EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

1575. Optimizing adaptive medical staff scheduling using recourse decisions amidst fluctuating patient demand

Invited abstract in session TC-15: Staffing and workforce planning and scheduling, stream OR in Health Services (ORAHS).

Tuesday, 12:30-14:00
Room: 18 (building: 116)

Authors (first author is the speaker)

1. Markus Schüller
Universität Augsburg
2. Jan Schoenfelder
LUMS, Lancaster University Leipzig
3. Jens Brunner
Department of Technology, Management, and Economics, Technical University of Denmark

Abstract

Scheduling of medical staff represents a time-consuming task, even during periods of relatively stable patient demand and personnel availability. Since rosters are built based on long-term patient loads, significant discrepancies between expected and actual patient emergences may occur, especially in times of high volatility like the COVID-19 pandemic. To ensure adequate care in short-term, recourse decisions, such as extra shifts or transferring patients are necessary to cover high workload peaks in terms of demand. Nevertheless, exact forecasts about number of patients cannot be made for more than a few days in advance. This makes it nearly impossible for schedulers to anticipate unexpected demand when creating the upcoming schedule. In this work, we provide a Mixed-Integer Program (MIP) to (re-)allocate medical staff and therefore ensure appropriate care of all patients. Our MIP consists of a two-stage optimization model, which at first performs the initial schedule while on the second stage applying recourse decisions to cover realized patient demand. The expected workload is determined on forecasts about patient emergence and the acuity level of patients by partners of the PROGNOSIS consortium. Our temporal scope encompasses a time horizon of one week. As patient demand is subject to numerous uncertainties, we evaluate scenario-based rosters by applying Sample-Average Approximation and provide generalized insights about short-term adjustments in personnel scheduling.

Keywords

Status: accepted


Back to the list of papers