Artificial Intelligence-based social assistive robots in dementia care: a systematic review and meta-analysis

Alzheimer's disease and related dementias (ADRD) significantly affects older adults and their caregivers, necessitating innovative caregiving solutions. This systematic review and meta-analysis evaluate the efficacy of the application of AI-based socially assistive robots (AI-SARs) in ADRD care.

A comprehensive literature search of randomized controlled trials was conducted across 11 databases (e.g., PubMed, Web of Science) following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Eligible trial studies must be interventions that adopted AI-SARs in supporting older adults with ADRD or family caregivers. Outcomes analyzed included care recipient cognitive function, depression, anxiety, and agitation.

Fourteen studies were included in the systematic review and ten in the meta-analysis. AI-SAR interventions showed a statistically significant reduction in depression [standardized mean difference (SMD) = -0.30; 95% confidence interval (CI): -0.56 to -0.03; p = .027] and agitation (SMD = -0.26; 95% CI: -0.49 to -0.03; p = .027). No significant effects were found on cognitive function (SMD = -0.07; 95% CI: -0.30 to 0.16; p = .555), or anxiety (SMD = 1.12; 95% CI: -1.73 to 3.98; p = .440).

AI-SARs may reduce depressive symptoms and agitation among older adults with ADRD. However, evidence for other outcomes remains inconclusive. Future research should focus on large-scale trials with standardized outcomes and explore the role of AI-SARs in supporting caregivers.