scholarly journals Sensitivity Analysis in Discrete Event Simulation Using Design of Experiments

10.5772/50196 ◽  
2012 ◽  
Author(s):  
Jos Arnaldo Barra Montevechi ◽  
Rafael de Carvalho Miranda ◽  
Jonathan Daniel
Keyword(s):  
Sensitivity Analysis ◽  
Design Of Experiments ◽  
Discrete Event Simulation ◽  
Discrete Event ◽  
Event Simulation

scholarly journals Lean healthcare integrated with discrete event simulation and design of experiments: an emergency department expansion

2019 ◽  
Author(s):  
Gustavo Teodoro Gabriel ◽  
Afonso Teberga Campos ◽  
Aline de Lima Magacho ◽  
Lucas Cavallieri Segismondi ◽  
Flávio Fraga Vilela ◽  
...  
Keyword(s):  
Emergency Department ◽  
Confidence Interval ◽  
Design Of Experiments ◽  
Discrete Event Simulation ◽  
Discrete Event ◽  
Optimal Number ◽  
Management Tools ◽  
Lean Principles ◽  
Event Simulation ◽  
Lean Healthcare

Background. Discrete Event Simulation (DES) and Lean Healthcare are management tools that are efficient and assist in the quality and efficiency of health services. In this sense, the purpose of the study is to use lean principles jointly with DES to plan the expansion of a Canadian emergency department and to the demand that comes from small closed care centers. Methods. For this, we used simulation and modeling method. We simulated the emergency department in FlexSim Healthcare® software and, with the Design of Experiments (DoE), we defined the optimal number of locations and resources for each shift. Results. The results show that the ED cannot meet expected demand in the current state. Only 17.2% of the patients were completed treated, and the Length of Stay (LOS), on average, was 2213.7, with a confidence interval of (2131.8 - 2295.6) minutes. However, after changing decision variables, the number of treated patients increased to 95.7% (approximately 600%). Average LOS decreased to 461.2, with a confidence interval of (453.7 - 468.7) minutes, about 79.0%. In addition, the study shows that emergency department staff are balanced, according to Lean principles.

Sensitivity analysis in discrete-event simulation using fractional factorial designs

2010 ◽  
Vol 4 (2) ◽  
pp. 128-142 ◽  
Author(s):  
J A B Montevechi ◽  
R G de Almeida Filho ◽  
A P Paiva ◽  
R F S Costa ◽  
A L Medeiros
Keyword(s):  
Sensitivity Analysis ◽  
Discrete Event Simulation ◽  
Discrete Event ◽  
Fractional Factorial ◽  
Factorial Designs ◽  
Fractional Factorial Designs ◽  
Event Simulation

Discrete Event Simulation (DES) and Design of Experiments (DOE) in Manufacturing Systems Development: an Application in Automotive Sector

2008 ◽  
Author(s):  
Marcelo Machado Fernandes ◽  
Jose Arnaldo Barra Montevechi ◽  
Ana Emilia Salomon ◽  
Antonio Cesar Rosati ◽  
Helio Maciel ◽  
...  
Keyword(s):  
Design Of Experiments ◽  
Discrete Event Simulation ◽  
Manufacturing Systems ◽  
Discrete Event ◽  
Systems Development ◽  
Automotive Sector ◽  
Event Simulation

scholarly journals Discrete-Event Simulation of Ground-Based Timber Harvesting Operations

Forests ◽  
2018 ◽  
Vol 9 (11) ◽  
pp. 683 ◽  
Author(s):  
Ji She ◽  
Woodam Chung ◽  
David Kim
Keyword(s):  
Sensitivity Analysis ◽  
Discrete Event Simulation ◽  
Discrete Event ◽  
Timber Harvesting ◽  
Cycle Times ◽  
Event Simulation ◽  
Machine Cycle ◽  
Forest Industries ◽  
Machine Utilization ◽  
The Difference

Operational studies are necessary to support production and management decisions of forest industries. A time study (TS) approach is widely used in timber harvesting operations to understand the performance of individual harvesting machines as well as the entire system. However, several limitations of the TS approach include the use of generalized utilization rates, incapability of capturing interactions among equipment, and model extrapolation in sensitivity analysis. In this study, we demonstrated the use of discrete event simulation (DES) techniques in modeling a ground-based timber harvesting system, and compared the DES results with those of the TS model developed with the same observed data. Although both TS and DES models provided similar estimation results for individual machine cycle times and productivities, the estimated machine utilization rates were somewhat different due to the difference in synthesizing machine processes in each approach. Our sensitivity analysis and model expansion to simulate a hypothetical harvesting system suggest that the DES approach may become an appropriate method for analyzing complex systems especially where interactions among different machine processes are unknown.

scholarly journals Lean healthcare integrated with discrete event simulation and design of experiments: an emergency department expansion

2019 ◽  
Author(s):  
Gustavo Teodoro Gabriel ◽  
Afonso Teberga Campos ◽  
Aline de Lima Magacho ◽  
Lucas Cavallieri Segismondi ◽  
Flávio Fraga Vilela ◽  
...  
Keyword(s):  
Emergency Department ◽  
Confidence Interval ◽  
Design Of Experiments ◽  
Discrete Event Simulation ◽  
Discrete Event ◽  
Optimal Number ◽  
Management Tools ◽  
Lean Principles ◽  
Event Simulation ◽  
Lean Healthcare

Background. Discrete Event Simulation (DES) and Lean Healthcare are management tools that are efficient and assist in the quality and efficiency of health services. In this sense, the purpose of the study is to use lean principles jointly with DES to plan the expansion of a Canadian emergency department and to the demand that comes from small closed care centers. Methods. For this, we used simulation and modeling method. We simulated the emergency department in FlexSim Healthcare® software and, with the Design of Experiments (DoE), we defined the optimal number of locations and resources for each shift. Results. The results show that the ED cannot meet expected demand in the current state. Only 17.2% of the patients were completed treated, and the Length of Stay (LOS), on average, was 2213.7, with a confidence interval of (2131.8 - 2295.6) minutes. However, after changing decision variables, the number of treated patients increased to 95.7% (approximately 600%). Average LOS decreased to 461.2, with a confidence interval of (453.7 - 468.7) minutes, about 79.0%. In addition, the study shows that emergency department staff are balanced, according to Lean principles.

scholarly journals Lean thinking by integrating with discrete event simulation and design of experiments: an emergency department expansion

2020 ◽  
Vol 6 ◽  
pp. e284
Author(s):  
Gustavo Teodoro Gabriel ◽  
Afonso Teberga Campos ◽  
Aline de Lima Magacho ◽  
Lucas Cavallieri Segismondi ◽  
Flávio Fraga Vilela ◽  
...  
Keyword(s):  
Emergency Department ◽  
Confidence Interval ◽  
Design Of Experiments ◽  
Discrete Event Simulation ◽  
Health Care Quality ◽  
Discrete Event ◽  
Optimal Number ◽  
Care Quality ◽  
Lean Thinking ◽  
Event Simulation

Background Many management tools, such as Discrete Event Simulation (DES) and Lean Healthcare, are efficient to support and assist health care quality. In this sense, the study aims at using Lean Thinking (LT) principles combined with DES to plan a Canadian emergency department (ED) expansion and at meeting the demand that comes from small care centers closed. The project‘s purpose is reducing the patients’ Length of Stay (LOS) in the ED. Additionally, they must be assisted as soon as possible after the triage process. Furthermore, the study aims at determining the ideal number of beds in the Short Stay Unit (SSU). The patients must not wait more than 180 min to be transferred. Methods For this purpose, the hospital decision-makers have suggested planning the expansion, and it was carried out by the simulation and modeling method. The emergency department was simulated by the software FlexSim Healthcare®, and, with the Design of Experiments (DoE), the optimal number of beds, seats, and resources for each shift was determined. Data collection and modeling were executed based on historical data (patients’ arrival) and from some databases that are in use by the hospital, from April 1st, 2017 to March 31st, 2018. The experiments were carried out by running 30 replicates for each scenario. Results The results show that the emergency department cannot meet expected demand in the initial planning scenario. Only 17.2% of the patients were completed treated, and LOS was 2213.7 (average), with a confidence interval of (2131.8–2295.6) min. However, after changing decision variables and applying LT techniques, the treated patients’ number increased to 95.7% (approximately 600%). Average LOS decreased to 461.2, with a confidence interval of (453.7–468.7) min, about 79.0%. The time to be attended after the triage decrease from 404.3 min to 20.8 (19.8–21.8) min, around 95.0%, while the time to be transferred from bed to the SSU decreased by 60.0%. Moreover, the ED reduced human resources downtime, according to Lean Thinking principles.

Reducing Consultation Waiting Time and Overtime in Outpatient Clinic

2011 ◽  
pp. 229-245
Author(s):  
Zhu Zhecheng ◽  
Heng Bee Hoon ◽  
Teow Kiok Liang
Keyword(s):  
Patient Safety ◽  
Design Of Experiments ◽  
Discrete Event Simulation ◽  
Waiting Time ◽  
Outpatient Clinic ◽  
Performance Indicators ◽  
Discrete Event ◽  
Outpatient Clinics ◽  
Event Simulation ◽  
Growing Population

Outpatient clinics face increasing pressure to handle more appointment requests due to aging and growing population. The increase in workload impacts two critical performance indicators: consultation waiting time and clinic overtime. Consultation waiting time is the physical waiting time a patient spends in the waiting area of the clinic, and clinic overtime is the amount of time the clinic is open beyond its normal opening hours. Long consultation waiting time negatively affects patient safety and satisfaction, while long clinic overtime negatively affects the morale of clinic staff. This chapter analyzes the complexity of an outpatient clinic in a Singapore public hospital, and factors causing long consultation waiting time and clinic overtime. Discrete event simulation and design of experiments are applied to quantify the effects of the factors on consultation waiting time/clinic overtime. Implementation results show significant improvement once those factors are well addressed.

Sign in / Sign up

Export Citation Format

Share Document