人工智能应用于心血管影像的文献计量学分析

Bibliometric Analysis of Application Artificial Intelligence to Cardiovascular

关键词:  人工智能  心血管影像  文献计量学分析  VOSviewer  CiteSpace

Key words:  artificial intelligence  cardiovascular imaging  bibliometric analysis  VOSviewer  CiteSpace

摘要:

心血管疾病是影响人类健康的严重疾病，近年来随着人工智能的发展，将其应用于心血管疾病影像诊断的研究不断增加，但目前尚未有学者对其进行文献计量分析。本文利用文献计量学分析人工智能（artificial intelligence，AI）应用于心血管影像的研究现状、热点及演化趋势，为AI应用于心血管影像的研究提供借鉴。对Web of Science（WOS）核心合集数据库内有关AI应用于心血管影像的相关文献进行检索。采用Excel、CiteSpace、VOSviewer、R软件对数据进行文献计量分析。本研究共纳入1 112篇文献，该领域发文量自2020年开始大规模增长，近4年发文量占总发文量71.3%，预计未来发文量还将持续增加。该领域发文量最多的国家、机构、作者分别为美国、伦敦国王学院、Dey, Damini。共被引频次最高的作者为RONNEBERGER O，同时也是共被引频次及突现力最强的参考文献U-Net: Convolutional Networks for Biomedical Image Segmentation的作者。IEEE Transactions on Medical Imaging、Medical Image Analysis、JACC-Cardiovascular Imaging在发文量排名及共被引排名中均位列前十，是该领域重要的学术期刊。根据关键词分析，“机器学习”和“深度学习”是目前研究热点，该领域关键词主要可以分为3类，一类是人工智能技术，另一类主要为心脏影像工具，最后一类是心脏疾病。本研究表明，人工智能在超声心动图、CT和磁共振成像中的应用显著提升了心血管疾病的诊断准确性和效率。如何进一步通过结合AI以提高心血管影像技术对心血管疾病识别及评估的准确性、便捷性及效率是未来的研究重点。

Abstract:

Cardiovascular diseases are a significant health concern, and the use of artificial intelligence in cardiovascular imaging research has been on the rise in recent years. Despite this growth, there has been a lack of bibliometric analysis in this area. This article utilizes bibliometric analysis to to analyze the current status, hotspots, and evolutionary trends of artificial intelligence applied to cardiovascular imaging research, to provide reference for the application of artificial intelligence in cardiovascular imaging. Literature retrieval on the application of artificial intelligence to cardiovascular imaging was conducted in the core collection database of Web of Science (WOS). Bibliometric analysis was performed using Excel, CiteSpace and VOSviewer and R. A total of 1 112 articles were included in this study, indicating a rapid growth in publications in this field since 2020, with 71.3% of total publications in the past 4 years. It is anticipated that this trend will continue in the future. The leading publishing country, institution, and author were the United States, King's College London, and Dey, Damini, respectively. The author with the highest citation frequency is RONNEBERGER O, known for the highly cited reference 'U-Net: Convolutional Networks for Biomedical Image Segmentation'. Notably, IEEE Transactions on Medical Imaging, Medical Image Analysis, and JACC-Cardiovascular Imaging rank among the top ten in both publication and citation rankings, solidifying their importance in this academic field. According to keyword analysis, 'machine learning' and 'deep learning' are current research hotspots. All keywords were classified into 3 categories based on keyword clustering results, artificial intelligence technology, heart imaging tools and heart disease. This study demonstrated that the application of AI in echocardiography, CT, and magnetic resonance imaging significantly improved the diagnostic accuracy and efficiency of cardiovascular diseases. How to improve the accuracy, convenience and efficiency of cardiovascular imaging technology for the identification and evaluation of cardiovascular diseases by combining AI is the focus of future research.