Researchers use smartphone data to detect Alzheimer’s early

Researchers from the DZNE and the Otto von Guericke University of Magdeburg identified people at increased risk for dementia using mobility data, recorded during a smartphone-based wayfinding task on campus. The findings are reported in the journal PLOS Digital Healthshow the potential of smartphone data, collected in close-to-everyday conditions, for the early detection and monitoring of Alzheimer’s disease. The study included 72 adults. about a third of those with subjective cognitive impairment (SCD), a condition known to be a risk factor for dementia.

Alzheimer’s disease usually develops unnoticed over the years and eventually leads to dementia. To date, there is no cure.

Currently, Alzheimer’s disease is often treated too late to ensure effective treatment. Even the new antibody drugs that are much talked about at the moment only work if given at an early stage. Thus, we must be able to diagnose the disease earlier, when the symptoms are still mild. This calls for advances in diagnosis.”

Dr. Anne Maass, Head of Research Group at DZNE and Visiting Professor at the University of Magdeburg

With her colleagues, she has now tested a new approach to assess problems in spatial navigation, as one of the earliest possible symptoms of Alzheimer’s disease.

Application in use

“Our study is based on a kind of scavenger hunt where the participants had to find predetermined points of interest. For this, they used a smartphone equipped with a special application that we developed,” explains Dr. Nadine Diersch. The neuroscientist started the research program at DZNE several years ago and currently works in the private sector, but continues to be associated with DZNE as a visiting researcher. “We found that some app data allows reliable identification of people at increased risk for dementia,” he says. “This shows that digital technologies such as mobile apps offer completely new possibilities for assessing cognitive function under realistic low-threshold conditions. In the future, this may help detect subtle cognitive changes and thus precursors of dementia earlier than today.”

“Scavenger Hunt” on campus

In total, 72 women and men between the ages of 20 and 60 took part in the study. Of the 48 elderly subjects, 23 were diagnosed as SCD patients. People with this condition perceive a loss of mental capacity, but this cannot be detected by conventional neuropsychological tests. These people do not inevitably develop dementia. However, they have been shown to be at increased risk. All study participants were instructed to independently find various buildings on the medical campus of the University of Magdeburg, guided by the app, while their movement patterns were tracked with GPS. “Our participants had similar knowledge of the campus area and all had experience using smartphones. We also practiced using the app beforehand,” explains Jonas Marquardt, first author of the study and a PhD student in Anne Maass’ research group.

Assessment of sense of direction

During the task, which each study participant had to perform individually, five buildings had to be visited in a row along a route of about 800 meters. The app served as a pacemaker: It displayed a map of the current location and the next destination, including a photo of it. However, the map disappeared as soon as a participant started walking. “Participants had to memorize the layout of the streets, their location and destination, and then follow their sense of direction and spatial memory,” says Marquardt. “If they got lost, they could press a help button in the app. The map, their location and their destination would reappear briefly.” The researchers used the GPS data to create individual mobility profiles and other information.

Suspicious attitudes

In most cases, participants reached all five destinations in less than half an hour. “Overall, the younger participants performed better. On average, they walked shorter distances and generally didn’t use the assist mode as often as the older ones,” says Marquardt. The differences between the elderly with and without SCD were mainly reflected in the number of so-called orientation postures. Jonas Marquardt explains: “Elderly people with SCD paused during walking more often, probably to orient themselves, than elderly people without SCD. In fact, we were able to identify participants with SCD based on this parameter.”

Prospects for early diagnosis

It is not yet clear why people with SCD stand out in this respect. “We found that they tend to hesitate more at intersections in particular. This suggests that some decision-making processes have changed. However, the data is not yet conclusive,” explains Nadine Diersch. “However, the results of our study are a promising proof of concept. They show that smartphone data can help detect subtle signs of cognitive decline in realistic contexts.” The scientist sees this as an opportunity for early detection and early treatment of dementia: “I could imagine such applications being used in the future to identify people at risk and then decide whether they need further tests or already treatment.”