Back

Artificial Intelligence in Reminiscence Therapy for Older Adults: A Systematic Review Protocol

Shankar, R.; Ali, J. M.; Xu, Q.

2025-09-22 geriatric medicine
10.1101/2025.09.21.25336299 medRxiv
Show abstract

BackgroundThe global aging population faces increasing challenges related to cognitive decline, social isolation, and psychological well-being. Reminiscence therapy has emerged as an effective non-pharmacological intervention, and recent advances in artificial intelligence offer opportunities to enhance these therapeutic approaches. ObjectiveTo systematically review and synthesize evidence on the integration of artificial intelligence technologies in reminiscence therapy for aging populations, examining effectiveness, acceptability, implementation factors, and ethical considerations. MethodsThis protocol follows PRISMA-P guidelines and employs the PICOS framework. Comprehensive searches will be conducted in PubMed, Web of Science, Embase, CINAHL, MEDLINE, The Cochrane Library, PsycINFO, and Scopus from inception to October 2025. Studies examining AI-enhanced reminiscence therapy in adults aged 60 years and above will be included. Two independent reviewers will screen studies using Covidence, extract data, and assess quality using appropriate risk of bias tools. Data synthesis will involve meta-analysis where appropriate or narrative synthesis following SWiM guidelines. DiscussionThis protocol establishes a rigorous methodology for examining an emerging field at the intersection of gerontology and artificial intelligence. The systematic approach will provide evidence-based insights for clinical practice, technology development, and policy-making while identifying research gaps and ethical considerations in AI-enhanced therapeutic interventions for older adults.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.