This scoping review explores the use of artificial intelligence (AI) and machine learning (ML) in emergency department (ED) triage, aiming to identify their potential benefits and research gaps. The review analyzed 29 studies published between 2013 and 2023, focusing on AI's impact on triage accuracy, patient outcomes, and resource allocation. Key findings indicate that ML models consistently outperform traditional triage systems in discrimination ability, predictive accuracy, and risk assessment. AI enhances triage efficiency by improving patient flow, reducing mortality, and enabling better resource management. ML algorithms can predict hospitalization needs, identify critically ill patients, and improve clinical decision-making. They also contribute to more accurate triage by analyzing vast patient data, identifying patterns, and reducing human error. However, challenges remain, including data variability, potential biases, and the need for further research to ensure generalizability across different healthcare settings. The review highlights the transformative potential of AI in emergency care, emphasizing its ability to improve patient outcomes, streamline workflows, and enhance the precision of triage decisions. Despite these benefits, ethical considerations, data privacy, and the need for education on AI's appropriate use remain critical. Overall, AI shows promise in redefining triage precision and improving emergency care through data-driven insights and efficient resource allocation.This scoping review explores the use of artificial intelligence (AI) and machine learning (ML) in emergency department (ED) triage, aiming to identify their potential benefits and research gaps. The review analyzed 29 studies published between 2013 and 2023, focusing on AI's impact on triage accuracy, patient outcomes, and resource allocation. Key findings indicate that ML models consistently outperform traditional triage systems in discrimination ability, predictive accuracy, and risk assessment. AI enhances triage efficiency by improving patient flow, reducing mortality, and enabling better resource management. ML algorithms can predict hospitalization needs, identify critically ill patients, and improve clinical decision-making. They also contribute to more accurate triage by analyzing vast patient data, identifying patterns, and reducing human error. However, challenges remain, including data variability, potential biases, and the need for further research to ensure generalizability across different healthcare settings. The review highlights the transformative potential of AI in emergency care, emphasizing its ability to improve patient outcomes, streamline workflows, and enhance the precision of triage decisions. Despite these benefits, ethical considerations, data privacy, and the need for education on AI's appropriate use remain critical. Overall, AI shows promise in redefining triage precision and improving emergency care through data-driven insights and efficient resource allocation.