Increasing the performance of a hospital department with budget allocation model and machine learning assisted by simulation

Muzaffer Alim, Yıldıran Yilmaz and Esra Boz

Journal of Simulation, 2025, vol. 19, issue 2, 127-140

Abstract: The COVID-19 pandemic highlighted the critical need for efficient resource management in healthcare. In this study, the internal medicine outpatient clinic in a hospital is modelled by simulation method. Appropriate statistical distributions of the parameters are derived from past data. The results of a limited number of simulation runs are used as training data for machine learning techniques and an estimation model is selected among them. The estimation results are considered as input to a mathematical model which determines the optimal budget allocation for improving the system performance. Analysis considers patient waiting times and system throughput under varied parameters. A significant amount of time is saved by using machine learning to predict the simulation model outcomes, which had previously taken a total of around 7 hours reduced to 30–40 minutes. Time savings through machine learning are projected to be notably greater for more complex simulations comparing to current case.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/17477778.2024.2349160 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:tjsmxx:v:19:y:2025:i:2:p:127-140

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/tjsm20

DOI: 10.1080/17477778.2024.2349160

Access Statistics for this article

Journal of Simulation is currently edited by Christine Currie

More articles in Journal of Simulation from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().