目的 探寻和解析我国机器学习相关学位论文的基本情况及其研究热点。方法 基于中国知网、万方数据知识服务平台,检索时间自建库起至2023年2月14日,检索关键词包含“医学”和“机器学习”的所有全文发表的中文学位论文。采用Microsoft Excel 2016软件进行数据整理,提取的数据包括学位论文收录年份、学位授予单位、导师、被引频次信息。运用VOS viewer软件对高频关键词进行可视化分析。结果 共检索出299所高校机器学习相关学位论文2 662篇,论文数量排名前10位的学校论文数量之和占全部论文的29.9%(797/2 662)。学位论文指导教师共2 533名,论文被引频次分布为0至204次。在所有已经发表的学位论文中有46.2%(1 229/2 662)的论文未曾被引用。学位论文的研究主题主要包括医学影像的辅助诊断、电子病历文本提取、医学图像分割算法优化、多模型高效准确利用等。结论 医学专业机器学习相关学位论文及其所属单位和导师数量均较多,但论文质量有待提高,论文热点相对集中于医学辅助诊断方面。
Objective To find and analyze the research trends and future research directions of academic dissertations of medical machine learning in China. Methods All academic dissertations on medical machine learning published in full text in Chinese were obtained by searching the CNKI and Wanfang database. The retrieval period was from the establishment of the database to February 14, 2023. The search keywords included ″medicine″ and ″machine learning″. Microsoft Excel 2016 software was used to organize data from retrieved records, including the year of thesis inclusion, institution of degree, supervisor and cited frequency. VOS viewer software was used to visualize and analyze the high-frequency keywords. Results A total of 2 662 academic dissertations in the field of machine learning were retrieved from 299 universities. The combined number of dissertations from the top 10 universities accounted for 29.9%(797/2 662) of all the dissertations. There were 2 533 academic dissertation supervisors, and the citation frequency of the dissertations ranged from 0 to 204 times. However, 46.2%(1 229/2 662) of the published dissertations had never been cited. The research topics of the dissertations mainly included assisted diagnosis in medical imaging, extraction of electronic medical record texts, optimization of medical image segmentation algorithms, and efficient and accurate utilization of multimodal models. Conclusions There is a relatively large number of machine learning-related dissertations in the field of medicine, as well as a significant number of institutions and supervisors. However, the quality of the dissertations needs improvement, and the research hotspots are relatively concentrated in the area of medical assisted diagnosis.
[1] Choi RY, Coyner AS, Kalpathy-Cramer J, et al. Introduction to machine learning, neural networks, and deep learning[J]. Transl Vis Sci Technol, 2020,9(2):14. DOI: 10.1167/tvst.9.2.14.
[2] 纪守领, 李进锋, 杜天宇, 等. 机器学习模型可解释性方法、应用与安全研究综述[J].计算机研究与发展,2019,56(10):2071-2096. DOI: 10.7544/issn1000-1239.2019.20190540.
[3] 张润, 王永滨. 机器学习及其算法和发展研究[J].中国传媒大学学报(自然科学版),2016,23(2):10-18,24. DOI: 10.3969/j.issn.1673-4793.2016.02.002.
[4] Zhu Y, Li JJ, Reng J, et al. Global trends of pseudomonas aeruginosa biofilm research in the past two decades: a bibliometric study[J]. Microbiologyopen, 2020,9(6):1102-1112. DOI: 10.1002/mbo3.1021.
[5] Mi J, Zhang L, Sun W, et al. Research hotspots and new trends in the impact of resistance training on aging, bibliometric and visual analysis based on CiteSpace and VOSviewer[J]. Front Public Health, 2023, 11: 1133972.
[6] 刘雅娟, 王岩. 用文献计量学评价基础研究的几项指标探讨——论文、引文和期刊影响因子[J].科研管理,2000,21(1):93-98. DOI: 10.3969/j.issn.1000-2995.2000.01.014.
[7] 谭向龙, 赵之明. 机器学习在医学中的应用现状[J].中华腔镜外科杂志(电子版),2020,13(1):61-64. DOI: 10.3877/cma.j.issn.1674-6899.2020.01.015.
[8] 施盛威. 新工科环境下人工智能专业人才培养策略研究[J].电子元器件与信息技术,2023,7(1):133-136. DOI: 10.19772/j.cnki.2096-4455.2023.1.031.
[9] Deo RC. Machine learning in medicine[J]. Circulation, 2015,132(20):1920-1930. DOI: 10.1161/CIRCULATIONAHA.115.001593.
[10] 殷晓丽, 郭立, 门寒隽, 等. 我国医学教育研究的现状及反思——基于5本主要医学教育学术刊物2007年刊载论文的分析[J].复旦教育论坛,2011,9(1):87-91. DOI: 10.3969/j.issn.1672-0059.2011.01.018.
[11] Handelman GS, Kok HK, Chandra RV, et al. eDoctor: machine learning and the future of medicine[J]. J Intern Med, 2018,284(6):603-619. DOI: 10.1111/joim.12822.
[12] 吴越, 翟双庆, 袁娜, 等. 我国医学教育研究热点与发展趋势分析[J].中华医学教育杂志,2020,40(11):853-857. DOI: 10.3760/cma.j.cn115259-20200309-00289.
[13] Binvignat M, Pedoia V, Butte AJ, et al. Use of machine learning in osteoarthritis research: a systematic literature review[J]. RMD Open, 2022,8(1):e001998. DOI: 10.1136/rmdopen-2021-001998.
[14] 肖焕辉, 袁程朗, 冯仕庭, 等. 基于深度学习的癌症计算机辅助分类诊断研究进展[J].国际医学放射学杂志,2019,42(1):22-25,58. DOI: 10.19300/j.2019.Z6366zt.
[15] Abedin J, Antony J, McGuinness K, et al. Predicting knee osteoarthritis severity: comparative modeling based on patient′s data and plain X-ray images[J]. Sci Rep, 2019,9(1):5761. DOI: 10.1038/s41598-019-42215-9.
[16] Schwartz AJ, Clarke HD, Spangehl MJ, et al. Can a convolutional neural network classify knee osteoarthritis on plain radiographs as accurately as fellowship-trained knee arthroplasty surgeons?[J]. J Arthroplasty, 2020,35(9):2423-2428. DOI: 10.1016/j.arth.2020.04.059.
[17] Su K, Yuan X, Huang Y, et al. Improved prediction of knee osteoarthritis by the machine learning model XGBoost[J]. Indian J Orthop, 2023,57(10):1667-1677. DOI: 10.1007/s43465-023-00936-0.
[18] 孔祥溢,王任直. 人工智能及在医疗领域的应用[J]. 医学信息学杂志,2016,37(11):1-5. DOI:10.3969/j.issn.1673-6036.2016.11.001.
[19] 张荣,李伟平,莫同. 深度学习研究综述[J]. 信息与控制,2018,47(4):385-397,410. DOI:10.13976/j.cnki.xk.2018.8091.
