• Shuaa Abdulrahman Alyami
• Refah Rashed Al Dhawi
• Ahmad Mohammed Al Mosabi

This study aims to apply machine learning techniques to simulate the classification of patients in a hospital emergency department using a dataset that includes patient information such as consciousness level, heart rate, blood pressure, and more. Several machine learning models such as Random Forest, Logistic Regression, and Neural Networks were used to analyze the data and classify patients into emergency and non-emergency cases.A simulated dataset containing over 5000 patient cases was utilized. The models were evaluated based on accuracy, recall, precision, and F1 score. The results showed that the trained models performed well in classifying emergency cases, with accuracy exceeding 90% and a high F1 score.The confusion matrices demonstrated significant improvement in the models' ability to distinguish between emergency and non-emergency cases, indicating the potential application of these models in real emergency environments to enhance medical decision-making processes.

Machine Learning, Emergency Department, Triage, Predictive Modeling, Simulation, Patient Classification, Artificial Intelligence, Healthcare Analytics, Random Forest, Gradient Boosting, XGBoost, Super Ensemble Model, ROC Curve, AUC, Wait Time Prediction, Treatment Duration.

"Machine Learning Models for Simulating Emergency Patient ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.h49-h53, November-2025, Available :http://www.jetir.org/papers/JETIR2511717.pdf

"Machine Learning Models for Simulating Emergency Patient ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. pph49-h53, November-2025, Available at : http://www.jetir.org/papers/JETIR2511717.pdf