ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING APPLICATIONS FOR OLDER ADULTS: A BIBLIOMETRIC ANALYSIS (2015-2025)

9th INTERNATIONAL HEALTH SCIENCE AND LIFE CONGRESS, Antalya, Türkiye, 15 - 18 Nisan 2026, ss.579, (Özet Bildiri)

Background: The integration of artificial intelligence (AI), machine learning, and voice

assistants into gerontology and geriatric care is a rapidly evolving field that offers innovative

solutions for the aging population.

Aim: The aim of this study is to determine the publication trends, foundational literature, and

core thematic focuses regarding the application of AI and machine learning technologies for

older adults.

Methods: This descriptive bibliometric study analyzed literature retrieved from the Web of

Science (WoS) database. The search was limited to English-language research articles

published between 2015 and 2025 in the SCI-EXP, SSCI, and ESCI indexes. Using a

comprehensive search strategy focusing on older adults and AI/machine learning technologies,

a total of 2360 articles were extracted. The data were analyzed using the bibliometrix package

in R software.

Results: The annual scientific production demonstrated a dramatic exponential growth over the

study period. Publications increased steadily from 11 articles in 2015 to 89 in 2020, followed

by a rapid surge reaching 884 articles by 2025. Analysis of the top local cited documents

revealed two primary themes within the field: the application of machine learning for the early

prediction of health risks (such as falls, cognitive impairment, and depression) and the use of

smart voice assistants to support independent living and reduce social isolation. Conversely,

analysis of the top local cited references identified Leo Breiman's foundational paper on the

"Random Forests" algorithm as the most frequently cited reference, indicating that this specific

machine learning algorithm serves as the primary methodological backbone for predictive

models in gerontechnology.

Discussion and Conclusion: The exponential increase in publications highlights a surging

academic interest in AI applications for older adults. While the core literature focuses on

predictive health modeling and assistive voice technologies, the foundational knowledge base

heavily relies on robust ensemble learning algorithms, particularly Random Forests. Focusing

on both algorithmic accuracy using these foundational models and user-friendly interface

designs is recommended for future research to facilitate successful aging in place.