Robotics and artificial intelligence applications in neurorehabilitation: a bibliometric analysis (2003–2025)

Abstract

BACKGROUND: Robotic and artificial intelligence (AI)-assisted neurorehabilitation has emerged as a rapidly growing interdisciplinary field, integrating engineering innovations with clinical practice to enhance motor and cognitive recovery in neurological disorders. While research in this domain has expanded substantially over the last two decades, only a few bibliometric studies have examined related topics (e.g., new technologies in neurorehabilitation, rehabilitation robotics after stroke, AI in stroke care), and, to our knowledge, no study has provided a comprehensive bibliometric mapping specifically focused on robotics and artificial intelligence applications in neurorehabilitation. This study aimed to analyse the global trends, influential contributors, thematic evolution, and collaborative networks in robotic and AI-assisted neurorehabilitation. METHODS: A bibliometric analysis was conducted using the Web of Science Core Collection. A comprehensive search covering 2003-2025 identified relevant articles using controlled terms for neurorehabilitation, robotics, and AI. Data were exported as plain text files (savedrecs.txt) from the Web of Science Core Collection and processed using the Bibliometrix R package via the Biblioshiny interface. Analyses included annual growth, citation performance, authorship patterns, journal impact, keyword co-occurrence, thematic mapping, and international collaboration networks. RESULTS: A total of 468 articles were retrieved from 191 sources, showing a rapid annual growth rate of 19.57%. The average citation per article was 24.22, with 17,792 references cited overall. Authorship analysis revealed contributions from 1,972 authors, with an average of 5.49 co-authors per paper and 32.05% international collaboration. The Journal of NeuroEngineering and Rehabilitation (h-index = 15, 1,740 citations) and Sensors (m-index = 1.714) were identified as the leading journals. The most prolific authors included Aiguo Song (8 publications) and Robert Riener (6 publications), while Marchal-Crespo L. and Reinkensmeyer D.J. were the most locally cited. Keyword analysis highlighted "stroke" (n = 93), "rehabilitation" (n = 82), "design" (n = 58), "recovery" (n = 53), and "exoskeleton" (n = 49) as dominant themes, with stroke rehabilitation and robotic exoskeletons representing core research foci. China (n = 697) and the USA (n = 251) emerged as the most productive countries, with strong collaborative ties. CONCLUSION: Robotic and AI-assisted neurorehabilitation has demonstrated exponential growth, reflecting both technological innovation and clinical translation. Stroke rehabilitation and gait training remain central themes, while emerging areas such as AI-based assessment systems, wearable sensors, and tele-rehabilitation suggest future directions. To our knowledge, this study provides a comprehensive bibliometric overview specifically centred on robotics and artificial intelligence applications in neurorehabilitation, offering strategic insights for guiding future research and clinical integration.

Ähnliche Arbeiten