Exploring the growth and impact of artificial intelligence in anesthesiology: a bibliometric study from 2004 to 2024
Keke Liu, Qiu Weicheng, Xinping Yang
Abstract
Background: The integration of artificial intelligence (AI) in anesthesiology is revolutionizing clinical practice by enhancing patient monitoring, improving risk assessment, and enabling personalized anesthetic care. This bibliometric analysis aims to evaluate publication trends, key contributors, and emerging translational pathways in AI research in anesthesiology, with special emphasis on clinical relevance, thematic clustering, and future application prospects. Materials and methods: Publications related to AI in anesthesiology from 2004 to 2024 were retrieved from the Web of Science Core Collection database, resulting in 658 articles. VOSviewer and CiteSpace were employed for the bibliometric analysis. Results: play central roles in disseminating key findings. Keyword and journal cluster analyses revealed three major translational domains: real-time perioperative risk prediction (e.g., hypotension, mortality), AI-assisted ultrasound for regional anesthesia, and intelligent anesthesia monitoring systems. Despite progress, emerging concerns such as model interpretability, patient-centered outcomes, and multimodal data integration remain underexplored. Conclusion: AI in anesthesiology is entering a phase of rapid interdisciplinary expansion, integrating clinical needs with computational innovation. Future research should prioritize the clinical validation of AI tools, foster stronger collaboration between computer scientists and anesthesiologists, and address unresolved translational gaps such as model interpretability and cross-modal data fusion.