Examining Radiation Therapy Planning Knowledge in Large Language Models
Publication
, Conference
Ghorbani, O; Helmy, A; Wu, QJ; Ge, Y
Published in: Bcb 2025 Proceedings of the 16th ACM International Conference on Bioinformatics Computational Biology and Health Informatics
December 10, 2025
Personalized radiation therapy (RT) planning is crucial for minimizing toxicities. As large language models (LLMs) advance, it is vital to assess the RT planning knowledge across model types and sizes. We introduce a board-exam-style RT dataset and benchmark proprietary and open-weight LLMs in a zero-shot setting. Results show that state-of-the-art models exceed 80% accuracy, with larger models outperforming smaller ones, while fine-tuned compact models remain competitive, underscoring the potential of LLM-based decision support for clinical RT planning.
Duke Scholars
Published In
Bcb 2025 Proceedings of the 16th ACM International Conference on Bioinformatics Computational Biology and Health Informatics
DOI
Publication Date
December 10, 2025
Citation
APA
Chicago
ICMJE
MLA
NLM
Ghorbani, O., Helmy, A., Wu, Q. J., & Ge, Y. (2025). Examining Radiation Therapy Planning Knowledge in Large Language Models. In Bcb 2025 Proceedings of the 16th ACM International Conference on Bioinformatics Computational Biology and Health Informatics. https://doi.org/10.1145/3765612.3767795
Ghorbani, O., A. Helmy, Q. J. Wu, and Y. Ge. “Examining Radiation Therapy Planning Knowledge in Large Language Models.” In Bcb 2025 Proceedings of the 16th ACM International Conference on Bioinformatics Computational Biology and Health Informatics, 2025. https://doi.org/10.1145/3765612.3767795.
Ghorbani O, Helmy A, Wu QJ, Ge Y. Examining Radiation Therapy Planning Knowledge in Large Language Models. In: Bcb 2025 Proceedings of the 16th ACM International Conference on Bioinformatics Computational Biology and Health Informatics. 2025.
Ghorbani, O., et al. “Examining Radiation Therapy Planning Knowledge in Large Language Models.” Bcb 2025 Proceedings of the 16th ACM International Conference on Bioinformatics Computational Biology and Health Informatics, 2025. Scopus, doi:10.1145/3765612.3767795.
Ghorbani O, Helmy A, Wu QJ, Ge Y. Examining Radiation Therapy Planning Knowledge in Large Language Models. Bcb 2025 Proceedings of the 16th ACM International Conference on Bioinformatics Computational Biology and Health Informatics. 2025.
Published In
Bcb 2025 Proceedings of the 16th ACM International Conference on Bioinformatics Computational Biology and Health Informatics
DOI
Publication Date
December 10, 2025