JMIR Publications

ABSTRACT

Background:

The behavioural and psychological symptoms of dementia (BPSD) are common among residents with dementia living in nursing homes (NHs). They have multiple negative consequences. Artificial-intelligence-based technologies (AITs) have the potential to help NH nurses in the early prodromal detection of the BPSD. Despite significant recent interest in the topic and the increasing number of technical devices on the market, little information is available on integrating AITs into NHs to help nurses striving to detect the BPSD early on.

Objective:

Identify the number and characteristics of existing publications on integrating AITs into NHs to support nursing interventions to detect and manage the BPSD early.

Methods:

A literature review of publications referring to AIT and dementia was conducted in September 2023 in the PubMed database. A detailed analysis was carried out to identify the characteristics of the available publications. The results were reported using a narrative approach.

Results:

Twenty-five publications were identified, originating from 15 countries; most described prospective observational studies. We identified three categories of publications on using AITs: predicting behaviours and the stages and progression of dementia; screening and assessing clinical symptoms; and managing dementia and the BPSD. Most of the publications referred to managing dementia and the BPSD. Only one publication reported on using AIT devices to assess the BPSD in the specific context of NHs.

Conclusions:

Despite growing interest in using AITs in NHs, most of those currently in use are designed to support a psychosocial approach to treating and caring for existing clinical signs of the BPSD. This type of technology remains largely unexplored and underused in the early, real-time detection of the BPSD. Nevertheless, in NH contexts, AITs could provide nurses with accurate, reliable systems for assessing, monitoring, planning and supporting safe therapeutic interventions.