大语言模型在病例生成、个性化教学与评估中的研究进展

doi:10.3870/j.issn.1672-8009.2026.01.014

医学分子生物学杂志 ›› 2026, Vol. 23 ›› Issue (1): 97-106.doi: 10.3870/j.issn.1672-8009.2026.01.014

• 医学教育 • 上一篇

大语言模型在病例生成、个性化教学与评估中的研究进展

丛尚^1,2#, 白沃涵^1,3#, 陈钟⁴, 苏钰⁵, 易跃雄¹

¹武汉大学中南医院妇科武汉市,43007
²武汉大学第一临床学院武汉市,430070
³武汉大学第二临床学院武汉市,430071
⁴武汉大学中南医院科研处武汉市,430071
⁵武汉大学人民医院眼科中心武汉市,430070

收稿日期:2025-08-08 发布日期:2026-01-29
通讯作者: 易跃雄(E-mail:yiyuexiong@163.com)
作者简介:#:共同第一作者
基金资助:
武汉大学中南医院住培/专培教学研究重点项目(No.ZP-202402),武汉大学中南医院科技创新培育基金(No.CXPY2022049)

Research Progress of Large Language Models in Case Generation,Personalized Teaching and Assessment

CONG Shang^1,2#, BAI Wohan^1,3#, CHEN Zhong⁴, SU Yu⁵, YI Yuexiong¹

¹Department of Gynecology,Zhongnan Hospital of Wuhan University,Wuhan,430071,China
²The First Clinical College,Wuhan University,Wuhan,430070,China
³The Second Clinical College,Wuhan University,Wuhan,430071,China
⁴Department of Scientific Research,Zhongnan Hospital of Wuhan University,Wuhan,430071,China
⁵Ophthalmology Center,Renmin Hospital of Wuhan University,Wuhan,430070,China

Received:2025-08-08 Published:2026-01-29
Contact: YI Yuexiong(E-mail:yiyuexiong@163.com)
About author:#:These authors contributed equally as first author
Supported by:
Key Teaching and Research Project for Residency/Fellowship Training of Zhongnan Hospital of Wuhan University(No.ZP-202402),Science and Technology Innovation Cultivation Fund of Zhongnan Hospital of Wuhan University(No.CXPY2022049)

摘要/Abstract

摘要： 大语言模型(large language model,LLM)为医学教育带来新机遇。文章考察LLM在病例生成、个性化教学及智能评估方面的技术基础与应用手段。借助合理挑选模型、提示词,开展多模态融合与学术校正,LLM可生成仿真教学案例,利于临床推理训练;将学生画像与学习行为结合,LLM可实现路径推荐、内容定制的操作,提升教学适配度;LLM助力构建涵盖医学准确性、逻辑结构与因果推理方面的多维评分体系,产出个性化反馈内容。当前LLM仍面临幻觉与知识更新滞后等挑战,未来应加强人机协同、数据安全与标准资源建设,从而推动医学教育向智能化、规范化发展。

关键词: 大语言模型, 病例生成, 个性化教学, 教学评估, 医学教育

Abstract: Large language model(LLM)offers new opportunities for medical education.This paper examines its technical foundations and applications in case generation,personalized teaching,and intelligent assessment.By selecting appropriate models and prompts,and incorporating multimodal integration and academic validation,LLM can generate simulated teaching cases for clinical reasoning training.By combining student profiles and learning behaviors,LLM enables path recommendations and content customization,enhancing teaching adaptability.LLM also helps build multidimensional scoring systems focusing on medical accuracy,logical structure,and causal reasoning,providing personalized feedback.Despite challenges like hallucinations and outdated knowledge,future improvements should focus on human-machine collaboration,data security,and standardized resources to promote intelligent and standardized medical education.

Key words: large language model, case generation, personalized teaching, teaching assessment, medical education

中图分类号:

丛尚, 白沃涵, 陈钟, 苏钰, 易跃雄. 大语言模型在病例生成、个性化教学与评估中的研究进展[J]. 医学分子生物学杂志, 2026, 23(1): 97-106.

CONG Shang, BAI Wohan, CHEN Zhong, SU Yu, YI Yuexiong. Research Progress of Large Language Models in Case Generation,Personalized Teaching and Assessment[J]. Journal of Medical Molecular Biology, 2026, 23(1): 97-106.

参考文献

[1] LUCAS H C,UPPERMAN J S,ROBINSON J R.A systematic review of large language models and their implications in medical education[J].Med Educ,2024,58(11):1276-1285.
[2] KAMBIRE J,BARRO S G,STACCINI P.Designing a custom GPT model for medical dialogue simulation[J].Stud Health Technol Inform,2025,328:11-15.
[3] WANG Y M,CHEN T J.ChatGPT surges ahead:GPT-4 has arrived in the arena of medical research[J].J Chin Med Assoc,2023,86(9):784.
[4] SINGHAL K,AZIZI S,TU T,et al.Large language models encode clinical knowledge[J].Nature,2023,620(7972):172-180.
[5] ZHU S,HU W,YANG Z,et al.Qwen-2.5 outperforms other large language models in the chinese national nursing licensing examination:retrospective cross-sectional comparative study[J].JMIR Med Inform,2025,13(1):e63731.
[6] WU J,WANG Z,QIN Y.Performance of DeepSeek-R1 and ChatGPT-4 o on the chinese national medical licensing examination:a comparative study[J].J Med Syst,2025,49(1):74.
[7] ALSAAD R,ABD-ALRAZAQ A,BOUGHORBEL S,et al.Multimodal large language models in health care:applications,challenges,and future outlook[J].J Med Internet Res,2024,26:e59505.
[8] LIU Y,WU F,LIU Z,et al.Can language models be used for real-world urban-delivery route optimization?[J].Innovation(Camb),2023,4(6):100520.
[9] ZHANG S,DONG L,LI X,et al.Instruction tuning for large language models:a survey[J].ArXiv,2023.DOI:10.48550/arXiv.2308.10792.
[10] ZHANG D,DU H,WANG X,et al.CMedRAGBot:a chinese medical chatbot based on graph RAG and large language models[J].Interdiscip Sci,2025.DOI:10.1007/s12539-025-00715-5.
[11] SU J,AHMED M,LU Y,et al.RoFormer:enhanced transformer with rotary position embedding[J].Neurocomputing,2024,568:127063.
[12] SUN S,HU Q,XU F,et al.Medical named entity recognition based on domain knowledge and position encoding[J].BMC Med Inform Decis Mak,2025,25(1):235.
[13] TU T,AZIZI S,DRIESS D,et al.Towards generalist biomedical AI[J].NEJM AI,2024,1(3):AIoa2300138.
[14] LUO R,SUN L,XIA Y,et al.BioGPT:generative pre-trained transformer for biomedical text generation and mining[J].Brief Bioinform,2022,23(6):bbac409.
[15] 陈春,卢巍.虚拟数字人与三维重建在脊柱外科临床教学中的应用探讨[J].中国继续医学教育,2023,15(2):163-167.
CHEN C,LU W.The clinical teaching of spinesurgery by application of virtual digitalhuman and 3D Reconstruction[J.China Contin Med Educ,2023,15(2):163-167.
[16] ZHONG T,ZHU G,HOU C,et al.The influences of ChatGPT on undergraduate students’demonstrated and perceived interdisciplinary learning[J].Educ Inf Technol,2024,29(17):23577-23603.
[17] LI Y,LI Z,ZHANG K,et al.ChatDoctor:a medical chat model fine-tuned on a large language model meta-AI(LLaMA)using medical domain knowledge[J].Cureus,2023,15(6):e40895.
[18] SAVAGE C H,KANHERE A,PAREKH V,et al.Open-source large language models in radiology:a review and tutorial for practical research and clinical deployment[J].Radiology,2025,314(1):e241073.
[19] WANG D,ZHANG S.Large language models in medical and healthcare fields:applications,advances,and challenges[J].Artif Intell Rev,2024,57(11):299.
[20] KURESHI A,LANDMAN S,AHMED M,et al.Addressing disparities in medicine through medical curriculum change:a student perspective[J].J Osteopath Med,2022,122(7):353-357.
[21] GAO Y,LI R,CROXFORD E,et al.Leveraging medical knowledge graphs into large language models for diagnosis prediction:design and application study[J].JMIR AI,2025,4:e58670.
[22] KERNBERG A,GOLD J A,MOHAN V.Using ChatGPT-4 to create structured medical notes from audio recordings of physician-patient encounters:comparative study[J].J Med Internet Res,2024,26(1):e54419.
[23] CHANG E,SUNG S.Use of SNOMED CT in large language models:scoping review[J].JMIR Med Inform,2024,12(1):e62924.
[24] CHU X,WU S,SUN B,et al.Data-driven quantification and intelligent decision-making in traditional chinese medicine:a review[J].Int J Mach Learn Cyber,2024,15(8):3455-3470.
[25] 汪恒,王妍,沈宁,等.人工智能教学病例库在住院医师临床思维培训中的应用[J].医院管理论坛,2024,41(1):60-63.
WANG H,WANG Y,SHEN N,et al.Application of artificialintelligence teaching case databasein clinical thinking training ofresidents[J].Hosp Manage Forum,2024,41(1):60-63.
[26] ZAGHIR J,NAGUIB M,BJELOGRLIC M,et al.Prompt engineering paradigms for medical applications:scoping review[J].J Med Internet Res,2024,26:e60501.
[27] LEE D,PALMER E.Prompt engineering in higher education:a systematic review to help inform curricula[J].Int J Educ Technol High Educ,2025,22(1):7.
[28] SAPUTRA D,DIYASA I G S M,PUSPANINGRUM E Y,et al.Comparing structured prompts for denoising noisy certificate text[J].IJCONSIST,2025,6(2):73-80.
[29] LI X,LI T,WANG M,et al.Navigating the textual maze:enhancing textual analytical skills through an innovative GAI prompt framework[J].IEEE Trans Learn Technol,2025,18:206-215.
[30] WU T,WANG M,XI Y,et al.Intent recognition model based on sequential information and sentence features[J].Neurocomputing,2024,566:127054.
[31] DAGDELEN J,DUNN A,LEE S,et al.Structured information extraction from scientific text with large language models[J].Nat Commun,2024,15(1):1418.
[32] NG K K Y,MATSUBA I,ZHANG P C.RAG in health care:a novel framework for improving communication and decision-making by addressing LLM limitations[J].NEJM AI,2025,2(1):AIra2400380.
[33] GUO G,ZHANG K,HOO B,et al.Structured outputs enable general-purpose LLMs to be medical experts[J].arXiv,2025.DOI:10.48550/arXiv.2503.03194.
[34] SEO J,CHOI D,KIM T,et al.Evaluation framework of large language models in medical documentation:development and usability study[J].J Med Internet Res,2024,26(1):e58329.
[35] LI Y,CHEN J,MA J,et al.Gaze estimation based on convolutional structure and sliding window-based attention mechanism[J].Sensors(basel,Switzerland),2023,23(13):6226.
[36] SHAH N H,ENTWISTLE D,PFEFFER M A.Creation and adoption of large language models in medicine[J].JAMA,2023,330(9):866-869.
[37] HU Y,HU Z,LIU W,et al.Exploring the potential of ChatGPT as an adjunct for generating diagnosis based on chief complaint and cone beam CT radiologic findings[J].BMC Med Inform Decis Mak,2024,24(1):55.
[38] BRÜGGE E,RICCHIZZI S,ARENBECK M,et al.Large language models improve clinical decision making of medical students through patient simulation and structured feedback:a randomized controlled trial[J].BMC Med Educ,2024,24(1):1391.
[39] REDDIG J M,ARORA A,MACLELLAN C J.Generating In-context,personalized feedback for intelligent tutors with large language models[J].Int J Artif Intell Educ,2025,3459-3500.
[40] LI M,YU T.Methodological issues on evaluating agreement between two detection methods by cohen’s kappa analysis[J].Parasit Vectors,2022,15:270.
[41] WANG M,SUN Z,JIA M,et al.Intelligent virtual case learning system based on real medical records and natural language processing[J].BMC Med Inform Decis Mak,2022,22(1):60.
[42] CHEN X,ZHAO Z,ZHANG W,et al.EyeGPT for patient inquiries and medical education:development and validation of an ophthalmology large language model[J].J Med Internet Res,2024,26(1):e60063.
[43] YANG Q,ZUO H,SU R,et al.Dual retrieving and ranking medical large language model with retrieval augmented generation[J].Sci Rep,2025,15(1):18062.
[44] LUO M J,BI S,PANG J,et al.A large language model digital patient system enhances ophthalmology history taking skills[J].NPJ Digit Med,2025,8(1):502.
[45] TU T,SCHAEKERMANN M,PALEPU A,et al.Towards conversational diagnostic artificial intelligence[J].Nature,2025,642(8067):442-450.
[46] WEISMAN D,SUGARMAN A,HUANG Y M,et al.Development of a GPT-4-powered virtual simulated patient and communication training platform for medical students to practice discussing abnormal mammogram results with patients:multiphase study[J].JMIR Form Res,2025,9(1):e65670.
[47] MINTY I,LAWSON J,GUHA P,et al.The use of mixed reality technology for the objective assessment of clinical skills:a validation study[J].BMC Med Edu,2022,22(1):639.
[48] LE T D,TI NGUYEN T,NGUYEN HA V,et al.The impact of LoRA adapters on LLMs for clinical text classification under computational and data constraints[J].IEEE Access,2025,13:109365-109377.
[49] ABOUAMMOH N,ALHASAN K,ALJAMAAN F,et al.Perceptions and earliest experiences of medical students and faculty with ChatGPT in medical education:qualitative study[J].JMIR Med Edu,2025,11(1):e63400.
[50] BUSCH F,HOFFMANN L,RUEGER C,et al.Current applications and challenges in large language models for patient care:a systematic review[J].Commun Med(Lond),2025,5(1):26.

大语言模型在病例生成、个性化教学与评估中的研究进展

Research Progress of Large Language Models in Case Generation,Personalized Teaching and Assessment

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价