Stochastic multi-objective auto-optimization for resource allocation decision-making in fixed-input health systems

Bastian, Nathaniel D.; Ekin, Tahir; Kang, Hyojung; Griffin, Paul M.; Fulton, Lawrence V.; Grannan, Benjamin C.

doi:10.1007/s10729-015-9350-2

Cited by 14 publications

(5 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is perhaps in the best interest not to actively influence further reduction in doctor–patient interaction time. Hence this variable has been included in the queuing–DEA model as a “non-discretionary” output with a view of keeping it constant; as opposed to previous DEA studies where “non-discretionary” inputs are considered such as treatment population (Mitropoulos et al ., 2013; Bastian et al , 2017) and number of beds (Herwartz and Strumann, 2014).…”

Section: Methodsmentioning

confidence: 99%

An optimized queue management system to improve patient flow in the absence of appointment system

Safdar

Emrouznejad

Dey

2020

IJHCQA

View full text Add to dashboard Cite

PurposeThe aim of this research study is to develop a queue assessment model to evaluate the inflow of walk-in outpatients in a busy public hospital of an emerging economy, in the absence of appointment systems, and construct a dynamic framework dedicated towards the practical implementation of the proposed model, for continuous monitoring of the queue system.Design/methodology/approachThe current study utilizes data envelopment analysis (DEA) to develop a combined queuing–DEA model as applied to evaluate the wait times of patients, within different stages of the outpatients' department at the Combined Military Hospital (CMH) in Lahore, Pakistan, over a period of seven weeks (23rd April to 28th May 2014). The number of doctors/personnel and consultation time were considered as outputs, where consultation time was the non-discretionary output. The two inputs were wait time and length of queue. Additionally, VBA programming in Excel has been utilized to develop the dynamic framework for continuous queue monitoring.FindingsThe inadequate availability of personnel was observed as the critical issue for long wait times, along with overcrowding and variable arrival pattern of walk-in patients. The DEA model displayed the “required” number of personnel, corresponding to different wait times, indicating queue build-up.Originality/valueThe current study develops a queue evaluation model for a busy outpatients' department in a public hospital, where “all” patients are walk-in and no appointment systems. This model provides vital information in the form of “required” number of personnel which allows the administrators to control the queue pre-emptively minimizing wait times, with optimal yet dynamic staff allocation. Additionally, the dynamic framework specifically targets practical implementation in resource-poor public hospitals of emerging economies for continuous queue monitoring.

show abstract

Section: Methodsmentioning

confidence: 99%

An optimized queue management system to improve patient flow in the absence of appointment system

Safdar

Emrouznejad

Dey

2020

IJHCQA

View full text Add to dashboard Cite

show abstract

“…This approach draws parallels to previous work by Bastian et al, which developed the Stochastic Multi-Objective Auto-Optimization Model for resource allocation in fixed-input health systems. 11 This model automatically identifies optimal re-allocation of system input resources at the hospital level, considering the uncertainty in model parameters, and has been applied to 128 hospitals across the nation. Part of this paper highlights the importance of considering uncertainty in performance measurement systems.…”

Section: Related Workmentioning

confidence: 99%

Stochastic optimization of inference execution on tactical edge networks

Willeke,

Harding,

Chan

et al. 2024

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications VI

View full text Add to dashboard Cite

In tactical edge networks, the volatility of computational and communication resources complicates the consistent processing of data. Previous work has developed a system that allows execution of inference task applications throughout a network using a variety of adaptations to machine learning models that offer accuracy and latency trade-offs as conditions change in order adaptively perform deterministic resource allocation at the tactical edge. This paper expands on previous work that proposed a system that allows execution of inference task applications throughout a network and then developed a resource allocation algorithm that optimally places intelligence, surveillance, and reconnaissance related machine learning tasks throughout the network. We propose utilizing stochastic optimization to analyze the computational time and performance for inference tasks. Instead of adhering to deterministic averages, we use sample average approximation as a solution technique to optimize and analyze the inherent uncertainties of tactical edge environments, optimizing over the distribution of inference data rather than average-case scenarios. This paper verifies Jensen’s inequality gap within deterministic optimization and proposes an improved resource allocation algorithm that optimally places tasks throughout a network under uncertainty. We present initial results on a military relevant tactical edge network scenario.

show abstract

“…It was suggested that for a complex non-trivial problem of this kind, a hybrid approach combining several optimisation techniques might be successful. Bastian et al [91] optimised resources across the United States Military Hospital System using mixed-integer linear programming, including some stochastic elements, but this was only for staff and funding. Another study by Feng et al [92] produced a multi-objective stochastic mathematical model for medical resource allocation in emergency departments.…”

Section: Core Activitiesmentioning

confidence: 99%

An Overview of Hospital Capacity Planning and Optimisation

et al. 2022

View full text Add to dashboard Cite

Health care is uncertain, dynamic, and fast growing. With digital technologies set to revolutionise the industry, hospital capacity optimisation and planning have never been more relevant. The purposes of this article are threefold. The first is to identify the current state of the art, to summarise/analyse the key achievements, and to identify gaps in the body of research. The second is to synthesise and evaluate that literature to create a holistic framework for understanding hospital capacity planning and optimisation, in terms of physical elements, process, and governance. Third, avenues for future research are sought to inform researchers and practitioners where they should best concentrate their efforts. In conclusion, we find that prior research has typically focussed on individual parts, but the hospital is one body that is made up of many interdependent parts. It is also evident that past attempts considering entire hospitals fail to incorporate all the detail that is necessary to provide solutions that can be implemented in the real world, across strategic, tactical and operational planning horizons. A holistic approach is needed that includes ancillary services, equipment medicines, utilities, instrument trays, supply chain and inventory considerations.

show abstract

Stochastic multi-objective auto-optimization for resource allocation decision-making in fixed-input health systems

Cited by 14 publications

References 52 publications

An optimized queue management system to improve patient flow in the absence of appointment system

An optimized queue management system to improve patient flow in the absence of appointment system

Stochastic optimization of inference execution on tactical edge networks

An Overview of Hospital Capacity Planning and Optimisation

Contact Info

Product

Resources

About