Artificial Intelligence in emergency department triage: A scoping review

Clinical Snapshot

Key Findings

• P Value: Not reported at review level

• Effect Size: Not quantified — narrative synthesis only; no pooled effect size reported

• Primary Outcome: ML-based AI models consistently outperformed traditional triage systems in predictive accuracy for clinical severity classification and patient prioritisation across the 19 included studies

• Nnt Or Sensitivity: Individual study sensitivity/specificity/AUC values not reported in the abstract; variability in model performance acknowledged by authors without quantification

• Confidence Interval: Not reported — scoping review design precludes meta-analytic pooling

Clinical Application

Currently limited. The review identifies lack of external validation, population-specific constraints, and heterogeneous model performance as key barriers to safe large-scale deployment. Implementation would require significant investment in data infrastructure, clinician training, regulatory approval, and ongoing model monitoring. Real-world deployment remains in early-adopter phase globally. Australian EDs use the Australasian Triage Scale (ATS), a five-category system mandated nationally. Any AI triage tool deployed in Australia would need to demonstrate compatibility with or superiority to the ATS, require TGA regulatory approval as a Software as a Medical Device (SaMD) under the TGA's Digital Health framework, and align with RACGP and Australasian College for Emergency Medicine (ACEM) clinical governance standards. The Australian Digital Health Agency's national strategy supports AI integration in healthcare, but no AI triage tool is currently PBS-listed or TGA-approved for routine ED use. Australian EDs, particularly in rural and remote settings, may represent high-value implementation targets given workforce constraints, but equity and connectivity challenges must be addressed. The review's findings do not include Australian-specific validation data. Adult and paediatric patients presenting to emergency departments requiring triage; most applicable to high-volume EDs with electronic health record infrastructure capable of supporting AI integration

Abstract

BACKGROUND: Triage in emergency departments (ED) is a critical process for prioritizing care and ensuring clinical safety. However, current triage systems often exhibit vulnerabilities that compromise the efficiency and quality of healthcare delivery. Artificial Intelligence (AI) has emerged as a promising innovation to support decision-making and optimize patient flow in these high-pressure environments. OBJECTIVE: To map the available evidence regarding the implementation and performance of artificial intelligence in emergency department triage. METHOD: This scoping review followed the Joanna Briggs Institute (JBI) methodology and the PRISMA-ScR guidelines. A comprehensive search was conducted across 13 databases (CINAHL, Cochrane Library, PubMed Central, SciELO, Web of Science, SCOPUS, Science Direct, VHL, Embase, and several regional dissertation repositories), with no language or time restrictions. Two independent reviewers performed the selection process using the Rayyan platform, with discrepancies resolved by a third evaluator. Data were synthesized using the PAGER framework, categorizing findings into Patterns, Advances, Gaps, Evidence for practice, and Recommendations for research. RESULTS: Nineteen studies met the inclusion criteria. AI was primarily implemented through Machine Learning (ML) algorithms, including Deep Learning architectures. Natural Language Processing (NLP) was frequently employed to process unstructured clinical data, with recent studies exploring the potential of Large Language Models (LLMs). Overall, ML-based models consistently outperformed traditional triage systems in predictive accuracy. These techniques were mainly utilized for automated classification, predicting clinical severity, and enhancing patient prioritization by integrating both objective and subjective assessment data. CONCLUSIONS: The findings indicate that AI has significant potential to enhance emergency triage by streamlining service flows and providing robust clinical decision support. However, the current evidence remains heterogeneous and largely exploratory. Key challenges include variability in model performance, a lack of external validation, and studies often limited to specific populations. Consequently, many current tools still lack the necessary reliability for safe, large-scale clinical implementation.

References

1. 1.Souza, L. L., de Oliveira, Y. C. N., Campos da Costa, L. C., Silva Filho, J. A. A. da, de Souza, A. T. F., Mourão, V. G., Neves Dantas, R. A., Botarelli, F. R., & Ribeiro, K. R. B. (2026). Artificial Intelligence in emergency department triage: A scoping review. PLOS ONE. https://doi.org/10.1371/journal.pone.0352338