Retrospective Comparative Analysis of Prostate Cancer In-Basket Messages: Responses From Closed-Domain Large Language Models Versus Clinical Teams
RadOnc-GPT has the potential to considerably reduce the workload of clinical care teams by generating high-quality, timely responses for in-basket message interactions. This could lead to improved efficiency in health care workflows and reduced costs while maintaining or enhancing the quality of communication between patients and health care providers.Abbreviations and AcronymsAI; artificial intelligence; LLM; large language model; NLP; natural language processing; RadOnc-GPT; radiation oncology generative pretrained transformer.
Authors
- Mark Raymond Waddle (ORCID: https://orcid.org/0000-0002-6017-8850)
- Yuexing Hao (ORCID: https://orcid.org/0000-0003-4375-7655)
- Chris L. Hallemeier
- Jared Hobson
- Samir H. Patel (ORCID: https://orcid.org/0000-0002-8251-574X)
- Nathan Y. Yu (ORCID: https://orcid.org/0000-0003-4059-650X)
- Daniel K. Ebner (ORCID: https://orcid.org/0000-0001-6053-5865)
- David M. Routman (ORCID: https://orcid.org/0000-0002-2768-003X)
- Satomi Shiraishi (ORCID: https://orcid.org/0000-0002-9522-014X)
- Elizabeth L. McKone (ORCID: https://orcid.org/0000-0002-9386-6369)
- Alexandra Bennett (ORCID: https://orcid.org/0000-0002-5403-0382)
- Jason Holmes (ORCID: https://orcid.org/0000-0001-8943-9471)
- Wei Liu (ORCID: https://orcid.org/0000-0003-0935-3999)
- Brooke E. Ball
Institutions
- Cornell University (US)
- Mayo Clinic in Arizona (US)
Publication Details
- Journal
- Mayo Clinic Proceedings Digital Health
- Published
- 2025-02-06
- DOI
- https://doi.org/10.1016/j.mcpdig.2025.100198
- Citations
- 6
- Primary Topic
- Clinical practice guidelines implementation
- Type
- article
- Field-Weighted Citation Impact
- 11.27
Funders
- American Psychological Foundation
- National Cancer Institute