Background: With the advent of big data, artificial intelligence (AI) is rapidly emerging as a promising avenue for pain management research. Integrating big data analytics, machine learning, and intelligent algorithms within AI can facilitate several significant advancements in healthcare. These include the ability to provide clinical diagnoses of pain, risk prediction, and the development of precision medicine. The number of articles on the application of AI to pain management is on the rise. However, there needs to be more information regarding the quality of the research output in this area, as well as the current hotspots and trends in research. At the same time, no bibliometric metrics have been identified that assess scientific progress in this area. In order to gain an understanding of the current status and potential future directions in the application of AI within the field of pain management, it is first necessary to undertake a visual and analytical study of the relevant research.
Objectives: A bibliometric and visual analysis was conducted to identify research hotspots and trends in the application of AI in pain management over the past 30 years.
Methods: The data information source was the SCI-EXPANDED subset database of the WOS database. A manual search was conducted of all articles and reviews from the database's inception to June 29, 2024. The search was limited to English language sources. A bibliometric analysis was conducted using VOSviewer, CiteSpace, and Bibliometrix (an R-Tool of R-Studio). The analysis encompassed a range of aspects related to the global publication status of papers in the field, including countries and regions, institutions, authors, journals, keywords, and co-cited references.
Results: A total of 970 published papers were obtained for this study. The articles were published in 496 journals by 5679 authors affiliated with 2030 academic institutions in 84 countries or regions. From 2014 to 2024, there was a gradual increase in the number of papers published within this field, with 97% of the total published papers. The United States and China contribute the most to this growth. The most prominent research institutions are Harvard University, the University of California system, and Harvard Medical School. At the author level, Mork, Paul Jarle, Bach, and Kerstin of the Norwegian University of Science & Technology (NTNU) were identified as the authors with the highest research output. Breiman, L. of the University of California, Berkeley, emerged as the most influential author, exhibiting the highest co-citation frequency. From the perspective of journals, the Journal of Medical Internet Research, Scientific Reports, PAIN, PLOS ONE, and SPINE are the primary core journals in the field. They have a high number of published papers and co-citation frequency. Furthermore, of the 46,170 co-cited references, Loetsch J's "Machine learning in pain research," published in PAIN in 2018, had the highest number of co-citations, thus making it the most influential article in the study. Combining keywords and co-cited references for analysis leads to the conclusion that using AI for accurate clinical monitoring and risk prediction, clinical diagnosis and classification, and providing personalized treatment plans and care measures for pain has become a current research hotspot and a future trend. Machine learning, deep learning, artificial neural networks, and clinical decision support systems in artificial intelligence are frequently mentioned and commonly used to build predictive models. These are also hot research topics and trends in the field.
Conclusions: The field of research on using AI for pain management is experiencing unprecedented growth and development. This study offers a novel perspective on applying AI to pain management, which may inform researchers' selection of potential journals and institutions to collaborate with. Furthermore, this study furnishes researchers with the requisite data to comprehend the present state of research, research focal points, and research tendencies in this field, thereby facilitating the implementation of AI in pain management.
Keywords: Artificial intelligence; Bibliometrics; CiteSpace; Machine learning; Pain; VOSviewer.
© 2025. The Author(s).