Daniyal, Faiza Aljarameez, Nadiah A. Baghdadi et al.
Scientific Reports
Emergency and Acute Care Studies
article

Explainable machine learning analysis of factors associated with emergency nurses’ triage competency following CTAS training in Saudi Arabia

Hanan Alyami, Muhammad Daniyal, Faiza Aljarameez, Nadiah A. Baghdadi, Amal I. Al Hasawi, Zahra M. Al Muslim, Abbas Al Mutair, Fatimah S. Al Ahmed, Mohammed I. Al Bazroun, Salman hamdan Alsarqi, Sakina Al Sulais
article en

Abstract

Abstract A systematic and straightforward triage system is significant for the proper and timely care of patients within the emergency department (ED). The Canadian Triage and Acuity Scale (CTAS) is a well-recognized and validated triage system that gives priority to patient care with respect to severity of illness. This study aimed to evaluate the impact of a CTAS educational intervention on emergency nurses’ triage knowledge, skills, and attitudes in a tertiary hospital in Saudi Arabia, while identifying demographic predictors of workforce competency using explainable machine learning approaches. Among 110 eligible nurses, 85 emergency nurses participated, who were selected by convenience sampling. The study used a one-group pre-posttest design methodology, and a triage-training workshop was presented on CTAS by face-to-face education through PowerPoint slides and a video projector. At the end of each session, questions and answers on practical examples were asked. We analyzed the data using paired t-tests and multiple machine learning (ML) models with SHAP interpretation to identify key predictive demographic factors. We observed significant improvements in knowledge (12.6 ± 3.2 vs. 7.2 ± 4.1, p < 0.001), skills (85.9 ± 9.5 vs. 61.9 ± 13.2, p < 0.001), and attitude (65.8 ± 7.2 vs. 46.5 ± 8.9, p < 0.001). The neural network slightly achieved better performance in predicting Triage Knowledge (TAK) and Triage Skills (TAS), while the random forest model showed slightly closer fit for Triage Attitude (TAA). These models yielded the lowest RMSE values of 3.03 for TAK, 14.32 for TAS, and 8.44 for TAA, respectively. Within the trained neural network, higher years of experience were associated with increased predicted skill and attitude scores (SHAP values + 4.53 and + 4.36, respectively), while showing a slight negative association with predicted knowledge (–0.29). Similarly, a higher educational level had a positive association with predicted skill scores (SHAP + 12.02). The study showed that the triage education program improved the emergency nurses’ triage CTAS knowledge, attitude, and skills in the short term, with a potential role in strengthening emergency care preparedness. We suggest having more and regular standardized triage training programs should be integrated into emergency nursing professional development and national healthcare quality strategies.

Scientific Reports
Princess Nourah bint Abdulrahman University (SA), King Saud bin Abdulaziz University for Health Sciences (SA), Saudi Aramco Medical Services Organization (SA), Saad Specialist Hospital (SA), University of Ha'il (SA), King Abdullah International Medical Research Center (SA), Queens University (BD), Qatif Central Hospital (SA), National Guard Health Affairs (SA)
Quality Education
Openalex Percentile: Top 7%
Emergency and Acute Care Studies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.