Evaluating a Large Language Model for Radiotherapy Patient Scheduling under Realistic Clinical and Operational Constraints: a Feasibility Study
Abstract
Radiotherapy scheduling must balance clinical constraints and operational objectives. We evaluated the feasibility of using a large language model (LLM) to generate treatment schedules through simulation and retrospective clinical comparison. A one-year simulation modeled 1,400 new patients across 12 treatment categories and three linear accelerators (LINACs). Structured prompts provided ChatGPT with patient information, schedule status, clinical rules, and operational objectives. Scenarios assessed treatment-time consistency, LINAC continuity, gap reduction, and handling of infeasible requests. LLM schedules were compared with heuristic and constraint programming (CP-SAT) approaches under two objective settings. A six-week retrospective analysis included 2,043 clinical appointments. LLM-generated schedules met all predefined feasibility constraints in the evaluated scenarios, with 98.6-98.8% of fractions within preferred treatment-time windows. Prioritizing LINAC continuity reduced switching from 52.4 +/- 2.6% to 9.4 +/- 0.6%. Gap-constrained temporal relaxation reduced average daily gaps to 47.1 +/- 8.5 minutes and Friday gaps to 89.2 +/- 18.4 minutes while maintaining low overtime. The framework identified predefined violations in infeasible requests and suggested corrective actions. Heuristic and CP-SAT methods also generated feasible schedules, with performance dependent on objective weighting. In retrospective evaluation, all approaches scheduled appointments without overtime; LLM strategies reduced mean gaps by 50.8-77.1% and improved treatment-time consistency from 86.7% to 99.5-99.9%. These findings support further evaluation of structured LLM scheduling as a human-in-the-loop decision-support approach for radiotherapy.
Related
- Feasibility of Urethra-Sparing Ultra-Hypofractionated Three-Dose-Level Radiotherapy for Prostate Cancer with a Dominant Intraprostatic Lesion Abutting the High-Dose Avoidance Zone.
- Priority-Aware Routing for Quantum Networks:Integrating Coherence-Time Constraints into Scheduling
- Local optical feasibility maps for compound lens optimization under direct modulation transfer function constraints
- OpenGray: a benchmark for evaluating the decisions of radiotherapy planning agents
- Diagnostic CT-Based Palliative Radiotherapy Using kV Image Verification: A Prospective Feasibility Study.
BibTeX
@misc{zhang2026evaluating,
title = {{Evaluating a Large Language Model for Radiotherapy Patient Scheduling under Realistic Clinical and Operational Constraints: a Feasibility Study}},
author = {Eric Zhang and Youfang Lai and Wen Li and Annette Souranis and Georgia Paparoidamis and Michael Roumeliotis and Xun Jia},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.12896},
eprint = {2605.12896},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.12896},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Evaluating a Large Language Model for Radiotherapy Patient Scheduling under Realistic Clinical and Operational Constraints: a Feasibility Study
AU - Eric Zhang
AU - Youfang Lai
AU - Wen Li
AU - Annette Souranis
AU - Georgia Paparoidamis
AU - Michael Roumeliotis
AU - Xun Jia
PY - 2026
DA - 2026/10/25
PB - arXiv
DO - 10.48550/arxiv.2605.12896
UR - https://arxiv.org/abs/2605.12896
AB - Radiotherapy scheduling must balance clinical constraints and operational objectives. We evaluated the feasibility of using a large language model (LLM) to generate treatment schedules through simulation and retrospective clinical comparison. A one-year simulation modeled 1,400 new patients across 12 treatment categories and three linear accelerators (LINACs). Structured prompts provided ChatGPT with patient information, schedule status, clinical rules, and operational objectives. Scenarios assessed treatment-time consistency, LINAC continuity, gap reduction, and handling of infeasible requests. LLM schedules were compared with heuristic and constraint programming (CP-SAT) approaches under two objective settings. A six-week retrospective analysis included 2,043 clinical appointments. LLM-generated schedules met all predefined feasibility constraints in the evaluated scenarios, with 98.6-98.8% of fractions within preferred treatment-time windows. Prioritizing LINAC continuity reduced switching from 52.4 +/- 2.6% to 9.4 +/- 0.6%. Gap-constrained temporal relaxation reduced average daily gaps to 47.1 +/- 8.5 minutes and Friday gaps to 89.2 +/- 18.4 minutes while maintaining low overtime. The framework identified predefined violations in infeasible requests and suggested corrective actions. Heuristic and CP-SAT methods also generated feasible schedules, with performance dependent on objective weighting. In retrospective evaluation, all approaches scheduled appointments without overtime; LLM strategies reduced mean gaps by 50.8-77.1% and improved treatment-time consistency from 86.7% to 99.5-99.9%. These findings support further evaluation of structured LLM scheduling as a human-in-the-loop decision-support approach for radiotherapy.
ER -