Identification of unobservable behavior in stochastic discrete event systems with a low number of sensors.

Dynamic discrete event systems (DDES) are systems that evolve from the asynchronous occurrence of discrete events. Their versatility has become a critical modeling tool in different applications. Finding models that define the behavior of DES is a topic that has been addressed from different approaches, depending on the type of system to be modeled and the model's objective. This article focuses on the identification of timed models for stochastic discrete event systems. The identified model includes both observable and unobservable behavior. The objective of the method is achieved through the following steps:•Identifying the sequences of events observed at different time instances during the closed-loop operation of the system (observed language),•Inferring the stochastic behavior of time between events and modeling the observable behavior as a stochastic timed Interpreted Petri Net (st-IPN),•and finally, inferring the non-observable behavior using the language projection operation between the observed language and the language generated by the st-IPN.This method has novel aspects because it uses timed events, can be applied to systems with a low number of sensors and can infer unobservable behavior for any sequence of events.

Artificial intelligence and discrete-event simulation for capacity management of intensive care units during the Covid-19 pandemic: A case study.

The Covid-19 pandemic has pushed the Intensive Care Units (ICUs) into significant operational disruptions. The rapid evolution of this disease, the bed capacity constraints, the wide variety of patient profiles, and the imbalances within health supply chains still represent a challenge for policymakers. This paper aims to use Artificial Intelligence (AI) and Discrete-Event Simulation (DES) to support ICU bed capacity management during Covid-19. The proposed approach was validated in a Spanish hospital chain where we initially identified the predictors of ICU admission in Covid-19 patients. Second, we applied Random Forest (RF) to predict ICU admission likelihood using patient data collected in the Emergency Department (ED). Finally, we included the RF outcomes in a DES model to assist decision-makers in evaluating new ICU bed configurations responding to the patient transfer expected from downstream services. The results evidenced that the median bed waiting time declined between 32.42 and 48.03 min after intervention.

An Automated Machine Learning Approach for Real-Time Fault Detection and Diagnosis.

This work presents a novel Automated Machine Learning (AutoML) approach for Real-Time Fault Detection and Diagnosis (RT-FDD). The approach's particular characteristics are: it uses only data that are commonly available in industrial automation systems; it automates all ML processes without human intervention; a non-ML expert can deploy it; and it considers the behavior of cyclic sequential machines, combining discrete timed events and continuous variables as features. The capacity for fault detection is analyzed in two case studies, using data from a 3D machine simulation system with faulty and non-faulty conditions. The enhancement of the RT-FDD performance when the proposed approach is applied is proved with the Feature Importance, Confusion Matrix, and F1 Score analysis, reaching mean values of 85% and 100% in each case study. Finally, considering that faults are rare events, the sensitivity of the models to the number of faulty samples is analyzed.

Planning for resilience in screening operations using discrete event simulation modeling: example of HPV testing in Peru.

BACKGROUND: The World Health Organization (WHO) has called for the elimination of cervical cancer. Unfortunately, the implementation of cost-effective prevention and control strategies has faced significant barriers, such as insufficient guidance on best practices for resource and operations planning. Therefore, we demonstrate the value of discrete event simulation (DES) in implementation science research and practice, particularly to support the programmatic and operational planning for sustainable and resilient delivery of healthcare interventions. Our specific example shows how DES models can inform planning for scale-up and resilient operations of a new HPV-based screen and treat program in Iquitos, an Amazonian city of Peru. METHODS: Using data from a time and motion study and cervical cancer screening registry from Iquitos, Peru, we developed a DES model to conduct virtual experimentation with "what-if" scenarios that compare different workflow and processing strategies under resource constraints and disruptions to the screening system. RESULTS: Our simulations show how much the screening system's capacity can be increased at current resource levels, how much variability in service times can be tolerated, and the extent of resilience to disruptions such as curtailed resources. The simulations also identify the resources that would be required to scale up for larger target populations or increased resilience to disruptions, illustrating the key tradeoff between resilience and efficiency. Thus, our results demonstrate how DES models can inform specific resourcing decisions but can also highlight important tradeoffs and suggest general "rules" for resource and operational planning. CONCLUSIONS: Multilevel planning and implementation challenges are not unique to sustainable adoption of cervical cancer screening programs but represent common barriers to the successful scale-up of many preventative health interventions worldwide. DES represents a broadly applicable tool to address complex implementation challenges identified at the national, regional, and local levels across settings and health interventions-how to make effective and efficient operational and resourcing decisions to support program adaptation to local constraints and demands so that they are resilient to changing demands and more likely to be maintained with fidelity over time.

Reduction of the Cycle Time in the Biopsies Diagnosis Through a Simulation Based on the Box Müller Algorithm.

Anatomic pathology services study disease in hospitals on the basis of macroscopic and microscopic examination of organs and tissues. The focus of this research investigation was on improving clinical biopsy diagnosis times through simulation based on the Box-Muller algorithm to reduce the waiting time in the diagnosis of clinical biopsies. The data were provided by a hospital in San José (Costa Rica). They covered 5 years and showed waiting times for a pathological diagnosis that for some biopsies were close to 120 days. The correlation between the main causes identified and the cycle time in the biopsy diagnostic process was defined. A statistical analysis of the variables most representative of the process and of the waiting times was carried out. It followed the DMAIC structure (Define, Measure, Analyse, Improve, Control) for the continuous improvement of processes. Two of the activities of the process were identified as being the main bottlenecks. Their processing times had a normal distribution, for which reason a Box-Muller algorithm was used to generate the simulation model. The results showed that waiting times for a diagnosis can be reduced to 3 days, for a productive capacity of 8 000 biopsies per annum, optimizing the logistics performance of health care.

Discrete-event models for the simulation of computed tomography sectors according to hospital structural/organizational changes and expected patient arrival rates.

OBJECTIVE: To analyze the types of computed tomography (CT) scanners most suitable for different hospital sizes and 'scenarios' (exam rates and structural/organizational changes), using discrete-event simulation models. MATERIALS AND METHODS: CT exams were divided into stages, measured during on-site surveys at CT services in small and average size private hospitals. Ten devices in nine health units, five cities and two states of Brazil were studied to this end, and the following data were collected: Time spent in each stage for each type of exam; average monthly number of exams performed and general characteristics of exams. Three arrival rates were defined (103, 154 and 206 patients/day), representing expected demand for the studied units. From these parameters, six scenarios were simulated, consisting of changes in personnel and hospital structure (e.g., 'adding a changing room') in a base scenario (one CT, one changing room, no nursing assistance, arrival rate 1). RESULTS: It was possible to identify a scenario most useful for very large demands, such as large emergency hospitals in big cities, (a CT, nursing assistance and three changing rooms added to the base scenario). Another identified scenario was more adequate for small demands (adding a changing room to the base scenario). CONCLUSION: Administrative/organizational measures are a very important factor in defining productivity in a hospital imaging sector. The focus of these measures should be on detecting bottlenecks and improving processes, regardless of the type of equipment used.

Safety assessment for temporary hospitals during the COVID-19 pandemic: A simulation approach.

Amid the devastating effects caused by the pandemic of the new Coronavirus (COVID-19), health leaders around the world are adding efforts to search efficient and effective responses in the fight against the disease. Conventional health centers, such as hospitals and emergency departments have been registering an increase in demand and atypical patterns due to the high transmissibility of the virus. In this context, the adoption of Temporary Hospitals (THs) is effective in trying to relieve conventional hospitals and direct efforts in the treatment of suspected and positive patients for COVID-19. However, some requirements should be considered regarding the processes performed by THs to maintain the health and safety of patients and staff. Based on the literature, we evaluated aspects related to patient safety in THs, especially linked to biosafety of medical facilities, and patient transport and visit. We highlight the analysis of flows and layouts, hospital cleaning and patient care. We described two case studies to demonstrate the proposed approach. As result, simulation tests improved safety metrics, such as waiting time for procedures, movement intensity in each area, length of stay and TH capacity. We conclude that the approach allows us to provide better THs that prevent cross-contamination, provide suitable care, and meet the demand.

Discrete-Event Simulation Modeling in Healthcare: A Comprehensive Review.

Discrete-event simulation (DES) is a stochastic modeling approach widely used to address dynamic and complex systems, such as healthcare. In this review, academic databases were systematically searched to identify 231 papers focused on DES modeling in healthcare. These studies were sorted by year, approach, healthcare setting, outcome, provenance, and software use. Among the surveys, conceptual/theoretical studies, reviews, and case studies, it was found that almost two-thirds of the theoretical articles discuss models that include DES along with other analytical techniques, such as optimization and lean/six sigma, and one-third of the applications were carried out in more than one healthcare setting, with emergency departments being the most popular. Moreover, half of the applications seek to improve time- and efficiency-related metrics, and one-third of all papers use hybrid models. Finally, the most popular DES software is Arena and Simul8. Overall, there is an increasing trend towards using DES in healthcare to address issues at an operational level, yet less than 10% of DES applications present actual implementations following the modeling stage. Thus, future research should focus on the implementation of the models to assess their impact on healthcare processes, patients, and, possibly, their clinical value. Other areas are DES studies that emphasize their methodological formulation, as well as the development of frameworks for hybrid models.

A Simulation-Optimisation approach for hospital beds allocation.

The planning of hospital beds is among the most debated problems in healthcare. Despite being an important issue, many initiatives have failed to sustain services improvements, resulting in high costs and also high refusal rates. The stochastic problem involves conflicting criteria, therefore, we propose a Simulation-Optimisation approach to solve it. The Evolutionary Algorithm NSGA-II drives the process, and the solutions are validated and evaluated via Discrete Event Simulation. An application is performed in one of the health regions of the state of Minas Gerais, Brazil, where the public health system assists nearly 80% of the patients. The results pointed out that the proposed approach could find efficient and feasible solutions for the problem. Therefore, it is a good alternative to empirical methods currently used in Brazil to set hospital beds allocation.

Improving emergency department resource planning: a multiple case study.

Sizing and allocating health-care professionals are a critical problem in the management of emergency departments (EDs) managed by a public company in Rio de Janeiro (Brazil). An efficient ED configuration that is cost and time effective must be developed by this company for hospital managers. In this paper, the problem of health-care professional configurations in EDs is modelled to minimise the total labour cost while satisfying patient queues and waiting times as defined by the actual ED capacity and current clinical protocols. To solve this issue, mixed integer linear programming (MILP) that allocates health-care professionals and specifies the amount of professionals who must be hired is proposed. To consider the uncertainties in this environment and evaluate their impacts, a discrete-event simulation model is developed to reflect patient flow. An optimisation and simulation approach is used to search for efficiency leads for different ED configurations. These configurations change depending on the shift and the day of the week.

Discrete event simulation as a decision-making tool for end-of-life tire reverse logistics in a Brazilian city consortium.

Tires require adequate disposal at the end of their useful life due to the environmental damage that improper disposal can cause. Since the 1990s, Brazilian legislation has laid out specific rules for tire disposal. This brought about results in 2017, when 93% of the target was met for environmentally correct tire disposal, according to the Brazilian Institute of the Environment and Renewable Natural Resources. To reach this index, consumers, business people, city halls, and manufacturers had to work together. However, cities with fewer than 100,000 inhabitants continued to encounter difficulties to carry out the process efficiently. Thus, the objective of this study is to propose new alternatives so that small cities can plan and implement reverse logistics management for unusable tires. The tool used to verify improvement was discrete event simulation, which allowed for the creation of scenarios, experimenting with changes to the consortium's operation. The analysis confirms that the consortium of cities can have a more efficient process in the destination of tires, with the possibility of reducing costs by 15%, emission of pollutant gases by 71%, and CO2 by 57%.

Analysis of the Influence of Standard Time Variability on the Reliability of the Simulation of Assembly Operations in Manufacturing Systems.

OBJECTIVE: The aim of this article is to analyze the influence of the variability of the standard time in the simulation of the assembly operations of manufacturing systems. BACKGROUND: Discrete event simulation (DES) has been used to provide efficient analysis during the design of a process or scenario. However, the modeling activities of new configurations face the problem of data availability and reliability when it comes to seeking standard times that are effective in representing the actual process under analysis, especially when the process cannot be monitored. METHOD: The methods-time measurement (MTM) is used as a source of standard times for simulation. Assembly activities were performed at a Learning Factory facility, which provided the necessary structure for simulating real production processes. Simulation performances using different variability of standard times were analyzed to define the impact of data characteristics. RESULTS: The MTM standard time presented an error of approximately 5%. The definition of the data variability of standard times and the statistical distribution impacts were shown in the simulation results, with errors above 6% being observed, interfering with the model reliability. CONCLUSION: Based on the study, to increase the adherence of a simulation to represent a real process, it is recommended to use triangular distributions with central values greater than those established via the MTM for the representation of the standard times of new assembly processes or scenarios using DES. APPLICATION: The study contributions can be applied in assembly line design, providing a reliable model representing real processes and scenarios.

Knowledge Management for Brazilian Cancer Care Services.

Nowadays Brazil has a complex cancer care scenario. There are nearly 600.000 new cancer cases each year in Brazil, and the huge majority of patients have some contact with hospital services. However, long waiting queues for diagnostics and treatments have become common. One of the critical success factors in a cancer treatment is early diagnosis. The reduction of waiting time to start therapeutic procedures is one of the main issues for improvement of patient's quality of life and possibilities of cure. The objective of this work is to describe the development of a decision support system that improves the identification of access alternatives, appointment scheduling and employment of available resources. The Theory of Constraints was used to identify bottlenecks in patient treatment flow and a Discrete Events Simulation model was used to reduce patients' waiting time to start cancer treatment.

Decision Support Systems in Cancer Treatment: A Case Study at Brazilian National Cancer Institute.

Nowadays Brazil has a complex cancer care scenario. There are nearly 600.000 new cancer cases each year in Brazil, and the huge majority of patients have some contact with hospital services. However, long waiting queues for diagnostics and treatments have become common. One of the critical success factors in a cancer treatment is early diagnosis. The reduction of waiting time to start therapeutic procedures is one of the main issues for improvement of patient's quality of life and possibilities of cure. The objective of this work is to describe the development of a decision support system that improves the identification of access alternatives, appointment scheduling and employment of available resources. The Theory of Constraints was used to identify bottlenecks in patient treatment flow and a Discrete Events Simulation model was used to reduce patients' waiting time to start cancer treatment.

Reducing Emergency Medical Service response time via the reallocation of ambulance bases.

The demand for highly efficient and effective services and consumer goods is an essential prerequisite for modern organizations. In healthcare, efficiency and effectiveness mean reducing disabilities and maintaining human life. One challenge is guaranteeing rapid Emergency Medical Service (EMS) response. This study analyzes the EMS of Belo Horizonte, Brazil, using two modeling techniques: optimization and simulation. The optimization model locates ambulance bases and allocates ambulances to those bases. A simulation of this proposed configuration is run to analyze the dynamic behavior of the system. The main assumption is that optimizing the ambulance base locations can improve the system response time. Feasible solutions were found and the current system may be improved while considering economic and operational changes.

Incorporating discrete event simulation into quality improvement efforts in health care systems.

Quality improvement (QI) efforts are an indispensable aspect of health care delivery, particularly in an environment of increasing financial and regulatory pressures. The ability to test predictions of proposed changes to flow, policy, staffing, and other process-level changes using discrete event simulation (DES) has shown significant promise and is well reported in the literature. This article describes how to incorporate DES into QI departments and programs in order to support QI efforts, develop high-fidelity simulation models, conduct experiments, make recommendations, and support adoption of results. The authors describe how DES-enabled QI teams can partner with clinical services and administration to plan, conduct, and sustain QI investigations.

Economic Evaluation of Bariatric Surgery in Mexico Using Discrete Event Simulation.

OBJECTIVES: Morbid obesity represents high costs to health institutions in controlling associated comorbidities. It has been shown that bariatric surgery resolves or improves comorbidities, thus reducing resource utilization. This analysis estimated the total costs of treating morbid obesity and related comorbidities through conventional treatment compared to bariatric surgery under the Mexican public health system perspective. METHODS: An economic evaluation model was developed by using discrete event simulation. One hundred fifty patients were created in each arm, with considered comorbidities allocated randomly. Preoperative comorbidity prevalences and bariatric surgery's efficacy for resolving them were obtained from published literature. Comorbidity treatment costs were obtained from the 2007 Mexican Institute of Social Security diagnosis-related group list and publications from the National Institute of Public Health. Only 12 patients were operated each month on the surgical arm. Complications associated with comorbidities were not considered. The considered time frame for simulation was 10 years, with a 4.5% annual discount rate. RESULTS: Return on investment, or cost breakeven point, for bariatric surgery was obtained after 6.8 years. Total costs for the surgical group were 52% less than conventional treatment group costs after 10 years. Bariatric surgery reduced the cost of treating type 2 diabetes, hypertension, and hypercholesterolemia by 59%, 53%, and 65%, respectively. Return on investment for bariatric surgery in patients with type 2 diabetes as the only comorbidity was 4.4 years. CONCLUSIONS: Despite conservative assumptions, investment in bariatric surgery is recouped in 6.8 years, generating relevant potential savings in the treatment of morbidly obese patients. In high-risk subpopulations, return on investment time is shorter.