糖尿病教育中ChatGPT的应用：潜力、准确性与可及性——数据表1
包含ChatGPT-4o对10个糖尿病常见问题回答质量评估的数据表，包括专家评分和可读性分析。
基本信息
资源简介
糖尿病教育中ChatGPT的应用：潜力、准确性与可及性——数据表1
【一句话概览】
本数据集是 figshare 公开的文本数据集，收录 1 个文件、合计 42.28 KB，主题涵盖 AI in healthcare、artificial intelligence、blood glucose control、ChatGPT、diabetes mellitus，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《Data Sheet 1_ChatGPT for diabetes education: potential, accuracy, and accessibility in patient support.docx》。配套论文《Plastic Surgery and Artificial Intelligence: How ChatGPT Improved Operation Note Accuracy, Time, and Education》发表于 Mayo Clinic Proceedings: Digital Health（2023），DOI：10.1016/j.mcpdig.2023.06.002。源站首次发布：2026-04-13。
【数据内容】
源站原始描述：BackgroundDiabetes mellitus is a chronic metabolic disease with rising global prevalence. Adequate patient education is essential to encourage self-management and reduce complications. Artificial intelligence applications such as ChatGPT have emerged as potential supplementary resources for patient education alongside the broader integration of technology in healthcare. MethodsA cross-sectional evaluation was conducted using ten frequently asked questions (FAQs) on diabetes, selected from the Di…
中文译文（机器翻译，仅供快速理解，请以原文为准）：背景 糖尿病是一种慢性代谢性疾病，全球患病率不断上升。充分的患者教育对于鼓励自我管理和减少并发症至关重要。随着技术在医疗保健中的更广泛整合，ChatGPT等人工智能应用已成为患者教育的潜在补充资源。 方法 采用横断面评估，使用从印度糖尿病协会和国际糖尿病联盟选取的10个糖尿病常见问题（FAQ）。ChatGPT-4o（于2025年3月通过网页界面访问）在单独、独立的聊天会话中分别针对每个问题生成回答，以模拟典型的患者互动。5名获得委员会认证的内分泌科医师（糖尿病专科医师），平均临床经验≥10年，使用4分Likert量表独立从五个维度评估回答：总体质量、内容准确性、清晰度、相关性和可信度。最终各维度得分计算为所有5名评分者评分的均值。可读性使用Flesch Reading Ease Score（FRES）和Flesch-Kincaid Grade Level（FKGL）评估。所有可读性分析仅适用于本研究生成的英文输出。 结果 平均FRES为38.19，平均FKGL为16.87，表明阅读水平适合受过大学教育的人群，且显著高于患者健康材料推荐的六年级基准。十个提示的平均回答长度为300 ± 100词。专家评分总体较高：内容准确性和总体质量的汇总平均得分（±SD）为4.0（±0.0），相关性为3.98（±0.10），清晰度和可信度均为3.9（±0.20）。评分者未发现临床不准确的表述；然而，高评分和狭窄的评分范围表明可能存在天花板效应，限制了对不同回答的区分。评分者对语言复杂性表示担忧，这可能阻碍健康素养有限患者的理解。 结论 ChatGPT-4o生成的糖尿病教育内容总体准确且相关，提示其作为糖尿病护理补充工具的潜力。然而，较高的阅读水平复杂性、较小的评估范围（十个提示、一个模型、一次会话）以及仅英文评估限制了这些发现的可推广性。AI生成的内容应补充而非替代临床医生主导的教育。未来…
【数据结构与技术规格】
文件数 1 个，合计 42.28 KB。Data Sheet 1_ChatGPT for diabetes education: potential, accuracy, and accessibility in patient support.docx：application/vnd.openxmlformats-officedocument.wordprocessingml.document，42.28 KB。数据集 DOI：10.3389/fdgth.2026.1768843.s001。
【主题与分类】
源站学科分类：Health Informatics。主题标签：AI in healthcare、artificial intelligence、blood glucose control、ChatGPT、diabetes mellitus、patient education。
【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://frontiersin.figshare.com/articles/dataset/Data_Sheet_1_ChatGPT_for_diabetes_education_potential_accuracy_and_accessibility_in_patient_support_docx/31994310
使用许可：CC BY 4.0（https://creativecommons.org/licenses/by/4.0/）。
规范引用：Abuzar, Mohammad; Rai, Sandeep; Pathan, Tabreskhan; Fakki, Foorkan; Syed, Shariq (2026). Data Sheet 1_ChatGPT for diabetes education: potential, accuracy, and accessibility in patient support.docx. Frontiers. Dataset
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：Data Sheet 1_ChatGPT for diabetes education: potential, accuracy, and accessibility in patient support.docx
- DOI：10.3389/fdgth.2026.1768843.s001
- 发布日期：2026-04-13
- 文件数：1 个
- 文件总体积：42.28 KB
- 源站页面：https://frontiersin.figshare.com/articles/dataset/Data_Sheet_1_ChatGPT_for_diabetes_education_potential_accuracy_and_accessibility_in_patient_support_docx/31994310
命令行下载
curl -L -o "Data Sheet 1_ChatGPT for diabetes education: potential, accuracy, and accessibility in patient support.docx" "https://ndownloader.figshare.com/files/63672483"
文件清单
Data Sheet 1_ChatGPT for diabetes education: potential, accuracy, and accessibility in patient support.docx（42.28 KB）
文件总体积 42.28 KB（源站 API 实测）。
数据说明
BackgroundDiabetes mellitus is a chronic metabolic disease with rising global prevalence. Adequate patient education is essential to encourage self-management and reduce complications. Artificial intelligence applications such as ChatGPT have emerged as potential supplementary resources for patient education alongside the broader integration of technology in healthcare.
MethodsA cross-sectional evaluation was conducted using ten frequently asked questions (FAQs) on diabetes, selected from the Diabetic Association of India and the International Diabetes Federation. ChatGPT-4o (accessed via the web interface in March 2025) generated responses to each question in separate, stand-alone chat sessions to simulate typical patient interactions. Five board-certified endocrinologists (diabetologists) with a mean clinical experience of ≥10 years independently evaluated the responses using a 4-point Likert scale across five domains: overall quality, content accuracy, clarity, relevance, and trustworthiness. Final domain scores were computed as the mean of all five raters’ scores. Readability was assessed using the Flesch Reading Ease Score (FRES) and Flesch-Kincaid Grade Level (FKGL). All readability analyses apply exclusively to the English-language outputs generated in this study.
ResultsThe mean FRES was 38.19 and the mean FKGL was 16.87, indicating a reading level appropriate for college-educated individuals and substantially above the recommended sixth-grade benchmark for patient health materials. Mean response length was 300 ± 100 words across the ten prompts. Expert ratings were generally high: aggregated mean scores (±SD) were 4.0 (±0.0) for content accuracy and overall quality, 3.98 (±0.10) for relevance, and 3.9 (±0.20) for clarity and trustworthiness. No clinically inaccurate statements were identified by the raters; however, the high scores and narrow score range indicate a potential ceiling effect that limits discrimination between responses. Raters expressed concern about linguistic complexity, which may impede comprehension among patients with limited health literacy.
ConclusionsChatGPT-4o generated generally accurate and relevant diabetes education content,
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.3389/fdgth.2026.1768843.s001（source: https://frontiersin.figshare.com/articles/dataset/Data_Sheet_1_ChatGPT_for_diabetes_education_potential_accuracy_and_accessibility_in_patient_support_docx/31994310）。
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。
