Comparative evaluation of large language models for hip fracture-related patient questions: DeepSeek-V3-FW, Gemini 2.0 Flash, and ChatGPT-4.5.

Saved in:
Bibliographic Details
Title: Comparative evaluation of large language models for hip fracture-related patient questions: DeepSeek-V3-FW, Gemini 2.0 Flash, and ChatGPT-4.5.
Authors: Zhang Y; Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong, Hong Kong, China., Huang T; Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong, Hong Kong, China., Liu C; Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong, Hong Kong, China., Miller AN; Department of Orthopedics, Dartmouth Hitchcock Medical Center and the Geisel School of Medicine at Dartmouth, Lebanon, NH, USA., Yang M; Department of Orthopaedics and Traumatology, Beijing Jishuitan Hospital, Beijing, China., Harris IA; School of Clinical Medicine, Faculty of Medicine and Health, UNSW, Sydney, Australia., Sawaguchi T; Department of Traumatology, Fukushima Medical University, Fukushima, Japan., Miclau T; Department of Orthopaedic Surgery, University of California, School of Medicine, Orthopaedic Trauma Institute, Zuckerberg San Francisco General Hospital, San Francisco, CA, USA., Tian M; School of Public Health, Harbin Medical University, Harbin, China., Chui CS; Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong, Hong Kong, China., Zhang N; Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong, Hong Kong, China., Cheung WH; Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong, Hong Kong, China., Wong RMY; Department of Orthopaedics and Traumatology, The Chinese University of Hong Kong, Hong Kong, China.
Source: Digital health [Digit Health] 2026 Jan 30; Vol. 12, pp. 20552076251412989. Date of Electronic Publication: 2026 Jan 30 (Print Publication: 2026).
Publication Type: Journal Article
Journal Info: Publisher: SAGE Publications Ltd Country of Publication: United States NLM ID: 101690863 Publication Model: eCollection Cited Medium: Print ISSN: 2055-2076 (Print) Linking ISSN: 20552076 NLM ISO Abbreviation: Digit Health Subsets: PubMed not MEDLINE
Database: MEDLINE Ultimate
Full text is not displayed to guests.
Description
ISSN:2055-2076
DOI:10.1177/20552076251412989