The explainable AI (XAI) in healthcare: A bibliometric analysis using VOSviewer and R Studio

Abstract

This study aims to perform a comprehensive bibliometric analysis to map the global research structure, evolution, and key trends of explainable XAI in healthcare. Utilizing Web of Science data (covering 2018–March 2025) and employing tools including VOSviewer and Bibliometrix, the analysis examined publication trends, keyword co-occurrence networks and centrality, thematic evolution, conceptual structure, author productivity, international collaboration networks, and co-citation patterns. Findings indicate exponential growth in XAI in healthcare research, peaking notably in 2024. “Explainable AI”, “machine learning”, and “deep learning” constitute the core conceptual basis, with “explainable AI” identified as structurally central. Key research themes driving the field, influential authors (e.g., Holzinger, Mueller, Guidotti, Lundberg, Ribeiro), major collaborating countries led by the USA and China, and foundational cited works were identified. Emerging themes like “fairness”, “transparency”, and “trust” were also emphasized. This bibliometric overview describes the dynamic landscape that defines XAI in healthcare, its main research areas, key players, and international collaboration networks, providing informative guidance for future research and development in this critical area.

Ähnliche Arbeiten