Driving Safety and Real-Time Glucose Monitoring in Insulin-Dependent Diabetes

Abstract

Our goal is to address the need for driver-state detection using wearable and in-vehicle sensor measurements of driver physiology and health. To address this goal, we deployed in-vehicle systems, wearable sensors, and procedures capable of quantifying real-world driving behavior and performance in at-risk drivers with insulin-dependent type 1 diabetes mellitus (DM). We applied these methodologies over 4 weeks of continuous observation to quantify differences in realworld driver behavior profiles associated with physiologic changes in drivers with DM (N=19) and without DM (N=14). Results showed that DM driver behavior changed as a function of glycemic state, particularly hypoglycemia. DM drivers often drive during at-risk physiologic states, possibly due to unawareness of impairment, which in turn may relate to blunted physiologic responses (measurable heart rate) to hypoglycemia after repeated episodes of hypoglycemia. We found that this DM driver cohort has an elevated risk of crashes and citations, which our results suggest is linked to the DM driver's own momentary physiology. Overall, our findings demonstrate a clear link between at-risk driver physiology and real-world driving. By discovering key relationships between naturalistic driving and parameters of contemporaneous physiologic changes, like glucose control, this study directly advances the goal of driver-state detection through wearable physiologic sensors as well as efforts to develop "gold standard" metrics of driver safety and an individualized approach to driver health and wellness.

Quantifying vehicle control from physiology in type 1 diabetes

“…Our results are consistent with prior studies suggesting that vehicle control impairments due to hypoglycemia may persist for hours after hypoglycemia resolves (Weinger et al 1999;Merickel et al 2019), even in T1D drivers whose blood glucose levels are currently normal. We find that impairments due to prior hypoglycemia affect vehicle control behavior for 2-3 hours after hypoglycemia resolves, which provides an important foundation for developing objective, clinical recommendations to preserve safety in at-risk drivers with diabetes.…”

“…Vehicle Control Outcomes: Vehicle control was modeled using acceleration variability (AV) across lateral (AVy, steering) and longitudinal (AVx, braking/accelerating) axes in 45-second segments (Bishop et al 2018). Vehicle acceleration has been used previously in the literature to identify individual driver patterns (Fung et al 2017), risky driving (Kluger et al 2014), crashes/crash severity (Stipancic et al 2018), and driver impairments (Merickel et al 2019). Increased AV can be linked to erratic driving, harsh braking and accelerating, poor steering control, lane variability, and swerving (Palat et al 2019).…”

“…Increased AV can be linked to erratic driving, harsh braking and accelerating, poor steering control, lane variability, and swerving (Palat et al 2019). Decreased AV has been linked to attentional impairments, reduced driver responsiveness to the environment, and may indicate failure to appropriately adjust the vehicle relative to the roadway or other on-road vehicles (Merickel et al 2019). To calculate AV, each drive was divided into 45-seconds segments and AV was calculated using the standard deviation of lateral/longitudinal acceleration values.…”

Real-Time Effects of Age-Related Cognitive Dysfunction on Driver Vehicle Control

“…Increased AV is linked to erratic driving, poor control, swerving, and harsh braking and accelerating (McGehee et al, 2007a;McGehee et al, 2007b;Aksan et al, 2017;Palat et al, 2019). Decreased AV is linked to decreased driver responsiveness to the environment, attentional impairments, and driver distraction and may indicate failure to appropriately adjust the vehicle relative to the roadway or other on-road vehicles (Thompson et al, 2012;Merickel et al, 2019). Vehicle control was modeled using beta regression models with a by-subject random intercept.…”

A Review on Measuring Affect with Practical Sensors to Monitor Driver Behavior

“…Figure 1 illustrates a pressure sensor for tracking a driver's grip pressure in (a) a body-worn format, and (b) a vehicle surface format. Wearable sensors such as the glove in (a) are more practical for daily use than, for example, blood sampling to measure glucose [2] or cortisol levels, or neural implants to detect brain activity in animal studies. Such invasive sampling can validate conclusions drawn from proxy signals available at the body surface, but a sensor glove is better for daily wear from the user's viewpoint.…”