EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY-NC-ND 4.0

Large language models for structuring knee ultrasound reports-A comparative evaluation of DeepSeek R1, gemini 2.5 flash, and GPT-4o

Min Tang, Le Xu, Libiao Zhu, Abasi Maimaitiabula, Xianzuo Zhang, Chong Pei, Lei Hu iD

BMC Medical Informatics and Decision Making · 03.03.2026 · 26 (1)

DOI: 10.1186/s12911-026-03415-2 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift BMC Medical Informatics and Decision Making, online erschienen am 03.03.2026. Verfasst von Min Tang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ultrasound, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of Chin…. Hauptthemen laut MEDLINE: Large Language Models, Knee, Knee Joint. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsKneeKnee JointHumansRetrospective StudiesUltrasonography

Stichwörter der Autor:innen

Clinical decision supportKnee ultrasonographyLarge language modelsNatural language processingStructured reporting

Autor:innen und Institutionen

  • Department of Ultrasound, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230001, China.
  • Department of Orthopedics, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230001, China.
  • Department of Orthopedics, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230001, China. zhangxianzuo@ustc.edu.cn.
  • Department of Respiratory and Critical Care Medicine, The First People's Hospital of Hefei City, The Third Affiliated Hospital of Anhui Medical University, Hefei, 230001, China. pchl331@126.com.
  • Department of Ultrasound, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230001, China. hulei@ustc.edu.cn.

ORCID-Profile: Lei Hu

Zitieren

APA

Tang, M., Xu, L., Zhu, L., Maimaitiabula, A., Zhang, X., Pei, C., & Hu, L. (2026). Large language models for structuring knee ultrasound reports-A comparative evaluation of DeepSeek R1, gemini 2.5 flash, and GPT-4o. BMC Medical Informatics and Decision Making, 26(1). https://doi.org/10.1186/s12911-026-03415-2

Vancouver

Tang M, Xu L, Zhu L, Maimaitiabula A, Zhang X, Pei C, et al. Large language models for structuring knee ultrasound reports-A comparative evaluation of DeepSeek R1, gemini 2.5 flash, and GPT-4o. BMC Medical Informatics and Decision Making. 2026;26(1). doi:10.1186/s12911-026-03415-2

BibTeX
@article{Tang2026,
  author = {Tang, Min and Xu, Le and Zhu, Libiao and Maimaitiabula, Abasi and Zhang, Xianzuo and Pei, Chong and Hu, Lei},
  title = {Large language models for structuring knee ultrasound reports-A comparative evaluation of DeepSeek R1, gemini 2.5 flash, and GPT-4o},
  journal = {BMC Medical Informatics and Decision Making},
  year = {2026},
  volume = {26},
  number = {1},
  doi = {10.1186/s12911-026-03415-2}
}
Kostenlos starten →