View in EDS HTML Full Text PDF Full Text

Evaluating prompt and data perturbation sensitivity in large language models for radiology reports classification.

Saved in:
Bibliographic Details
Title: Evaluating prompt and data perturbation sensitivity in large language models for radiology reports classification.
Authors: Sorin V; Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, MN 55905, United States., Collins JD; Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, MN 55905, United States., Bratt AK; Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, MN 55905, United States., Kusmirek JE; Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, MN 55905, United States., Mugu VK; Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, MN 55905, United States., Kline TL; Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, MN 55905, United States., Butler CL; Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, MN 55905, United States., Wood NG; Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, MN 55905, United States., Cook CJ; Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, MN 55905, United States., Korfiatis P; Department of Radiology, Mayo Clinic College of Medicine and Science, Mayo Clinic, Rochester, MN 55905, United States.
Source: JAMIA open [JAMIA Open] 2025 Aug 12; Vol. 8 (4), pp. ooaf073. Date of Electronic Publication: 2025 Aug 12 (Print Publication: 2025).
Publication Type: Journal Article
Journal Info: Publisher: Oxford University Press on behalf of the American Medical Informatics Association Country of Publication: United States NLM ID: 101730643 Publication Model: eCollection Cited Medium: Internet ISSN: 2574-2531 (Electronic) Linking ISSN: 25742531 NLM ISO Abbreviation: JAMIA Open Subsets: PubMed not MEDLINE
Database: MEDLINE Ultimate
Full text is not displayed to guests.
Description
ISSN:2574-2531
DOI:10.1093/jamiaopen/ooaf073