ChatGPT与DeepSeek在脊髓损伤患者教育中的比较研究：人工智能能“说”脊髓损伤吗？

数据集获取（Figshare）

• 源站标题：A comparative study of ChatGPT and DeepSeek in spinal cord injury patient education: Can artificial intelligence “speak” spinal cord injury?
• DOI：10.6084/m9.figshare.30113011.v1
• 发布日期：2025-09-12
• 文件数：3 个
• 文件总体积：881.78 KB
• 源站页面：https://tandf.figshare.com/articles/dataset/A_comparative_study_of_ChatGPT_and_DeepSeek_in_spinal_cord_injury_patient_education_Can_artificial_intelligence_speak_spinal_cord_injury_/30113011

命令行下载

curl -L -o "yscm_a_2554013_sm0341.xlsx" "https://ndownloader.figshare.com/files/57917281"
curl -L -o "yscm_a_2554013_sm0340.xlsx" "https://ndownloader.figshare.com/files/57917284"
curl -L -o "yscm_a_2554013_sm0339.xls" "https://ndownloader.figshare.com/files/57917287"

文件清单

• yscm_a_2554013_sm0341.xlsx（97.14 KB）
• yscm_a_2554013_sm0340.xlsx（32.00 KB）
• yscm_a_2554013_sm0339.xls（752.64 KB）

文件总体积 881.78 KB（源站 API 实测）。

数据说明

Large language models (LLMs), such as ChatGPT and DeepSeek, are increasingly used by patients for medical information about their health condition. While several studies have explored ChatGPT’s performance in spinal cord injury (SCI)-related queries, no direct comparison between GPT-4o and DeepSeek-V3 has been conducted in this context.
The five most-searched SCI-related topics comprising of forty-eight questions were generated based on top Google Trends search terms. Responses were generated using GPT-4o and DeepSeek-V3, with three outputs per question. A total of two hundred and eighty-eight responses were independently evaluated by three Rehabilitation Physicians using the S.C.O.R.E. framework, which evaluates five domains: Safety, Consensus with Guidelines, Objectivity, Reproducibility, and Explainability on a 5-point Likert scale. Paired t-tests were used to compare model performance.
Both models achieved high ratings for Safety and Consensus with Guidelines. DeepSeek-V3 scored slightly but significantly higher in Objectivity (P = 0.014), Reproducibility (P = 0.007), and Explainability (P While both GPT-4o and DeepSeek-V3 are generally safe and informative tools for SCI patient education, DeepSeek-V3 demonstrated slightly superior performance in delivering consistent, objective, and well-explained responses. LLMs may serve as useful adjuncts in SCI patient education, but ongoing evaluation and clinician oversight remains essential.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.30113011.v1（source: https://tandf.figshare.com/articles/dataset/A_comparative_study_of_ChatGPT_and_DeepSeek_in_spinal_cord_injury_patient_education_Can_artificial_intelligence_speak_spinal_cord_injury_/30113011）。