Using large language models to automate summarization of CT simulation orders in radiation oncology
Journal of Applied Clinical Medical Physics · 2025
DOI: 10.1002/acm2.70310 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, 2025. Verfasst von Meiyun Cao und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, Mayo Clinic Hospital, Phoenix, Arizona, USA. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Radiation Oncology, Neoplasms, Radiotherapy Planning, Computer-Assisted. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, Kemper Marley Foundation, Eric & Wendy Schmidt Fund for AI Research & Innovation.
Abstract (Originalsprache)
Background
In the current clinical workflow of radiation oncology, therapists manually summarize the physician‐issued Computed Tomography (CT) simulation orders to prepare patients' CT simulations. This process increases the workload, introduces variability in documentation quality, and is prone to human errors.
Purpose
This study aims to address these challenges using a large language model (LLM) to automate the generation of summaries from the CT simulation orders and evaluate its performance.
Methods
A total of 607 CT simulation orders were collected from the Aria database at our institution. A locally hosted LLaMa 3.1 405B model, accessed via the Application Programming Interface (API) service, was used to extract keywords from the CT simulation orders and generate summaries. The downloaded CT simulation orders were categorized into seven groups based on treatment modalities and disease sites. For each group, a customized instruction prompt was developed collaboratively with therapists to guide the LLaMa 3.1 405B model in generating summaries. The ground truth for the corresponding summaries was manually derived by carefully reviewing each CT simulation order and subsequently verified by therapists. The accuracy of the LLM‐generated summaries was evaluated by therapists using the ground truth.
Results
Over 98% of the LLM‐generated summaries aligned with the ground truth in terms of accuracy. Our evaluations showed an improved consistency in format and enhanced readability from the LLM‐generated summaries compared to the corresponding therapist‐generated summaries. This automated approach demonstrated consistent performance across all groups, regardless of treatment modality or disease site.
Conclusions
This study demonstrated the high precision and consistency of the LLaMa 3.1 405B model in extracting keywords and summarizing CT simulation orders, suggesting that LLMs have great potential to assist in this task, reduce the workload of CT simulation therapists and improve radiation oncology workflow efficiency.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiation Oncology, Mayo Clinic Hospital, Phoenix, Arizona, USA.
- Corcoran College of Arts and Sciences, George Washington University-Washington DC, Washington DC, USA.
ORCID-Profile: Edward Lee Clouser, Peilong Wang, Wei Liu
Förderung
- NCI NIH HHS
- Kemper Marley Foundation
- Eric & Wendy Schmidt Fund for AI Research & Innovation
- Fred C. and Katherine B. Anderson Foundation
- National Cancer Institute
Zitieren
APA
Cao, M., Hu, S., Sharp, J., Clouser, E. L., Holmes, J. M., Lam, L. L., Ding, X., Toesca, D. S., Raulston, B. C., Lindholm, W. S., Patel, S. H., Vora, S. A., Wang, P., & Liu, W. (2025). Using large language models to automate summarization of CT simulation orders in radiation oncology. Journal of Applied Clinical Medical Physics. https://doi.org/10.1002/acm2.70310
Vancouver
Cao M, Hu S, Sharp J, Clouser EL, Holmes JM, Lam LL, et al. Using large language models to automate summarization of CT simulation orders in radiation oncology. Journal of Applied Clinical Medical Physics. 2025. doi:10.1002/acm2.70310
BibTeX
@article{Cao2025,
author = {Cao, Meiyun and Hu, Shaw and Sharp, Jason and Clouser, Edward Lee and Holmes, Jason M and Lam, Linda L and Ding, Xiaoning and Toesca, Diego Santos and Raulston, Brianne C and Lindholm, Wendy S and Patel, Samir H and Vora, Sujay A and Wang, Peilong and Liu, Wei},
title = {Using large language models to automate summarization of CT simulation orders in radiation oncology},
journal = {Journal of Applied Clinical Medical Physics},
year = {2025},
doi = {10.1002/acm2.70310}
}
EUVIMED