Smartphone data can reveal early dementia risks during real-world navigation

Research highlights how smartphone-based navigation tasks can serve as an innovative tool for identifying subtle cognitive changes in older adults, potentially providing early insight into dementia risk.

Study: Identifying older adults at risk for dementia from smartphone data obtained during a real-world wayfinding task. Image credits: Lee Charlie / Shutterstock.com

A recent study published in the journal PLOS Digital Health reports that subtle cognitive changes in people with subjective cognitive decline (SCD) can be inferred from smartphone data collected during a wayfinding task.

The importance of diagnosing dementia early

Worldwide, approximately 58 million people live with dementia, of which an estimated 69 million are in the prodromal stage. The prevalence of dementia is expected to triple by 2050 due to increasing life expectancy and population growth in many countries.

Although phase III clinical trials have shown that several medications can alter the trajectory of dementia, there is currently no cure for this disease. Thus, there remains an urgent need for the development of new diagnostic tools that can assess cognitive functioning in asymptomatic individuals, people who may exhibit subtle changes associated with an increased risk of dementia.

Recently, researchers have become increasingly interested in the potential utility of digital cognitive assessment tools, as they have the potential to detect episodic memory impairment of mild cognitive impairment (MCI). These approaches can facilitate the early identification of people at increased risk of developing dementia, which can provide important insights into when and what interventions to initiate to ultimately improve patient prognosis.

About the study

The current study investigated the diagnostic value of movement trajectories and related data during real-world navigation via a smartphone-based wayfinding task. The sample consisted of 25 cognitively healthy older adults, 24 younger adults, and 23 SCD patients.

The signage task was carried out on the campus of the German Center for Neurodegenerative Diseases (DZNE) and was assisted by the mobile app ‘Explore’. All study participants were familiar with the campus area and reported no mobility limitations.

During the task, study participants walked from the DZNE to five Points of Interest (POIs), covering a route of 820 meters. They viewed a map on their smartphone, which showed their current location and photos and locations of POIs, before being told to close the map and then find the POIs.

If necessary, study participants were allowed to view the map again, with the number of views recorded. At the POI, a quick response code (QR) was scanned to indicate completion and initiate the procedure for the next issue.

The relative distances between individual Global Positioning System (GPS) trajectories were measured. Subgroups of participants with similar wayfinding patterns were identified using a cluster analysis.

Findings of the study

The researchers evaluated how well the clusters represented the three classes of participants. Most subjects in the first cluster walked directly from one POI to another or showed minor deviations/detours.

The second cluster followed a less direct path to POIs, with incorrect turns at certain intersections. By comparison, the third cluster followed different paths than the rest of the sample. The similarity between the participant classes and these clusters was low.

The first cluster consisted of 18 younger adults, seven SCD subjects, and 10 healthy older adults. The second cluster included five younger adults, ten SCD patients, and nine healthy older adults, while the third cluster included one SCD patient and one healthy older adult.

Five performance measures were also estimated based on user input and GPS data. This data includes signage distance, duration, movement speed, number of map views while walking, and the number of short stops while walking.

A latent profile analysis was performed on these measures to identify profiles that were then evaluated for how well they matched the participant classes. The study participants in the first profile performed at a high level with less time, distance, faster movements and fewer stops and map views while walking. The second and third profiles represented mid- and low-end artists, respectively.

The participant classes were well represented by performance profiles. The high-level performers were primarily younger adults, two SCD subjects, and five older adults. Most healthy older adults, SCD patients, and five younger adults performed at intermediate levels. Low performance levels were observed in one healthy older adult and six SCD subjects.

Younger adults differed significantly on all measures, with less time, distance, faster movements, and fewer stops and map views. SCD patients had significantly more stops than healthy older adults, viewed the map more often while walking, and took longer to complete tasks.

SCD patients did not walk more distance than healthy older adults, with average movement speed being similar between these two groups. More stops were associated with a significantly greater risk of being an SCD patient.

The number of stops, which varied between SCD patients across the different trajectories, correlated with the overall cognitive and visual memory functioning of these individuals; however, this association was not statistically significant.

Conclusions

The current study evaluated the potential of using smartphone data from real-world wayfinding to distinguish between SCD patients and healthy older adults. The study results suggest that behavioral performance indicators contain information about participants’ SCD status and age group.

Healthy younger adults showed better overall performance, while the differences between SCD subjects and healthy older adults were more nuanced. More specifically, differences in the number of stops between SCD patients and healthy older adults were observed. This effect was able to predict SCD status, making it a promising digital footprint for cognitive decline associated with dementia.