This scoping review explores the integration of artificial intelligence (AI) and machine learning (ML) in emergency department (ED) triage, aiming to identify the impact and potential benefits of AI on patient outcomes. The review was conducted using systematic methods, including a search of electronic databases such as EMBASE, Ovid MEDLINE, and Web of Science. The inclusion criteria required peer-reviewed articles published in US journals between 2013 and 2023, focusing on studies with patients needing hospital ED admission and the use of AI in triage. The review identified 29 studies that demonstrated the superior performance of ML models in triage compared to conventional systems. These models showed enhanced discrimination abilities, improved predictive accuracy, and better identification of critically ill patients. ML algorithms were also effective in predicting hospital admission, disease severity, and resource allocation, leading to more efficient and effective patient care. Key findings include: 1. **Triage Efficiency**: ML models reduced under-triaging and over-triaging, improving the accuracy of triage decisions. 2. **Predictive Modeling**: ML algorithms accurately predicted critical conditions and disease outcomes, enhancing early intervention. 3. **Hospital Admission Prediction**: ML models outperformed traditional methods in forecasting hospitalization needs, particularly for critical cases. 4. **Resource Allocation**: AI improved resource allocation by accurately predicting patient outcomes, leading to better management of ED resources. The review highlights the potential of AI and ML to redefine triage precision, improve patient outcomes, and enhance healthcare efficiency. However, it also emphasizes the need for further research to address limitations and ensure consistent data scaling.This scoping review explores the integration of artificial intelligence (AI) and machine learning (ML) in emergency department (ED) triage, aiming to identify the impact and potential benefits of AI on patient outcomes. The review was conducted using systematic methods, including a search of electronic databases such as EMBASE, Ovid MEDLINE, and Web of Science. The inclusion criteria required peer-reviewed articles published in US journals between 2013 and 2023, focusing on studies with patients needing hospital ED admission and the use of AI in triage. The review identified 29 studies that demonstrated the superior performance of ML models in triage compared to conventional systems. These models showed enhanced discrimination abilities, improved predictive accuracy, and better identification of critically ill patients. ML algorithms were also effective in predicting hospital admission, disease severity, and resource allocation, leading to more efficient and effective patient care. Key findings include: 1. **Triage Efficiency**: ML models reduced under-triaging and over-triaging, improving the accuracy of triage decisions. 2. **Predictive Modeling**: ML algorithms accurately predicted critical conditions and disease outcomes, enhancing early intervention. 3. **Hospital Admission Prediction**: ML models outperformed traditional methods in forecasting hospitalization needs, particularly for critical cases. 4. **Resource Allocation**: AI improved resource allocation by accurately predicting patient outcomes, leading to better management of ED resources. The review highlights the potential of AI and ML to redefine triage precision, improve patient outcomes, and enhance healthcare efficiency. However, it also emphasizes the need for further research to address limitations and ensure consistent data scaling.