头颈肿瘤学中ChatGPT-4o与DeepSeek-V3的比较评估
包含154个头颈癌临床问题及ChatGPT-4o与DeepSeek-V3的回答与专家评分，用于评估LLM在头颈肿瘤学中的准确性和一致性。
基本信息
资源简介
头颈肿瘤学中ChatGPT-4o与DeepSeek-V3的比较评估
【一句话概览】
本数据集是 figshare 公开的文本数据集，收录 2 个文件、合计 717.33 KB，主题涵盖 Head and neck cancer、large language models、ChatGPT、DeepSeek、artificial intelligence，可用于医学自然语言处理（实体识别、信息抽取等），CC BY 4.0 许可开放获取。
【数据集背景】
本数据集源站标题为《Comparative evaluation of ChatGPT-4o and DeepSeek-V3 in head and neck oncology》。配套论文《Comparative evaluation of ChatGPT-4o and DeepSeek-V3 in head and neck oncology》发表于 Acta Oto-Laryngologica（2025），DOI：10.1080/00016489.2025.2563035。项目资助方：The authors declare that the study received no funding.。源站首次发布：2025-10-29。
【数据内容】
源站原始描述：Large language models (LLMs) are increasingly used in clinical decision-making and patient education, including in complex specialties such as head and neck cancer (HNC). To evaluate the performance of ChatGPT-4o and DeepSeek-V3 in answering HNC-related clinical questions. A set of 154 questions across six clinical categories was submitted twice to both models. Responses were independently graded by head and neck surgeons using a four-point accuracy scale. Accuracy, reproducibility, and inter-mo…
【数据结构与技术规格】
文件数 2 个，合计 717.33 KB。ioto_a_2563035_sm7373.docx：application/vnd.openxmlformats-officedocument.wordprocessingml.document，366.11 KB。ioto_a_2563035_sm7372.docx：application/vnd.openxmlformats-officedocument.wordprocessingml.document，351.22 KB。数据集 DOI：10.6084/m9.figshare.30472568.v1。
【主题与分类】
源站学科分类：Medicine、Biological Sciences not elsewhere classified、Information Systems not elsewhere classified、Science Policy。主题标签：Head and neck cancer、large language models、ChatGPT、DeepSeek、artificial intelligence。
【适用方向】
文本类数据可用于医学自然语言处理，如命名实体识别、信息抽取与文本分类。
【获取与许可】
源站页面：https://tandf.figshare.com/articles/dataset/Comparative_evaluation_of_ChatGPT-4o_and_DeepSeek-V3_in_head_and_neck_oncology/30472568
使用许可：CC BY 4.0（https://creativecommons.org/licenses/by/4.0/）。
规范引用：Comparative evaluation of ChatGPT-4o and DeepSeek-V3 in head and neck oncology. Taylor & Francis. Tellioğlu, Burçay; Pamuk, Erim; Külekci, Çağrı; Pamuk, Gözde; Süslü, Nilda; Kuşcu, Oğuz
【使用注意】
· 源站最后修改于 2025-12-09，引用时请注意版本时效。
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取（Figshare）
- 源站标题：Comparative evaluation of ChatGPT-4o and DeepSeek-V3 in head and neck oncology
- DOI：10.6084/m9.figshare.30472568.v1
- 发布日期：2025-10-29
- 文件数：2 个
- 文件总体积：717.33 KB
- 源站页面：https://tandf.figshare.com/articles/dataset/Comparative_evaluation_of_ChatGPT-4o_and_DeepSeek-V3_in_head_and_neck_oncology/30472568
命令行下载
curl -L -o "ioto_a_2563035_sm7373.docx" "https://ndownloader.figshare.com/files/59136968"
curl -L -o "ioto_a_2563035_sm7372.docx" "https://ndownloader.figshare.com/files/59136971"
文件清单
ioto_a_2563035_sm7373.docx（366.11 KB）ioto_a_2563035_sm7372.docx（351.22 KB）
文件总体积 717.33 KB（源站 API 实测）。
数据说明
Large language models (LLMs) are increasingly used in clinical decision-making and patient education, including in complex specialties such as head and neck cancer (HNC).
To evaluate the performance of ChatGPT-4o and DeepSeek-V3 in answering HNC-related clinical questions.
A set of 154 questions across six clinical categories was submitted twice to both models. Responses were independently graded by head and neck surgeons using a four-point accuracy scale. Accuracy, reproducibility, and inter-model agreement were assessed.
ChatGPT-4o and DeepSeek-V3 provided ‘’comprehensive/correct’’ answers in 92.2% and 89.6% of cases, respectively (p = .42). The accuracy ratings of both models’ responses overlapped in 85.1% of cases; however, the statistical agreement between them remained low (Cohen’s κ = 0.12; ICC = 0.21, p = .006). DeepSeek-V3 outperformed ChatGPT in Treatment category (96.3% vs. 81.5%, p = .08), while ChatGPT excelled in Recovery, Complications, and Follow-up (95.0% vs. 82.5%, p = .08); however, these differences did not reach statistical significance. Reproducibility was high for both models (ChatGPT-4o: 96.1%; DeepSeek-V3: 96.8%).
Both models demonstrated strong accuracy and consistency in HNC-related queries.
LLMs hold promise as reliable tools in clinical decision-making and patient education within HNCs when used with careful consideration of their inherent limitations.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.6084/m9.figshare.30472568.v1（source: https://tandf.figshare.com/articles/dataset/Comparative_evaluation_of_ChatGPT-4o_and_DeepSeek-V3_in_head_and_neck_oncology/30472568）。
数据缺失？
依托陕西、四川两大基地，我们与超过十家三甲医院建立直接合作关系，覆盖合规授权、采集治理、专业标注、数据交付的全流程，为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务？立即联系我们获取专业方案。
