Researchers at Florida Atlantic University have found that in-vehicle sensor data can detect subtle differences in driving behavior between cognitively healthy older adults and those showing early signs of cognitive decline, according to a study published in the journal Sensors.
The study analyzed nearly 4,800 real-world driving trips from 36 older adults. Researchers installed sensors in participants’ vehicles and tracked their driving over three years. Participants also underwent neuropsychological testing every three months during that period.
The sensor network, developed by FAU College of Engineering and Computer Science researchers, uses commercially available hardware and software. The compact system includes two units, one for telematics data and one for video, and is designed to be unobtrusive.
Each recorded trip captures measures including distance traveled, trip duration, average and maximum speed, engine performance, throttle patterns, fuel level, and counts of driving events such as hard braking, rapid acceleration, and sharp turns.
Researchers compared trip-level data between cognitively unimpaired drivers and those with pre-mild cognitive impairment or mild cognitive impairment. Drivers with pre-MCI or MCI tended to show less consistent control of the gas pedal, took shorter or more fragmented trips and demonstrated less efficient speed regulation. Cognitively unimpaired drivers, by contrast, drove at higher average speeds, braked more frequently when needed, and maintained steadier use of the accelerator.
Importantly, no single behavior, by itself, distinguished the groups. Instead, the combination of driving behaviors together produced the most accurate results.
“When all the behaviors were analyzed together, the model was highly accurate at distinguishing cognitively unimpaired drivers from those with early impairment,” said Ruth Tappen, a professor and eminent scholar in FAU’s Christine E. Lynn College of Nursing and senior author of the study. “Everyday driving habits, captured passively through in-car sensors, may offer a powerful new way to detect subtle cognitive changes long before they become obvious.”
The research comes as the number of older drivers in the United States continues to grow. More than 50 million licensed drivers nationwide are age 65 or older, including roughly 5 million in Florida. The study notes that driving is a complex activity that involves memory, attention, and decision-making, yet most prior research has relied on simulations or self-reports rather than on actual driving behavior.
The study was funded by the National Institutes of Health’s National Institute on Aging. Researchers note that the work is ongoing and that early-stage cognitive changes, when detected, may represent a window of opportunity for intervention.
Get the latest insurance market updates and discover exclusive program opportunities at ProgramBusiness.com.