Department of Radiology, The First Affiliated Hospital of Huzhou Normal University, Huzhou, Zhejiang, People's Republic of China.
Department of Endocrinology, The First Affiliated Hospital of Huzhou Normal University, Huzhou, Zhejiang, People's Republic of China.
Int J Chron Obstruct Pulmon Dis. 2024 Aug 21;19:1849-1864. doi: 10.2147/COPD.S474402. eCollection 2024.
A bibliometric analysis was conducted using VOSviewer and CiteSpace to examine studies published between 2009 and 2023 on the utilization of artificial intelligence (AI) in chronic obstructive pulmonary disease (COPD).
On March 24, 2024, a computer search was conducted on the Web of Science (WOS) core collection dataset published between January 1, 2009, and December 30, 2023, to identify literature related to the application of artificial intelligence in chronic obstructive pulmonary disease (COPD). VOSviewer was utilized for visual analysis of countries, institutions, authors, co-cited authors, and keywords. CiteSpace was employed to analyze the intermediary centrality of institutions, references, keyword outbreaks, and co-cited literature. Relevant descriptive analysis tables were created using Excel2021 software.
This study included a total of 646 papers from WOS. The number of papers remained small and stable from 2009 to 2017 but started increasing significantly annually since 2018. The United States had the highest number of publications among countries/regions while Silverman Edwin K and Harvard Medical School were the most prolific authors and institutions respectively. Lynch DA, Kirby M. and Vestbo J. were among the top three most cited authors overall. Scientific Reports had the largest number of publications while Radiology ranked as one of the top ten influential journals. The Genetic Epidemiology of COPD (COPDGene) Study Design was frequently cited. Through keyword clustering analysis, all keywords were categorized into four groups: epidemiological study of COPD; AI-assisted imaging diagnosis; AI-assisted diagnosis; and AI-assisted treatment and prognosis prediction in the COPD research field. Currently, hot research topics include explainable artificial intelligence framework, chest CT imaging, and lung radiomics.
At present, AI is predominantly employed in genetic biology, early diagnosis, risk staging, efficacy evaluation, and prediction modeling of COPD. This study's results offer novel insights and directions for future research endeavors related to COPD.
使用 VOSviewer 和 CiteSpace 对 2009 年至 2023 年间发表的关于人工智能（AI）在慢性阻塞性肺疾病（COPD）中的应用的研究进行文献计量分析。
于 2024 年 3 月 24 日，在 Web of Science（WOS）核心合集数据集上进行了计算机检索，检索时间范围为 2009 年 1 月 1 日至 2023 年 12 月 30 日，以确定与人工智能在慢性阻塞性肺疾病（COPD）中的应用相关的文献。使用 VOSviewer 对国家/地区、机构、作者、共被引作者和关键词进行可视化分析。使用 CiteSpace 分析机构、参考文献、关键词爆发和共被引文献的中介中心度。使用 Excel2021 软件创建相关描述性分析表。
本研究共纳入来自 WOS 的 646 篇论文。2009 年至 2017 年，论文数量一直较小且稳定，但自 2018 年以来，每年的发文量呈显著增长趋势。美国在国家/地区中发表的论文数量最多，而 Silverman Edwin K 和哈佛医学院则是最具影响力的作者和机构。在所有作者中，Lynch DA、Kirby M. 和 Vestbo J. 排名前三；在所有期刊中，Scientific Reports 的发文量最大，Radiology 则排名前十。COPDGene 研究设计被频繁引用。通过关键词聚类分析，所有关键词被分为四组：COPD 的流行病学研究；AI 辅助成像诊断；AI 辅助诊断；COPD 研究领域中的 AI 辅助治疗和预后预测。目前，热门研究主题包括可解释的人工智能框架、胸部 CT 成像和肺部放射组学。
目前，人工智能主要应用于 COPD 的遗传生物学、早期诊断、风险分期、疗效评估和预测模型。本研究结果为 COPD 的未来研究提供了新的见解和方向。
