Optimization of Service Process in Emergency Department Using Discrete Event Simulation and Machine Learning Algorithm

Abstract

Background - Emergency Department(ED) are operating with limited resources and high levels of unexpected requests. As a result, it is really precious to try for improving the productivity level of EDs. The aims of this study was minimizing the patients waiting time at ED as well as maximizing the percentage of units’ engagement in order to improve the ED efficiency in a public hospital in Iran. Methods - Optimization method used in this research is a comprehensive combination method. After simulating the case and making sure about the validity of the model, experiments were designed to study the effects of change in individuals – equipment on the average time that patients wait, as well as units’ engagement in ED. In order to determine objective functions, Artificial Neural Network (ANN) algorithm was used and MATLAB software was used to train it. Finally, after estimating objective functions and adding related constraints to the problem, fractional Genetic Algorith (GA) was used to solve the model. Results – The results show that the average waiting time in triage section reached near to zero and the average waiting time in screening section reduced to 158/97 min and also coefficient of units’ engagement in both sections has been 69% and 84%. Conclusions- The optimization of patient stream at ED is possible through appropriate allocation of the human and material resources.

Keywords

• Efficiency
• Emergency Service, Hospital
• Operations Research
• Patients