Augmented reality based assistive technologies for the safety of people with dementia and related mild cognitive impairment: a systematic review

Dementia is a neurodegenerative condition affecting 55 million people globally, with nearly 10 million new cases each year. The societal and economic impacts of dementia are significant and are steadily increasing for caregivers and the healthcare systems. Assistive Technologies (AT), including Augmented Reality (AR), have significantly improved independence, safety, and Quality of Life (QoL) for People with Dementia (PwD) and Mild Cognitive Impairment (MCI). This study, therefore, investigates the state-of-the-art applications of AR-based AT focusing on improving the safety of PwD and MCI. It aimed at exploring areas of safety where AR-based AT have been applied, the interaction modalities employed to facilitate user engagement and situation awareness the systems are capable of drawing the attention of users or caregivers to in order to avoid danger. The study followed the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines to identify 31 relevant studies for the review. The quality of the included studies was assessed with Mixed Methods Appraisal Tool (MMAT). The findings from the review shows that AR-based AT for the safety of individual with cognitive impairments is still limited. The few available studies can be categorised into three safety support types: mobility, medication management, and home safety and control. While most research focuses on mobility and medication management, there is a notable gap in addressing home safety and control, with interventions often targeting specific concerns. Most AR-based AT rely on smartphones, though prolonged use may cause fatigue. While wearable smart glasses are still developing and face ergonomic challenges, emerging lightweight designs show promise for wider adoption among older adults. Although AR-based AT demonstrate considerable potential to improve safety for PwD and those with MCI, the existing evidence is largely confined to small pilot and feasibility studies. There is a clear need for large, rigorous Randomised Controlled Trial (RCT) to evaluate their effectiveness in safety support in these target populations.