EUVIMEDAvasta EUVIMED
Crossref

Evaluating a large language model for radiotherapy patient scheduling under realistic clinical and operational constraints: A feasibility study

Eric Zhang, Youfang Lai, Wen Li, Annette Souranis, Georgia Paparoidamis, Michael Roumeliotis, Xun Jia

Medical Physics · 2026-12 · 53 (12)

DOI: 10.1002/mp.70767 ↗

At a glance

Journal article in Medical Physics, published online on 2026-11-18. Written by Eric Zhang and 6 co-authors. 30 references.

AbstraktBibliograafilised andmedCiteRelated studies

Abstract (original language)

Background

Radiation Therapy (RT) scheduling requires coordination of clinical constraints and operational objectives. Large language models (LLMs) may provide a natural‐language interface for generating candidate schedules.

Purpose

To evaluate the feasibility of using an existing LLM to generate RT patient schedules under clinical and operational constraints through simulation and retrospective clinical comparison.

Methods

A one‐year, three‐linear‐accelerator (LINAC) simulation included 1400 new patients across 12 treatment categories modeled after clinical practice. Structured prompts supplied ChatGPT with patient data, the current schedule state, clinical rules, and scenario‐specific objectives. Performance was evaluated across scenarios addressing weekly treatment‐time consistency, LINAC continuity, gap‐constrained temporal relaxation, and infeasible request handling. LLM‐generated schedules were benchmarked against heuristic and CP‐SAT schedules under two objective settings. A six‐week retrospective comparison evaluated 2043 appointments against a clinical schedule.

Results

The LLM‐generated schedules satisfied the predefined feasibility rules in all evaluated scenarios. Across scenarios, 98.6%–98.8% of evaluated fractions remained within the preferred treatment‐time window. Adding a LINAC‐continuity objective reduced the LINAC switch rate from 52.4 2.6% to 9.4 0.6%, and gap‐constrained temporal relaxation reduced daily gap to 47.1 8.5 min and Friday gap to 89.2 18.4 min while maintaining low overtime. In infeasible request tests, the framework identified predefined constraint violations and returned interpretable corrective suggestions. The optimization benchmarks also generated feasible schedules, but their results showed strong objective‐weight trade‐offs. In the retrospective comparison, all computational approaches scheduled the workload without overtime; the LLM strategies reduced mean gap by 50.8%–77.1% and increased time consistency from 86.7% to 99.5%–99.9%.

Conclusion

Structured LLM‐assisted scheduling was feasible in the simulation and retrospective clinical comparison, producing candidate schedules under predefined constraints. The findings support further investigation of LLMs as flexible, human‐in‐the‐loop decision‐support tools for translating clinical priorities into feasible candidate schedules.

Cite

APA

Zhang, E., Lai, Y., Li, W., Souranis, A., Paparoidamis, G., Roumeliotis, M., & Jia, X. (2026). Evaluating a large language model for radiotherapy patient scheduling under realistic clinical and operational constraints: A feasibility study. Medical Physics, 53(12). https://doi.org/10.1002/mp.70767

Vancouver

Zhang E, Lai Y, Li W, Souranis A, Paparoidamis G, Roumeliotis M, et al. Evaluating a large language model for radiotherapy patient scheduling under realistic clinical and operational constraints: A feasibility study. Medical Physics. 2026;53(12). doi:10.1002/mp.70767

BibTeX
@article{Zhang2026,
  author = {Zhang, Eric and Lai, Youfang and Li, Wen and Souranis, Annette and Paparoidamis, Georgia and Roumeliotis, Michael and Jia, Xun},
  title = {Evaluating a large language model for radiotherapy patient scheduling under realistic clinical and operational constraints: A feasibility study},
  journal = {Medical Physics},
  year = {2026},
  volume = {53},
  number = {12},
  doi = {10.1002/mp.70767}
}
Start for free →