Developmental Patterns of Artificial Intelligence Research in Geriatric Diseases: A Bibliometric Analysis of Growth and Evidence Depth

Abstract

The rapid adoption of artificial intelligence (AI) in geriatric medicine has led to substantial growth in related research, yet the overall structure and developmental patterns of this field remain incompletely understood. In this study, we conducted a comprehensive bibliometric analysis of AI-based research in geriatric diseases published between 2006 and 2025. Publications were retrieved from the Web of Science Core Collection and analyzed across multiple dimensions, including annual publication trends, geographic and institutional contributions, collaboration networks, thematic structure and evolution, alignment between research activity and aging-related disease burden, and the relationship between research growth and citation-based evidence depth. The results demonstrate a clear stage-dependent development pattern, characterized by rapid expansion in publication output in recent years accompanied by declining average citation impact. Research activity is highly concentrated among a limited number of countries, institutions, and authors, forming a centralized collaboration structure. Thematic analyses reveal a gradual shift from early neuroimaging focused and disease-centered studies toward more method-driven and application-oriented research, with Alzheimer’s disease and machine learning remaining dominant organizing cores. However, many rapidly growing topics exhibit limited citation depth, indicating exploratory or transitional stages of development rather than consolidated research cores. In addition, the geographic distribution of research output shows marked heterogeneity and does not consistently align with global patterns of aging-related disease burden. Overall, this bibliometric study highlights substantial structural heterogeneity within geriatric disease-AI research, reflecting uneven thematic maturity, concentrated knowledge production, and variable evidence consolidation. These findings provide a quantitative perspective on the current developmental stage of the field and may inform more balanced and integrative future research efforts.