• 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

ChatGPT 在台湾药剂师执照考试中的表现。

Performance of ChatGPT on the pharmacist licensing examination in Taiwan.

机构信息

Department of Medical Education and Research, Taipei Veterans General Hospital Hsinchu Branch, Hsinchu, Taiwan, ROC.

Department of Pharmacy, Taipei Veterans General Hospital Hsinchu Branch, Hsinchu, Taiwan, ROC.

出版信息

J Chin Med Assoc. 2023 Jul 1;86(7):653-658. doi: 10.1097/JCMA.0000000000000942. Epub 2023 Jul 5.

DOI:10.1097/JCMA.0000000000000942
PMID:37227901
Abstract

BACKGROUND

ChatGPT is an artificial intelligence model trained for conversations. ChatGPT has been widely applied in general medical education and cardiology, but its application in pharmacy has been lacking. This study examined the accuracy of ChatGPT on the Taiwanese Pharmacist Licensing Examination and investigated its potential role in pharmacy education.

METHODS

ChatGPT was used on the first Taiwanese Pharmacist Licensing Examination in 2023 in Mandarin and English. The questions were entered manually one by one. Graphical questions, chemical formulae, and tables were excluded. Textual questions were scored according to the number of correct answers. Chart question scores were determined by multiplying the number and the correct rate of text questions. This study was conducted from March 5 to March 10, 2023, by using ChatGPT 3.5.

RESULTS

The correct rate of ChatGPT in Chinese and English questions was 54.4% and 56.9% in the first stage, and 53.8% and 67.6% in the second stage. On the Chinese test, only pharmacology and pharmacochemistry sections received passing scores. The English test scores were higher than the Chinese test scores across all subjects and were significantly higher in dispensing pharmacy and clinical pharmacy as well as therapeutics.

CONCLUSION

ChatGPT 3.5 failed the Taiwanese Pharmacist Licensing Examination. Although it is not able to pass the examination, it can be improved quickly through deep learning. It reminds us that we should not only use multiple-choice questions to assess a pharmacist's ability, but also use more variety of evaluations in the future. Pharmacy education should be changed in line with the examination, and students must be able to use AI technology for self-learning. More importantly, we need to help students develop humanistic qualities and strengthen their ability to interact with patients, so that they can become warm-hearted healthcare professionals.

摘要

背景

ChatGPT 是一款经过对话训练的人工智能模型。它已广泛应用于普通医学教育和心脏病学领域,但在药学领域的应用却相对较少。本研究旨在检验 ChatGPT 在台湾药师执照考试中的准确性,并探讨其在药学教育中的潜在作用。

方法

2023 年,我们在首次以普通话和英语进行的台湾药师执照考试中使用了 ChatGPT。问题由人工逐个输入。排除图形问题、化学公式和表格。根据正确答案的数量给文本问题打分。图表问题的分数通过将文本问题的数量和正确率相乘来确定。本研究于 2023 年 3 月 5 日至 3 月 10 日进行,使用的是 ChatGPT 3.5。

结果

ChatGPT 在第一阶段的中文和英文问题中的正确率分别为 54.4%和 56.9%,第二阶段分别为 53.8%和 67.6%。在中文考试中,只有药理学和药物化学部分达到及格分数。在所有科目中,英语考试的分数均高于中文考试,在配药和临床药学以及治疗学方面的分数差异尤为显著。

结论

ChatGPT 3.5 未能通过台湾药师执照考试。虽然它还无法通过考试,但通过深度学习可以迅速提高它的表现。这提醒我们,我们不仅应该使用选择题来评估药师的能力,还应该在未来使用更多样化的评估方式。未来的药学教育应与考试相结合,学生必须能够使用 AI 技术进行自主学习。更重要的是,我们需要帮助学生培养人文素质,增强与患者互动的能力,使他们成为有温度的医疗保健专业人员。

相似文献

1
Performance of ChatGPT on the pharmacist licensing examination in Taiwan.ChatGPT 在台湾药剂师执照考试中的表现。
J Chin Med Assoc. 2023 Jul 1;86(7):653-658. doi: 10.1097/JCMA.0000000000000942. Epub 2023 Jul 5.
2
Performance of ChatGPT-3.5 and ChatGPT-4 in the Taiwan National Pharmacist Licensing Examination: Comparative Evaluation Study.ChatGPT-3.5和ChatGPT-4在台湾国家药剂师执照考试中的表现:比较评估研究。
JMIR Med Educ. 2025 Jan 17;11:e56850. doi: 10.2196/56850.
3
Performance of ChatGPT on Chinese national medical licensing examinations: a five-year examination evaluation study for physicians, pharmacists and nurses.ChatGPT 在国家医师、药师、护士等医学类考试中的表现:一项针对医、药、护人员的五年考试评估研究。
BMC Med Educ. 2024 Feb 14;24(1):143. doi: 10.1186/s12909-024-05125-7.
4
Performance of ChatGPT-3.5 and GPT-4 in national licensing examinations for medicine, pharmacy, dentistry, and nursing: a systematic review and meta-analysis.ChatGPT-3.5 和 GPT-4 在医学、药学、牙科和护理国家执照考试中的表现:系统评价和荟萃分析。
BMC Med Educ. 2024 Sep 16;24(1):1013. doi: 10.1186/s12909-024-05944-8.
5
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.
6
Performance of ChatGPT-4 on Taiwanese Traditional Chinese Medicine Licensing Examinations: Cross-Sectional Study.ChatGPT-4在台湾中医师执照考试中的表现:横断面研究。
JMIR Med Educ. 2025 Mar 19;11:e58897. doi: 10.2196/58897.
7
Accuracy of ChatGPT on Medical Questions in the National Medical Licensing Examination in Japan: Evaluation Study.ChatGPT在日本国家医师资格考试医学问题上的准确性:评估研究
JMIR Form Res. 2023 Oct 13;7:e48023. doi: 10.2196/48023.
8
While GPT-3.5 is unable to pass the Physician Licensing Exam in Taiwan, GPT-4 successfully meets the criteria.虽然GPT-3.5无法通过台湾的医师执照考试,但GPT-4成功达到了标准。
J Chin Med Assoc. 2025 May 1;88(5):352-360. doi: 10.1097/JCMA.0000000000001225. Epub 2025 Mar 14.
9
Performance of GPT-3.5 and GPT-4 on the Korean Pharmacist Licensing Examination: Comparison Study.GPT-3.5和GPT-4在韩国药剂师执照考试中的表现:比较研究。
JMIR Med Educ. 2024 Dec 4;10:e57451. doi: 10.2196/57451.
10
Assessing question characteristic influences on ChatGPT's performance and response-explanation consistency: Insights from Taiwan's Nursing Licensing Exam.评估问题特征对 ChatGPT 表现和回应解释一致性的影响:来自台湾护理执照考试的见解。
Int J Nurs Stud. 2024 May;153:104717. doi: 10.1016/j.ijnurstu.2024.104717. Epub 2024 Feb 8.

引用本文的文献

1
Exploring the role of DeepSeek-R1, ChatGPT-4, and Google Gemini in medical education: How valid and reliable are they?探索DeepSeek-R1、ChatGPT-4和谷歌Gemini在医学教育中的作用:它们的有效性和可靠性如何?
Pak J Med Sci. 2025 Jul;41(7):1887-1892. doi: 10.12669/pjms.41.7.12183.
2
Evaluation of ChatGPT's performance in providing treatment recommendations for pediatric diseases.评估ChatGPT在提供儿科疾病治疗建议方面的表现。
Pediatr Discov. 2023 Nov 20;1(3):e42. doi: 10.1002/pdi3.42. eCollection 2023 Dec.
3
Comparative analysis of ChatGPT 3.5 and ChatGPT 4 obstetric and gynecological knowledge.
ChatGPT 3.5与ChatGPT 4妇产科知识的对比分析
Sci Rep. 2025 Jul 1;15(1):21133. doi: 10.1038/s41598-025-08424-1.
4
Advancing medical AI: GPT-4 and GPT-4o surpass GPT-3.5 in Taiwanese medical licensing exams.推进医学人工智能:GPT-4和GPT-4o在台湾医学执照考试中超越GPT-3.5。
PLoS One. 2025 Jun 4;20(6):e0324841. doi: 10.1371/journal.pone.0324841. eCollection 2025.
5
Performance of ChatGPT-4 on Taiwanese Traditional Chinese Medicine Licensing Examinations: Cross-Sectional Study.ChatGPT-4在台湾中医师执照考试中的表现:横断面研究。
JMIR Med Educ. 2025 Mar 19;11:e58897. doi: 10.2196/58897.
6
Performance assessment of ChatGPT 4, ChatGPT 3.5, Gemini Advanced Pro 1.5 and Bard 2.0 to problem solving in pathology in French language.ChatGPT 4、ChatGPT 3.5、Gemini Advanced Pro 1.5和Bard 2.0解决法语病理学问题的性能评估。
Digit Health. 2025 Jan 31;11:20552076241310630. doi: 10.1177/20552076241310630. eCollection 2025 Jan-Dec.
7
ChatGPT-4 Omni's superiority in answering multiple-choice oral radiology questions.ChatGPT-4 Omni在回答口腔放射学选择题方面的优势。
BMC Oral Health. 2025 Feb 1;25(1):173. doi: 10.1186/s12903-025-05554-w.
8
Performance of ChatGPT-3.5 and ChatGPT-4 in the Taiwan National Pharmacist Licensing Examination: Comparative Evaluation Study.ChatGPT-3.5和ChatGPT-4在台湾国家药剂师执照考试中的表现:比较评估研究。
JMIR Med Educ. 2025 Jan 17;11:e56850. doi: 10.2196/56850.
9
Enhancing Patient Comprehension of Glomerular Disease Treatments Using ChatGPT.使用ChatGPT提高患者对肾小球疾病治疗的理解
Healthcare (Basel). 2024 Dec 31;13(1):57. doi: 10.3390/healthcare13010057.
10
Evaluation of the ability of large language models to self-diagnose oral diseases.评估大语言模型自我诊断口腔疾病的能力。
iScience. 2024 Nov 29;27(12):111495. doi: 10.1016/j.isci.2024.111495. eCollection 2024 Dec 20.