Smartphone data may reveal early dementia risk 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, with the potential to provide early insight into dementia risk. I am.

study: Identify older adults at risk of dementia based on smartphone data captured during real-world wayfinding tasks. Image credit: Lee Charlie / Shutterstock.com

Recent research published in journals PLOS Digital Health report that subtle cognitive changes in people with subjective cognitive decline (SCD) can be inferred from smartphone data collected during wayfinding tasks.

The importance of early diagnosis of dementia

Approximately 58 million people worldwide are living with dementia, of which 69 million are estimated to be in the prodromal stage. The prevalence of dementia is predicted to triple by 2050 due to increased life expectancy and population growth in many countries.

Although Phase III clinical trials have demonstrated that several drugs can change the trajectory of dementia, there is currently no cure for the disease. Therefore, there is an urgent need to develop new diagnostic tools that can assess cognitive function in asymptomatic individuals who may exhibit subtle changes associated with 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 mild cognitive impairment (MCI) grade episodic memory impairment. These approaches may facilitate early identification of patients at high risk of developing dementia and provide important insights into when and what interventions should be initiated to ultimately improve patient outcomes. You can.

About research

In this study, we investigated the diagnostic value of movement trajectories and related data during real-world navigation through a smartphone-based wayfinding task. The sample included 25 cognitively healthy older adults, 24 younger adults, and 23 patients with SCD.

The wayfinding task was carried out at the German Center for Neurodegenerative Diseases (DZNE) campus and was supported by the mobile app “Explore”. All study participants were familiar with the campus area and did not report movement disorders.

During the task, study participants walked an 820-meter route from the DZNE to five points of interest (POIs). They viewed a map on their smartphone and were shown their current location, photo, and POI location, and then were instructed to close the map and then find the POI.

If desired, study participants were able to view the map again and the number of views was recorded. A quick response (QR) code was scanned at the POI to indicate completion and begin the next track step.

The relative distances between individual Global Positioning System (GPS) orbits were measured. Clustering analysis was used to identify subgroups of participants with similar wayfinding patterns.

Research results

The researchers assessed how well the clusters represented the three participant classes. Most subjects in the first cluster either walked directly from one POI to another or showed slight deviations/detours.

The second cluster took a wrong turn at a particular intersection and took a less direct path to the POI. By comparison, the third cluster followed a different path than the rest of the sample. The correspondence between participant classes and these clusters was low.

The first cluster consisted of 18 young adults, 7 SCD subjects, and 10 healthy older adults. The second cluster included 5 young adults, 10 SCD patients, and 9 healthy older adults, and the third cluster included 1 SCD patient and 1 healthy older adult. It was included.

Five performance metrics were also estimated based on user input and GPS data. These data include wayfinding distance, travel time, travel speed, number of map views during the walk, and number of short stops during the walk.

Latent profile analysis was performed on these measurements to identify profiles and then assess how well the profiles corresponded to the class of participants. Study participants in the first profile were high-level performers with shorter times, shorter distances, faster movements, fewer stops and map views while walking. The second and third profiles show medium and low levels of performance, respectively.

The classes of participants were well represented by their performance profiles. High-level performers were mainly young adults: 2 SCD subjects and 5 older adults. Most healthy older adults, SCD patients, and 5 young adults were intermediate performers. Low levels of performance were observed in one healthy elderly and six SCD subjects.

Young people differed significantly across all measures, including shorter times, distances, faster travel speeds, and fewer stops and map displays. SCD patients stopped significantly more, were more likely to look at a map while walking, and took more time to complete tasks than healthy older adults.

SCD patients walked no more distance than healthy older adults, and mean travel speed was similar between these two groups. More stops were associated with a significantly increased risk of becoming an SCD patient.

The number of stops varied between tracks and SCD patients and correlated with the general cognitive and visual memory functions of these patients. However, this association was not statistically significant.

conclusion

In the current study, we evaluated the potential of using real-world wayfinding smartphone data to distinguish between SCD patients and healthy older adults. Findings suggest that behavioral performance indicators include information about participants’ SCD status and age group.

Although healthy young adults had better overall performance, the differences between SCD subjects and healthy older adults were more subtle. More specifically, we observed differences in the number of stops between SCD patients and healthy older adults. This effect can predict SCD status and represents a promising digital footprint for cognitive decline associated with dementia.