Evaluating Large Language Models for Preoperative Patient Education in Superior Capsular Reconstruction: Comparative Study of Claude, GPT, and Gemini
JMIR Perioperative Medicine · 2025-06-12 · 8 · e70047-e70047
DOI: 10.2196/70047 ↗At a glance
Vergleichsstudie in JMIR Perioperative Medicine, published online on 2025-06-12. Written by Yukang Liu and 8 co-authors. Institution: The Second School of Clinical Medicine, Southern Medical University, Guangzhou, China. Major MEDLINE topics: Patient Education as Topic, Plastic Surgery Procedures, Preoperative Care, Natural Language Processing. Cited 16 times so far (Crossref); 69 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Large language models (LLMs) are revolutionizing natural language processing, increasingly applied in clinical settings to enhance preoperative patient education.
Objective
This study aimed to evaluate the effectiveness and applicability of various LLMs in preoperative patient education by analyzing their responses to superior capsular reconstruction (SCR)–related inquiries.
Methods
In total, 10 sports medicine clinical experts formulated 11 SCR issues and developed preoperative patient education strategies during a webinar, inputting 12 text commands into Claude-3-Opus (Anthropic), GPT-4-Turbo (OpenAI), and Gemini-1.5-Pro (Google DeepMind). A total of 3 experts assessed the language models’ responses for correctness, completeness, logic, potential harm, and overall satisfaction, while preoperative education documents were evaluated using DISCERN questionnaire and Patient Education Materials Assessment Tool instruments, and reviewed by 5 postoperative patients for readability and educational value; readability of all responses was also analyzed using the cntext package and py-readability-metrics.
Results
Between July 1 and August 17, 2024, sports medicine experts and patients evaluated 33 responses and 3 preoperative patient education documents generated by 3 language models regarding SCR surgery. For the 11 query responses, clinicians rated Gemini significantly higher than Claude in all categories ( P
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- The Second School of Clinical Medicine, Southern Medical University, Guangzhou, China.
- Department of Orthopedics, Beijing Jishuitan Hospital, Beijing, China.
- Zhuhai People's Hospital (The Affiliated Hospital of Beijing Institute of Technology, Zhuhai Clinical Medical College of Jinan University), 79 Kangning Road, Xiangzhou District, Zhuhai, Guangdong, 519000, China, 86 1307…
- Department of Sports Medicine, The First Affiliated Hospital of Jinan University, Guangzhou, China.
- Department of Orthopaedics, Guangzhou Red Cross Hospital of Jinan University, Guangzhou, China.
- Department of Joint Surgery and Sports Medicine, The Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou, China.
ORCID profiles: Yukang Liu, Hua Li, Jianfeng Ouyang, Zhaowen Xue, Min Wang, Hebei He, Bin Song, Xiaofei Zheng, Wenyi Gan
Cite
APA
Liu, Y., Li, H., Ouyang, J., Xue, Z., Wang, M., He, H., Song, B., Zheng, X., & Gan, W. (2025). Evaluating Large Language Models for Preoperative Patient Education in Superior Capsular Reconstruction: Comparative Study of Claude, GPT, and Gemini. JMIR Perioperative Medicine, 8, e70047-e70047. https://doi.org/10.2196/70047
Vancouver
Liu Y, Li H, Ouyang J, Xue Z, Wang M, He H, et al. Evaluating Large Language Models for Preoperative Patient Education in Superior Capsular Reconstruction: Comparative Study of Claude, GPT, and Gemini. JMIR Perioperative Medicine. 2025;8:e70047-e70047. doi:10.2196/70047
BibTeX
@article{Liu2025,
author = {Liu, Yukang and Li, Hua and Ouyang, Jianfeng and Xue, Zhaowen and Wang, Min and He, Hebei and Song, Bin and Zheng, Xiaofei and Gan, Wenyi},
title = {Evaluating Large Language Models for Preoperative Patient Education in Superior Capsular Reconstruction: Comparative Study of Claude, GPT, and Gemini},
journal = {JMIR Perioperative Medicine},
year = {2025},
volume = {8},
pages = {e70047--e70047},
doi = {10.2196/70047}
}
EUVIMED