Research output of artificial intelligence in arrhythmia from 2004 to 2021: a bibliometric analysis

Journal of Thoracic Disease

article

Junlin Huang¹  Yang Liu²  Shuping Huang²  Guibao Ke³  Xin Chen²  Bei Gong²  Wei Wei²  Yumei Xue²  Hai Deng²  Shulin Wu² 

[1] Guangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences;Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Guangdong Cardiovascular Institute;Department of Nephrology, The First Affiliated Hospital of Guangzhou Medical University;Department of Nephrology, Affiliated Hospital/Clinical Medical College of Chengdu University

关键词: Artificial intelligence (AI);    artificial neural network (ANN);    electrocardiogram;    arrhythmia;    bibliometric analysis;   

DOI  :  10.21037/jtd-21-1767

学科分类：呼吸医学

来源: Pioneer Bioscience Publishing Company

【 摘 要 】

Background: With the advancement in machine learning (ML) and artificial neural networks as well as the development of portable electrocardiogram devices, artificial intelligence (AI) has been increasing in popularity over the years. In this study, we aimed to provide an overview of the research regarding the utilization of AI techniques to improve the diagnosis of arrhythmia. Methods: We extracted data published 2004 to 2021 from Web of Science database. The online analytic platform, Literature Metrology (http://bibliometric.com), was used to analyze publication trends, including information about journals, authors, institutions, collaborations between countries, citations, and keywords. Results: Keywords, such as deep learning, electrocardiogram (ECG), and convolutional neural network, have been increasing in frequency over the years. The analysis outcomes demonstrated that topics associated with AI, robotic prosthesis, and big data analysis for arrhythmia have become increasingly popular since 2016. Our study also found that atrial fibrillation (AF) and ventricular arrhythmia were the two ECG signal sharing the most interest. Conclusions: The utility of deep learning in diagnostics and the prognostication of arrhythmia has been gaining traction over the years, covering areas from electrocardiogram detection to atrial arrhythmogenesis model construction. Our study revealed the trend of topics from 2004 to 2021, which may help researchers to monitor future trends.

【 授权许可】

Unknown