Operations Research 2025
Abstract Submission

36. Optimizing Inpatient Postoperative Therapy Scheduling: Integrating AI-assisted Physical Therapy

Invited abstract in session FA-12: Scheduling in Healthcare II, stream Health Care Management.

Friday, 8:45-10:15
Room: H10

Authors (first author is the speaker)

1. Lorenz Wagner
University of Augsburg
2. Christian Jost
Operations Management, Technical University of Munich
3. Sebastian Schiffels
Wirtschaftswissenschaftliche Fakultät, Universität Augsburg
4. Jens Brunner
Department of Technology, Management, and Economics, Technical University of Denmark

Abstract

At hospitals, receiving postoperative therapy is essential after lung cancer, cardiac, and orthopedic surgeries. However, the limited availability of specialized therapists often delays treatments and prolongs hospital stays. To address this challenge, companies offer visual AI assisted therapy to supplement in-person therapy. This creates new opportunities for the efficient scheduling of therapy sessions. Our research offers a comprehensive optimization model to derive therapy schedules that integrate traditional in-person and AI-assisted therapy. The proposed mathematical model minimizes the Length of Stay, contingent upon the treatment effectiveness of combined therapy and AI sessions, intending to optimize therapist resource utilization. To efficiently solve large-scale scheduling instances, we introduce a Column Generation heuristic. Computational experiments using real-world data from our practice partner, Breathment, demonstrate that our approach can effectively complement traditional physiotherapy, providing a scalable solution to address therapist shortages while maintaining high-quality patient care. This research contributes to healthcare operations research by offering practical solutions for hospitals to optimize their physiotherapy services through technology integration.

Keywords

Status: accepted


Back to the list of papers