• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

利用人工智能治疗失语症:关于ChatGPT在支持书面表达方面作用的病例报告

Harnessing AI for aphasia: a case report on ChatGPT's role in supporting written expression.

作者信息

Allen Avery K, Brennan Christine, Riseman Christina, Kleiber Holly, Hilger Allison I

机构信息

Department of Speech, Language, and Hearing Sciences, University of Colorado Boulder, Boulder, CO, United States.

出版信息

Front Rehabil Sci. 2025 May 30;6:1600145. doi: 10.3389/fresc.2025.1600145. eCollection 2025.

DOI:10.3389/fresc.2025.1600145
PMID:40519984
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12163031/
Abstract

INTRODUCTION

Aphasia is associated with impairments in written language, including difficulty with sentence formulation, word finding, and editing. While writing aids show promise, artificial intelligence (AI) tools, such as large language models (LLMs), offer new opportunities for individuals with language-based writing challenges.

METHODS

This case report describes the use of the LLM, ChatGPT, to improve accuracy, complexity, and productivity in an adult with aphasia. The intervention combined self-genrated content with AI-assisted editing, guided by a visual flow char and structured prompts. Writing samples were analyzed for sentence count, complexity, and errors, while the patient's attitudes toward writing were evaluated through surveys.

RESULTS

When using ChatGPT, the patient produced more sentences with fewer errors, while self-written samples showed reduced total errors but decreased sentence production and increased sentence length and syntactic complexity. Although the patient required clinician prompting and modeling to use ChatGPT effectively, he developed greater independence and confidence over time. One year later, he reported continued use of ChatGPT for creative and communicative tasks.

DISCUSSION

This case highlights how AI tools can enhance written communication and promote participation in meaningful activities for individuals with aphasia, especially those with prior experience using technology.

摘要

引言

失语症与书面语言障碍有关,包括句子构建、词汇查找和编辑方面的困难。虽然写作辅助工具显示出前景,但人工智能(AI)工具,如大语言模型(LLMs),为有基于语言的写作挑战的个体提供了新机会。

方法

本病例报告描述了使用大语言模型ChatGPT提高一名成年失语症患者写作的准确性、复杂性和效率的情况。干预措施将自我生成的内容与人工智能辅助编辑相结合,由视觉流程图和结构化提示引导。分析写作样本的句子数量、复杂性和错误,同时通过调查评估患者对写作的态度。

结果

使用ChatGPT时,患者写出的句子更多,错误更少,而自我书写的样本总错误减少,但句子数量减少,句子长度和句法复杂性增加。尽管患者需要临床医生的提示和示范才能有效使用ChatGPT,但随着时间的推移,他变得更加独立和自信。一年后,他报告仍在使用ChatGPT进行创造性和交流性任务。

讨论

本病例突出了人工智能工具如何能够增强失语症患者的书面交流能力,并促进他们参与有意义的活动,尤其是那些有使用技术经验的患者。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a4c6/12163031/468ae8933231/fresc-06-1600145-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a4c6/12163031/0328ff7635b1/fresc-06-1600145-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a4c6/12163031/c7e1c72954cc/fresc-06-1600145-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a4c6/12163031/468ae8933231/fresc-06-1600145-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a4c6/12163031/0328ff7635b1/fresc-06-1600145-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a4c6/12163031/c7e1c72954cc/fresc-06-1600145-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a4c6/12163031/468ae8933231/fresc-06-1600145-g003.jpg

相似文献

1
Harnessing AI for aphasia: a case report on ChatGPT's role in supporting written expression.利用人工智能治疗失语症:关于ChatGPT在支持书面表达方面作用的病例报告
Front Rehabil Sci. 2025 May 30;6:1600145. doi: 10.3389/fresc.2025.1600145. eCollection 2025.
2
Evaluating the Influence of Role-Playing Prompts on ChatGPT's Misinformation Detection Accuracy: Quantitative Study.评估角色扮演提示对 ChatGPT 错误信息检测准确率的影响:定量研究。
JMIR Infodemiology. 2024 Sep 26;4:e60678. doi: 10.2196/60678.
3
What's in a Name? Experimental Evidence of Gender Bias in Recommendation Letters Generated by ChatGPT.名字里的乾坤:ChatGPT 生成的推荐信中的性别偏见的实验证据。
J Med Internet Res. 2024 Mar 5;26:e51837. doi: 10.2196/51837.
4
Optimizing ChatGPT's Interpretation and Reporting of Delirium Assessment Outcomes: Exploratory Study.优化 ChatGPT 对谵妄评估结果的解释和报告:探索性研究。
JMIR Form Res. 2024 Oct 1;8:e51383. doi: 10.2196/51383.
5
The Readiness of ChatGPT to Write Scientific Case Reports Independently: A Comparative Evaluation Between Human and Artificial Intelligence.ChatGPT独立撰写科学病例报告的准备情况:人与人工智能的比较评估
Cureus. 2023 May 23;15(5):e39386. doi: 10.7759/cureus.39386. eCollection 2023 May.
6
Agraphia失写症
7
Application of Large Language Models in Medical Training Evaluation-Using ChatGPT as a Standardized Patient: Multimetric Assessment.大语言模型在医学培训评估中的应用——以ChatGPT作为标准化病人:多指标评估
J Med Internet Res. 2025 Jan 1;27:e59435. doi: 10.2196/59435.
8
Are ChatGPT and large language models "the answer" to bringing us closer to systematic review automation?ChatGPT 和大型语言模型是实现系统评价自动化的“答案”吗?
Syst Rev. 2023 Apr 29;12(1):72. doi: 10.1186/s13643-023-02243-z.
9
Exploring ChatGPT's potential for augmenting post-editing in machine translation across multiple domains: challenges and opportunities.探索ChatGPT在多个领域增强机器翻译后编辑方面的潜力:挑战与机遇。
Front Artif Intell. 2025 May 1;8:1526293. doi: 10.3389/frai.2025.1526293. eCollection 2025.
10
ChatGPT and assistive AI in structured radiology reporting: A systematic review.ChatGPT 和辅助人工智能在结构化放射学报告中的应用:一项系统评价。
Curr Probl Diagn Radiol. 2024 Nov-Dec;53(6):728-737. doi: 10.1067/j.cpradiol.2024.07.007. Epub 2024 Jul 9.

本文引用的文献

1
Automating Intended Target Identification for Paraphasias in Discourse Using a Large Language Model.使用大型语言模型自动识别话语中的意图目标歧义词。
J Speech Lang Hear Res. 2023 Dec 11;66(12):4949-4966. doi: 10.1044/2023_JSLHR-23-00121. Epub 2023 Nov 6.
2
Evaluating the performance of large language models: ChatGPT and Google Bard in generating differential diagnoses in clinicopathological conferences of neurodegenerative disorders.评估大型语言模型的性能:ChatGPT 和 Google Bard 在神经退行性疾病临床病理会议中生成鉴别诊断的能力。
Brain Pathol. 2024 May;34(3):e13207. doi: 10.1111/bpa.13207. Epub 2023 Aug 8.
3
Correlations between Dual-Pathway White Matter Alterations and Language Impairment in Patients with Aphasia: A Systematic Review and Meta-analysis.
失语症患者双通路白质改变与语言障碍的相关性:一项系统评价和荟萃分析
Neuropsychol Rev. 2021 Sep;31(3):402-418. doi: 10.1007/s11065-021-09482-8. Epub 2021 Mar 3.
4
A re-examination of neural basis of language processing: proposal of a dynamic hodotopical model from data provided by brain stimulation mapping during picture naming.语言处理神经基础的重新审视:基于图片命名过程中脑刺激映射所提供数据提出的动态拓扑模型
Brain Lang. 2014 Apr;131:1-10. doi: 10.1016/j.bandl.2013.05.011. Epub 2013 Jul 15.
5
Aphasia and text writing.失语症与文本书写。
Int J Lang Commun Disord. 2010 Mar-Apr;45(2):230-43. doi: 10.3109/13682820902936425.
6
The relationship of 60 disease diagnoses and 15 conditions to preference-based health-related quality of life in Ontario hospital-based long-term care residents.安大略省医院长期护理居民中 60 种疾病诊断和 15 种状况与基于偏好的健康相关生活质量的关系。
Med Care. 2010 Apr;48(4):380-7. doi: 10.1097/MLR.0b013e3181ca2647.
7
Aphasia and the process of revision in writing a text.失语症与文本写作中的修改过程。
Clin Linguist Phon. 2008 Feb;22(2):95-110. doi: 10.1080/02699200701699603.