JMIR Publications

ABSTRACT

Background:

With a rapidly aging population in most parts of the world, it is only natural that the need for caregivers for older adults is going to mount in the near future. Therefore, most developed countries are in the process of using AI to build socially assistive robots (SAR) to play the role of caregivers in enhancing interaction and social participation among the elderly. A meta-analysis was conducted of various existing studies on the effect of AI SAR on the cognitive function of the elderly to standardize the results and clarify the effect of each method and indicator.

Objective:

Therefore, this study aimed to examine effect of intervention through AI SAR on the cognitive function of the elderly through a systematic literature review.

Methods:

Cochrane collaboration and the systematic literature review flow of PRISMA (Preferred reporting item systematic reviews and meta-analysis) were used on original peer-reviewed studies published from 2010 to March 2022. The search words were derived by combining keywords including patients or population, intervention, and study design, according to the PISCOT-SD principle. The PICOTS-SD for the question, what is the effect of AI SAR on the cognitive function of the elderly in comparison with a comparison group? were adults aged 65 or above (Population), AI SAR (Intervention), comparison group (Comparison), popular function (Outcome), and prospective study (Study Design). In any study, even if one condition among subjects, intervention, group, and study methods was different from this, the study was excluded from the literature review.

Results:

Nine studies were selected (six randomized controlled trials and three quasi-experimental) for the meta-analysis. Publication bias was examined using the Contour-enhanced Funnel Plot method to confirm the reliability and validity of the nine studies. The meta-analysis revealed that the average effect size of AI SAR was shown to be Hedges’ g=0.43 (95% CI: [-0.04,0.90]), indicating that AI SAR is effective in reducing the MMSE scale, which reflects cognitive function.

Conclusions:

The nine studies that were analyzed used animal, robot, and human SARs. Among them, AI SAR in the anthropomorphic form was able to improve cognitive function more effectively. The development of AI SAR and the expansion of programs to various functions including health notification, play therapy, counseling service, conversation, and dementia prevention are expected to improve quality of care for the elderly and prevent an overload of caregivers. AI SAR can be considered a representative digital social prescription program and a non-pharmacological intervention program that communicates with the elderly, 24 hours a day. Despite its effectiveness, ethical issues, digital literacy needs of the elderly, social awareness/reliability, and technological advancement pose challenges in implementing AI SAR. Future research should include bigger sample sizes, pre-post studies, as well as studies using an elderly control group