Using kinematic driving data to detect sleep apnea treatment adherence

Anthony D. McDonald, John D. Lee, Nazan S. Aksan, Jeffrey D. Dawson, Jon Tippin, Matthew Rizzo

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

People spend a significant amount of time behind the wheel of a car. Recent advances in data collection facilitate continuously monitoring this behavior. Previous work demonstrates the importance of this data in driving safety but does not extended beyond the driving domain. One potential extension of this data is to identify driver states related to health conditions such as obstructive sleep apnea (OSA). We collected driving data and medication adherence from a sample of 75 OSA patients over 3.5 months. We converted speed and acceleration behaviors to symbols using symbolic aggregate approximation and converted these symbols to pattern frequencies using a sliding window. The resulting frequency data was matched with treatment adherence information. A random forest model was trained on the data and evaluated using a held-aside test dataset. The random forest model detects lapses in treatment adherence. An assessment of variable importance suggests that the important patterns of driving in classification correspond to route decisions and patterns that may be associated with drowsy driving. The success of this approach suggests driving data may be valuable for evaluating new treatments, analyzing side effects of medications, and that the approach may benefit other drowsiness detection algorithms.

Original languageEnglish (US)
Pages (from-to)422-434
Number of pages13
JournalJournal of Intelligent Transportation Systems: Technology, Planning, and Operations
Volume21
Issue number5
DOIs
StatePublished - Sep 3 2017

Fingerprint

Sleep
Kinematics
Wheels
Railroad cars
Random Forest
Health
Monitoring
Sliding Window
Wheel
Driver
Safety
Approximation
Model
Demonstrate

Keywords

  • driving
  • drowsiness
  • machine learning
  • sleep disorders
  • symbolic aggregate approximation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Information Systems
  • Automotive Engineering
  • Aerospace Engineering
  • Computer Science Applications
  • Applied Mathematics

Cite this

Using kinematic driving data to detect sleep apnea treatment adherence. / McDonald, Anthony D.; Lee, John D.; Aksan, Nazan S.; Dawson, Jeffrey D.; Tippin, Jon; Rizzo, Matthew.

In: Journal of Intelligent Transportation Systems: Technology, Planning, and Operations, Vol. 21, No. 5, 03.09.2017, p. 422-434.

Research output: Contribution to journalArticle

McDonald, Anthony D. ; Lee, John D. ; Aksan, Nazan S. ; Dawson, Jeffrey D. ; Tippin, Jon ; Rizzo, Matthew. / Using kinematic driving data to detect sleep apnea treatment adherence. In: Journal of Intelligent Transportation Systems: Technology, Planning, and Operations. 2017 ; Vol. 21, No. 5. pp. 422-434.
@article{de15124aac6b4c839ba2c8ebb858ddba,
title = "Using kinematic driving data to detect sleep apnea treatment adherence",
abstract = "People spend a significant amount of time behind the wheel of a car. Recent advances in data collection facilitate continuously monitoring this behavior. Previous work demonstrates the importance of this data in driving safety but does not extended beyond the driving domain. One potential extension of this data is to identify driver states related to health conditions such as obstructive sleep apnea (OSA). We collected driving data and medication adherence from a sample of 75 OSA patients over 3.5 months. We converted speed and acceleration behaviors to symbols using symbolic aggregate approximation and converted these symbols to pattern frequencies using a sliding window. The resulting frequency data was matched with treatment adherence information. A random forest model was trained on the data and evaluated using a held-aside test dataset. The random forest model detects lapses in treatment adherence. An assessment of variable importance suggests that the important patterns of driving in classification correspond to route decisions and patterns that may be associated with drowsy driving. The success of this approach suggests driving data may be valuable for evaluating new treatments, analyzing side effects of medications, and that the approach may benefit other drowsiness detection algorithms.",
keywords = "driving, drowsiness, machine learning, sleep disorders, symbolic aggregate approximation",
author = "McDonald, {Anthony D.} and Lee, {John D.} and Aksan, {Nazan S.} and Dawson, {Jeffrey D.} and Jon Tippin and Matthew Rizzo",
year = "2017",
month = "9",
day = "3",
doi = "10.1080/15472450.2017.1369060",
language = "English (US)",
volume = "21",
pages = "422--434",
journal = "Journal of Intelligent Transportation Systems",
issn = "1547-2450",
publisher = "Taylor and Francis Ltd.",
number = "5",

}

TY - JOUR

T1 - Using kinematic driving data to detect sleep apnea treatment adherence

AU - McDonald, Anthony D.

AU - Lee, John D.

AU - Aksan, Nazan S.

AU - Dawson, Jeffrey D.

AU - Tippin, Jon

AU - Rizzo, Matthew

PY - 2017/9/3

Y1 - 2017/9/3

N2 - People spend a significant amount of time behind the wheel of a car. Recent advances in data collection facilitate continuously monitoring this behavior. Previous work demonstrates the importance of this data in driving safety but does not extended beyond the driving domain. One potential extension of this data is to identify driver states related to health conditions such as obstructive sleep apnea (OSA). We collected driving data and medication adherence from a sample of 75 OSA patients over 3.5 months. We converted speed and acceleration behaviors to symbols using symbolic aggregate approximation and converted these symbols to pattern frequencies using a sliding window. The resulting frequency data was matched with treatment adherence information. A random forest model was trained on the data and evaluated using a held-aside test dataset. The random forest model detects lapses in treatment adherence. An assessment of variable importance suggests that the important patterns of driving in classification correspond to route decisions and patterns that may be associated with drowsy driving. The success of this approach suggests driving data may be valuable for evaluating new treatments, analyzing side effects of medications, and that the approach may benefit other drowsiness detection algorithms.

AB - People spend a significant amount of time behind the wheel of a car. Recent advances in data collection facilitate continuously monitoring this behavior. Previous work demonstrates the importance of this data in driving safety but does not extended beyond the driving domain. One potential extension of this data is to identify driver states related to health conditions such as obstructive sleep apnea (OSA). We collected driving data and medication adherence from a sample of 75 OSA patients over 3.5 months. We converted speed and acceleration behaviors to symbols using symbolic aggregate approximation and converted these symbols to pattern frequencies using a sliding window. The resulting frequency data was matched with treatment adherence information. A random forest model was trained on the data and evaluated using a held-aside test dataset. The random forest model detects lapses in treatment adherence. An assessment of variable importance suggests that the important patterns of driving in classification correspond to route decisions and patterns that may be associated with drowsy driving. The success of this approach suggests driving data may be valuable for evaluating new treatments, analyzing side effects of medications, and that the approach may benefit other drowsiness detection algorithms.

KW - driving

KW - drowsiness

KW - machine learning

KW - sleep disorders

KW - symbolic aggregate approximation

UR - http://www.scopus.com/inward/record.url?scp=85029412367&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029412367&partnerID=8YFLogxK

U2 - 10.1080/15472450.2017.1369060

DO - 10.1080/15472450.2017.1369060

M3 - Article

C2 - 30344458

AN - SCOPUS:85029412367

VL - 21

SP - 422

EP - 434

JO - Journal of Intelligent Transportation Systems

JF - Journal of Intelligent Transportation Systems

SN - 1547-2450

IS - 5

ER -