Large Language Models for Individualized Psychoeducational Tools for Psychosis: A cross-sectional study

Musa Yilanli, Ian McKay, Daniel I. Jackson BSc, Emre Sezgin
{"title":"Large Language Models for Individualized Psychoeducational Tools for Psychosis: A cross-sectional study","authors":"Musa Yilanli, Ian McKay, Daniel I. Jackson BSc, Emre Sezgin","doi":"10.1101/2024.07.26.24311075","DOIUrl":null,"url":null,"abstract":"Importance: In mental healthcare, the potential of Large Language Models (LLMs) to enhance psychoeducation is a burgeoning field. This study explored the potential of ChatGPT as an individualized psychoeducational support tool specifically for psychosis education. Objective: The study aims to evaluate psychosis-related questions to provide accurate, clear, and clinically relevant individualized information for patients and caregivers. Design: This cross-sectional study uses a qualitative analysis design. The researchers specifically employed a question-answering system (GPT-4 via ChatGPT) to generate responses to common questions about psychosis. Experts in the field then evaluated these responses to assess their quality for use in a clinical setting. Primary Outcome: Researchers presented ChatGPT with 20 common questions frequently asked by patients' caregivers and relatives. Two experts in psychosis then assessed the quality of the responses using six criteria: accuracy (1-3), clarity (1-3), inclusivity (1-3), completeness (0-1), clinical utility (1-5) and an overall score (1-4). Results: The evaluation yielded positive results overall. Responses were rated as accurate (M:SD= 2.89:0.22) and clear (mean score of 2.93:0.18). There was potential for improvement in terms of inclusivity (mean score of 2.30:0.41), suggesting a need to incorporate more diverse perspectives. Completeness received high ratings (mean score of 0.93:0.18), indicating responses addressed all aspects of the questions. Most importantly, the responses were deemed clinically useful (mean score of 4.35:0.52). Conclusions: In summary, this study underscores the significant promise of ChatGPT as a psychoeducational tool for patients with psychosis, their relatives, and their caregivers. The experts' findings affirm that the information delivered by ChatGPT is not only accurate and clinically relevant but also conveyed conversationally, enhancing its accessibility and usability. The initial performance of ChatGPT as a psychoeducational tool in the context of psychosis education is undeniably positive.","PeriodicalId":506788,"journal":{"name":"medRxiv","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"medRxiv","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1101/2024.07.26.24311075","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Importance: In mental healthcare, the potential of Large Language Models (LLMs) to enhance psychoeducation is a burgeoning field. This study explored the potential of ChatGPT as an individualized psychoeducational support tool specifically for psychosis education. Objective: The study aims to evaluate psychosis-related questions to provide accurate, clear, and clinically relevant individualized information for patients and caregivers. Design: This cross-sectional study uses a qualitative analysis design. The researchers specifically employed a question-answering system (GPT-4 via ChatGPT) to generate responses to common questions about psychosis. Experts in the field then evaluated these responses to assess their quality for use in a clinical setting. Primary Outcome: Researchers presented ChatGPT with 20 common questions frequently asked by patients' caregivers and relatives. Two experts in psychosis then assessed the quality of the responses using six criteria: accuracy (1-3), clarity (1-3), inclusivity (1-3), completeness (0-1), clinical utility (1-5) and an overall score (1-4). Results: The evaluation yielded positive results overall. Responses were rated as accurate (M:SD= 2.89:0.22) and clear (mean score of 2.93:0.18). There was potential for improvement in terms of inclusivity (mean score of 2.30:0.41), suggesting a need to incorporate more diverse perspectives. Completeness received high ratings (mean score of 0.93:0.18), indicating responses addressed all aspects of the questions. Most importantly, the responses were deemed clinically useful (mean score of 4.35:0.52). Conclusions: In summary, this study underscores the significant promise of ChatGPT as a psychoeducational tool for patients with psychosis, their relatives, and their caregivers. The experts' findings affirm that the information delivered by ChatGPT is not only accurate and clinically relevant but also conveyed conversationally, enhancing its accessibility and usability. The initial performance of ChatGPT as a psychoeducational tool in the context of psychosis education is undeniably positive.
用于个性化精神病心理教育工具的大型语言模型:横断面研究
重要性:在精神卫生保健领域,大语言模型(LLM)在加强心理教育方面的潜力是一个新兴领域。本研究探索了 ChatGPT 作为个性化心理教育支持工具的潜力,特别是在精神病教育方面。研究目的本研究旨在评估与精神病相关的问题,以便为患者和护理人员提供准确、清晰且与临床相关的个性化信息。设计:本横断面研究采用定性分析设计。研究人员特别采用了一个问题解答系统(通过 ChatGPT 生成 GPT-4)来生成对有关精神病的常见问题的回答。然后由该领域的专家对这些回答进行评估,以确定其质量是否适合在临床环境中使用。主要成果:研究人员向 ChatGPT 演示了患者护理人员和亲属经常提出的 20 个常见问题。然后,两位精神病学专家采用六项标准对回复质量进行评估:准确性(1-3)、清晰度(1-3)、包容性(1-3)、完整性(0-1)、临床实用性(1-5)和总分(1-4)。结果:评估结果总体良好。答复被评为准确(M:SD= 2.89:0.22)和清晰(平均分 2.93:0.18)。在包容性方面还有改进的余地(平均分 2.30:0.41),表明有必要纳入更多不同的观点。完整性得到了很高的评价(平均分 0.93:0.18),表明回答涉及了问题的所有方面。最重要的是,这些回答被认为对临床有用(平均分 4.35:0.52)。结论:总之,本研究强调了 ChatGPT 作为精神病患者、其亲属和护理人员的心理教育工具的重要前景。专家们的研究结果肯定了 ChatGPT 所提供的信息不仅准确、与临床相关,而且以对话的方式进行传达,从而提高了其可及性和可用性。不可否认,ChatGPT 作为心理教育工具在精神病教育方面的初步表现是积极的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
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