Smart driving technology for non-invasive detection of age-related cognitive decline

Dementia and other age-related neurodegenerative diseases such as Alzheimer’s Disease (AD) and Alzheimer’s Disease Related Dementias (ADRD) cause a marked decrease in quality of life for patients, an increased burden of care, and, for adults over 65, are a leading cause of death. Therefore, better understanding of the nature of

dementia is vital to the development and assessment of effective treatment options. Despite the grim lookout, clinical research suggests that intervening the disease before irreversible brain damage occurs is a key step to improve the outcomes of AD/ADRD. Specifically, Mild Cognitive Impairment (MCI), the stage before the onset of

dementia, could provide the largest “window of opportunity” for lifestyle interventions that can delay/prevent MCI and dementia. Our team has reported lifestyle changes which brings a window of opportunity for the disease treatment prior to irreversible brain damages. Several studies have demonstrated a relationship between MCI and driving performance including driving

behaviors. Although driving features provide an unobstructive window of opportunity to test the brain responses under everyday cognitive challenges, it is currently unrealistically costly and labor-intensive to be widely deployed. We hypothesize an unobstructive, continuous, economical system capable of assessing

driving signatures that can detect early stages of neurodegenerative diseases would offer a window to reverse AD and ADRD. In this work, we propose to develop and validate an unobtrusive and car-make agnostic sensing system, named Smart Pad, for daily assessment of driving indicators under free-living conditions. The

system: 1) automatically records and analyzes data with the integrated biosensor array and a mobile App to evaluate driving; 2) uses the biosensors array to detect not only driving habits, but also new driving performance indicators and unprecedented driver’s biomarker (posture and metabolic rate), which are

correlated with detrimental cognitive stages, and 3) is empowered by an Artificial Intelligence (AI) algorithm to predict cognitive performance and MCI. In this Phase I proposal, we will leverage the Smart Pad prototype design that we have developed and optimize it to for the diagnosis of driver’s cognitive status.

The TF Health Co.-ASU-BNI team will work together to build the unobtrusive, vehicle-based sensing system for daily assessment of driver performance and biometrics, and age-related cognitive decline to develop new technology for early diagnosis of dementia in free-living condition, seeking to improve patient care

options and promote cognitive decline prevention interventions.