本研究旨在突破传统静态病例设计的局限性,构建基于大语言模型的“动态提示词模型”,并探究其在儿科医学教育中的应用效果。该模型涵盖疾病病程推进信息(前驱期、急性期、恢复期)、完整的临床决策链条(问诊、查体、辅助检查、诊断、治疗)和由浅入深的认知目标(记忆、理解、应用、分析、评价)。疾病清单包括儿科常见病和少见病两大类。选取中国医科大学儿科医学专业四年级45名学生作为研究对象,开展为期4周的学习任务。研究结果表明,动态病例学习后,虚拟病例成绩从(75.31±15.21)分提高至(82.22±11.43)分;批判性思维能力从(102.67±10.93)分提高至(110.13±12.61)分,其中系统分析能力从(42.85±3.91)分提高至(45.13±4.61)分,知识探索意愿从(31.55±3.74)分提高至(36.32±5.11)分,其差异均具有统计学意义(均P<0.05)。不同病例的真实感评分较高(均>4分),难度评分分布具有一定合理性。在体验评价中,促进学习维度评分最高[(4.02±0.47)分]。“动态提示词模型”有效提升了医学生的临床思维能力和批判性思维能力,为儿科医学教育提供了一种高效、创新的教学工具。
This study aims to break through the limitations of traditional static case design by constructing a ″dynamic prompt model″ based on large language models and exploring its application and effectiveness in pediatric medical education. The model encompasses disease course progression information (prodromal, acute, and recovery phases), a complete clinical decision-making chain (history taking, physical examination, auxiliary investigations, diagnosis, and treatment), and progressively advanced cognitive objectives (remembering, understanding, applying, analyzing, and evaluating). The disease list includes two categories: common pediatric diseases and rare diseases. The study selected 45 fourth-year pediatric medical students from China Medical University as research participants to conduct a 4-week learning program. The results indicate that after learning with dynamic cases, the virtual case scores significantly increased from (75.31±15.21) to (82.22±11.43). Critical thinking ability improved from (102.67±10.93) to (110.13±12.61), with system analysis skills rising from (42.85±3.91) to (45.13±4.61) and knowledge exploration willingness increasing from (31.55±3.74) to (36.32±5.11), all P<0.05. The realism scores of different cases were relatively high (all>4), and the difficulty ratings were reasonably distributed. In the experience evaluation, the ″enhancing learning″ dimension scored the highest (4.02±0.47). Therefore, the ″dynamic prompt model″ effectively improved medical students′ clinical thinking and critical thinking abilities, providing an efficient and innovative tool for pediatric medical education.
[1] 国务院办公厅关于加快医学教育创新发展的指导意见[J].中华人民共和国国务院公报,2020(28):27-31.
[2] 国家卫生健康委. 2023年我国卫生健康事业发展统计公报[EB/OL].[2025-04-09].https://www.gov.cn/lianbo/bumen/202408/content_6971241.htm/2024-08-29,2024-04-08.
[3] 王维民. 新科技革命背景下的医学教育范式转型[J]. 中华医学教育杂志, 2024, 44(6):401-406. DOI: 10.3760/cma.j.cn115259-20240405-00352.
[4] Masters K, Benjamin J, Agrawal A, et al. Twelve tips on creating and using custom GPTs to enhance health professions education[J]. Med Teach, 2024,46(6):752-756. DOI: 10.1080/0142159X.2024.2305365.
[5] Cook DA. Creating virtual patients using large language models: scalable, global, and low cost[J]. Med Teach, 2025,47(1):40-42. DOI: 10.1080/0142159X.2024.2376879.
[6] 中共中央国务院关于优化生育政策促进人口长期均衡发展的决定[N].人民日报,2021-07-21(1).
[7] 孙锟.儿科临床决策支持手册[M].北京:人民卫生出版社,2021:3-4.
[8] 陈娜平, 唐陆禛, 黄贤生, 等. 基于ChatGPT-4的虚拟标准化病人应用研究[J].中华医学教育杂志,2025,45(1):44-49. DOI: 10.3760/cma.j.cn115259-20240307-00225.
[9] 闾海荣, 江瑞, 张学工, 等. DeepSeek与医学大语言模型:技术创新与医疗服务模式重构[J].医学信息学杂志,2025,46(2):1-7,13. DOI: 10.3969/j.issn.1673-6036.2025.02.001.
[10] Liaw SY, Tan JZ, Lim S, et al. Artificial intelligence in virtual reality simulation for interprofessional communication training: mixed method study[J]. Nurse Educ Today, 2023,122:105718. DOI: 10.1016/j.nedt.2023.105718.
[11] Baylor AL, Ryu J. The effects of image and animation in enhancing pedagogical agent persona[J]. J Educ Comput Res, 2003, 28 (4):373-394.
[12] Cui L, Zhu Y, Qu J, et al. Psychometric properties of the critical thinking disposition assessment test amongst medical students in China: a cross-sectional study[J]. BMC Med Educ, 2021,21(1):10. DOI: 10.1186/s12909-020-02437-2.