JMIR Publications

ABSTRACT

Background:

Artificial intelligence (AI) has great potential for improving the care for persons with Alzheimer’s disease and related dementias (ADRD) and the quality of life of family caregivers. To date, however, there is no systematic literature review on what has been studied on this topic or the efficacy of AI-based interventions for caregivers.

Objective:

This review aimed to address these gaps in the literature.

Methods:

Similar to the procedures used in our previous systematic literature reviews, during August and September 2019 we performed three rounds of systematic selection. First, we searched predetermined keywords in 5 databases, including: PubMed, CINAHL Plus with Full Text, PsycINFO, IEEE Xplore Digital Library, and the ACM Digital Library. This step generated a total of 113 non-duplicate results. Next, we screened the titles and abstracts of these 113 results using predetermined inclusion/exclusion criteria; 52 results were excluded; 61 remained. Finally, we screened the full-text of selected articles to ensure that they met the same inclusion/exclusion criteria; another 31 articles were excluded. We then analyzed the 30 remaining articles in the final sample.

Results:

These articles were published between 2001 and 2019, averaging 2 a year. The year of 2018 had the most of all years, suggesting an increasing interest in this topic. The majority of these articles were qualitative or cross-sectional and with small samples. The studies generally reported positive outcomes in favor of the AI tools being tested. Mixed results were reported in some studies (e.g., some participants liked the AI technology, while others did not). Regardless of the findings, the levels of evidence of all studies in our final sample were low.

Conclusions:

These findings suggest a great need for more systematic designs and evaluations of the feasibility and efficacy of AI-based interventions for ADRD caregivers.