The increasing demand for Intensive Care Unit (ICU) beds requires efficient admission, discharge, and care processes. These efforts require predictions of Length of Stay (LOS) values; however, it is unclear how accurate these predictions need to be. This study investigates the relationship between the accuracy level of LOS predictions and operational performance indicators. A discrete event simulation model is developed to model the ICU patient flows. A linear function of actual and simulated LOS values is used to measure the accuracy level of the predictions. Multiple configurations of patient mix and patient waiting threshold were included in the simulation scenarios. Performance indicators are the average waiting time of patients for an ICU bed and overall admission ratios. Further statistical tests were carried out to evaluate the significance of the results. Results suggest that inaccurate LOS predictions overestimated both the average waiting time of patients for an ICU bed and overall admission rates which can have several quality and performance implications for hospitals. The gaps increased when more elective patients were included in the patient mix. Moreover, higher waiting thresholds (i.e., the maximum amount of time a patient will wait for an ICU bed) yielded higher values in both performance indicators.

Despite extensive research and efforts to optimize Emergency Medical Service (EMS) during the last four decades, there are still critical and fundamental challenges to study. Operational problems experienced during implementation of the proposed models result in the emergence of new concerns and the development of other models. This research examines the optimal location of emergency medical centers in order to offer faster and more efficient care. The purpose of this study is to offer a mathematical model for locating emergency medical centers with the goal of increasing both the quantity and quality of demand coverage. Then, by defining numerical examples, the behavior of the model is analyzed. The model is first solved in small dimensions using GAMS, and due to the np-hard nature of the model, it is then studied in large dimensions using a meta-heuristic algorithm, which uses a Genetic Algorithm (GA) in this paper. Finally, the graphs’ results are compared to each other. Our findings indicate that as the dimensions of the problem increase, GAMS loses its ability to solve the problem and the solution time by GA decreases compared to GAMS. Ultimately, in a numerical example, we used contour lines to analyze the data. EMS potential points follow these lines and serve as demand points. Given the model’s accuracy has been proven with various parameters, the proposed model can be used to both meet demand for emergency medical services and determine the optimal location of emergency medical care facilities.