Mapping the Scientific Landscape of Artificial Intelligence in Endodontics: A Bibliometric Analysis

The aim of this bibliometric study was to systematically map the evolution, structural characteristics and methodological profile of artificial intelligence (AI) research in endodontics by analysing publication trends, collaboration networks, thematic development and citation impact.

A bibliometric analysis was conducted using publications indexed in the Web of Science Core Collection, Scopus and PubMed from 1 January 1990 to 19 August 2025. Following deduplication and eligibility screening, 245 articles were included. Authorship, country-level collaboration and keyword co-occurrence networks were analysed using VOSviewer. Citation data were harmonised across databases using regression-based normalisation. Negative binomial regression was applied to evaluate the association between citation counts and publication year, document type and open-access status.

AI-related research in endodontics showed minimal activity before 2020, followed by rapid growth driven predominantly by deep learning (DL) based imaging applications. Periapical radiographs (PA) and cone-beam computed tomography (CBCT) were the most frequently used data sources. China accounted for the highest publication volume, whereas the United States demonstrated the greatest citation-weighted influence and centrality within international collaboration networks. Keyword co-occurrence analysis identified six thematic clusters, dominated by radiographic diagnostics, with a recent emergence of natural language processing and generative AI applications. Publication year was the only significant predictor of citation counts (p < 0.001); document type and open-access status were not significantly associated.

AI research in endodontics has evolved into a rapidly expanding, imaging-centred research domain characterised by increasing output but limited methodological diversity, restricted use of explainable AI and inconsistent adoption of reporting guidelines. These findings provide a structured overview of the field's development and current research profile.