Background
The COVID-19 pandemic has spurred significant research into artificial intelligence (AI) applications in healthcare. This study analyzes the intellectual structure and knowledge flow in COVID-19 and AI research through descriptive citation and bibliographic coupling analysis.
Purpose
This study aims to explore the current research landscape on AI in the context of COVID-19, identify the most influential publications, and outline the conceptual framework of this research area.
Material and methods
Using the Web of Science (WoS) and Scopus databases, documents were collected with keywords such as “COVID-19,” “SARS-CoV-2,” “coronavirus,” “artificial intelligence” and “deep learning.” After merging results and removing duplicates, the final sample included 8057 documents. The top 1000 most cited papers were selected for descriptive citation analysis, while the entire sample was used for bibliographic coupling analysis. Data analysis and visualization were conducted using R Bibliometrix/Biblioshiny and VOSviewer.
Results
The descriptive analysis revealed that original research papers were predominant (85.21%), with a substantial increase in publications on COVID-19 and AI since the pandemic began. China and the United States led in publication volume, with notable international collaborations. Network analysis identified research clusters such as AI-driven diagnostics and healthcare resource optimization. The bibliographic coupling analysis highlighted influential research themes, mainly focusing on diagnostic imaging and AI algorithms.
Conclusion
AI has played a crucial role in addressing the COVID-19 crisis, especially in diagnostics and healthcare optimization. The bibliometric analysis provides insights into the research landscape, emphasizing AI's multifactorial contributions and suggesting areas for future research.
扫码关注我们
求助内容:
应助结果提醒方式:
