生成式人工智能在ICU初级模拟师资案例设计培训中的应用研究

doi:10.3761/j.issn.1672-9234.2025.03.003

摘要/Abstract

摘要：

目的探讨生成式人工智能（Generative Artificial Intelligence，Gen AI）在ICU初级模拟师资案例设计培训中的应用效果。方法 2024年8月将40名某院参加ICU初级模拟师资案例设计培训的ICU护士，采用随机数字表法，分为试验组（n=20）和对照组（n=20）。对照组在接受理论培训、考核基础上，人工设计模拟案例；试验组在接受与对照组相同的理论培训、考核的基础上，接受Gen AI在模拟案例设计中的使用培训，并依托Gen AI工具设计模拟案例。比较两组案例设计用时，以及培训满意度和案例质量得分。结果试验组案例设计用时为（56.20±9.35） min，短于对照组的（181.35±22.13） min（P<0.05）。试验组培训总体满意度得分为10（9，10）分，高于对照组的9（8，10）分（P<0.05）。案例质量方面，两组教学目标的明确性和适宜性、情景的仿真度和详细性、评估和反馈机制设计的合理性3个维度得分比较，差异无统计学意义（P>0.05）；对照组在场景设计的合理性与逻辑性、干预措施的科学性与可行性、教学材料的实用性与可及性、案例难易程度与教学对象的匹配度4个维度上得分优于试验组，差异有统计学意义（P<0.05）。结论 Gen AI提高了ICU初级模拟师资培训参与者的案例设计速度，并提升了其对培训的满意度。Gen AI在模拟案例设计上有较大的应用潜力，但在严谨性和专业性等方面未表现出优势，在使用Gen AI进行模拟案例设计时需进一步对案例内容进行评估和审核。

关键词: 生成式人工智能, 模拟教学, 案例设计, 师资培训, 重症监护病房

Abstract:

Objective To explore the application effects of Generative Artificial Intelligence（Gen AI） in case design training for novice simulation instructors in ICUs. Methods In August 2024，40 ICU nurses participating in case design training for novice simulation instructors in ICUs at a hospital were randomly divided into an experimental group（n=20） and a control group（n=20） using a random number table method. The control group manually designed a simulation case after receiving theoretical training and assessments. In addition to receiving the same theoretical training and assessments as the control group，the experimental group underwent training on the use of Gen AI in simulation case design and designed a simulation case using Gen AI. The time taken for case design，training satisfaction scores，and case quality scores were compared between the two groups. Results The experimental group took（56.20±9.35） minutes for case design，which was shorter than the（181.35±22.13） minutes of the control group（P<0.05）. The training satisfaction score of the experimental group was 10（9，10），which was higher than the 9（8，10） of the control group（P<0.05）. In terms of case quality，there were no statistically significant differences between the two groups in scores for the clarity and appropriateness of teaching objectives，the realism and detail of scenarios，and the design of evaluation and feedback mechanisms（P>0.05）. Meanwhile，the control group scored higher than the experimental group in the rationality and logic of scenario design，the scientific soundness and feasibility of interventions，the completeness and practicality of teaching materials，and the alignment of case difficulty to the target learners，with statistically significant differences（P<0.05）. Conclusion Gen AI improves the case design speed of trainees participating in novice simulation instructor training in ICUs and enhances their satisfaction with the training. Gen AI holds great application potential in simulation case design though show no obvious advantages in rigor and professionalism. Further evaluation and review of content are needed when using Gen AI for simulation case design.

Key words: Generative artificial intelligence, Simulation-based teaching, Case design, Teacher training, Intensive care units

刘经邦, 夏叶茹, 王莉, 吴黎莉, 宫晓艳, 曹勤利, 毛霞文, 庄一渝. 生成式人工智能在ICU初级模拟师资案例设计培训中的应用研究[J]. 中华护理教育, 2025, 22(3): 272-277.

LIU Jingbang, XIA Yeru, WANG Li, WU Lili, GONG Xiaoyan, CAO Qinli, MAO Xiawen, ZHUANG Yiyu. Study on the effects of generative artificial intelligence in ICU novice simulation instructor case design training[J]. Chinese Journal of Nursing Education, 2025, 22(3): 272-277.

图/表 2

参考文献 33

[1]	Herridge MS, Azoulay É. Outcomes after critical illness[J]. N Engl J Med, 2023, 388(10):913-924.
[2]	崔锦, 陈香萍, 隋伟静, 等. ICU护士跨专业合作核心能力指标体系的构建[J]. 中国护理管理, 2021, 21(6):839-844.
	Cui J, Chen XP, Sui WJ, et al. Construction of the index system of interprofessional collaboration core competence for ICU nurses[J]. Chin Nurs Manag, 2021, 21(6):839-844.
[3]	Jallad ST, Işık B. The effectiveness of virtual reality simulation as learning strategy in the acquisition of medical skills in nursing education:a systematic review[J]. Ir J Med Sci, 2022, 191(3):1407-1426.
[4]	Ward ZJ, Atun R, King G, et al. Simulation-based estimates and projections of global,regional and country-level maternal mortality by cause,1990-2050[J]. Nat Med, 2023, 29(5):1253-1261.
[5]	吴黎莉, 丁珊妮, 朱小莹, 等. 护理模拟教学临床师资培养的现状分析及展望[J]. 中华护理教育, 2024, 21(12):1523-1529.
	Wu LL, Ding SN, Zhu XY, et al. Analysis and prospect of the current situation and development of training for clinical nursing simulation teaching instructors[J]. Chin J Nurs Educ, 2024, 21(12):1523-1529.
[6]	INACSL Standards Committee. Healthcare simulation standards of best practice^TM simulation design[J]. Clin Simul Nurs, 2021, 58:14-21.
[7]	孙建玲, 孙立明, 张梅霓, 等. 急危重症护理高仿真模拟教学的设计与效果评价[J]. 中华现代护理杂志, 2020, 26(33):4697-4701.
	Sun JL, Sun LM, Zhang MN, et al. Design and effect evaluation of high-fidelity simulation teaching in emergency and critical care nursing[J]. Chin J Mod Nurs, 2020, 26(33):4697-4701.
[8]	胡阳, 李芳, 邢娟, 等. Jeffries模拟教学理论在外科护理实践教学中的应用效果研究[J]. 护理研究, 2023, 37(6):1091-1095.
	Hu Y, Li F, Xing J, et al. Application effect of Jeffries simulation teaching theory in surgical nursing practice teaching[J]. Chin Nurs Res, 2023, 37(6):1091-1095.
[9]	Boscardin CK, Gin B, Golde PB, et al. ChatGPT and generative artificial intelligence for medical education:potential impact and opportunity[J]. Acad Med, 2024, 99(1):22-27.
[10]	Moulaei K, Yadegari A, Baharestani M, et al. Generative artificial intelligence in healthcare:a scoping review on benefits,challenges and applications[J]. Int J Med Inform, 2024,188:105474.
[11]	Kucukkaya A, Arikan E, Goktas P. Unlocking ChatGPT’s potential and challenges in intensive care nursing education and practice:a systematic review with narrative synthesis[J]. Nurs Outlook, 2024, 72(6):102287.
[12]	乔晓婷, 庄一渝. 重症护理领域人工智能技术的应用与展望[J]. 护理与康复, 2022, 21(7):90-93.
[13]	Reed JM, Dodson TM. Generative AI backstories for simulation preparation[J]. Nurse Educ, 2024, 49(4):184-188.
[14]	Reid JA. Building clinical simulations with ChatGPT in nursing education[J]. J Nurs Educ,2024:1-2.
[15]	王雅琦, 高洁, 王克芳. 生成式人工智能在护理模拟教学中的潜在应用价值、挑战和展望[J]. 中华护理教育, 2024, 21(9):1076-1081.
	Wang YQ, Gao J, Wang KF. Potential application value,challenges,and prospects of generative artificial intelligence in nursing simulation education[J]. Chin J Nurs Educ, 2024, 21(9):1076-1081.
[16]	Sun GH. Prompt engineering for nurse educators[J]. Nurse Educ, 2024, 49(6):293-299. doi: 10.1097/NNE.0000000000001705 pmid: 38968442
[17]	Bozkurt A. Tell me your prompts and I will make them true:the alchemy of prompt engineering and generative AI[J]. Open Prax, 2024, 16(2):111-118.
[18]	Jeffries PR, Rodgers B, Adamson K. NLN jeffries simulation theory:brief narrative description[J]. Nurs Educ Perspect, 2015, 36(5):292-293. pmid: 26521496
[19]	金三丽, 庞冬, 李婷, 等. 护理专业情境模拟教学质量评价工具的研究进展[J]. 中华护理教育, 2020, 17(1):23-27.
	Jin SL, Pang D, Li T, et al. A review of instruments of simulation quality assessment in nursing[J]. Chin J Nurs Educ, 2020, 17(1):23-27.
[20]	Ahn J, Park HO. Development of a case-based nursing education program using generative artificial intelligence[J]. J Korean Acad Soc Nurs Educ, 2023, 29(3):234-246.
[21]	蒲清平, 向往. 生成式人工智能:ChatGPT的变革影响、风险挑战及应对策略[J]. 重庆大学学报(社会科学版), 2023, 29(3):102-114.
	Pu QP, Xiang W. Opportunities and challenges aroused by ChatGPT as generative AI and strategy for response[J]. J Chongqing Univ Soc Sci Ed, 2023, 29(3):102-114.
[22]	Tang A, Tung N, Nguyen HQ, et al. Health information for all:do large language models bridge or widen the digital divide[J]. BMJ, 2024,387:e080208.
[23]	Meskó B. Prompt engineering as an important emerging skill for medical professionals:tutorial[J]. J Med Internet Res, 2023,25:e50638.
[24]	Noy S, Zhang W. Experimental evidence on the productivity effects of generative artificial intelligence[J]. Science, 2023, 381(6654):187-192. doi: 10.1126/science.adh2586 pmid: 37440646
[25]	Herrmann-Werner A, Festl-Wietek T, Holderried F, et al. Assessing ChatGPT’s mastery of bloom’s taxonomy using psychosomatic medicine exam questions:mixed-methods study[J]. J Med Internet Res, 2024,26:e52113.
[26]	INACSL Standards Committee. Healthcare simulation standards of best practice^TM the debriefing process[J]. Clin Simul Nurs, 2021,58:27-32.
[27]	Gosak L, Pruinelli L, Topaz M, et al. The ChatGPT effect and transforming nursing education with generative AI:discussion paper[J]. Nurse Educ Pract, 2024,75:103888.
[28]	Le Lagadec D, Jackson D, Cleary M. Artificial intelligence in nursing education:prospects and pitfalls[J]. J Adv Nurs, 2024, 80(10):3883-3885.
[29]	Choi EPH, Lee JJ, Ho MH, et al. Chatting or cheating?The impacts of ChatGPT and other artificial intelligence language models on nurse education[J]. Nurse Educ Today, 2023,125:105796.
[30]	Bedi S, Liu YT, Orr-Ewing L, et al. Testing and evaluation of health care applications of large language models:a systematic review[J]. JAMA,2024:e2421700.
[31]	Tam W, Huynh T, Tang A, et al. Nursing education in the age of artificial intelligence powered chatbots(AI-Chatbots):are we ready yet?[J]. Nurse Educ Today, 2023,129:105917.
[32]	Foronda C, Porter A. Strategies to incorporate artificial intelligence in nursing education[J]. Nurse Educ, 2024, 49(3):173-174.
[33]	国家互联网信息办公室, 中华人民共和国国家发展和改革委员会, 中华人民共和国教育部, 等. 生成式人工智能服务管理暂行办法[EB/OL]. (2023-07-10). https://www.gov.cn/zhengce/zhengceku/202307/content_6891752.htm.