33. Predictive decision-support tool for improved nurse scheduling through the application of artificial intelligence
Invited abstract in session ME-3: Appointment scheduling, stream Sessions.
Monday, 15:30-17:00Room: NTNU, Realfagbygget R9
Authors (first author is the speaker)
| 1. | Agita Solzemniece
|
| Department of Technology, Management and Economics, Technical University of Denmark | |
| 2. | Jens Brunner
|
| Department of Technology, Management, and Economics, Technical University of Denmark |
Abstract
The nurse scheduling problem is a complex optimization task that needs to be solved. While conventional optimization approaches provide an optimal solution, relying on static nursing demand limits the adaptability to the real-world hospital setting. Given the highly specific and dynamic nature of the nursing workload, there is an extraordinary need for adaptive and data-driven decision-support methods. This research project aims to investigate how novel artificial intelligence (AI) methods can be utilized to identify key factors influencing nursing workload and how these can be leveraged to develop a predictive modeling tool for improved decision-support. Various aspects of nursing workload can be tackled to enhance the effectiveness of the nurse scheduling task, such as exploring underlying patterns of workload variables, estimating the required capacity levels, or improving the workload measurement. Applying machine learning to gain better insights into the complexities of nursing workload can deepen the understanding of the nurse scheduling task, leading to better estimates of demand, and better resource management. The main objective of this research is to design a predictive decision-support tool that can provide more accurate projections for required nurse resources and potentially lead to more efficient critical healthcare resource scheduling. We present our modeling ideas and preliminary experiments based on real-world data from a university hospital.
Keywords
- Artificial Intelligence
- Decision support
- Resource scheduling
Status: accepted
Back to the list of papers