前行或搁置:ChatGPT 可否应用于神经外科环境中的健康信息搜索?

Ibrain Pub Date : 2024-03-09 DOI:10.1002/ibra.12149
Si-Yu Yan, Yi-Fan Liu, Lu Ma, Ling-Long Xiao, Xin Hu, Rui Guo, Chao You, Rui Tian
{"title":"前行或搁置:ChatGPT 可否应用于神经外科环境中的健康信息搜索?","authors":"Si-Yu Yan,&nbsp;Yi-Fan Liu,&nbsp;Lu Ma,&nbsp;Ling-Long Xiao,&nbsp;Xin Hu,&nbsp;Rui Guo,&nbsp;Chao You,&nbsp;Rui Tian","doi":"10.1002/ibra.12149","DOIUrl":null,"url":null,"abstract":"<p>Self-management is important for patients suffering from cerebrovascular events after neurosurgical procedures. An increasing number of artificial intelligence (AI)-assisted tools have been used in postoperative health management. ChatGPT is a new trend dialog-based chatbot that could be used as a supplemental tool for seeking health information. Responses from ChatGPT version 3.5 and 4.0 toward 13 questions raised by experienced neurosurgeons were evaluated in this exploratory study for their consistency and appropriateness blindly by the other three neurosurgeons. The readability of response text was investigated quantitively by word count and the Gunning Fog and Flesch–Kincaid indices. Results showed that the chatbot could provide relatively stable output between the two versions on consistency and appropriateness (<i>χ</i>² = 0.348). As for readability, there was a higher demand for readers to comprehend the output text in the 4.0 version (more counts of words; lower Flesch–Kincaid reading ease score; and higher Flesch–Kincaid grade level). In general, the capacity of ChatGPT to deliver effective health information is still under debate.</p>","PeriodicalId":94030,"journal":{"name":"Ibrain","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ibra.12149","citationCount":"0","resultStr":"{\"title\":\"Walking forward or on hold: Could the ChatGPT be applied for seeking health information in neurosurgical settings?\",\"authors\":\"Si-Yu Yan,&nbsp;Yi-Fan Liu,&nbsp;Lu Ma,&nbsp;Ling-Long Xiao,&nbsp;Xin Hu,&nbsp;Rui Guo,&nbsp;Chao You,&nbsp;Rui Tian\",\"doi\":\"10.1002/ibra.12149\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Self-management is important for patients suffering from cerebrovascular events after neurosurgical procedures. An increasing number of artificial intelligence (AI)-assisted tools have been used in postoperative health management. ChatGPT is a new trend dialog-based chatbot that could be used as a supplemental tool for seeking health information. Responses from ChatGPT version 3.5 and 4.0 toward 13 questions raised by experienced neurosurgeons were evaluated in this exploratory study for their consistency and appropriateness blindly by the other three neurosurgeons. The readability of response text was investigated quantitively by word count and the Gunning Fog and Flesch–Kincaid indices. Results showed that the chatbot could provide relatively stable output between the two versions on consistency and appropriateness (<i>χ</i>² = 0.348). As for readability, there was a higher demand for readers to comprehend the output text in the 4.0 version (more counts of words; lower Flesch–Kincaid reading ease score; and higher Flesch–Kincaid grade level). In general, the capacity of ChatGPT to deliver effective health information is still under debate.</p>\",\"PeriodicalId\":94030,\"journal\":{\"name\":\"Ibrain\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/ibra.12149\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ibrain\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/ibra.12149\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ibrain","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/ibra.12149","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

自我管理对于神经外科手术后发生脑血管事件的患者非常重要。越来越多的人工智能(AI)辅助工具被用于术后健康管理。ChatGPT 是一种基于对话的新趋势聊天机器人,可用作寻求健康信息的辅助工具。在这项探索性研究中,其他三位神经外科医生对 ChatGPT 3.5 版和 4.0 版对经验丰富的神经外科医生提出的 13 个问题的回复进行了盲法评估,以确定其一致性和适当性。通过字数、Gunning Fog 和 Flesch-Kincaid 指数对回复文本的可读性进行了量化研究。结果显示,在一致性和适当性方面,两个版本的聊天机器人都能提供相对稳定的输出(χ² = 0.348)。在可读性方面,4.0 版本对读者理解输出文本的要求更高(字数更多;Flesch-Kincaid 阅读容易度得分更低;Flesch-Kincaid 等级更高)。总的来说,ChatGPT 能否提供有效的健康信息仍有待商榷。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Walking forward or on hold: Could the ChatGPT be applied for seeking health information in neurosurgical settings?

Walking forward or on hold: Could the ChatGPT be applied for seeking health information in neurosurgical settings?

Self-management is important for patients suffering from cerebrovascular events after neurosurgical procedures. An increasing number of artificial intelligence (AI)-assisted tools have been used in postoperative health management. ChatGPT is a new trend dialog-based chatbot that could be used as a supplemental tool for seeking health information. Responses from ChatGPT version 3.5 and 4.0 toward 13 questions raised by experienced neurosurgeons were evaluated in this exploratory study for their consistency and appropriateness blindly by the other three neurosurgeons. The readability of response text was investigated quantitively by word count and the Gunning Fog and Flesch–Kincaid indices. Results showed that the chatbot could provide relatively stable output between the two versions on consistency and appropriateness (χ² = 0.348). As for readability, there was a higher demand for readers to comprehend the output text in the 4.0 version (more counts of words; lower Flesch–Kincaid reading ease score; and higher Flesch–Kincaid grade level). In general, the capacity of ChatGPT to deliver effective health information is still under debate.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
0.90
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信