由无家可归者和ChatGPT共同设计的健康筛查项目概况:焦点小组研究。

IF 2 Q3 HEALTH CARE SCIENCES & SERVICES
Nóra Radó, Orsolya Németh, Sándor Békási
{"title":"由无家可归者和ChatGPT共同设计的健康筛查项目概况:焦点小组研究。","authors":"Nóra Radó, Orsolya Németh, Sándor Békási","doi":"10.2196/68316","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>People experiencing homelessness have worse oral health outcomes and a notable health informational asymmetry compared to the general population. Screening programs present a viable option for this population; however, barriers to access, such as lower levels of health literacy, lack of information, and mistrust, narrow their chances to participate in such programs.</p><p><strong>Objective: </strong>The aim of this study is to investigate the applicability of generative artificial intelligence (AI) in designing a homeless health screening program fact sheet with experts by experience using co-design principles.</p><p><strong>Methods: </strong>Six fact sheet text variants were created by the open-access version of ChatGPT 3.5 for an oral cancer screening program targeting people experiencing homelessness in Budapest, Hungary. Clients of homeless social services (N=23) were invited to a short questionnaire survey and 3 semistructured focus group discussions between May and July 2024. General opinions regarding generative AI technology and direct feedback on the text variants were obtained. Additionally, a standardized readability assessment of the text variants was completed via the Sydney Health Literacy Lab Editor.</p><p><strong>Results: </strong>Almost two-thirds of participants (17/23) stated that they had previously heard about AI; however, their self-assessment regarding the extent of their knowledge resulted in an average of 2.38 (n=16) on a 5-point Likert scale. During the first focus group discussion, all 6 variants received a high score (between 4.63 and 4.92 on a 5-point Likert scale). In the next sessions, participants remained positive when the pool was narrowed to 4 versions, although they scored the texts lower. During open discussions, text variants were considered understandable, while difficulties with medical expressions, lengthiness of sentences, and references to a stereotypical homeless subgroup (rough sleepers) were also reported. The health literacy editor showed that most AI-generated text variants were difficult to read and too complex for the target group.</p><p><strong>Conclusions: </strong>The co-design process revealed that focus group participants actively wanted to shape the fact sheet drafts. They shared their insights on how to make the text variants more appealing for the target audience. Moreover, the involvement of generative AI technology revealed that the participants have heard about the concept of AI and text generation as a potential function, and they have not rejected its use in health care settings.</p>","PeriodicalId":14841,"journal":{"name":"JMIR Formative Research","volume":"9 ","pages":"e68316"},"PeriodicalIF":2.0000,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12248257/pdf/","citationCount":"0","resultStr":"{\"title\":\"Co-Design of a Health Screening Program Fact Sheet by People Experiencing Homelessness and ChatGPT: Focus Group Study.\",\"authors\":\"Nóra Radó, Orsolya Németh, Sándor Békási\",\"doi\":\"10.2196/68316\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>People experiencing homelessness have worse oral health outcomes and a notable health informational asymmetry compared to the general population. Screening programs present a viable option for this population; however, barriers to access, such as lower levels of health literacy, lack of information, and mistrust, narrow their chances to participate in such programs.</p><p><strong>Objective: </strong>The aim of this study is to investigate the applicability of generative artificial intelligence (AI) in designing a homeless health screening program fact sheet with experts by experience using co-design principles.</p><p><strong>Methods: </strong>Six fact sheet text variants were created by the open-access version of ChatGPT 3.5 for an oral cancer screening program targeting people experiencing homelessness in Budapest, Hungary. Clients of homeless social services (N=23) were invited to a short questionnaire survey and 3 semistructured focus group discussions between May and July 2024. General opinions regarding generative AI technology and direct feedback on the text variants were obtained. Additionally, a standardized readability assessment of the text variants was completed via the Sydney Health Literacy Lab Editor.</p><p><strong>Results: </strong>Almost two-thirds of participants (17/23) stated that they had previously heard about AI; however, their self-assessment regarding the extent of their knowledge resulted in an average of 2.38 (n=16) on a 5-point Likert scale. During the first focus group discussion, all 6 variants received a high score (between 4.63 and 4.92 on a 5-point Likert scale). In the next sessions, participants remained positive when the pool was narrowed to 4 versions, although they scored the texts lower. During open discussions, text variants were considered understandable, while difficulties with medical expressions, lengthiness of sentences, and references to a stereotypical homeless subgroup (rough sleepers) were also reported. The health literacy editor showed that most AI-generated text variants were difficult to read and too complex for the target group.</p><p><strong>Conclusions: </strong>The co-design process revealed that focus group participants actively wanted to shape the fact sheet drafts. They shared their insights on how to make the text variants more appealing for the target audience. Moreover, the involvement of generative AI technology revealed that the participants have heard about the concept of AI and text generation as a potential function, and they have not rejected its use in health care settings.</p>\",\"PeriodicalId\":14841,\"journal\":{\"name\":\"JMIR Formative Research\",\"volume\":\"9 \",\"pages\":\"e68316\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2025-07-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12248257/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JMIR Formative Research\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2196/68316\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"HEALTH CARE SCIENCES & SERVICES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JMIR Formative Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2196/68316","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
引用次数: 0

摘要

背景:与一般人群相比,无家可归者的口腔健康状况较差,健康信息不对称明显。筛查项目为这一人群提供了一个可行的选择;然而,诸如卫生知识水平较低、信息缺乏和不信任等获取障碍缩小了她们参与此类项目的机会。目的:本研究的目的是探讨生成式人工智能(AI)在设计无家可归者健康筛查计划情况说明书时的适用性,专家通过经验使用共同设计原则。方法:使用ChatGPT 3.5的开放获取版本为匈牙利布达佩斯的一个针对无家可归者的口腔癌筛查项目创建了6个事实表文本变体。本文于2024年5月至7月对23名无家可归者进行问卷调查和3次半结构化焦点小组讨论。获得了关于生成式人工智能技术的一般意见和对文本变体的直接反馈。此外,通过悉尼健康素养实验室编辑器完成了文本变体的标准化可读性评估。结果:近三分之二的参与者(17/23)表示他们以前听说过人工智能;然而,他们对知识程度的自我评估在5点李克特量表上的平均得分为2.38 (n=16)。在第一次焦点小组讨论中,所有6个变体都获得了高分(在5分李克特量表上在4.63到4.92之间)。在接下来的会话中,当文本池缩小到4个版本时,参与者仍然保持积极态度,尽管他们对文本的评分较低。在公开讨论中,文本变体被认为是可以理解的,而医学表达的困难,句子的冗长,以及对无家可归者(露宿者)的刻板印象也被报道。健康素养编辑表明,大多数人工智能生成的文本变体难以阅读,对目标群体来说过于复杂。结论:共同设计过程表明,焦点小组参与者积极地想要塑造事实说明书草案。他们分享了如何使文本变体对目标受众更具吸引力的见解。此外,生成式人工智能技术的参与表明,参与者已经听说过人工智能和文本生成的概念作为一种潜在功能,并且他们没有拒绝在医疗保健环境中使用它。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Co-Design of a Health Screening Program Fact Sheet by People Experiencing Homelessness and ChatGPT: Focus Group Study.

Background: People experiencing homelessness have worse oral health outcomes and a notable health informational asymmetry compared to the general population. Screening programs present a viable option for this population; however, barriers to access, such as lower levels of health literacy, lack of information, and mistrust, narrow their chances to participate in such programs.

Objective: The aim of this study is to investigate the applicability of generative artificial intelligence (AI) in designing a homeless health screening program fact sheet with experts by experience using co-design principles.

Methods: Six fact sheet text variants were created by the open-access version of ChatGPT 3.5 for an oral cancer screening program targeting people experiencing homelessness in Budapest, Hungary. Clients of homeless social services (N=23) were invited to a short questionnaire survey and 3 semistructured focus group discussions between May and July 2024. General opinions regarding generative AI technology and direct feedback on the text variants were obtained. Additionally, a standardized readability assessment of the text variants was completed via the Sydney Health Literacy Lab Editor.

Results: Almost two-thirds of participants (17/23) stated that they had previously heard about AI; however, their self-assessment regarding the extent of their knowledge resulted in an average of 2.38 (n=16) on a 5-point Likert scale. During the first focus group discussion, all 6 variants received a high score (between 4.63 and 4.92 on a 5-point Likert scale). In the next sessions, participants remained positive when the pool was narrowed to 4 versions, although they scored the texts lower. During open discussions, text variants were considered understandable, while difficulties with medical expressions, lengthiness of sentences, and references to a stereotypical homeless subgroup (rough sleepers) were also reported. The health literacy editor showed that most AI-generated text variants were difficult to read and too complex for the target group.

Conclusions: The co-design process revealed that focus group participants actively wanted to shape the fact sheet drafts. They shared their insights on how to make the text variants more appealing for the target audience. Moreover, the involvement of generative AI technology revealed that the participants have heard about the concept of AI and text generation as a potential function, and they have not rejected its use in health care settings.

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
JMIR Formative Research
JMIR Formative Research Medicine-Medicine (miscellaneous)
CiteScore
2.70
自引率
9.10%
发文量
579
审稿时长
12 weeks
×
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:604180095
Book学术官方微信