Designing and building an interactive simulation-based decision support system in healthcare industry

Abstract

Long length of stay and overcrowding in emergency departments (EDs) are two common problems in the healthcare industry. To decrease the average length of stay (ALOS) and tackle overcrowding, numerous resources, including the number of doctors, nurses and receptionists need to be adjusted, while a number of constraints are to be considered at the same time. In the first part of this thesis, a novel group decision making approach is implemented and each staff agent took part in the process of allocating resources based on their observation in their respective sections, which gave the system the advantage of utilizing all the available human resources during the workday by being allocated to a different section. In this simulation, unlike previous studies, all staff agents took part in the decision-making process to re-allocate the resources in the emergency department. The simulation modeled the behavior of patients, receptionists, triage nurses, emergency room nurses and doctors. Patients were able to decide whether to stay in the system or leave the department at any stage of treatment. In order to evaluate the performance of this approach, 6 different scenarios were introduced. In each scenario, various key performance indicators were investigated before and after applying the group decision-making. The outputs of each simulation were number of deaths, number of patients who leave the emergency department without being attended, length of stay, waiting time and total number of discharged patients from the emergency department. Applying the self-organizing approach in the simulation showed an average of 12.7 and 14.4% decrease in total waiting time and number of patients who left without being seen, respectively. The results showed an average increase of 11.5% in total number of discharged patients from emergency department. The second part of the study, we implemented an efficient method based on agent-based simulation, machine learning and evolutionary algorithms (EAs) to determine near optimum resource allocation in an emergency department in Hospital Risoleta Tolentino Neves (HRTN), a teaching hospital in the capital of Minas Gerais state of Brazil, Belo Horizonte. The proposed decision support system (DSS) can effectively explore the entire domain of all 19 variables and identify an improved resource allocation. A model of the system needs to be run several thousand times through the algorithms evolution process to evaluate each solution, hence the process is computationally expensive. To overcome this drawback, a robust metamodel is initially constructed based on an agent-based system simulation. The simulation exhibits ED performance with various resource allocations and trains the metamodel. The metamodel is created with an ensemble of the adaptive neuro-fuzzy inference system (ANFIS), feedforward neural network (FFNN) and recurrent neural network (RNN) using the adaptive boosting (AdaBoost) ensemble algorithm. The proposed simulation-based optimization approach is tested in a public ED, and it is shown to decrease the ALOS in this ED case study by 14%. Additionally, the proposed metamodel shows a 26.6% improvement compared to the average results of ANFIS, FFNN and RNN in terms of mean absolute percentage error (MAPE).