A Bibliometric Analysis of the Global Research Output on Artificial Intelligence Clinical Research

  Objective  To explore the research status of randomized controlled trial (RCT) with the application of artificial intelligence (AI) in the medical field, in order to provide insights for Chinese scholars to carry out AI research.

  Methods  AI related RCT researches were obtained by searching PubMed database. The Web of Science was used to obtain the publication year, citations, authors, institutions, and countries of included AI related RCT researches. The VOSviewer 1.6.17 software was used to extract the related information, generate visual cooperation network maps for the country, institutions and authors, and perform cluster analysis for keywords. The Cite Space 5.8.R3 software was used to analyze the burst citation references and keywords.

  Results  A total of 1174 RCTs in AI field were included, with an average citation frequency of 36.09. The publication time was from 1989 to 2021, and the number of articles increased rapidly after 2007. Among them, the top 5 countries with the number of published articles were the United States (37.22%, 437 papers), Italy (10.90%, 128 papers), South Korea (8.86%, 104 papers), Germany (8.35%, 98 papers), China (7.84 %, 92 papers); the top 5 research institutions with the most published papers were Harvard University (2.98%, 35 papers), Yonsei University (2.73%, 32 papers), Northwestern University (2.21%, 26 papers), Massachusetts Institute of Technology (2.13%, 25 papers), Stanford University (1.96%, 23 papers), and the top 5 authors were Krebs (22 papers, Massachusetts Institute of Technology, US), Calabro (11 papers, IRCCS Neural Center, Italy), Picelli (11 papers, University of Verona, Italy), Smania (11 papers, University of Verona, Italy), Lin (10 papers, Taiwan University, China). Insufficient cooperation between prolific authors, research institutions, countries. The main hot topics were the application of robot technology in treatment, the application of machine learning in disease diagnosis and management, and the application of AI in rehabilitation training. Combined with strongest citation burst, it was found that robot assistance and machine learning may be the current research hot topics.

  Conclusions  AI has great application prospects in the medical field, and the number of AI related RCT medical research has increased rapidly in recent years. Although the developed countries are in the leading position in this field, the researchers and research institutions in China have shown great potential. At present, the cooperation between the authors, research institutions and countries conducting AI related RCT medical research is not close, and the research topic needs to be expanded.