2024-02-29 20:57:55
An estimated 4 to 8 million adults with mild cognitive impairment are driving in the United States today, and one-third of them will develop dementia within five years. People with advanced dementia are eventually unable to drive safely, but many are still unaware of their cognitive decline.
Currently, screening and assessment services for driving can only screen a small number of people with cognitive concerns, missing many who need to know if they need treatment.
Nursing, engineering and neuropsychology researchers at Florida Atlantic University are testing and evaluating an available, fast, non-invasive in-vehicle sensing system they have developed. This technology could provide the first step toward future widespread and low-cost early warnings of cognitive change for this large number of older drivers in the US and elsewhere.
In their study, published in the journal BMC Geriatrics, They are systematically testing how this system can detect abnormal driving behavior that indicates cognitive impairment. Few studies have reported the use of continuous and non-invasive sensors and associated monitoring devices to detect subtle variation in the performance of highly complex daily activities over time. This significant proportion of older drivers presents a previously unexplored opportunity to detect cognitive decline.
The neuropathologies of Alzheimer’s disease were found in the brains of elderly drivers who were killed in car accidents, who did not even know they had the disease and had no obvious signs of it. The purpose of our study was due to the importance of identifying disorders of cognitive function as early and efficiently as possible. Sensor systems installed in the vehicles of old drivers may detect these changes and can create early warnings of possible changes in cognition.”
Ruth Tappen, Ed.D., principal investigator, senior author, and Christine A. Distinguished Scholar and Professor. Lynn, the FAU, Christine E. Lynn College of Nursing
The study uses a naturalistic longitudinal design to obtain continuous information on driving behavior compared to the results of comprehensive cognitive tests conducted every three months for three years. A camera facing the driver, a camera facing forward and a telematics unit are installed in the vehicle and the data is downloaded every three months when the cognitive tests are performed.
Researchers measure abnormal driving such as getting lost, ignoring traffic signs and traffic signs, near-collision incidents, distraction and drowsiness, reaction time and braking patterns. They also look at driving patterns such as number of trips, miles driven, highway miles, night and day miles, and driving in severe weather.
The automotive sensor network developed by FAU researchers in the College of Engineering and Computer Science uses open source hardware and software components to reduce the time, risk and costs associated with developing in-vehicle sensing units. In-vehicle sensor systems are kept simple and compact by minimizing complex wiring, limiting the size of sensing units, and limiting the number of in-vehicle sensors to support the lack of in-vehicle sensor linguistics. Each sensor system in a vehicle consists of two distributed sensing units: one for telematics data and the other for video data.
Inertial measurement unit data is processed to determine hard braking, hard accelerations and hard turns and GPS data. It also includes time stamp, latitude, longitude, altitude, orbit on the ground and number of communicating satellites.
The video unit has built-in artificial intelligence functions that analyze video in real time. The camera facing the driver is installed in the left corner of the windshield and is aimed at the driver’s face to analyze his behavior and facial expressions. The forward-facing camera is installed under the rearview mirror and is used to record events outside the vehicle.
The driver-facing metrics include facial recognition, eye recognition (open or closed), yawning, distraction, smoking, and mobile phone use. Behavioral metrics include traffic sign detection (running a red light), object detection (pedestrians, cyclists, curbs, barriers, or nearby vehicles), lane crossing, near-collision, and pedestrian detection.
“These measures of driver behavior related to driving patterns are known to indicate the changes in cognition and physical functioning of older drivers as they tend to incorporate intentional avoidance strategies to compensate for age-related impairments,” Tappen said. “Driver behavior indicators are evaluated for each driver and summarized on a daily, weekly and monthly basis and classified into four categories.”
A total of 460 participants in the study will be recruited from Broward and Palm Beach counties in southeast Florida and they are classified into three diagnostic groups: mild cognitive impairment, early dementia and no defects (normal). The Louis Van Green Memory and Health Center operated by FAU’s College of Nursing serves as a testing site for a clinical battery that includes assessments of cognition, functioning in daily activities and mood (depression), and another set of tests that includes executive functioning and attention.
“The innovation of our research project lies in the non-invasive, available and fast in-vehicle sensing and monitoring system built on modern open source hardware and software using existing techniques to develop and customize the components and configure them for this new purpose.” Tappan said.
The research was supported by a grant from the National Institute on Aging, National Institutes of Health (1R01AG068472) awarded to Tappen.
#innovative #car #sensing #system #helps #detect #cognitive #decline #older #drivers