计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240400121-6.doi: 10.11896/jsjkx.240400121

• 大语言模型技术及应用 • 上一篇    下一篇

大语言模型在医学教育中的应用:现状、挑战与未来

涂吉1, 肖文栋2, 涂文记3, 李立健4   

  1. 1 中国医学科学院基础医学研究所北京协和医学院基础学院 北京 100005
    2 北京科技大学 北京 100083
    3 北京协和医学院教务处 北京 100005
    4 中国科学院自动化研究所 北京 100190
  • 出版日期:2025-06-16 发布日期:2025-06-12
  • 通讯作者: 涂文记(tuwenji@yzjg.pumc.edu.cn)
  • 作者简介:(ji.tu@ibms.pumc.edu.cn)
  • 基金资助:
    北京市教育委员会2024年学籍学历管理研究课题(XJXL202416);中国医学科学院基础医学研究所医学人工智能教学改革项目(2022jcjg0104);教育部2022年百度产学合作协同育人项目-医学人工智能课程建设(182215PC08768);中国计算机学会-百度松果基金:多模态协同医疗大模型基准数据集构建与应用评测(CCF-BAIDUOF202418)

Application of Large Language Models in Medical Education:Current Situation,Challenges and Future

TU Ji1, XIAO Wendong2, TU Wenji3, LI Lijian4   

  1. 1 Institute of Basic Medical Sciences Chinese Academy of Medical Sciences,School of Basic Medicine Peking Union Medical College,Beijing 100005,China
    2 University of Science and Technology,Beijing 100083,China
    3 Dean’s Office,Peking Union Medical College,Beijing 100005,China
    4 Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China
  • Online:2025-06-16 Published:2025-06-12
  • About author:TU Ji,born in 1986,senior engineer,is a senior member of CCF(31285M).His main research interests include the intersection of medicine and engineering,epidemiology and health statistics.
    TU Wenji,born in 1984,associate researcher.Her main research interests include medical education management and medical education evaluation.
  • Supported by:
    Beijing Municipal Commission of Education 2024 Academic Status Management Research Project(XJXL202416),Medical Artificial Intelligence Educational Reform Project of Institute of Basic Medical Sciences(2022jcjg0104),Ministry of Education 2022 Baidu Industry-academy Cooperation Collaborative Education Project-Medical Artificial Intelligence Curriculum Construction(182215PC08768) and China Computer Federation(CCF)-Baidu Pinecone Fund: Construction and Application Evaluation of a Multimodal Collaborative Healthcare Large Language Model Benchmark Dataset(CCF-BAIDUOF202418).

摘要: 医学教育数字化是医学教育发展的必然趋势。通过引入医学教育大语言模型,打破传统医学教育的局限,提高学生的学习兴趣和参与度,提供医学教育的个性化实践,加强因材施教的个性化临床实践教学和科研训练,可提升教学效率和效果。文中梳理了大语言模型技术的发展和医疗大模型的技术进展,列举了大模型的医学教育应用场景和大模型的医学教育应用七大挑战,指出了医学教育大模型的未来发展是采用知识与数据混合驱动的技术路线,研发自主可控的协同医学教育大模型。

关键词: 大语言模型, 医学教育, 人工智能, 教育数字化, 文心一言

Abstract: Digitization of medical education is an inevitable trend in the development of medical education.By introducing the large language model of medical education,the limitation of traditional medical education can be broken.Students’ learning interest and participation can be improved as well as personalized practice of medical education.Individualized clinical practice teaching and scientific research training can be strengthened,which can improve teaching efficiency and effect.This paper reviews the development of large language model technology and the technical progress of medical large language model.It also lists the application scenarios of large language model in medical education and points out seven challenges of large language model in medical education.It is announced that the future development of medical education large language model is to develop an autonomous and controllable collaborative medical education large language model by using the technology route driven by knowledge and data.

Key words: Large language model, Medical education, Artificial intelligence, Digitization of education, ERNIE bot

中图分类号: 

  • TP18
[1]VAPNIK V.The nature of statistical learning theory[M].Springer Science & Business Media,1999.
[2]MIKOLOV T,KARAFIÁT M,BURGET L,et al.Recurrent neural network based language model[C]//Interspeech:volume 2.Makuhari,2010:1045-1048.
[3]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.NY,USA:Curran Associates Inc.,2017:6000-6010.
[4]DEVLIN J,CHANG M W,LEE K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 1(Long and Short Papers).2019:4171-4186.
[5]ZHANG Q,GUI T,ZHENG R,et al.Large-Scale LanguageModels:From Theory to Practice[M].Publishing House of Electronics Industry,2024.
[6]SUTSKEVER I,VINYALS O,LE Q V.Sequence to sequence learning with neural networks[J].Advances in Neural Information Processing Systems,2014,4:3104-3112.
[7]RADFORD A,WU J,CHILD R,et al.Language models are unsupervised multitask learners[J].OpenAI blog,2019,1(8):9.
[8]ZHANG Q,GUI T,HUANG X J.Introduction to Natural Language Processing[M].Publishing House of Electronics Industry,2023.
[9]XIAO Y H,XU Y D.Applications of Large-Scale GenerativeLanguage Models in the Medical Field: Opportunities and Challenges [J].Journal of Medical Informatics,2023,44(9):1-11.
[10]HU Z S,YANG R,ZHU J H,et al.Research and Application Development of Large Language Models in the Medical Field [J].Artificial Intelligence,2023(4):10-19.
[11]OpenAI.GPT-4 Technical Report 2023[R].arXiv:2303.08774 [cs.CL].
[12]KARAN S,TAO T,JURAJ G,et al.Towards Expert-LevelMedical Question Answering with Large Language Models[J].arXiv:2305.09617,2023.
[13]KUNG T H,CHEATHAM M,MEDENILLA A,et al.Performance of ChatGPT on USMLE:Potential for AI-assisted medical education using large language models[J].PLOS Digit Health.2023 Feb 9;2(2):e0000198.
[14]Google.PaLM 2 Technical Report[OL].https://ai.google/sta-tic/documents/palm2tech report.pdf.2023.
[15]SINGHAL K,AZIZI S,TU T,et al.Large language models encode clinical knowledge[J].Nature,2023.DOI:10.1038/s41586-023-06291-2.
[16]AO T,SHEKOOFEH A,DANNY D,et al.Towards Generalist Biomedical AI[J].NEJM AI,2024,1(3):1-37.
[17]TAO T,ANIL P,MIKE S,et al.Towards Conversational Diagnostic AI.2024,arXiv:2401.05654v1[cs.CL].
[18]SHANG J J,LI X H.Challenges and Coping Strategies for the Digital Transformation of Education [J].Journal of East China Normal University(Educational Sciences),2023(3):72-81.
[19]LIU M,WU Z M,LIAO J,et al.Educational Applications of Large Language Models:Principles,Current Status, and Challenges-From Lightweight BERT to Conversational ChatGPT [J].Modern Educational Technology,2023,33(8):19-28.
[20]RAFFEL C,SHAZEER N,ROBERTS A,et al.Exploring the limits of transfer learning with a unified text-to text transformer[J].The Journal of Machine Learning Research,2020,21(1):5485-5551.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!