IF 3.2 3区 医学 Q2 PSYCHIATRY
Frontiers in Psychiatry Pub Date : 2025-03-19 eCollection Date: 2025-01-01 DOI:10.3389/fpsyt.2025.1473614
Namwoo Kim, Jiseon Lee, Sung Hyeon Park, Yoonseo On, Jieun Lee, Musung Keum, Sanghoon Oh, Yoojin Song, Junhee Lee, Geun Hui Won, Joon Sung Shin, Silvia Kyungjin Lho, Yoon Jung Hwang, Tae-Suk Kim
{"title":"GPT-4 generated psychological reports in psychodynamic perspective: a pilot study on quality, risk of hallucination and client satisfaction.","authors":"Namwoo Kim, Jiseon Lee, Sung Hyeon Park, Yoonseo On, Jieun Lee, Musung Keum, Sanghoon Oh, Yoojin Song, Junhee Lee, Geun Hui Won, Joon Sung Shin, Silvia Kyungjin Lho, Yoon Jung Hwang, Tae-Suk Kim","doi":"10.3389/fpsyt.2025.1473614","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Recently, there have been active proposals on how to utilize large language models (LLMs) in the fields of psychiatry and counseling. It would be interesting to develop programs with LLMs that generate psychodynamic assessments to help individuals gain insights about themselves, and to evaluate the features of such services. However, studies on this subject are rare. This pilot study aims to evaluate quality, risk of hallucination (incorrect AI-generated information), and client satisfaction with psychodynamic psychological reports generated by GPT-4.</p><p><strong>Methods: </strong>The report comprised five components: psychodynamic formulation, psychopathology, parental influence, defense mechanisms, and client strengths. Participants were recruited from individuals distressed by repetitive interpersonal issues. The study was conducted in three steps: 1) Questions provided to participants, designed to create psychodynamic formulations: 14 questions were generated by GPT for inferring psychodynamic formulations, while 6 fixed questions focused on the participants' relationship with their parents. A total of 20 questions were provided. Using participants' responses to these questions, GPT-4 generated the psychological reports. 2) Seven professors of psychiatry from different university hospitals evaluated the quality and risk of hallucinations in the psychological reports by reading the reports only, without meeting the participants. This quality assessment compared the psychological reports generated by GPT-4 with those inferred by the experts. 3) Participants evaluated their satisfaction with the psychological reports. All assessments were conducted using self-report questionnaires based on a Likert scale developed for this study.</p><p><strong>Results: </strong>A total of 10 participants were recruited, and the average age was 32 years. The median response indicated that quality of all five components of the psychological report was similar to the level inferred by the experts. The risk of hallucination was assessed as ranging from unlikely to minor. According to the median response in the satisfaction evaluation, the participants agreed that the report is clearly understandable, insightful, credible, useful, satisfying, and recommendable.</p><p><strong>Conclusion: </strong>This study suggests the possibility that artificial intelligence could assist users by providing psychodynamic interpretations.</p>","PeriodicalId":12605,"journal":{"name":"Frontiers in Psychiatry","volume":"16 ","pages":"1473614"},"PeriodicalIF":3.2000,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11963773/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Psychiatry","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3389/fpsyt.2025.1473614","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"PSYCHIATRY","Score":null,"Total":0}
引用次数: 0

摘要

背景:最近,关于如何在精神病学和心理咨询领域利用大型语言模型(LLMs)的提议十分活跃。利用大型语言模型开发可生成心理动力学评估的程序,以帮助个人深入了解自己,并对此类服务的特点进行评估,是一件非常有趣的事情。然而,这方面的研究却很少见。本试点研究旨在评估由 GPT-4 生成的心理动力心理报告的质量、幻觉风险(人工智能生成的错误信息)和客户满意度:报告由五个部分组成:心理动力学表述、心理病理学、父母影响、防御机制和客户优势。参与者是从因反复出现的人际关系问题而苦恼的人中招募的。研究分三步进行:1) 向参与者提供问题,旨在创建心理动力学公式:14 个问题是由 GPT 生成的,用于推断心理动力学公式,而 6 个固定问题则侧重于参与者与其父母的关系。总共提供了 20 个问题。根据参与者对这些问题的回答,GPT-4 生成心理报告。2) 七位来自不同大学医院的精神病学教授在未与参与者见面的情况下,仅通过阅读心理报告来评估报告的质量和出现幻觉的风险。这项质量评估将 GPT-4 生成的心理报告与专家推断的报告进行了比较。3) 参与者对心理报告的满意度评估。所有评估均采用基于本研究开发的李克特量表的自我报告问卷进行:共招募了 10 名参与者,平均年龄为 32 岁。回答的中位数表明,心理报告所有五个组成部分的质量与专家推断的水平相似。出现幻觉的风险被评估为从不太可能到轻微不等。根据满意度评价的中位数,参与者一致认为报告清晰易懂、有洞察力、可信、有用、令人满意和值得推荐:本研究表明,人工智能可以通过提供心理动力学解释来帮助用户。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
GPT-4 generated psychological reports in psychodynamic perspective: a pilot study on quality, risk of hallucination and client satisfaction.

Background: Recently, there have been active proposals on how to utilize large language models (LLMs) in the fields of psychiatry and counseling. It would be interesting to develop programs with LLMs that generate psychodynamic assessments to help individuals gain insights about themselves, and to evaluate the features of such services. However, studies on this subject are rare. This pilot study aims to evaluate quality, risk of hallucination (incorrect AI-generated information), and client satisfaction with psychodynamic psychological reports generated by GPT-4.

Methods: The report comprised five components: psychodynamic formulation, psychopathology, parental influence, defense mechanisms, and client strengths. Participants were recruited from individuals distressed by repetitive interpersonal issues. The study was conducted in three steps: 1) Questions provided to participants, designed to create psychodynamic formulations: 14 questions were generated by GPT for inferring psychodynamic formulations, while 6 fixed questions focused on the participants' relationship with their parents. A total of 20 questions were provided. Using participants' responses to these questions, GPT-4 generated the psychological reports. 2) Seven professors of psychiatry from different university hospitals evaluated the quality and risk of hallucinations in the psychological reports by reading the reports only, without meeting the participants. This quality assessment compared the psychological reports generated by GPT-4 with those inferred by the experts. 3) Participants evaluated their satisfaction with the psychological reports. All assessments were conducted using self-report questionnaires based on a Likert scale developed for this study.

Results: A total of 10 participants were recruited, and the average age was 32 years. The median response indicated that quality of all five components of the psychological report was similar to the level inferred by the experts. The risk of hallucination was assessed as ranging from unlikely to minor. According to the median response in the satisfaction evaluation, the participants agreed that the report is clearly understandable, insightful, credible, useful, satisfying, and recommendable.

Conclusion: This study suggests the possibility that artificial intelligence could assist users by providing psychodynamic interpretations.

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
Frontiers in Psychiatry
Frontiers in Psychiatry Medicine-Psychiatry and Mental Health
CiteScore
6.20
自引率
8.50%
发文量
2813
审稿时长
14 weeks
期刊介绍: Frontiers in Psychiatry publishes rigorously peer-reviewed research across a wide spectrum of translational, basic and clinical research. Field Chief Editor Stefan Borgwardt at the University of Basel is supported by an outstanding Editorial Board of international researchers. This multidisciplinary open-access journal is at the forefront of disseminating and communicating scientific knowledge and impactful discoveries to researchers, academics, clinicians and the public worldwide. The journal''s mission is to use translational approaches to improve therapeutic options for mental illness and consequently to improve patient treatment outcomes.
×
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