- Individuals with Alzheimer’s disease exhibit impairments in their ability to drive, with these deficits emerging in the early stages of dementia.
- Researchers of a new study found that older adults with mild cognitive impairment (MCI) drove less—especially long distances—than those with normal cognition.
- The study’s findings suggest that driving patterns could be used as a digital biomarker to spot cognitive impairment and associated deficits in driving performance.
Individuals with cognitive impairment are at a two- to five-fold increased risk of being involved in motor accidents, highlighting the deterioration of driving skills with the decline in cognitive function.
A recent study published in Neurology suggests that changes in daily driving patterns recorded using a vehicle datalogger could reliably distinguish individuals with mild cognitive impairment (MCI) from those with normal cognition.
The present study’s findings suggest that data collected by vehicle data loggers could be potentially used in the early identification of individuals at risk of a motor crash or those with cognitive impairment, prior to in-person cognitive assessments or brain imaging scans.
Driving data patterns could also serve as a tool to assess the effectiveness of interventions for treating cognitive impairment.
Mill Etienne, MD, an associate professor of neurology and medicine at New York Medical College, who was not involved in this research, told Medical News Today:
“Real-world driving behavior appears to be a promising digital biomarker for detecting early cognitive impairment. These subtle, progressive changes in mobility and driving patterns may help clinicians identify emerging cognitive impairment earlier, guide decisions around driving safety, and support timely interventions to preserve independence and mobility in aging adults.”
Individuals with Alzheimer’s disease show deficits in driving performance, owing to not only cognitive deficits but also sensory and motor impairments.
Consistently, studies have shown that individuals with Alzheimer’s disease are at an increased risk of at-fault crashes compared with those with normal cognition.
In addition, studies suggest that this deterioration in driving performance appears in the early stages of dementia.
Specifically, studies have shown that even older adults with MCI or early-stage Alzheimer’s disease show deficits in driving performance in simulator and
Even individuals showing increased expression of Alzheimer’s disease biomarkers, such as increased accumulation of beta amyloid protein in the brain, but with normal cognitive function, tend to show inferior performance in driving tests.
Together, these studies suggest that driving-related impairments arise during the early stages of Alzheimer’s disease or MCI, before symptoms become severe enough for a dementia diagnosis.
The subtle changes in driving performance and cognitive function during the early stages of dementia are often missed by family members and clinicians.
The use of an in-vehicle tracking device or datalogger can help identify changes in daily driving patterns, such as the time of trip initiation during the day or the number of trips, and potentially identify individuals with deficits in driving performance and cognitive impairments.
The continuous tracking of driving patterns could thus potentially help narrow down individuals for cognitive assessments and subsequent brain scans to identify structural changes associated with dementia.
The present study characterised how individuals with MCI differ from those with normal cognition in their day-to-day driving patterns over a follow-up period of up to 40 months using an in-vehicle tracking device.
The study consisted of 298 participants aged at least 65 who underwent a cognitive assessment at enrollment and then annually. Based on the initial cognitive assessments, 56 participants had MCI, whereas the remaining 242 had normal cognition.
The researchers used a global positioning system-enabled tracking device or datalogger to assess the participants’ driving performance.
The datalogger assessed variables, such as the number of trips, the time of the trip during the day, distance travelled, location of the destination, the number of trips, and the frequency of speeding, hard braking, and hard cornering.
During the follow-up period of up to 40 months, older adults with MCI made fewer trips, especially at night, than their counterparts with normal cognition.
Participants with MCI were also less likely to undertake long-distance trips and were more likely to avoid newer or unpredictable environments, sticking to familiar routes. Individuals with MCI showed an increase in the frequency of hard cornering during the follow-up period.
The researchers note that some of these changes in driving patterns, such as avoiding longer trips or unpredictable environments, could be adaptive strategies deployed by individuals with MCI to counteract the decline in their driving abilities.
In contrast, the more frequent instances of hard cornering could be attributed to the decline in driving performance.
The researchers then examined whether the participants’ driving patterns, as measured using the in-vehicle datalogger, could predict their cognitive status.
The ability of changes in driving patterns to predict cognitive status could aid in the early identification of individuals at risk of cognitive decline and unsafe driving.
In the present study, the researchers were able to predict the cognitive status of the participants solely based on driving patterns with a high level of accuracy.
In addition, the inclusion of data from cognitive assessments, age, sex, race, education, and genetic predisposition further improved the accuracy of the model.
Notably, the model based on driving patterns was more accurate in discriminating between individuals with and without MCI than models based on cognitive test scores, sex, age, race, education, and genetic predisposition.
While acknowledging that the ability of daily driving patterns to predict cognitive impairments needs to be validated using an external dataset, the researchers suggest that in-vehicle data sensors could help provide insights into changes in cognitive function during the period between annual cognitive assessments.
The researchers suggest that these results indicate the potential utility of data from dataloggers in facilitating the identification of individuals with cognitive impairment and at risk of a motor crash.
However, they noted that the study’s participants were predominantly white and highly educated, limiting the generalizability of these results.
Guoha Li, MD, DrPH, Professor of Epidemiology and Anesthesiology at Columbia University, who was not involved in this research, noted to MNT that:
“This study is limited by its modest sample size and comparative cohort design. The former makes it impractical to perform more nuanced analysis, such as analysis stratified by gender and race, and the latter lessens interpretive value and hinders causal inference.”
In addition, the differences in driving patterns observed in the study could also be influenced by factors beyond those directly associated with MCI, including caregiver input, social support, use of medications, other medical conditions, and variables related to the type and condition of the vehicle.
Hence, the driving metrics used in this study need to be validated using an external, more diverse sample.
“It would also be valuable in future research to compare these driving-based digital biomarkers with established biological markers of Alzheimer’s disease, such as PET amyloid imaging or emerging blood-based biomarkers, to better understand how changes in driving behavior align with underlying neuropathology,” Etienne also noted.
