培养医学生机器学习的实践素养

基础医学与临床 ›› 2021, Vol. 41 ›› Issue (7): 1071-1075.

培养医学生机器学习的实践素养

刘大路, 李静^*

空军军医大学军事预防医学系辐射防护医学教研室特殊作业环境危害评估与防治教育部重点实验室,陕西西安710032

收稿日期:2020-10-28 修回日期:2021-04-01 出版日期:2021-07-05 发布日期:2021-06-17
通讯作者: *jingli@fmmu.edu.cn
基金资助:
国家自然科学基金(32000876);陕西省自然科学研究计划(2019JQ-437)

Cultivating practical literacy of machine learning for medical students

LIU Da-lu, LI Jing^*

Department of Radiation Medicine and Protection, Ministry of Education Key Lab of Hazard Assessment and Control in Special Operational Environment, School of Military Preventive Medicine, Air Force Medical University, Xi'an 710032, China

Received:2020-10-28 Revised:2021-04-01 Online:2021-07-05 Published:2021-06-17
Contact: *jingli@fmmu.edu.cn

摘要/Abstract

摘要： 机器学习(ML)正快速发展为可辅助特定医学决策的临床人工智能(AI)系统。但是,目前ML面临临床数据不均一性高、临床任务机器转化难度大等限制因素。未来“智能”医生应当主导围绕临床目标和临床数据的医学和AI的创新。因此,在医学生实习或住院医师培训中以案例学习的形式,加入对ML所需最小样本量的估算和数据高级特征的临床解读等素养的实践训练,有利于培养医学生具备智能辅助诊疗的临床思维,创新更高效的智能医学决策体系。

关键词: 机器学习, 医学教育, 临床数据

Abstract: Machine learning (ML) is rapidly evolving into clinical artificial intelligence (AI) systems that can assist specific medical decisions. However, at present, ML faces the limitation factors such as high heterogeneity of clinical data and difficulty in data analysis for facilitating clinical performance. Future, “intelligent” doctors should dominate innovations in medicine and AI engineering around clinical mission and clinical data. Therefore, in the form of medical student internship or resident training case learning, adding practical training such as estimation of the minimum sample size required for ML and clinical interpretation of advanced characteristics of data is conducive to cultivating medical students with clinical capacity of reasoning to practice of computer-based diagnosis and treatment, and to develope a more efficient intelligent medical decision-making system.

Key words: machine learning, medical education, clinical data

中图分类号:

R445

刘大路, 李静. 培养医学生机器学习的实践素养[J]. 基础医学与临床, 2021, 41(7): 1071-1075.

LIU Da-lu, LI Jing. Cultivating practical literacy of machine learning for medical students[J]. Basic & Clinical Medicine, 2021, 41(7): 1071-1075.

参考文献

[1]Coles SL. The application of artificial intelligence to medicine[J]. Future,1977,9:315-323.
[2]Tu X, Xie M, Gao J, et al. Automatic categorization and scoring of solid, part-solid and non-solid pulmonary nodules in ct images with convolutional neural network[J]. Sci Rep, 2017, 7: 8533. doi: 10.1038/s41598-017-08040-8.
[3]Takahashi H, Tampo H, Arai Y, et al. Applying artificial intelligence to disease staging: Deep learning for improved staging of diabetic retinopathy[J]. PLoS One, 2017,12: e0179790. doi: 10.1371/journal.pone.0179790.
[4]Choi JY, Yoo TK, Seo JG, et al. Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database[J]. PLoS One, 2017, 12: e0187336. doi: 10.1371/journal.pone.0187336.
[5]Kong X, Gong S, Su L, et al. Automatic detection of acromegaly from facial photographs using machine learning methods[J]. EBioMedicine, 2018, 27: 94-102.
[6]Han L, Kamdar MR. Mri to mgmt: Predicting methyla-tion status in glioblastoma patients using convolutional recurrent neural networks[J]. Pac Symp Biocomput, 2018, 23: 331-342.
[7]Ye F, Yu Y. Advances in radiogenomics in precision radiotherapy[J]. Basic Clin Med, 2020, 40: 696-700.
[8]Vandenberghe ME, Scott ML, Scorer PW, et al. Relev-ance of deep learning to facilitate the diagnosis of her2 status in breast cancer[J]. Sci Rep, 2017, 7: 45938. doi: 10.1038/srep45938.
[9]Xu Y, Jia Z, Wang LB, et al. Large scale tissue histopathology image classification, segmentation, and visualiza-tion via deep convolutional activation features[J]. BMC Bioinformatics, 2017, 18: 281. doi: 10.1186/s12859-017-1685-x.
[10]Meng D, Cao G, Duan Y, et al. Tongue images classification based on constrained high dispersal network[J]. Evid Based Complement Alternat Med, 2017, 2017: 7452427. doi: 10.1155/2017/7452427.
[11]Wang Y, Tang F, Wang YF, et al. Content and approa-ches of professional competence development in eight-year program medical students of china[J]. Basic Med Sci Clin, 2014, 34: 573-576.
[12]Geraci J, Wilansky P, de Luca V, et al. Applying deep neural networks to unstructured text notes in electronic medical records for phenotyping youth depression[J]. Evid Based Ment Health, 2017, 20: 83-87.
[13]Xie H, Xue YQ, Liu P, et al. Multi-parameter gene expression profiling of peripheral blood for early detection of hepatocellular carcinoma[J]. World J Gastroenterol, 2018, 24: 371-378.
[14]Chen S, Bai X, Wang SR, et al. Training on diagnostic resoning for rare disease:Dwarfism case based clinical teaching[J]. Basic Clin Med, 2021:287-289.

[1]	王强, 周雅轩, 吴东. 依托于翻转课堂模式的医学教育题库建设及优化[J]. 基础医学与临床, 2024, 44(9): 1324-1327.
[2]	胡川丽, 贺晓松, 赵江, 李华. 基于机器学习算法的心力衰竭预测模型[J]. 基础医学与临床, 2024, 44(6): 845-852.
[3]	王含必, 陈洁, 张志媛, 赵春霞, 武童, 孙爱军. 合理设立考试内容及节点对培训效果的积极影响[J]. 基础医学与临床, 2023, 43(8): 1326-1329.
[4]	张晓彤, 徐凯峰. 人工智能在呼吸内科教学中的应用[J]. 基础医学与临床, 2023, 43(8): 1330-1333.
[5]	贾楠, 檀厚睿, 严毅飞, 何仲, 姚顺宇, 王颖轶. 北京协和医学院“精准治疗下的肿瘤学”课程教学实践[J]. 基础医学与临床, 2023, 43(12): 1896-1900.
[6]	樊佳赛, 杜艺菲, 许佳颖, 陈思臻, 高永桧, 任景怡. 基于中医证候和机器学习构建慢性心力衰竭中西医结合预后模型[J]. 基础医学与临床, 2022, 42(8): 1169-1175.
[7]	王含必, 王涛, 邓成艳. 八年制临床医学专业妇科内分泌学教学方法的调查[J]. 基础医学与临床, 2022, 42(5): 840-843.
[8]	裘耀扬, 桂家辉, 黄林, 虎学强, 李勤. 血管内光学相干层析成像技术在冠状动脉粥样硬化斑块检测方面的应用[J]. 基础医学与临床, 2022, 42(3): 360-365.
[9]	顾潇, 潘周娴, 陈适, 沈震, 牛璐璐, 潘慧, 姚勇. 3D打印可拆卸垂体瘤切除模型的真实性评估[J]. 基础医学与临床, 2022, 42(2): 340-344.
[10]	陈明扬, 蔡紫庭, 薛鹏, 江宇, 乔友林. 人工智能在肿瘤研究和临床中的应用[J]. 基础医学与临床, 2022, 42(11): 1637-1643.
[11]	白皙, 陈适, 李玥, 胡亚, 景泉, 王迁, 潘慧. 标准化病人与临床教学查房结合的价值[J]. 基础医学与临床, 2022, 42(10): 1634-1636.
[12]	韩诗远, 李永宁, 高俊. 神经外科专业学位研究生的科研诚信建设[J]. 基础医学与临床, 2022, 42(10): 1626-1629.
[13]	赵峻, 张荣华, 潘慧, 罗林枝. 中美高等医学教育的对比及启示[J]. 基础医学与临床, 2021, 41(9): 1392-1395.
[14]	王亚红, 张莉, 王莹, 张一休, 武玺宁, 高璐滢, 陶葸茜, 李建初. 分层分级的进阶式培养模式在超声住院医师规范化培训中的应用[J]. 基础医学与临床, 2021, 41(8): 1220-1223.
[15]	杨诗婕, 徐协群. 新型冠状病毒肺炎疫情下医学生的参与及其启示[J]. 基础医学与临床, 2021, 41(8): 1234-1237.