• 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

评估生成式预训练转换器(GPT)在阿尔茨海默病管理中的作用:神经科医生和人工智能生成的回复的对比研究。

Assessing the Role of the Generative Pretrained Transformer (GPT) in Alzheimer's Disease Management: Comparative Study of Neurologist- and Artificial Intelligence-Generated Responses.

机构信息

West China Medical School, Sichuan University, Chengdu, China.

Department of Neurology, West China Hospital, Sichuan University, Chengdu, China.

出版信息

J Med Internet Res. 2024 Oct 31;26:e51095. doi: 10.2196/51095.

DOI:10.2196/51095
PMID:39481104
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11565080/
Abstract

BACKGROUND

Alzheimer's disease (AD) is a progressive neurodegenerative disorder posing challenges to patients, caregivers, and society. Accessible and accurate information is crucial for effective AD management.

OBJECTIVE

This study aimed to evaluate the accuracy, comprehensibility, clarity, and usefulness of the Generative Pretrained Transformer's (GPT) answers concerning the management and caregiving of patients with AD.

METHODS

In total, 14 questions related to the prevention, treatment, and care of AD were identified and posed to GPT-3.5 and GPT-4 in Chinese and English, respectively, and 4 respondent neurologists were asked to answer them. We generated 8 sets of responses (total 112) and randomly coded them in answer sheets. Next, 5 evaluator neurologists and 5 family members of patients were asked to rate the 112 responses using separate 5-point Likert scales. We evaluated the quality of the responses using a set of 8 questions rated on a 5-point Likert scale. To gauge comprehensibility and participant satisfaction, we included 3 questions dedicated to each aspect within the same set of 8 questions.

RESULTS

As of April 10, 2023, the 5 evaluator neurologists and 5 family members of patients with AD rated the 112 responses: GPT-3.5: n=28, 25%, responses; GPT-4: n=28, 25%, responses; respondent neurologists: 56 (50%) responses. The top 5 (4.5%) responses rated by evaluator neurologists had 4 (80%) GPT (GPT-3.5+GPT-4) responses and 1 (20%) respondent neurologist's response. For the top 5 (4.5%) responses rated by patients' family members, all but the third response were GPT responses. Based on the evaluation by neurologists, the neurologist-generated responses achieved a mean score of 3.9 (SD 0.7), while the GPT-generated responses scored significantly higher (mean 4.4, SD 0.6; P<.001). Language and model analyses revealed no significant differences in response quality between the GPT-3.5 and GPT-4 models (GPT-3.5: mean 4.3, SD 0.7; GPT-4: mean 4.4, SD 0.5; P=.51). However, English responses outperformed Chinese responses in terms of comprehensibility (Chinese responses: mean 4.1, SD 0.7; English responses: mean 4.6, SD 0.5; P=.005) and participant satisfaction (Chinese responses: mean 4.2, SD 0.8; English responses: mean 4.5, SD 0.5; P=.04). According to the evaluator neurologists' review, Chinese responses had a mean score of 4.4 (SD 0.6), whereas English responses had a mean score of 4.5 (SD 0.5; P=.002). As for the family members of patients with AD, no significant differences were observed between GPT and neurologists, GPT-3.5 and GPT-4, or Chinese and English responses.

CONCLUSIONS

GPT can provide patient education materials on AD for patients, their families and caregivers, nurses, and neurologists. This capability can contribute to the effective health care management of patients with AD, leading to enhanced patient outcomes.

摘要

背景

阿尔茨海默病(AD)是一种进行性神经退行性疾病,给患者、照护者和社会带来挑战。可及且准确的信息对于 AD 的有效管理至关重要。

目的

本研究旨在评估生成式预训练转换器(GPT)在回答 AD 患者的管理和照护方面的准确性、可理解性、清晰度和有用性。

方法

共确定了 14 个关于 AD 的预防、治疗和照护的问题,并分别以中文和英文向 GPT-3.5 和 GPT-4 提出问题,4 名应答神经科医生被要求回答这些问题。我们生成了 8 组回答(共 112 个),并在答题卡上随机编码。接下来,5 名评估神经科医生和 5 名 AD 患者的家属被要求使用单独的 5 分李克特量表对 112 个回答进行评分。我们使用一套 8 个问题,每个问题的评价等级为 5 分,来评估回答的质量。为了评估可理解性和参与者满意度,我们在同一套 8 个问题中各包含 3 个问题。

结果

截至 2023 年 4 月 10 日,5 名评估神经科医生和 5 名 AD 患者家属对 112 个回答进行了评分:GPT-3.5:n=28,25%,回答;GPT-4:n=28,25%,回答;应答神经科医生:56(50%)回答。评估神经科医生评分最高的前 5 名(4.5%)回答中有 4 个(80%)GPT(GPT-3.5+GPT-4)回答和 1 个(20%)应答神经科医生的回答。对于患者家属评分最高的前 5 名(4.5%)回答,除了第三名回答外,其余都是 GPT 回答。根据神经科医生的评估,神经科医生生成的回答平均得分为 3.9(SD 0.7),而 GPT 生成的回答得分显著更高(平均 4.4,SD 0.6;P<.001)。语言和模型分析显示,GPT-3.5 和 GPT-4 模型的回答质量没有显著差异(GPT-3.5:平均 4.3,SD 0.7;GPT-4:平均 4.4,SD 0.5;P=.51)。然而,英语回答在可理解性(中文回答:平均 4.1,SD 0.7;英语回答:平均 4.6,SD 0.5;P=.005)和参与者满意度(中文回答:平均 4.2,SD 0.8;英语回答:平均 4.5,SD 0.5;P=.04)方面优于中文回答。根据评估神经科医生的回顾,中文回答的平均得分为 4.4(SD 0.6),而英语回答的平均得分为 4.5(SD 0.5;P=.002)。至于 AD 患者的家属,GPT 和神经科医生、GPT-3.5 和 GPT-4、中文和英文回答之间没有显著差异。

结论

GPT 可以为 AD 患者、其家属和照护者、护士和神经科医生提供 AD 患者教育材料。这一能力有助于有效管理 AD 患者的医疗保健,从而改善患者的预后。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/be88/11565080/3c2c7fe7d3a5/jmir_v26i1e51095_fig3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/be88/11565080/f73efb529193/jmir_v26i1e51095_fig1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/be88/11565080/a5ed634e3b0f/jmir_v26i1e51095_fig2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/be88/11565080/3c2c7fe7d3a5/jmir_v26i1e51095_fig3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/be88/11565080/f73efb529193/jmir_v26i1e51095_fig1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/be88/11565080/a5ed634e3b0f/jmir_v26i1e51095_fig2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/be88/11565080/3c2c7fe7d3a5/jmir_v26i1e51095_fig3.jpg

相似文献

1
Assessing the Role of the Generative Pretrained Transformer (GPT) in Alzheimer's Disease Management: Comparative Study of Neurologist- and Artificial Intelligence-Generated Responses.评估生成式预训练转换器(GPT)在阿尔茨海默病管理中的作用:神经科医生和人工智能生成的回复的对比研究。
J Med Internet Res. 2024 Oct 31;26:e51095. doi: 10.2196/51095.
2
The potential of Generative Pre-trained Transformer 4 (GPT-4) to analyse medical notes in three different languages: a retrospective model-evaluation study.生成式预训练变换器4(GPT-4)分析三种不同语言医学笔记的潜力:一项回顾性模型评估研究。
Lancet Digit Health. 2025 Jan;7(1):e35-e43. doi: 10.1016/S2589-7500(24)00246-2.
3
Thyroid Eye Disease and Artificial Intelligence: A Comparative Study of ChatGPT-3.5, ChatGPT-4o, and Gemini in Patient Information Delivery.甲状腺眼病与人工智能:ChatGPT-3.5、ChatGPT-4o和Gemini在患者信息传递方面的比较研究
Ophthalmic Plast Reconstr Surg. 2024 Dec 24. doi: 10.1097/IOP.0000000000002882.
4
Evaluation of Large Language Models in Tailoring Educational Content for Cancer Survivors and Their Caregivers: Quality Analysis.大型语言模型在为癌症幸存者及其护理人员量身定制教育内容方面的评估:质量分析
JMIR Cancer. 2025 Apr 7;11:e67914. doi: 10.2196/67914.
5
Assessing the Accuracy and Reliability of Large Language Models in Psychiatry Using Standardized Multiple-Choice Questions: Cross-Sectional Study.使用标准化多项选择题评估大型语言模型在精神病学中的准确性和可靠性:横断面研究
J Med Internet Res. 2025 May 20;27:e69910. doi: 10.2196/69910.
6
Application of Large Language Models in Stroke Rehabilitation Health Education: 2-Phase Study.大语言模型在中风康复健康教育中的应用:两阶段研究
J Med Internet Res. 2025 Jul 22;27:e73226. doi: 10.2196/73226.
7
Evaluation of ChatGPT-4 as an Online Outpatient Assistant in Puerperal Mastitis Management: Content Analysis of an Observational Study.评估ChatGPT-4作为产褥期乳腺炎管理在线门诊助手的效果:一项观察性研究的内容分析
JMIR Med Inform. 2025 Jul 24;13:e68980. doi: 10.2196/68980.
8
neuroGPT-X: toward a clinic-ready large language model.神经 GPT-X:迈向临床就绪的大型语言模型。
J Neurosurg. 2023 Oct 6;140(4):1041-1053. doi: 10.3171/2023.7.JNS23573. Print 2024 Apr 1.
9
Potential of ChatGPT in youth mental health emergency triage: Comparative analysis with clinicians.ChatGPT在青少年心理健康紧急分诊中的潜力:与临床医生的比较分析
PCN Rep. 2025 Jul 15;4(3):e70159. doi: 10.1002/pcn5.70159. eCollection 2025 Sep.
10
Performance of ChatGPT Across Different Versions in Medical Licensing Examinations Worldwide: Systematic Review and Meta-Analysis.ChatGPT 在全球医学执照考试不同版本中的表现:系统评价和荟萃分析。
J Med Internet Res. 2024 Jul 25;26:e60807. doi: 10.2196/60807.

引用本文的文献

1
Large Language Models in Medical Diagnostics: Scoping Review With Bibliometric Analysis.医学诊断中的大语言模型:基于文献计量分析的综述
J Med Internet Res. 2025 Jun 9;27:e72062. doi: 10.2196/72062.
2
Clinical Reasoning and Knowledge Assessment of Rheumatology Residents Compared to AI Models: A Pilot Study.与人工智能模型相比,风湿病住院医师的临床推理与知识评估:一项试点研究。
J Clin Med. 2024 Dec 5;13(23):7405. doi: 10.3390/jcm13237405.

本文引用的文献

1
Assessing the performance of ChatGPT's responses to questions related to epilepsy: A cross-sectional study on natural language processing and medical information retrieval.评估 ChatGPT 对癫痫相关问题回答的性能:自然语言处理和医学信息检索的横断面研究。
Seizure. 2024 Jan;114:1-8. doi: 10.1016/j.seizure.2023.11.013. Epub 2023 Nov 23.
2
Feasibility of GPT-3 and GPT-4 for in-Depth Patient Education Prior to Interventional Radiological Procedures: A Comparative Analysis.GPT-3和GPT-4在介入放射学程序前进行深入患者教育的可行性:一项比较分析。
Cardiovasc Intervent Radiol. 2024 Feb;47(2):245-250. doi: 10.1007/s00270-023-03563-2. Epub 2023 Oct 23.
3
ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports.
ChatGPT 让医学文献通俗易懂:简化放射学报告的探索性案例研究。
Eur Radiol. 2024 May;34(5):2817-2825. doi: 10.1007/s00330-023-10213-1. Epub 2023 Oct 5.
4
Comparing ChatGPT and GPT-4 performance in USMLE soft skill assessments.比较 ChatGPT 和 GPT-4 在 USMLE 软技能评估中的表现。
Sci Rep. 2023 Oct 1;13(1):16492. doi: 10.1038/s41598-023-43436-9.
5
Using ChatGPT and Google Bard to improve the readability of written patient information: a proof of concept.利用 ChatGPT 和 Google Bard 提高书面患者信息的可读性:概念验证。
Eur J Cardiovasc Nurs. 2024 Mar 12;23(2):122-126. doi: 10.1093/eurjcn/zvad087.
6
Ethical Considerations of Using ChatGPT in Health Care.使用 ChatGPT 在医疗保健中的伦理考虑。
J Med Internet Res. 2023 Aug 11;25:e48009. doi: 10.2196/48009.
7
ChatGPT vs Google for Queries Related to Dementia and Other Cognitive Decline: Comparison of Results.ChatGPT 与谷歌在痴呆症和其他认知能力下降相关查询上的对比:结果比较。
J Med Internet Res. 2023 Jul 25;25:e48966. doi: 10.2196/48966.
8
Artificial Intelligence in Ophthalmology: A Comparative Analysis of GPT-3.5, GPT-4, and Human Expertise in Answering StatPearls Questions.眼科中的人工智能:GPT-3.5、GPT-4与人类专家回答StatPearls问题的比较分析
Cureus. 2023 Jun 22;15(6):e40822. doi: 10.7759/cureus.40822. eCollection 2023 Jun.
9
Performance of GPT-3.5 and GPT-4 on the Japanese Medical Licensing Examination: Comparison Study.GPT-3.5和GPT-4在日本医师执照考试中的表现:比较研究。
JMIR Med Educ. 2023 Jun 29;9:e48002. doi: 10.2196/48002.
10
Utility of ChatGPT in Clinical Practice.ChatGPT 在临床实践中的应用。
J Med Internet Res. 2023 Jun 28;25:e48568. doi: 10.2196/48568.