Datasheet2_Use of large language model-based chatbots in managing the rehabilitation concerns and education needs of outpatient stroke survivors and caregivers.docx
基于大语言模型聊天机器人在门诊中风康复咨询中的表现评估数据集。
基本信息
资源简介
Datasheet2_Use of large language model-based chatbots in managing the rehabilitation concerns and education needs of outpatient stroke survivors and caregivers.docx
【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 24.16 KB，主题涵盖 stroke、rehabilitation、caregivers、artificial intelligence、large language model，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】
配套论文《Pros and Cons of Using Artificial Intelligence Chatbots for Musculoskeletal Rehabilitation Management》发表于 Journal of Orthopaedic & Sports Physical Therapy（2023），DOI：10.2519/jospt.2023.12000。源站首次发布：2024-05-09。
【数据内容】
源站原始描述：BackgroundThe utility of large language model-based (LLM) artificial intelligence (AI) chatbots in many aspects of healthcare is becoming apparent though their ability to address patient concerns remains unknown. We sought to evaluate the performance of two well-known, freely-accessible chatbots, ChatGPT and Google Bard, in responding to common questions about stroke rehabilitation posed by patients and their caregivers. MethodsWe collected questions from outpatients and their caregivers through…
【数据结构与技术规格】
文件数 1 个，合计 24.16 KB。Datasheet2_Use of large language model-based chatbots in managing the rehabilitation concerns and education needs of outpatient stroke survivors and c.docx：application/vnd.openxmlformats-officedocument.wordprocessingml.document，24.16 KB。数据集 DOI：10.3389/fdgth.2024.1395501.s002。
【主题与分类】
源站学科分类：Mobile Technologies、Health Information Systems (incl. Surveillance)、Health Informatics、Innovation and Technology Management。主题标签：stroke、rehabilitation、caregivers、artificial intelligence、large language model、chatbots、ChatGPT、Google Bard。
【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/Datasheet2_Use_of_large_language_model-based_chatbots_in_managing_the_rehabilitation_concerns_and_education_needs_of_outpatient_stroke_survivors_and_caregivers_docx/25778664
使用许可：CC BY 4.0（https://creativecommons.org/licenses/by/4.0/）。
规范引用：Neo, Jin Rui Edmund; Ser, Joon Sin; Tay, San San (2024). Datasheet2_Use of large language model-based chatbots in managing the rehabilitation concerns and education needs of outpatient stroke survivors and caregivers.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：Datasheet2_Use of large language model-based chatbots in managing the rehabilitation concerns and education needs of outpatient stroke survivors and caregivers.docx
- DOI：10.3389/fdgth.2024.1395501.s002
- 发布日期：2024-05-09
- 文件数：1 个
- 文件总体积：24.16 KB
- 源站页面：https://frontiersin.figshare.com/articles/dataset/Datasheet2_Use_of_large_language_model-based_chatbots_in_managing_the_rehabilitation_concerns_and_education_needs_of_outpatient_stroke_survivors_and_caregivers_docx/25778664
命令行下载
curl -L -o "Datasheet2_Use of large language model-based chatbots in managing the rehabilitation concerns and education needs of outpatient stroke survivors and c.docx" "https://ndownloader.figshare.com/files/46199568"
文件清单
Datasheet2_Use of large language model-based chatbots in managing the rehabilitation concerns and education needs of outpatient stroke survivors and c.docx（24.16 KB）
文件总体积 24.16 KB（源站 API 实测）。
数据说明
BackgroundThe utility of large language model-based (LLM) artificial intelligence (AI) chatbots in many aspects of healthcare is becoming apparent though their ability to address patient concerns remains unknown. We sought to evaluate the performance of two well-known, freely-accessible chatbots, ChatGPT and Google Bard, in responding to common questions about stroke rehabilitation posed by patients and their caregivers.
MethodsWe collected questions from outpatients and their caregivers through a survey, categorised them by theme, and created representative questions to be posed to both chatbots. We then evaluated the chatbots’’ responses based on accuracy, safety, relevance, and readability. Interrater agreement was also tracked.
ResultsAlthough both chatbots achieved similar overall scores, Google Bard performed slightly better in relevance and safety. Both provided readable responses with some general accuracy, but struggled with hallucinated responses, were often not specific, and lacked awareness of the possibility for emotional situations with the potential to turn dangerous. Additionally, interrater agreement was low, highlighting the variability in physician acceptance of their responses.
ConclusionsAI chatbots show potential in patient-facing support roles, but issues remain regarding safety, accuracy, and relevance. Future chatbots should address these problems to ensure that they can reliably and independently manage the concerns and questions of stroke patients and their caregivers.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.3389/fdgth.2024.1395501.s002（source: https://frontiersin.figshare.com/articles/dataset/Datasheet2_Use_of_large_language_model-based_chatbots_in_managing_the_rehabilitation_concerns_and_education_needs_of_outpatient_stroke_survivors_and_caregivers_docx/25778664）。
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。
