AI-driven scientometric analysis with recency insights: lower urinary tract symptoms in older and frail populations.

Purpose: This artificial intelligence (AI)-driven scientometric analysis, conducted using the Mynd discovery platform, explores research trends in lower urinary tract symptoms (LUTS) among older patients. By applying its novel recency metric, the study identified emerging areas, longstanding research themes, and critical gaps in literature.

Methods: Mynd applies AI-driven scientometric analysis to map research trends in LUTS and frailty using PubMed abstracts. A total of 13,737 PubMed-indexed publications were analyzed. Through unsupervised topic modeling, Mynd extracts key terminology and builds hierarchical topic structures to enhance contextual understanding. Quantitative metrics-such as the novel recency metric-measure publication trends, categorizing topics as emerging, mainstream, declining, or hot. This approach enables data-driven insights into LUTS research in older persons.

Results: While research on LUTS has grown steadily since the 1980s, a decline in publication output has been observed since 2020. Geographical analysis reflects a shift in scientific prominence towards Asia. More in-depth analysis reveals a shift towards minimally invasive diagnostic methods, with a decline in research interest in invasive urodynamics. A similar pattern is observed in therapeutics. Frailty remains significantly underrepresented in literature, accounting for only 2.5% of the related studies, yet its high recency score indicates a rising focus.

Conclusion: These insights underscore the evolving landscape of LUTS research, with growing attention to patient-centered, less invasive management strategies. However, major research gaps persist, particularly in the study of frail patients, necessitating further investigations to ensure evidence-based approaches tailored to aging populations.