1659. Online Multi-appointment Scheduling for Outpatient Examinations with Genetic Programming
Invited abstract in session TA-13: Appointment scheduling, stream OR in Healthcare (ORAHS).
Tuesday, 8:30-10:00Room: Clarendon SR 1.01
Authors (first author is the speaker)
| 1. | Zhang Huan
|
| School of Management, Northwestern Polytechnical University | |
| 2. | Yang Wang
|
| School of Management, Northwestern Polytechnical University | |
| 3. | Lihui Zeng
|
| West China Hospital, Sichuan University | |
| 4. | Li Luo
|
| Sichuan University |
Abstract
Centralized appointment platforms in hospitals enable patients to submit requests online and receive immediate allocations of date and time slots, significantly enhancing convenience and operational efficiency. However, existing multi-appointment scheduling algorithms predominantly rely on simplistic dispatching rules, which are short-sighted and fail to effectively balance patients' dual needs for reduced waiting times and fewer visits. To address this limitation, we introduce a novel online multi-appointment scheduling problem (OMASP) and develop a genetic programming (GP) algorithm to evolve high-quality dispatching rules. Our proposed GP algorithm integrates two key components: a multi-fidelity simulation evaluator to filter out underperforming rules, and a feature selection to enhance the interpretability of the evolved rules. Leveraging real-world data from a partner hospital, we design simulation scenarios that capture the distributions of the number of patient examinations and daily request arrival rates. Experimental results demonstrate that our GP-based method achieves an average improvement of 20.16% over the existing appointment dispatching rules.
Keywords
- Health Care
- Machine Learning
- Scheduling
Status: accepted
Back to the list of papers