Machine Learning (ML) has garnered considerable attention from researchers and practitioners as a new and adaptable tool for disease diagnosis. With the advancement of ML and the proliferation of papers and research in this field, a complete examination of Machine Learning-Based Disease Diagnosis (MLBDD) is required. From a bibliometrics standpoint, this article comprehensively studies MLBDD papers from 2012 to 2021. Consequently, with particular keywords, 1710 papers with associate information have been extracted from the Scopus and Web of Science (WOS) database and integrated into the excel datasheet for further analysis. First, we examine the publication structures based on yearly publications and the most productive countries/regions, institutions, and authors. Second, the co-citation networks of countries/regions, institutions, authors, and articles are visualized using R-studio software. They are further examined in terms of citation structure and the most influential ones. This article gives an overview of MLBDD for researchers interested in the subject and conducts a thorough and complete study of MLBDD for those interested in conducting more research in this field.
翻译:机器学习(ML)作为疾病诊断的适应性新工具,引起了研究人员和从业者的大量关注。随着ML的进步和该领域论文和研究的激增,需要对机器学习-疾病诊断(MLBDD)进行彻底检查。从生物量学角度,这一文章全面研究了2012年至2021年MLBD文件。因此,用特殊关键词,从Scopus和Web科学数据库中提取了1710份连带信息的文件,并将其纳入优秀数据表,供进一步分析。首先,我们根据年度出版物和最有成果的国家/区域、机构和作者对出版物结构进行审查。第二,利用R-studio软件将国家/区域、机构、作者和文章的共同引用网络进行视觉化,进一步从引用结构和最有影响力的方面加以审视。文章概述了对这一主题感兴趣的研究人员的MLBDDD,并对MLBDDD进行彻底和彻底的研究,供有兴趣在这一领域进行更多研究的研究人员使用。