Hospital-Wide Inpatient Flow Optimization

Dimitris Bertsimas () and Jean Pauphilet ()
Additional contact information
Dimitris Bertsimas: Sloan School of Management, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139
Jean Pauphilet: London Business School, London NW1 4SA, United Kingdom

Management Science, 2024, vol. 70, issue 7, 4893-4911

Abstract: An ideal that supports quality and delivery of care is to have hospital operations that are coordinated and optimized across all services in real time. As a step toward this goal, we propose a multistage adaptive robust optimization approach combined with machine learning techniques. Informed by data and predictions, our framework unifies the bed assignment process across the entire hospital and accounts for present and future inpatient flows, discharges, and bed requests from the emergency department, scheduled surgeries and admissions, and outside transfers. We evaluate our approach through simulations calibrated on historical data from a large academic medical center. For the 600-bed institution, our optimization model was solved in seconds and reduced off-service placement by 24% on average and boarding delays in the emergency department and postanesthesia units by 35% and 18%, respectively. We also illustrate the benefit of using adaptive linear decision rules instead of static assignment decisions.

Keywords: hospital operations; flow management; machine learning; multistage robust optimization (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/mnsc.2023.4933 (application/pdf)

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:inm:ormnsc:v:70:y:2024:i:7:p:4893-4911

Access Statistics for this article

More articles in Management Science from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().