Application of Artificial Intelligence in Chronic Pain: Bibliometric Analysis.

BACKGROUND

In recent years, artificial intelligence (AI) has demonstrated great potential in the field of managing chronic pain (CP). AI can optimize treatment decisions, improve the quality of life of patients with CP, and promote the rational allocation of medical resources. However, the existing studies are mostly scattered, lack systematic integration and analysis, and have not yet constructed a knowledge map reflecting the whole picture of the research.

OBJECTIVES

This study aims to apply bibliometric analysis methods to explore the current research status and hotspots in the intersection of AI and CP, providing valuable insights for researchers in this field.

METHODS

In this study, the Web of Science Core Collection was used as the data source, and the search time limit was from the establishment of the database to October 2025. The search scope included the Science Citation Index Expanded (SCI-EXPANDED), Current Chemical Reactions (CCR-EXPANDED), and Index Chemicus (IC). VOSviewer software was used to conduct a visual analysis of the cooperation networks among countries, institutions, journals, and authors, as well as the co-occurrence relationships of keywords. Furthermore, the CiteSpace tool was adopted to identify burst keywords to reveal the latest research trends.

RESULTS

A total of 356 studies related to AI and CP were ultimately included for analysis after a systematic screening of records retrieved from the Web of Science Core Collection. These studies originated from 882 institutions across 54 countries and regions, were published in 190 journals, and involved 2,207 authors. The number of publications increased rapidly between 2018 and 2025. The United States ranked first in both the number of publications and total citations. At the institutional level, Harvard University was the most productive institution. In terms of journal distribution, the journal Pain published the largest number of documents and received the highest total number of citations. The keyword co-occurrence network revealed four major research clusters: CP, machine learning, low back pain, and prediction. Recent trend analysis revealed that prediction, neural networks, pain management, and neck pain have emerged as key research areas in the application of AI to CP.

CONCLUSIONS

Although significant progress has been made in the application of AI in CP management, there are still some key challenges, including a lack of cooperation among countries and institutions, limited adaptability and stability of AI models in clinical scenarios, as well as data privacy and security. Future research should actively promote international cooperation and facilitate the interdisciplinary integration and practical application of AI technology on a global scale. Moreover, researchers should focus on enhancing the reproducibility and scientific rigor of their studies to ensure their wide applicability and practical effectiveness in clinical practice.