Real-time location system (RTLS) technology can derive digital markers and phenotypes of rest-activity rhythms in people with advanced dementia, with RTLS-derived markers associated with clinical assessments of motor agitation and sleep disruption over time.
Wrist-worn RTLS devices successfully tracked continuous location data for up to 16 weeks in people with advanced dementia in residential care.
Higher RTLS-derived activity intensity was correlated with increased clinical motor agitation scores.
Disrupted rhythmicity and reduced time in bed were associated with difficulty falling asleep and increased nighttime motor agitation.
Unsupervised machine learning identified 6 distinct rest-activity phenotypes over 1-week periods in people with advanced dementia.
The six RTLS-derived rest-activity phenotypes differed significantly by age, cognition, mood disturbance, and functional status.
RTLS-derived rest-activity markers and phenotypes were associated with changes in clinical assessments over time.
This research suggests that small wrist-worn tracking devices — the kind already used in care facilities to locate residents and prevent wandering — can also provide meaningful information about sleep and activity patterns in people with advanced dementia. By measuring how far residents moved every 15 minutes over up to 16 weeks, the researchers were able to calculate digital measures of rest and activity rhythms. They found that these measures were linked to clinical observations: residents who were more active overall tended to show more physical agitation, and those with more disrupted or irregular rhythms had more trouble falling asleep and more nighttime restlessness. Using a machine learning approach, the researchers also identified six distinct 'types' of rest-activity patterns — ranging from spending a lot of time in bed, to having well-regulated rhythms, to being highly active or predominantly active at night. These groups differed in meaningful ways: they were associated with differences in age, cognitive ability, mood, and physical function. This suggests that dementia affects sleep and activity patterns in several different ways, and that one-size-fits-all care approaches may not be appropriate. This research suggests that repurposing existing location-tracking technology in care facilities could allow staff to continuously and passively monitor residents' rest-activity patterns without additional burden on residents or staff. Over time, this could help identify when a resident's condition is changing, support more personalized care decisions, and provide objective data to complement traditional clinical assessments in people with advanced dementia who may not be able to self-report their symptoms.
Karam Y, Shum L, Faruk T, Arora T, McArthur C, Chu C, et al.. (2026). Digital markers and phenotypes of rest-activity rhythms in people with advanced dementia using real-time location data.. The journals of gerontology. Series A, Biological sciences and medical sciences. https://doi.org/10.1093/gerona/glaf288