University of Twente Student Theses
Designing a DLA-CFA policy for patient admission within a rehabilitation clinic’s multi-disciplinary, multi-appointment environment
Janssen, Renske (2024) Designing a DLA-CFA policy for patient admission within a rehabilitation clinic’s multi-disciplinary, multi-appointment environment.
|
PDF
5MB |
| Abstract: | In rehabilitation clinics, inpatient and outpatient patients follow treatment with different health professionals, e.g., physiotherapists, occupational therapists, and speech therapists. The type and number of therapy sessions and the length of the total admission or amount of outpatient visits differ per patient. A clinic often has limited capacity, but a fast start of treatment is often crucial to gain the best improvement. We developed a method for an admission policy for outpatients that balances the waiting times and the overuse of capacity. We design a Markov Decision Process (MDP) that models the arrivals and length of stay of both inpatients, who are directly admitted, and outpatients, who first enter the waiting list. We define set decision moments where the patient's length of stay can be increased, resulting in extra unknown demand. We solve the obtained MDP by using a combined Direct Lookahead and Cost Function Approximation policy (DLA-CFA) policy. This policy forecasts the demand resulting from exogenous information for a couple of weeks in advance. We use a stochastic approximation algorithm and a newsvendor model to forecast the demand. We apply the model to a simple multi-appointment but single-discipline setting and a system resembling a multi-disciplinary rehabilitation clinic, and compare the results with a myopic policy without such a forecast. We conclude that our developed method outperforms the myopic policy. We note that the stochastic approximation and newsvendor models achieve similar objective function costs. However, their performance may differ in other assessment factors. |
| Item Type: | Essay (Master) |
| Clients: | Merem, Hilversum |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 31 mathematics |
| Programme: | Applied Mathematics MSc (60348) |
| Link to this item: | https://purl.utwente.nl/essays/104747 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page