评估ChatGPT-4o对圆锥角膜患者问题的准确性和可读性
该数据集包含ChatGPT-4o对30个圆锥角膜患者问题的回答，以及眼科医生的准确性评分和可读性评估结果。
基本信息
资源简介
评估ChatGPT-4o对圆锥角膜患者问题的准确性和可读性
【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 22.70 KB，主题涵盖 ChatGPT-4o、healthcare、keratoconus、large language models、readability，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《Evaluating the Accuracy and Readability of ChatGPT-4o’s Responses to Patient-Based Questions about Keratoconus》。配套论文《Evaluating the Accuracy and Readability of ChatGPT-4o’s Responses to Patient-Based Questions about Keratoconus》发表于 Ophthalmic Epidemiology（2025），DOI：10.1080/09286586.2025.2484760。项目资助方：The author(s) reported there is no funding associated with the work featured in this article.。源站首次发布：2025-03-29。
【数据内容】
源站原始描述：This study aimed to evaluate the accuracy and readability of responses generated by ChatGPT-4o, an advanced large language model, to frequently asked patient-centered questions about keratoconus. A cross-sectional, observational study was conducted using ChatGPT-4o to answer 30 potential questions that could be asked by patients with keratoconus. The accuracy of the responses was evaluated by two board-certified ophthalmologists and scored on a scale of 1 to 5. Readability was assessed using the…
中文译文（机器翻译，仅供快速理解，请以原文为准）：本研究旨在评估先进大型语言模型ChatGPT-4o针对圆锥角膜患者常见以患者为中心的问题所生成回答的准确性和可读性。 采用横断面观察性研究，使用ChatGPT-4o回答圆锥角膜患者可能提出的30个问题。由两名获得专科认证的眼科医生对回答的准确性进行评估，并采用1至5分制评分。使用Simple Measure of Gobbledygook（SMOG）、Flesch-Kincaid Grade Level（FKGL）和Flesch Reading Ease（FRE）评分评估可读性。对描述性、治疗相关和随访相关问题进行分析，并对这些类别进行统计比较。 回答的平均准确性评分为4.48 ± 0.57（5分制Likert量表）。评分者间信度为0.769的组内相关系数，表明一致性较强。可读性评分显示，SMOG评分为15.49 ± 1.74，FKGL评分为14.95 ± 1.95，FRE评分为27.41 ± 9.71，表明理解这些回答需要较高的教育水平。不同问题类别之间的准确性无显著差异（p = 0.161），但可读性差异显著，其中治疗相关的问题最容易理解。 ChatGPT-4o针对圆锥角膜以患者为中心的问题提供了高度准确的回答，但其语言的复杂性可能限制普通人群的可及性。仍需进一步开发，以提高AI生成医学内容的可读性。
【数据结构与技术规格】
文件数 1 个，合计 22.70 KB。iope_a_2484760_sm0686.xlsx：application/vnd.openxmlformats-officedocument.spreadsheetml.sheet，22.70 KB。数据集 DOI：10.6084/m9.figshare.28689210.v1。
【主题与分类】
源站学科分类：Medicine、Cell Biology、Genetics、Biotechnology、Ecology、Sociology。主题标签：ChatGPT-4o、healthcare、keratoconus、large language models、readability。
【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/Evaluating_the_Accuracy_and_Readability_of_ChatGPT-4o_s_Responses_to_Patient-Based_Questions_about_Keratoconus/28689210
使用许可：CC BY 4.0（https://creativecommons.org/licenses/by/4.0/）。
规范引用：Evaluating the Accuracy and Readability of ChatGPT-4o’s Responses to Patient-Based Questions about Keratoconus. Taylor & Francis. Balci, Ali Safa; Çakmak, Semih
【使用注意】
· 源站最后修改于 2025-12-19，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：Evaluating the Accuracy and Readability of ChatGPT-4o’s Responses to Patient-Based Questions about Keratoconus
- DOI：10.6084/m9.figshare.28689210.v1
- 发布日期：2025-03-29
- 文件数：1 个
- 文件总体积：22.70 KB
- 源站页面：https://tandf.figshare.com/articles/dataset/Evaluating_the_Accuracy_and_Readability_of_ChatGPT-4o_s_Responses_to_Patient-Based_Questions_about_Keratoconus/28689210
命令行下载
curl -L -o "iope_a_2484760_sm0686.xlsx" "https://ndownloader.figshare.com/files/53293665"
文件清单
iope_a_2484760_sm0686.xlsx（22.70 KB）
文件总体积 22.70 KB（源站 API 实测）。
数据说明
This study aimed to evaluate the accuracy and readability of responses generated by ChatGPT-4o, an advanced large language model, to frequently asked patient-centered questions about keratoconus.
A cross-sectional, observational study was conducted using ChatGPT-4o to answer 30 potential questions that could be asked by patients with keratoconus. The accuracy of the responses was evaluated by two board-certified ophthalmologists and scored on a scale of 1 to 5. Readability was assessed using the Simple Measure of Gobbledygook (SMOG), Flesch-Kincaid Grade Level (FKGL), and Flesch Reading Ease (FRE) scores. Descriptive, treatment-related, and follow-up-related questions were analyzed, and statistical comparisons between these categories were performed.
The mean accuracy score for the responses was 4.48 ± 0.57 on a 5-point Likert scale. The interrater reliability, with an intraclass correlation coefficient of 0.769, indicated a strong level of agreement. Readability scores revealed a SMOG score of 15.49 ± 1.74, an FKGL score of 14.95 ± 1.95, and an FRE score of 27.41 ± 9.71, indicating that a high level of education is required to comprehend the responses. There was no significant difference in accuracy among the different question categories (p = 0.161), but readability varied significantly, with treatment-related questions being the easiest to understand.
ChatGPT-4o provides highly accurate responses to patient-centered questions about keratoconus, though the complexity of its language may limit accessibility for the general population. Further development is needed to enhance the readability of AI-generated medical content.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.6084/m9.figshare.28689210.v1（source: https://tandf.figshare.com/articles/dataset/Evaluating_the_Accuracy_and_Readability_of_ChatGPT-4o_s_Responses_to_Patient-Based_Questions_about_Keratoconus/28689210）。
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。
