Summary: Researchers found that long-term driving behavior can reveal early signs of cognitive impairment years before clinical diagnosis. Older adults who subsequently developed impairment showed gradual reductions in travel frequency, nighttime driving, and route variety compared to their cognitively healthy peers.
Machine learning models using GPS data predicted cognitive decline more accurately than age, genetics, or cognitive testing alone. This low-burden follow-up approach could allow for earlier interventions while preserving independence and safety.
Key facts
Passive detection: GPS driving patterns predicted cognitive decline with up to 87% accuracy. Early behavioral changes: reduced night driving, shorter trips, and reduced route variation indicated risk. Real-world monitoring: Daily driving outperformed traditional detection methods alone.
Source: AAN
Using in-vehicle driving data may be a new way to identify people at risk of cognitive decline, according to a study published Nov. 26, 2025, in Neurology.
“Early identifying older drivers who are at risk for accidents is a public health priority, but identifying unsafe people is challenging and time-consuming,” said study author Ganesh M. Babulal, PhD, OTD, of Washington University School of Medicine in St. Louis, Missouri.
“We found that by using a GPS data tracking device, we could more accurately determine who had developed cognitive problems than simply looking at factors such as age, cognitive test scores, and whether they had a genetic risk factor related to Alzheimer’s disease.”
The study included 56 people with mild cognitive impairment, which is a precursor to Alzheimer’s disease, and 242 cognitively healthy people with an average age of 75 years. All participants drove at least once a week at the start of the study.
Participants agreed to take thinking skills tests and install the data tracking device in their vehicles. They were then followed for more than three years.
Although the driving patterns of the two groups were similar at the beginning of the study, over time older adults with mild cognitive impairment had greater reductions in the number of times they drove each month, how often they drove at night, and how much they varied their routines where they drove.
The researchers used driving factors such as average and maximum travel distance, how often people exceeded the speed limit, and how much they varied their routine to predict whether a person had developed mild cognitive impairment with 82% accuracy.
Once they added age and other demographic factors, cognitive test scores, and whether people had a gene associated with Alzheimer’s, accuracy improved to 87%. In comparison, using all those factors without any driving information resulted in an accuracy of 76%.
“Observing people’s daily driving behavior is an unobtrusive and relatively simple way to monitor people’s cognitive abilities and ability to function,” Babulal said.
“This could help identify drivers who are at risk earlier for early intervention, before they get into an accident or near-accident, which is often what happens now. Of course, we must also respect people’s autonomy, privacy and informed decision-making and ensure ethical standards are met.”
A limitation of the study is that the majority of participants were highly educated white people, so the results may not be generalizable to the general population.
Funding: The study was supported by the National Institutes of Health and the National Institute on Aging.
Key questions answered:
A: Yes. Subtle changes in routine, distance, and nighttime driving predicted cognitive decline with high accuracy.
A: Driving data predicted impairment with up to 87% accuracy, single-handedly outperforming traditional screening tests.
A: Yes. Passive, continuous monitoring could identify risks before significant symptoms or dangerous driving occur.
Editorial notes:
This article was edited by a Neuroscience News editor. Magazine article reviewed in its entirety. Additional context added by our staff.
About this cognitive impairment and neurology research news
Author: Renée Tessman
Source: AAN
Contact: Renée Tessman – AAN
Image: Image is credited to Neuroscience News.
Original research: Open access.
“Association of daily driving behaviors with mild cognitive impairment in older adults followed for 10 years” by Ganesh M. Babulal et al. Neurology
Abstract
Association of daily driving behaviors with mild cognitive impairment in older adults followed for 10 years
Background and objectives
Driving integrates multiple cognitive, sensory, and motor systems and may serve as a real-world indicator of functional decline in aging. Older adults with mild cognitive impairment (MCI) often experience subtle changes in driving before formal dementia diagnosis, but real-world longitudinal evidence is limited.
This study examined whether naturalistic driving data can differentiate older adults with MCI from those with normal cognition (NC) over time and evaluated the discriminative ability of driving characteristics compared to conventional risk factors.
Methods
We conducted a prospective observational cohort study of community-dwelling older drivers enrolled in the Real-World Driving Vehicle Assessment System Project at the University of Washington. Participants underwent an annual clinical dementia rating evaluation, neuropsychological testing, and apolipoprotein ε4 (APOE ε4) genotyping.
Driving behaviors were captured daily for up to 40 months using data loggers integrated into the global positioning system, recording trip frequency, duration, distance, time of day, speeding, hard braking, and spatial mobility (entropy, maximum distance, turning radius).
Longitudinal changes were analyzed using linear mixed-effects models, adjusting for age, sex, race, education, and APOE ε4. Logistic regression with receiver operator curve analysis assessed discrimination between older adults with mild cognitive impairment and those with CKD, compared with conventional sociodemographic and genetic markers.
Results
Among 298 participants (MCI, n = 56; NC, n = 242; mean age 75.1 years; 45.6% female), the groups were similar in age, sex, race, and APOE ε4 status at baseline, as well as in most driving behaviors. Over time, drivers with MCI showed greater reductions in monthly trip count (MCI: −0.501, standard error (SE): 0.21, 95% CI (−0.923 to −0.083) vs NC: −0.523, SE: 0.09, 95% CI (−0.709 to −0.337); p < 0.001), night trips (MCI: −0.334, SE: 0.17, 95% CI (−0.675 to 0.001) vs NC: −0.339, SE: 0.07, 95% CI (−0.480 to −0.197) and random entropy (MCI: −0.008, SE: 0.004, 95% CI); (-0.016 to -0.001); NC: -0.014, SE: 0.002, 95% CI (-0.017 to -0.011);
Key characteristics, such as mean trip distance, speeding events, entropy, and maximum distance, distinguished drivers with MCI from those with NC (area under the curve (AUC) 0.82, 95% CI 0.75 to 0.89). Adding demographics, APOE ε4, and cognitive composite improved the AUC to 0.87 (95% CI: 0.81 to 0.93).
Discussion
MCI was associated with progressive decreases in driving frequency, complexity, and spatial range, supporting naturalistic driving data as a potential discrete digital biomarker for early cognitive decline. Limitations of the study include a predominantly white, highly educated sample, and a lack of external validation, warranting cautious interpretation. Continuous monitoring could augment clinical assessments, inform driving safety decisions, and guide interventions to preserve mobility in aging.
