Meta-Analysis Studies on Artificial Intelligence in Healthcare: A Bibliometric Analysis (2010-2025)
Year: 2026
Type: preprint
Abstract: Aim Meta-analyses of artificial intelligence (AI) in healthcare have proliferated across many clinical domains, yet no study has mapped this literature as a body of scholarship in its own right. This study aims to conduct a bibliometric analysis of meta-analysis studies on AI in healthcare published between 2010 and 2025. Methods Following the PRISMA 2020 guidelines, 646 research and review articles indexed in the Web of Science Core Collection and Scopus databases (2010–2025) were analyzed for citation patterns, annual trends, and leading countries, institutions, authors, publishers, and journals. Co-authorship and keyword co-occurrence networks were constructed using VOSviewer (v.1.6.19.0) and Bibliometrix. Results Publication output remained minimal before 2019 but rose sharply thereafter, reaching 153 publications in 2024 and 280 in 2025, together accounting for about two-thirds of the dataset. The most cited article was Christodoulou et al. (2019, 1,663 citations), followed by Aggarwal et al. (2021, 848). China led in publication output (221 articles, 34.21%), while the United Kingdom led in citation impact (6,269 citations, 30.25%) despite ranking third in output. Tehran University of Medical Sciences was the most productive institution, Habibi, M.A. the most productive author, and the Journal of Medical Internet Research the leading journal. Author-level productivity was concentrated within a small set of interconnected teams, institutional collaboration was sparse, and country-level collaboration was broad and international. Keyword analysis identified artificial intelligence, machine learning, meta-analysis, and deep learning as core terms, organized around three further axes: imaging-based diagnostic accuracy, outcome and risk prediction, and disease-specific evidence synthesis. Conclusion This study provides the first structural bibliometric mapping of the meta-analytic literature on AI in healthcare, revealing rapid recent growth alongside concentrated authorship and institutional collaboration. These findings suggest that publication growth has outpaced methodological consolidation and offer a reference point for future work in the field.
Source: Research Square
Authors: Furkan Alp, Merve İnan Budak
Institution: Istanbul Medeniyet University
Language: English
Subfield: Library and Information Sciences
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7225647735