EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

681. Data-Driven Robust Scheduling of Elective Patients

Invited abstract in session WD-10: Admission and discharge, stream OR in Health Services (ORAHS).

Wednesday, 14:30-16:00
Room: 11 (building: 116)

Authors (first author is the speaker)

1. Nan Yang
School of Management, Technical University of Munich
2. Jingui Xie
Technical University of Munich

Abstract

Hospital beds are an important medical resource, and the dynamic admission scheduling of elective patients can help to avoid bed shortages. However, such elective patients scheduling problem is challenging due to the high level of uncertainty behind the bed availability and its impact on admission rates. In fact, Meng et al. (2015) proposed a robust optimization approach to determine the elective admission quotas based on budgeted uncertainty sets to minimize the expected bed shortages. A key challenge to be addressed by this approach is the uncertainty behind the stochastic patient arrival and length of stay (LoS). However, the budget of the uncertainty set is not easy to determine, which in contrast can be avoided in the robust satisficing approach proposed by Long et al. (2022). Robust satisficing favors solutions where the risk-aware objective function best achieves an acceptable goal even when the actual probability distribution deviates significantly from the empirical distribution, and it can tolerate greater uncertainty than robust optimization. In this paper, we propose a robust satisficing method for determining quotas for elective admissions, which will best avoid bed shortages under extreme uncertainty. We do numerical experiments for the proposed robust satisficing model based on the MIMIC-IV dataset and compare it with the results generated by robust optimization methods. The results show that the robust satisficing model can withstand greater uncertainty.

Keywords

Status: accepted

Back to the list of papers