Artificial intelligence-enabled social robots for facilitating social interactions in patients with dementia: a systematic review

Abstract

Background The global rise in dementia, closely linked to aging populations, necessitates innovative interventions to address care challenges. Artificial Intelligence-Enabled Social Robots (AI-ESRs) present a promising approach by leveraging multi-modal communication to enhance social engagement and alleviate isolation. However, evidence regarding their efficacy remains inconsistent and fragmented. This systematic review evaluates the effectiveness of AI-ESRs in enhancing social interactions among people with dementia, examines factors contributing to outcome variability, and provides recommendations for optimizing their integration into care models. Methodology A comprehensive search was conducted across five electronic databases (PubMed, Web of Science Core Collection, EBSCO, Scopus, and Cochrane Library) for peer-reviewed articles published up to May 2026. Inclusion criteria encompassed studies addressing AI-ESRs interventions in dementia care, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Data extraction was standardized to ensure consistency across selected studies. Results 16 studies met the inclusion criteria, comprising seven randomized controlled trials (RCTs) and 9 pre-post studies. 15 studies demonstrated the potential of AI-ESRs to significantly enhance multiple dimensions of social interactions. These included verbal and non-verbal communication, the frequency and quality of interactions with caregivers, peers, and robotic systems, as well as behavioral indicators (e.g., smiling and laughter) and participation in activities. One study reported no statistically significant differences between intervention and control groups (p = 0.18) but noted a marginal improvement in communication scores. Conclusions AI-ESRs show promise in facilitating social interactions among patients with dementia, with their effectiveness influenced by participant characteristics, intervention design, and contextual factors. Further research is warranted to explore long-term outcomes, tailor interventions to individual needs, and address ethical and implementation challenges, thereby advancing the integration of AI-ESRs into dementia care.