Using naturalistic driving data and machine learning techniques, researchers at Columbia University’s Mailman School of Public Health and Columbia’s Fu Foundation School of Engineering and Applied Science developed highly precise algorithms to detect mild cognitive impairment and dementia in older drivers. Naturalistic driving data refers to data captured by on-board recording devices or other technologies in the real world. This data could be processed to measure driving exposure, space and performance in great detail. The results are published in the journal Geriatrics.
The researchers developed models of random forests, a statistical technique widely used in AI to classify disease status, which worked exceptionally well. “Based on variables derived from 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, ”said Sharon Di, associate professor of civil science. engineering and engineering mechanics at Columbia Engineering and lead author of the study.
Investigators constructed 29 variables using naturalistic driving data captured by on-board recording devices from 2,977 participants in the Longitudinal Research on Aging Drivers (LongROAD) project, a multi-site cohort study sponsored by the AAA Road Safety Foundation. . At the time of enrollment, participants were active drivers aged 65 to 79 and had no significant cognitive impairment or degenerative medical conditions. The data used in this study covered the period from August 2015 to March 2019.
Of the 2,977 participants whose cars were fitted with on-board recording devices, 33 were newly diagnosed with mild cognitive impairment and 31 with dementia in April 2019. The researchers trained a series of machine learning models to detect mild cognitive impairment / dementia and found the model based on motor variables and demographic characteristics to be 88% accurate, much better than models based only on demographic characteristics (29%) and motor variables only (66% ). Further analysis found that age was the most predictor of mild cognitive impairment and dementia, followed by percentage of trips made within 15 miles of home, race / ethnicity, minutes per trip chain (ie, duration of trips starting and ending at home), minutes per trip and number of hard braking events with deceleration rates ≥ 0.35 g.
“Driving is a complex task involving dynamic cognitive processes and requiring essential cognitive functions and perceptual motor skills. Our study indicates that naturalistic driving behaviors can be used as comprehensive and reliable markers for mild cognitive impairment and dementia, ”said Guohua Li, MD, DrPH, professor of epidemiology and anesthesiology at the Columbia Mailman School of Public Health and the Vagelos College of Physicians and Surgeons, and senior author. “If validated, the algorithms developed in this study could provide a new discreet screening tool for the early detection and management of mild cognitive impairment and dementia in older drivers.”
Source of the story:
Material provided by Columbia University Mailman School of Public Health. Note: Content can be changed for style and length.