Daily driving patterns may reveal early memory problems

How you drive may say as much about your brain as any office test. A new study, based on hundreds of older drivers, found that patterns captured by simple GPS devices could flag early cognitive problems with an accuracy of about 87 percent.

Some participants showed these driving changes years before dementia, during mild cognitive impairment (MCI) – a stage of memory and thinking problems before dementia develops. 

The research followed community dwelling drivers in their seventies who were still getting behind the wheel at least once each week.

Driving patterns reveal brain changes

The study was led by Dr. Ganesh M. Babulal of Washington University School of Medicine. His research focuses on how everyday activities such as driving reflect early changes in brain health in older adults.

Driving demands quick decisions that pull together attention, memory, vision, and movement. Federal crash data show that in 2022 older drivers accounted for about one in five traffic deaths in the United States.

Health agencies see those numbers as one piece of a safety problem for aging drivers. The Centers for Disease Control and Prevention estimates that in 2022, 9100 older adults were killed in crashes in the United States.

Tracking older adults behind the wheel

In the main driving project, 298 older adults with normal cognition or MCI had GPS devices installed in their cars. 

Sensors logged trips for up to 40 months, including how often participants drove, how far they went, and what time of day they traveled.

The team rated thinking and memory using the Clinical Dementia Rating (CDR), a structured scale that grades cognitive changes from normal aging to dementia. 

They also repeated paper and pencil tests that checked attention, processing speed, and planning skills over time.

Based on those assessments, some participants were classified as having MCI while others remained cognitively normal over the follow up period. 

The researchers also noted whether each person carried apolipoprotein E4, a gene variant that makes Alzheimer disease more likely to develop.

Clues from shifting driving patterns

At the start of the study, drivers with and without MCI logged similar numbers of trips and often chose the same kinds of roads. 

Over time, the MCI group began taking fewer trips each month and cut back more sharply than their peers on night driving.

People with MCI also shortened routes, so medium trips and the longest distances from home became smaller than in the healthy group. 

The variety of destinations, captured using entropy, a mathematical score that reflects how predictable travel patterns are, also dropped in the MCI group. Algorithms that relied only on driving features spotted MCI about 82 percent of the time. 

With age, test scores, and Alzheimer genetic risk added, accuracy rose to 87 percent – compared to 76 percent when measures were used without driving information.

Driving patterns and disease risk

These patterns make driving an appealing digital biomarker, a stream of real world data that can warn about disease risk. 

Other research teams have shown that GPS-based driving features can identify cognitively normal older adults with very early Alzheimer changes, using machine learning to sort risky patterns.

Several years before the current work, a pilot study of 20 older adults with and without preclinical Alzheimer’s disease used similar in-car monitoring. 

Even in that small group, those with preclinical disease tended to drive less often, avoid night trips, and make fewer abrupt maneuvers.

Privacy and next steps

Turning car trips into a health signal raises hopes for earlier support, but it also raises questions about how much monitoring people are willing to accept. 

“Early identification of older drivers who are at risk for accidents is a public health priority, but identifying people who are unsafe is challenging and time-consuming,” said Babulal.

He noted that the data stream can be collected passively, without asking older adults to spend extra time in clinics or labs. 

Monitoring cognitive skills

“Looking at people’s daily driving behavior is a relatively low-burden, unobtrusive way to monitor people’s cognitive skills and ability to function,” said Babulal.

Still, the study mostly involved white, highly educated participants, so it cannot yet tell whether the same driving signals appear in more diverse communities. 

Any system that flags cognitive changes from in car technology must respect privacy, ensure consent, and avoid penalizing drivers for age or neighborhood.

In practice, this kind of monitoring could help doctors notice when a patient begins shrinking their driving world before family members see problems. 

For older adults, the same information might help them plan a gradual driving retirement on their terms instead of waiting for a serious crash.

The study is published in the journal Neurology.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–