人工智能赋能外科手术基础技能教学：模型构建与评估体系的研究

李由; 冉志川; 王小寒; 周静; 郭洪峰; 段然

doi:10.3760/cma.j.cn116021-20240922-02183

您当前的位置：

首页 >

文章列表页 >

人工智能赋能外科手术基础技能教学：模型构建与评估体系的研究

临床教学 | 更新时间：2026-06-17

- 人工智能赋能外科手术基础技能教学：模型构建与评估体系的研究
- Empowering the teaching of basic surgical skills with artificial intelligence technology: establishment of assessment models and skill enhancement
- 中华医学教育探索杂志 2026年25卷第6期页码：734-739
- 作者机构：
  
  1.重庆大学附属沙坪坝医院信息科，重庆 400030
  2.重庆大学附属沙坪坝医院科教科，重庆 400030
  3.重庆医药高等专科学校临床医学院，重庆 401331
  4.陆军军医大学第一附属医院外科手术学教研室，重庆 400038
  5.重庆大学附属人民医院信息处，重庆 401147
- 作者简介：
  
  段然，Email：1261103@qq.com
- 基金信息：
  
  2023年中央高校基本科研业务费医工融合项目(2023CDJYGRH-YB18);2023年重庆医药职业教育集团教科研项目(CQZJ202311)
- DOI：10.3760/cma.j.cn116021-20240922-02183
  中图分类号： R33
- 收稿：2024-09-22，
  
  纸质出版：2026-06-20
- 稿件说明：
移动端阅览
李由, 冉志川, 王小寒, 等. 人工智能赋能外科手术基础技能教学：模型构建与评估体系的研究[J]. 中华医学教育探索杂志, 2026, 25(6): 734-739.

Li You, Ran Zhichuan, Wang Xiaohan, et al. Empowering the teaching of basic surgical skills with artificial intelligence technology: establishment of assessment models and skill enhancement[J]. Chinese Journal of Medical Education Research, 2026, 25(6): 734-739.
李由, 冉志川, 王小寒, 等. 人工智能赋能外科手术基础技能教学：模型构建与评估体系的研究[J]. 中华医学教育探索杂志, 2026, 25(6): 734-739. DOI： 10.3760/cma.j.cn116021-20240922-02183.

Li You, Ran Zhichuan, Wang Xiaohan, et al. Empowering the teaching of basic surgical skills with artificial intelligence technology: establishment of assessment models and skill enhancement[J]. Chinese Journal of Medical Education Research, 2026, 25(6): 734-739. DOI： 10.3760/cma.j.cn116021-20240922-02183.

摘要

现有《外科手术学》在基础操作方面存在传统理论教学与实践演练失衡，实践教学训练与评估机制不够完善等问题。随着人工智能、虚拟现实等技术在医学教育信息化不断发展，临床医学中视频目标检测和动作捕捉识别技术得到广泛应用，将该技术应用于手术打结技能操作的融合教学中，对外科手术学基础实践教学中的打结、切开缝合、止血结扎以及无菌技术等“教”与“学”的过程提供标准评估，并对操作数据进行分析赋能，采集教师操作时间、动作关键帧和流畅度等，形成手部轨迹动作、手术器械的标准模型，得到关于外科手术学基础操作中手术打结操作的动作识别模型和器械识别模型。将在模拟手术训练中的操作数据带入模型综合分析，通过辅助手术教学系统实时分析其考核成绩、手术时间、易错点，建立手术打结教学评估标准，人工智能大模型的分析与反馈能更好地满足教学与实践结合需求、培养临床外科医生手术基本操作能力。

Abstract

The existing "Surgery" has issues in basic operations

such as an imbalance between traditional theoretical teaching and practical drills. Moreover

the training and evaluation mechanisms for practical teaching are not fully developed.With the continuous progress of information technology in medical education

including the application of artificial intelligence and virtual reality

video object detection and motion capture recognition technologies have been widely utilized in clinical medicine. Applying these technologies to the integrated teaching of surgical knot-tying skills can provide a standardized evaluation for the "teaching" and "learning" processes in basic practical teaching of surgery. This includes aspects such as knot-tying

incision and suture

hemostasis and ligation

and aseptic techniques.Furthermore

by analyzing and leveraging the operation data

key parameters such as the teacher's operation time

critical action frames

and smoothness can be collected. This enables the establishment of standard models for hand trajectory movements and surgical instruments

leading to the development of action recognition models and instrument recognition models for surgical knot-tying operations in basic surgical procedures.When the operation data from simulated surgical training is incorporated into these models for comprehensive analysis

the system can analyze assessment scores

surgical time

and error-prone areas in real time through an auxiliary surgical teaching system. This helps to establish teaching evaluation criteria for surgical knot-tying. The analysis and feedback provided by artificial intelligence large models can better meet the requirements of integrating teaching with practice and contribute to cultivating the basic surgical operation capabilities of clinical surgeons.

关键词

Keywords

references

Davis CR , Toll EC , Bates AS , et al . Surgical and procedural skills training at medical school—a national review [J ] . Int J Surg , 2014 , 12 ( 8 ): 877 - 882 . DOI: 10.1016/j.ijsu.2014.05.069 http://dx.doi.org/10.1016/j.ijsu.2014.05.069 .

Fergusson SJ , Sedgwick DM , Ntakiyiruta G , et al . The basic surgical skills course in sub-Saharan Africa: an observational study of effectiveness [J ] . World J Surg , 2018 , 42 ( 4 ): 930 - 936 . DOI: 10.1007/s00268-017-4274-2 http://dx.doi.org/10.1007/s00268-017-4274-2 .

Gonzalez-Navarro AR , Quiroga-Garza A , Acosta-Luna AS , et al . Comparison of suturing models: the effect on perception of basic surgical skills [J ] . BMC Med Educ , 2021 , 21 ( 1 ): 250 . DOI: 10.1186/s12909-021-02692-x http://dx.doi.org/10.1186/s12909-021-02692-x .

Emmanuel T , Nicolaides M , Theodoulou I , et al . Suturing skills for medical students: a systematic review [J ] . In Vivo , 2021 , 35 ( 1 ): 1 - 12 . DOI: 10.21873/invivo.12226 http://dx.doi.org/10.21873/invivo.12226 .

朱磊，闫敏，孙璟川，等 . 评价与反馈法在提高《外科手术学基础》课程授课效果中的探究 [J ] . 中华医学教育探索杂志， 2020 ， 19 （ 12 ）： 1422 - 1426 . DOI: 10.3760/cma.j.cn116021-20191206-00336 http://dx.doi.org/10.3760/cma.j.cn116021-20191206-00336 .

王浩然，乔鹏飞，姚磊 . Kolb经验学习理论在《外科手术学基础》课程教学中的应用研究 [J ] . 中华医学教育探索杂志， 2025 ， 24 （ 9 ）： 1223 - 1229 . DOI: 10.3760/cma.j.cn116021-20241008-02112 http://dx.doi.org/10.3760/cma.j.cn116021-20241008-02112 .

盛丽芳，岳健 . 推进继续医学教育信息化建设的思考 [J ] . 继续医学教育， 2011 ， 25 （ 8 ）： 8 - 10 .

何茂章，王姝妹，丁瑞培，等 . 基于新医科与AI技术融合的医学教学模式探讨 [J ] . 湘南学院学报（医学版）， 2024 ， 26 （ 3 ）： 63 - 66 . DOI: 10.16500/j.cnki.1673-498x.2024.03.015 http://dx.doi.org/10.16500/j.cnki.1673-498x.2024.03.015 .

陈凯泉，吴玥玥，刘璐 . 人工智能赋能“4C能力” 培养的路径分析与实践探索：以IBM Watson系统为例 [J ] . 中国教育信息化， 2019 ， 25 （ 21 ）： 54 - 59 . DOI: 10.3969/j.issn.1673-8454.2019.11.014 http://dx.doi.org/10.3969/j.issn.1673-8454.2019.11.014 .

卫荣，马锋，侯梦薇，等 . 人工智能在医学教育领域的应用研究 [J ] . 医学教育研究与实践， 2017 ， 25 （ 6 ）： 835 - 838 . DOI: 10.13555/j.cnki.c.m.e.2017.06.005 http://dx.doi.org/10.13555/j.cnki.c.m.e.2017.06.005 .

Prechtl HF . General movement assessment as a method of developmental neurology: new paradigms and their consequences. The 1999 Ronnie MacKeith lecture [J ] . Dev Med Child Neurol , 2001 , 43 ( 12 ): 836 - 842 . DOI: 10.1017/s0012162201001529 http://dx.doi.org/10.1017/s0012162201001529 .

Poewe W , Seppi K , Tanner CM , et al . Parkinson disease [J ] . Nat Rev Dis Primers , 2017 , 3 : 17013 . DOI: 10.1038/nrdp.2017.13 http://dx.doi.org/10.1038/nrdp.2017.13 .

Lam WWT , Tang YM , Fong KNK . A systematic review of the applications of markerless motion capture (MMC) technology for clinical measurement in rehabilitation [J ] . J Neuroeng Rehabil , 2023 , 20 ( 1 ): 57 . DOI: 10.1186/s12984-023-01186-9 http://dx.doi.org/10.1186/s12984-023-01186-9 .

Alarcón-Aldana AC , Callejas-Cuervo M , Bo APL . Upper limb physical rehabilitation using serious videogames and motion capture systems: a systematic review [J ] . Sensors (Basel) , 2020 , 20 ( 21 ): 5989 . DOI: 10.3390/s20215989 http://dx.doi.org/10.3390/s20215989 .

黄新瑞，黄河颂，黄渝川，等 . 基于视频的动作智能识别在医学中的应用 [J ] . 中国医学物理学杂志， 2024 ， 41 （ 1 ）： 1 - 7 . DOI: 10.3969/j.issn.1005-202X.2024.01.001 http://dx.doi.org/10.3969/j.issn.1005-202X.2024.01.001 .

Karpathy A , Toderici G , Shetty S , et al . Large-scale video classification with convolutional neural networks [C ] // 2014 IEEE Conference on Computer Vision and Pattern Recognition , June 23-28, 2014 , Columbus, OH , USA . IEEE , 2014 : 1725 - 1732 .

陈迪，陈云虹，叶青，等 . 融合k-means与多维特征分析的生物医学图像分类算法 [J ] . 信息技术， 2024 ， 48 （ 7 ）： 65 - 70 . DOI: 10.13274/j.cnki.hdzj.2024.07.011 http://dx.doi.org/10.13274/j.cnki.hdzj.2024.07.011 .

魏秋月，刘雨帆 . 基于Kinect和改进DTW算法的动态手势识别 [J ] . 传感器与微系统， 2021 ， 40 （ 11 ）： 127 - 130 . DOI: 10.13873/J.1000-9787(2021)11-0127-04 http://dx.doi.org/10.13873/J.1000-9787(2021)11-0127-04 .

钟学斌，翁立壮 . 基于运动检测的人体骨骼关键点检测算法 [J ] . 工业控制计算机， 2022 ， 35 （ 6 ）： 62 - 63 .

Laptev I . On space-time interest points [J ] . Int J Comput Vis , 2005 , 64 ( 2 ): 107 - 123 . DOI: 10.1007/s11263-005-1838-7 http://dx.doi.org/10.1007/s11263-005-1838-7 .

Olshausen BA , Field DJ . Emergence of simple-cell receptive field properties by learning a sparse code for natural images [J ] . Nature , 1996 , 381 ( 6583 ): 607 - 609 . DOI: 10.1038/381607a0 http://dx.doi.org/10.1038/381607a0 .

Olshausen BA , Field DJ . Sparse coding with an overcomplete basis set: a strategy employed by V1? [J ] . Vision Res , 1997 , 37 ( 23 ): 3311 - 3325 . DOI: 10.1016/s0042-6989(97)00169-7 http://dx.doi.org/10.1016/s0042-6989(97)00169-7 .

Chawla NV , Bowyer KW , Hall LO , et al . SMOTE: synthetic minority over-sampling technique [J ] . Jair , 2002 , 16 : 321 - 357 . DOI: 10.1613/jair.953 http://dx.doi.org/10.1613/jair.953 .

吴晓丽，海杰，马秀珍，等 . 人工智能辅助手术系统对医院外科手术的影响与应用研究 [J ] . 中国数字医学， 2018 ， 13 （ 10 ）： 20 - 22 . DOI: 10.3969/j.issn.1673-7571.2018.10.007 http://dx.doi.org/10.3969/j.issn.1673-7571.2018.10.007 .

江哲涵，奉世聪，王维民 . 人工智能生成内容在医学教育中的应用、挑战与展望 [J ] . 中国教育信息化， 2024 ， 30 （ 8 ）： 29 - 40 . DOI: 10.3969/j.issn.1673-8454.2024.08.003 http://dx.doi.org/10.3969/j.issn.1673-8454.2024.08.003 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

人工智能赋能医学职业素养教育的内涵、实践和挑战

AI与教师在医学呼吸系统试题解析撰写中的优劣势比较

医学教学对象人工智能使用现状及伦理认知调查研究

智能体赋能模拟导尿在临床实习教学中的应用

静脉血栓栓塞症智能知识库的构建及在医学教育中的应用评价