74. A Data-Driven Approach for Integrated Operating Room Scheduling and Bed Management
Contributed abstract in session HB-5: Operating Room Scheduling /2, stream Regular talks.
Thursday, 11:00-12:30Room: Room S6
Authors (first author is the speaker)
| 1. | Dimitrios Karagiannis
|
| 2. | Nalan Gulpinar
|
| Warwick Business School, Warwick University | |
| 3. | Xuan Vinh Doan
|
| Warwick Business School, University of Warwick |
Abstract
Operating room scheduling, with an emphasis on downstream unit considerations, presents a substantial challenge for hospital management systems. This study explores the integration of machine learning—emerging data-driven methodologies—and traditional operational research techniques to improve decision-making processes and resource utilization. We introduce a stochastic optimization model to address the uncertainties associated with initial bed occupancy at the commencement of a surgical week. We demonstrate the performance of this model using a real hospital case. Our approach demonstrates that minimizing variability in Length of Stay (LoS) through personalized patient LoS predictions, derived from machine learning, can significantly enhance ward management. Results indicate reduced last-minute cancellations due to bed shortages and smoother bed occupancy rates, enhancing scheduling efficiency.
Keywords
- Operating room planning and scheduling
- Patient scheduling
- Artificial Intelligence
Status: accepted
Back to the list of papers