EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Integrating natural language processing into radiation oncology: a practical guide to transformer architecture and large language models

Reza Khanmohammadi iD, Mohammad M Ghassemi iD, Kyle Verdecchia, Ahmed I Ghanem iD, Bing Luo, Indrin J Chetty iD, Hassan Bagher-Ebadian iD, Farzan Siddiqui iD, Mohamed Elshaikh iD, Benjamin Movsas iD, Kundan Thind iD

BJR|Artificial Intelligence · 2025

DOI: 10.1093/bjrai/ubaf010 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift BJR|Artificial Intelligence, 2025. Verfasst von Reza Khanmohammadi und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824, United States. Die Arbeit nennt 107 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Natural language processing (NLP) is a key technique for developing medical artificial intelligence (AI) systems that leverage electronic health record data to build diagnostic and prognostic models. NLP enables the conversion of unstructured clinical text into structured data that can be fed into AI algorithms. The emergence of transformer architecture and large language models (LLMs) has led to advances in NLP for various healthcare tasks, such as entity recognition, relation extraction, sentence similarity, text summarization, and question-answering. In this article, we review the major technical innovations that underpin modern NLP models and present state-of-the-art NLP applications that employ LLMs in radiation oncology research. However, it is crucial to recognize that LLMs are prone to hallucinations, biases, and ethical violations, which necessitate rigorous evaluation and validation prior to clinical deployment. As such, we propose a comprehensive framework for assessing the NLP models based on their purpose and clinical fit, technical performance, bias and trust, legal and ethical implications, and quality assurance prior to implementation in clinical radiation oncology. Our article aims to provide guidance and insights for researchers and clinicians who are interested in developing and using NLP models in clinical radiation oncology.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencelarge language modelsnatural language processingpersonalized medicineradiation oncology

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824, United States.
  • Department of Radiation Oncology, Henry Ford Health, Detroit, MI 48202, United States.
  • Alexandria Department of Clinical Oncology, Alexandria University, Alexandria 21561, Egypt.
  • Department of Radiation Oncology, Cedars Sinai Medical Center, Los Angeles, CA 90048, United States.
  • Departments of Radiology and Osteopathic Medicine, Michigan State University, East Lansing, MI 48824, United States.
  • Department of Physics, Oakland University, Rochester, MI 48326, United States.

ORCID-Profile: Reza Khanmohammadi, Mohammad M Ghassemi, Ahmed I Ghanem, Indrin J Chetty, Hassan Bagher-Ebadian, Farzan Siddiqui, Mohamed Elshaikh, Benjamin Movsas, Kundan Thind

Zitieren

APA

Khanmohammadi, R., Ghassemi, M. M., Verdecchia, K., Ghanem, A. I., Luo, B., Chetty, I. J., Bagher-Ebadian, H., Siddiqui, F., Elshaikh, M., Movsas, B., & Thind, K. (2025). Integrating natural language processing into radiation oncology: a practical guide to transformer architecture and large language models. BJR|Artificial Intelligence. https://doi.org/10.1093/bjrai/ubaf010

Vancouver

Khanmohammadi R, Ghassemi MM, Verdecchia K, Ghanem AI, Luo B, Chetty IJ, et al. Integrating natural language processing into radiation oncology: a practical guide to transformer architecture and large language models. BJR|Artificial Intelligence. 2025. doi:10.1093/bjrai/ubaf010

BibTeX
@article{Khanmohammadi2025,
  author = {Khanmohammadi, Reza and Ghassemi, Mohammad M and Verdecchia, Kyle and Ghanem, Ahmed I and Luo, Bing and Chetty, Indrin J and Bagher-Ebadian, Hassan and Siddiqui, Farzan and Elshaikh, Mohamed and Movsas, Benjamin and Thind, Kundan},
  title = {Integrating natural language processing into radiation oncology: a practical guide to transformer architecture and large language models},
  journal = {BJR|Artificial Intelligence},
  year = {2025},
  doi = {10.1093/bjrai/ubaf010}
}
Kostenlos starten →