For a better experience, click the Compatibility Mode icon above to turn off Compatibility Mode, which is only for viewing older websites.

Tuesday Topics: DETECTING DROWSY DRIVING BEHAVIOR IN PATIENTS WITH SLEEP APNEA

Tuesday, June 18, 2019

2:00 PM-3:00 PM

Obstructive sleep apnea (OSA) is a sleep disorder involving the repetitive collapse of the upper airway during sleep, which results in impaired sleep and chronic drowsiness. Individuals with untreated OSA have an increased risk for motor vehicle crashes. Impairment from drowsiness is one mechanism that might explain the added risk. To observe the effects of untreated OSA on driving behavior in a real-world context, a study was conducted in which naturalistic driving data was collected from individuals with untreated OSA and a control group. One challenge in using naturalistic driving data is producing a holistic analysis of these highly variable datasets that enables a comparison of driver behaviors. Typical analyses focus on isolated events, such as large g-force accelerations indicating a possible near-crash. Examining isolated events is ill-suited for identifying patterns in continuous activities such as maintaining vehicle control. I will describe the results of a study which used topic models in an alternate approach for the analysis of these data. The study results provide a foundation for investigating the use of feedback to patients with OSA about how treatment impacts their everyday performance in high-risk situations, such as driving, as a motivational strategy to increase treatment adherence.

Presenter:
Elease McLaurin, PhD, is a recent graduate from the University of Wisconsin-Madison. Her work in the field of human factors engineering has focused on identifying ways to improve patient health management once they leave the hospital or clinic environment. Her specific research interests include the development of data analysis tools to expand the methods available for understanding naturalistic decision making. McLaurin will be presenting work from her dissertation on the use of machine learning methods to understand the impact of sleep impairment from obstructive sleep apnea on naturalistic driving behavior.

Open to any doctoral students or faculty within the College.
 

Remind me about this event. Notify me if this event changes. Add this event to my personal calendar.

Location

Tuesday, June 18, 2019
2:00 - 3:00 p.m.
Three Parkway, Room 639 or via live webcast

Audience

  • Everyone