Science Mapping Analysis of Artificial Intelligence Applied in Stroke Research

doi:10.3969/j.issn.1673-5765.2022.12.015

Abstract

Abstract: Objective To construct and visualize the knowledge structure and development trend of artificial intelligence (AI) application in stroke research based on a science mapping analysis.
Methods Web of Science Core Collection was retrieved for the literatures on AI and stroke from January 1985 to March 2022. The publication date, countries or regions, institutions, authors, and research domains were analyzed. CiteSpace was used to perform bibliometrics analysis including key words co-occurring, co-citation and cluster analysis, to generate visualized science mapping.
Results A total of 924 articles from 73 countries or regions were included in this analysis, published from 1999 to 2022. The countries that published the most were USA (n=274, 29.7%) and China (n=255, 27.6%). Of the top 10 institutions publishing papers, 6 were from USA and 2 from China. The research of AI application in stroke increased rapidly since 2012, which involved multiple disciplines and fields, including engineering and computer science, as well as neurology, surgery, radiology and etc. Based on the science mapping analysis, the main research in the field of stroke were the application of AI in stroke classification, treatment decision, prognosis and rehabilitation. The application of AI can stimulate the development of AI theory and technology. Applying more advanced and appropriate AI to improve the basic and clinical research of stroke was the research trend in this field.
Conclusions The visualized science mapping analysis can help researchers and physicians better understand the development tread of AI application in stroke research, to provide reference for future research in the field of stroke.

Key words: Artificial intelligence; Stroke; Bibliometrics; Science mapping; Machine learning

摘要： 目的通过知识可视化分析方法，对人工智能技术用于卒中的研究构建知识图谱，探索知识结构，总结该领域的研究现状、热点和趋势。
方法检索Web of Science核心合集中1985年1月-2022年3月有关人工智能和卒中相关的文献。对文献发表时间、国家/地区、机构、作者、研究领域进行分析。并利用CiteSpace软件进行文献计量学分析，包括关键词共现分析、引文共引及聚类分析，并绘制可视化图谱。
结果通过检索和筛查，共有73个国家和地区的924篇文献纳入分析，发表时间跨度为1999-2022年。发表文献最多的是美国（274篇，29.7%）和中国（255篇，27.6%），发文前10位的机构中有6所来自美国，只有2所来自中国。人工智能技术用于卒中的研究从2012年开始快速增长，涉及多学科、多领域，包括人工智能相关的理论和技术研究，如工程学、计算机科学等，也包括卒中相关的神经科学、外科学、影像医学等。通过知识图谱分析，该领域主要的研究内容是人工智能应用于卒中的分类、治疗方式选择、预后及康复研究。在应用人工智能技术的同时，也会激发人工智能理论和技术的研究发展。应用更具潜力、更恰当的人工智能技术提升各种类型卒中的基础和临床研究是本领域的研究趋势。
结论通过知识图谱分析该领域的关键研究、发展脉络，有助于科研人员和临床医师更好地理解人工智能用于卒中研究的现状和发展趋势，为未来的研究和临床实践提供参考。

关键词: 人工智能; 卒中; 文献计量学; 科学图谱; 机器学习

JIANG Lin, LI Jing. Science Mapping Analysis of Artificial Intelligence Applied in Stroke Research [J]. Chinese Journal of Stroke, 2022, 17(12): 1372-1380.

蒋林, 李靖. 基于知识图谱分析人工智能用于卒中研究的现状及趋势 [J]. 中国卒中杂志, 2022, 17(12): 1372-1380.

References

[1] 《中国脑卒中防治报告》编写组. 我国脑卒中防治仍面临巨大挑战——《中国脑卒中防治报告2018》概要[J]. 中国循环杂志，2019，34（2）：105-119.
[2] WANG W Z，JIANG B，SUN H X，et al. Prevalence，incidence，and mortality of stroke in China：results from a nationwide population-based survey of 480 687 adults[J]. Circulation，2017，135（8）：759-771.
[3] CHEN C M. CiteSpace Ⅱ：Detecting and visualizing emerging trends and transient patterns in scientific literature[J]. J Am Soc Inf Sci Tec，2006，57（3）：359-377.
[4] SMALL H. Co-citation in the scientific literature：a new measure of the relationship between two documents[J].J Am Soc Inf Sci Tec，1973，24（4）：265-269.
[5] CHEN C M. Science mapping：a systematic review of the literature[J]. JDIS，2017，2（2）：1-40.
[6] NOGUEIRA R G，JADHAV A P，HAUSSEN D C，et al. Thrombectomy 6 to 24 hours after stroke with a mismatch between deficit and infarct[J]. N Eng J Med，2018，378（1）：11-21.
[7] ASADI H，DOWLING R，YAN B，et al. Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy [J/OL]. PLoS One，2014，9（2）：e88225[2022-04-02]. https://doi.org/10.1371/journal.pone.0088225.
[8] FENG R，BADGELEY M，MOCCO J，et al. Deep learning guided stroke management：a review of clinical applications[J]. J Neurointerv Surg，2018，10（4）：358-362.
[9] 顾险峰. 人工智能的历史回顾和发展现状[J]. 自然杂志，2016，38（3）：157-166.
[10] LANSBERG M G，STRAKA M，KEMP S，et al. MRI profile and response to endovascular reperfusion after stroke（DEFUSE 2）：a prospective cohort study[J]. Lancet Neurol，2012，11（10）：860-867.
[11] ALBERS G W，MARKS M P，KEMP S，et al. Thrombectomy for stroke at 6 to 16 hours with selection by perfusion imaging[J]. N Engl J Med，2018，378（8）：708-718.
[12] MONTEIRO M，FONSECA A C，FREITAS A T，et al. Using machine learning to improve the prediction of functional outcome in ischemic stroke patients[J]. IEEE/ACM Trans Comput Biol Bioinform，2018，15（6）：1953-1959.
[13] YU Y，GUO D，LOU M，et al. Prediction of hemorrhagic transformation severity in acute stroke from source perfusion MRI[J]. IEEE trans Biomed Eng，2018，65（9）：2058-2065.
[14] MURRAY N M，UNBERATH M，HAGER G D，et al. Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions：a systematic review[J]. J Neurointerv Surg，2020，12（2）：156-164.
[15] POWERS W J，RABINSTEIN A A，ACKERSON T，et al. Guidelines for the early management of patients with acute ischemic stroke：2019 update to the 2018 guidelines for the early management of acute ischemic stroke：a guideline for healthcare professionals from the American Heart Association/American Stroke Associatio[J/OL]. Stroke，2019，50（12）：e344-e418[2022-04-02]. https://doi.org/10.1161/str.0000000000000211.
[16] RONNEBERGER O，FISCHER P，BROX T. U-Net：convolutional networks for biomedical image segmentation[J/OL]. MICCA，2015，9351：234-241[2022-04-02]. https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/.
[17] KAMNITSAS K，LEDIG C，NEWCOMBE V F J，et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation[J/OL]. Med Image Anal，2017，36：61-78[2022-04-02]. https://doi.org/10.1016/j.media.2016.10.004.
[18] ZHANG R Z，ZHAO L，LOU W T，et al. Automatic segmentation of acute ischemic stroke from DWI using 3-D fully convolutional denseNets[J]. IEEE Trans Med Imaging，2018，37（9）：2149-2160.
[19] SHNEIDER A M. Four stages of a scientific discipline：four types of scientist[J]. Trends Biochem Sci，2009，34（5）：217-223.