It should hardly come as a surprise that dementia and mild cognitive impairment (MCI) would have an impact on driving. Researchers have found, though, that driving data could be a useful tool in diagnosing those conditions, too.

According to new research published in the Geriatrics journal, using driving data as well as demographics information, dementia and MCI can be consistently predicted.

“Based on variables derived from the naturalistic driving data and basic demographic characteristics, such as age, sex, race/ethnicity, and education level, we could predict mild cognitive impairment and dementia with 88% accuracy,” Sharon Di, lead author on the new study, told New Atlas.

Read Also: Volvo Has Been Investigating Car Crashes For Half A Century

The study used data from The Longitudinal Research on Aging Drivers (LongROAD), which tracked 3,000 older drivers for up to four years, over the course of which 33 subjects were diagnosed with MCI and 31 with dementia.

The team then trained a series of machine learning models to detect the medical conditions based on subjects’ driving behavior. Although the model is promising, there’s still more work to be done.

Moreover, even though the model is 88% accurate with demographic information, it’s only 66% accurate driving data alone. That’s because age is the number one factor for detecting MCI and dementia. But the driving data can help.

How many trips are taken within 15 miles (24 km) of home, the length of trips starting and ending at home, minutes per trip, and the number of hard braking events of more than 0.35g were all helpful indicators of these issues.

With so few cases of MCI and dementia in the LongROAD study, though, the team is quick to add that more data is needed. But the research remains valuable.

“Our study indicates that naturalistic driving behaviors can be used as comprehensive and reliable markers for mild cognitive impairment and dementia,” said senior author Guohua Li. “If validated, the algorithms developed in this study could provide a novel, unobtrusive screening tool for early detection and management of mild cognitive impairment and dementia in older drivers.”