Work

Machine learning in mental health promotion for older adults: a scoping review

Year: 2026

Type: article

Abstract: OBJECTIVES: Owing to the rapidly aging global population, an increasing number of older adults are experiencing mental health problems. Although machine learning has shown a lot of potential for promoting mental health in this group, there are no scoping reviews in this field. This study aimed to provide an overview of the applications of machine learning in promoting the mental health of older adults and identify associated trends and challenges. METHODS: A scoping review was conducted based on the framework by Arksey and O’Malley. Three electronic databases, including Web of Science, PubMed, and IEEE Xplore, were systematically searched from database inception to March 15, 2026. We included English-language studies on the use of machine learning to promote mental health among older adults. Relevant information was extracted, summarized, and analyzed. RESULTS: A total of 144 articles were included in this review. Our review showed that the current research reveals diverse data and algorithms, with machine learning applications concentrated in two directions. One is the prediction of the risk of mental health problems, and the other is the detection and identification of mental health status. There are still challenges in methodology and application directions, although machine learning effectively helps address some limitations of existing research. CONCLUSIONS: Future research may consider improving data quality, implementing longitudinal designs more extensively, enhancing model interpretability, and broadening research on various mental health problems and intervention–effect prediction. These initiatives may strengthen the empirical basis for clinical judgment and public health policy.

Source: BMC Geriatrics

DOI: 10.1186/s12877-026-07543-2

Authors: Yunchen Ruan, Haodong Liang, Seita Yamamoto, Shiqi Lin

Institutions: Fuzhou University, Peking University

Language: English

Topic: Artificial Intelligence in Healthcare

Subfield: Health Information Management

Field: Health Professions

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $3,190