EUVIMEDEUVIMED entdecken
Open Access

BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study

Andrea Cozzi iD, Katja Pinker iD, Andri Hidber iD, Tianyu Zhang iD, Luca Bonomo iD, Roberto Lo Gullo, Blake Christianson iD, Marco Curti, Stefania Rizzo iD, Filippo Del Grande, Ritse M Mann iD, Simone Schiaffino

Radiology · 01.04.2024 · 311 (1)

DOI: 10.1148/radiol.232133 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology, erschienen am 01.04.2024. Verfasst von Andrea Cozzi und 11 weiteren Autor:innen. Beteiligte Einrichtung: From the Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale, Via Tesserete 46, 6900 Lugano, Switzerland (A.C., L.B., M.C.,…. Hauptthemen laut MEDLINE: Breast Neoplasms. Die Arbeit wurde bisher 101-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, National Cancer Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Based on breast imaging reports written in three languages, GPT-3.5, GPT-4, and Google Bard achieved moderate agreement with human reader–assigned Breast Imaging Reporting and Data System categories but also yielded a high percentage of discordant category assignments that would negatively impact clinical management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsAdultAgedFemaleHumansMiddle AgedBreastLanguageMagnetic Resonance ImagingMammographyRadiology Information SystemsRetrospective StudiesUltrasonography, Mammary

Autor:innen und Institutionen

  • From the Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale, Via Tesserete 46, 6900 Lugano, Switzerland (A.C., L.B., M.C., S.R., F.D.G., S.S.); Breast Imaging Service, Department of Radiology,…

ORCID-Profile: Andrea Cozzi, Katja Pinker, Andri Hidber, Tianyu Zhang, Luca Bonomo, Blake Christianson, Stefania Rizzo, Ritse M Mann

Förderung

  • NCI NIH HHS
  • National Cancer Institute

Zitieren

APA

Cozzi, A., Pinker, K., Hidber, A., Zhang, T., Bonomo, L., Lo Gullo, R., Christianson, B., Curti, M., Rizzo, S., Del Grande, F., Mann, R. M., & Schiaffino, S. (2024). BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study. Radiology, 311(1). https://doi.org/10.1148/radiol.232133

Vancouver

Cozzi A, Pinker K, Hidber A, Zhang T, Bonomo L, Lo Gullo R, et al. BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study. Radiology. 2024;311(1). doi:10.1148/radiol.232133

BibTeX
@article{Cozzi2024,
  author = {Cozzi, Andrea and Pinker, Katja and Hidber, Andri and Zhang, Tianyu and Bonomo, Luca and Lo Gullo, Roberto and Christianson, Blake and Curti, Marco and Rizzo, Stefania and Del Grande, Filippo and Mann, Ritse M and Schiaffino, Simone},
  title = {BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study},
  journal = {Radiology},
  year = {2024},
  volume = {311},
  number = {1},
  doi = {10.1148/radiol.232133}
}
Kostenlos starten →