A simulation and optimization based method for calibrating agent-based emergency department models under data scarcity

Liu, Zhengchun; Rexachs, Dolores; Epelde, Francisco; Luque, Emilio

doi:10.1016/j.cie.2016.11.036

Cited by 49 publications

(40 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The values of the PaT have been calculated from the calibration of the ED simulator using actual historical records from Tauli Hospital. Furthermore, it is important to note that the ED simulator contemplates a random exponential distribution to model the behavior of attention time by the staff, as well as the acuity level and the age of each patient [27]. We carried out a statistical analysis using the output of the simulation, which is given as the result of the mean PaT value for patients.…”

Section: A Distribution Of Non-critical Patients: System Statementioning

confidence: 99%

An Intelligent Scheduling of Non-Critical Patients Admission for Emergency Department

Bruballa¹,

Wong²,

Rexachs³

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

The combination of the progressive growth of an aging population, increased life expectancy and a greater number of chronic diseases all contribute significantly to the growing demand for emergency medical care, and thus, causing saturation in Emergency Departments (EDs). This saturation is usually due to the admission of non-urgent patients, who constitute a high percentage of patients in an ED. The Agentbased Model (ABM) is one of the most important tools that helps to study complex systems and explores the emergent behavior of this type of department. Its simulation more accurately reflects the complexity of the operation of real systems. Our proposal is the design of an ABM to schedule the access of these noncritical patients into an ED, which can be useful for the service management dealing with the actual growing demand for emergency care. We suppose that a relocation of these non-critical patients within the expected input pattern, provided initially by historical records, enables a reduction in waiting time for all patients, and therefore, it will lead to an improvement in the quality of service. It would also allow us to avoid long waiting times. This research offers the availability of relevant knowledge for Emergency Department managers in order to help them make decisions to improve the quality of the service, in anticipation of the expected growing demand of the service in the very near future. INDEX TERMS Agent-based modeling and simulation (ABMS), Emergency Department (ED), response capacity, decision support systems (SDS), length of stay (LoS).

show abstract

Section: A Distribution Of Non-critical Patients: System Statementioning

confidence: 99%

An Intelligent Scheduling of Non-Critical Patients Admission for Emergency Department

Bruballa¹,

Wong²,

Rexachs³

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this method, a complex system can be modeled as a set of independent entities called agents who can interact with each other, make self-governing decisions, and indicate proactive behavior based on their goals [15], [16], [17], [18] and [19]. Linear and non-linear analyses with different levels of modeling complexities have been used in earlier studies to investigate impacts of patient's behavior, number of ED visits [20], [21] and [8], aging population and NCDs [22], on LoS and ED quality of care [23], [24]. Liu at [21] simulated ED using ABMS where patients were classified according to their level of acuity.…”

Section: Introductionmentioning

confidence: 99%

“…Linear and non-linear analyses with different levels of modeling complexities have been used in earlier studies to investigate impacts of patient's behavior, number of ED visits [20], [21] and [8], aging population and NCDs [22], on LoS and ED quality of care [23], [24]. Liu at [21] simulated ED using ABMS where patients were classified according to their level of acuity. In this model, patients, ED staff, and hospital physical resources were agents whose actions and interactions were modeled in the ED simulator.…”

Section: Introductionmentioning

confidence: 99%

“…The first objective of this study was to improve an existing agent-based ED simulator [21] by taking into account patients with NCDs, in addition to regular patients, as inputs into the model. Hence, new variables and attributes were added to the patient's agent characteristics of which were obtained through clinical data (collected from Parc Tauli Hospital in Sabadell/Spain and from GDB, WHO) [21] as well as data from statistical models that we developed to predict how population and age distribution of patients with NCDs changes in Spain in future years. The second objective of this study was to use the ED simulator to investigate and predict impacts of changes in population and age distribution of patients with NCDs on ED performance through estimations of LoS between years 2019 and 2039.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Method for Projections of the Emergency Department Behaviour by Non-Communicable Diseases from 2019 to 2039

Shojaei

Rexachs

Epelde

et al. 2020

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

In this paper, a new method for prediction of future performance and demand on emergency department (ED) in Spain is presented. Increased life expediency and population aging in Spain, along with their corresponding health conditions such as non-communicable diseases (NCDs), have been suggested to contribute to higher demands on ED. These lead to inferior performance of the department and cause longer ED length of stay (LoS). Prediction and quantification of behavior of ED is, however, challenging as ED is one of the most complex parts of hospitals. Using detailed computational approaches integrated with clinical data behavior of Spain's ED in future years was predicted. First, statistical models were developed to predict how the population and age distribution of patients with non-communicable diseases change in Spain in future years. Then, an agent-based modeling approach was used for simulation of the emergency department to predict impacts of the changes in population and age distribution of patients with NCDs on the performance of ED, reflected in ED LoS, between years 2019 and 2039. Results from different projection scenarios indicated that Spain would experience a continuous increase in total ED LoS from 5.7 million hours in 2019 to 6.2 million hours in 2039 if same human and physical resources, as well as same ED configuration, are used. The results from this study can provide health care provider with quantitative information on required staff and physical resources in the future and allow health care policymakers to improve modifiable factors contributing to the demand and performance of ED.

show abstract

“…For example, in the context of a biomedical ABM one of those rules might be the definition of a cytokine signaling pathway, i.e., Tumor Necrosis Factor α (TNFα) upregulates Interleukin-10 (IL-10). The quantification of the effect that TNFα has on IL-10 in this hypothetical rule is determined during the model calibration, a critical step in the development and refinement of an ABM (11)(12)(13)(14)(15).…”

Section: Introductionmentioning

confidence: 99%

Genetic Algorithms for model refinement and rule discovery in a high-dimensional agent-based model of inflammation

Cockrell

2019

Preprint

View full text Add to dashboard Cite

AbstractIntroductionAgent-based modeling frequently used modeling method for multi-scale mechanistic modeling. However, the same properties that make agent-based models (ABMs) well suited to representing biological systems also present significant challenges with respect to their construction and calibration, particularly with respect to the selection of potential mechanistic rules and the large number of free parameters often present in these models. We have proposed that various machine learning approaches (such as genetic algorithms (GAs)) can be used to more effectively and efficiently deal with rule selection and parameter space characterization; the current work applies GAs to the challenge of calibrating a complex ABM to a specific data set, while preserving biological heterogeneity.MethodsThis project uses a GA to augment the rule-set for a previously validated ABM of acute systemic inflammation, the Innate Immune Response ABM (IIRABM) to clinical time series data of systemic cytokine levels from a population of burn patients. The genome for the GA is a vector generated from the IIRABM’s Model Rule Matrix (MRM), which is a matrix representation of not only the constants/parameters associated with the IIRABM’s cytokine interaction rules, but also the existence of rules themselves. Capturing heterogeneity is accomplished by a fitness function that incorporates the sample value range (“error bars”) of the clinical data.ResultsThe GA-enabled parameter space exploration resulted in a set of putative MRM rules and associated parameterizations which closely match the cytokine time course data used to design the fitness function. The number of non-zero elements in the MRM increases significantly as the model parameterizations evolve towards a fitness function minimum, transitioning from a sparse to a dense matrix. This results in a model structure that more closely resembles (at a superficial level) the structure of data generated by a standard differential gene expression experimental study.ConclusionWe present an HPC-enabled evolutionary computing approach to calibrate a complex ABM to clinical data while preserving biological heterogeneity. The integration of machine learning, HPC, and multi-scale mechanistic modeling provides a pathway forward to effectively represent the heterogeneity of clinical populations and their data.Author SummaryIn this work, we utilize genetic algorithms (GA) to operate on the internal rule set of a computational of the human immune response to injury, the Innate Immune Response Agent-Based Model (IIRABM), such that it is iteratively refined to generate cytokine time series that closely match what is seen in a clinical cohort of burn patients. At the termination of the GA, there exists an ensemble of candidate model rule-sets/parameterizations which are validated by the experimental data;

show abstract

A simulation and optimization based method for calibrating agent-based emergency department models under data scarcity

Cited by 49 publications

References 22 publications

An Intelligent Scheduling of Non-Critical Patients Admission for Emergency Department

An Intelligent Scheduling of Non-Critical Patients Admission for Emergency Department

A Method for Projections of the Emergency Department Behaviour by Non-Communicable Diseases from 2019 to 2039

Genetic Algorithms for model refinement and rule discovery in a high-dimensional agent-based model of inflammation

Contact Info

Product

Resources

About