Answers are grounded in this paper and cite their sources.
Background: Emergency department (ED) overcrowding is a global challenge, particularly acute in low-resource settings, where staff and equipment shortages exacerbate inefficiencies. Conventional triage systems are static and often fail to detect patient deterioration after the initial assessment. This study aims to explore the potential of AI-driven dynamic triage systems for continuous reassessment of patient risk in low-resource EDs. Methods: A narrative review was conducted through a literature search from 2014 to 2025, following a structured selection process using PubMed, Google Scholar, Web of Science, and ResearchGate, synthesizing evidence on conventional triage models, AI- based decision support, and machine learning applications in emergency care. Results: This study shows that the Emergency Severity Index (ESI) achieves a pooled sensitivity of 81.8% and specificity of 70.5-81.7 for predicting short-term mortality and ICU admissions; yet, under-triage rates in LMICs reach 25%-30%. AI-driven models, including logistic regression, random forests, gradient boosting, and LSTM networks, demonstrate superior predictive accuracy, reducing prioritization errors by up to 9% and improving detection of high-risk patients. Pilot programs in LMICs confirm the feasibility of mobile and cloud-based AI tools, though challenges remain in data quality, infrastructure, and clinician trust. Conclusion: AI-enabled dynamic triage offers promise for enhancing patient safety, optimizing resource allocation, and reducing mortality in overcrowded EDs. However, successful implementation requires prospective validation, infrastructure investment, and co-design with clinicians to ensure adaptability in low-resource settings
No takes yet. Share an insight, caveat, or question.
Nwadinigwe et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: