Exploring an AI-driven dynamic triage system for real-time patient risk reassessment in emergency departments in low-resource settings
Abstract
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…
How strong is the evidence?
Evidence Hub reads this as a systematic review, done in people. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- The Matrisome: In Silico Definition and In Vivo Characterization by Proteomics of Normal and Tumor Extracellular Matrices
- The Escherichia coli MG1655 in silico metabolic genotype: Its definition, characteristics, and capabilities
- In silico pharmacology for drug discovery: methods for virtual ligand screening and profiling
- In silico prediction of splice-altering single nucleotide variants in the human genome
- In silico clinical trials: how computer simulation will transform the biomedical industry
- In silico optimization of a guava antimicrobial peptide enables combinatorial exploration for peptide design
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.