Highway healthcare: How naturalistic driving data index adherence to CPAP therapy in obstructive sleep apnea

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Drowsy driving is a major factor in many vehicle crashes around the world. Sleep disorders, such as obstructive sleep apnea (OSA), underpin many of these crashes. Continuous positive airway pressure (CPAP) therapy is an effective treatment for sleep apnea but it requires consistent use and is often rejected by OSA patients. Rejection of CPAP treatment creates a dangerous on-road environment for both OSA sufferers and the general public. Algorithms capable of detecting CPAP use and its effects on driving are integral to identifying and mitigating this danger. This work uses naturalistic kinematic driving data to develop an algorithm which can detect nightly CPAP abstinence and adequate CPAP use. Speed and lateral acceleration data were collected using a data recorder in participant's primary vehicle and CPAP data were collected by downloading adherence data from participant CPAP machines. The speed and acceleration data were reduced to a set of symbols using Symbolic Aggregate approximation (SAX) time-series analysis. The symbols were converted into a sequence frequency dataset using sliding windows of size 1 to 10 s with a 1 Hz sampling rate. A Random Forest classifier was trained on the data to create a classification algorithm. On a held aside testing set, the Random Forest algorithm correctly identified 71% of the instances and had an area under the receiver operating characteristic curve of 0.76. The variable importance of the algorithm suggested that kinematic patterns associated with common drowsy driver crash types were key features in the algorithm's prediction performance.

Original languageEnglish (US)
Title of host publicationProceedings of the Human Factors and Ergonomics Society Annual Meeting, HFES 2013
Pages1859-1863
Number of pages5
DOIs
StatePublished - Dec 13 2013
Event57th Human Factors and Ergonomics Society Annual Meeting - 2013, HFES 2013 - San Diego, CA, United States
Duration: Sep 30 2013Oct 4 2013

Publication series

NameProceedings of the Human Factors and Ergonomics Society
ISSN (Print)1071-1813

Conference

Conference57th Human Factors and Ergonomics Society Annual Meeting - 2013, HFES 2013
CountryUnited States
CitySan Diego, CA
Period9/30/1310/4/13

Fingerprint

sleep
symbol
Kinematics
Time series analysis
time series analysis
Sleep
Classifiers
recipient
driver
road
Sampling
Testing
performance

ASJC Scopus subject areas

  • Human Factors and Ergonomics

Cite this

McDonald, A. D., Lee, J. D., Aksan, N. S., Dawson, J. D., Tippin, J., & Rizzo, M. (2013). Highway healthcare: How naturalistic driving data index adherence to CPAP therapy in obstructive sleep apnea. In Proceedings of the Human Factors and Ergonomics Society Annual Meeting, HFES 2013 (pp. 1859-1863). (Proceedings of the Human Factors and Ergonomics Society). https://doi.org/10.1177/1541931213571415

Highway healthcare : How naturalistic driving data index adherence to CPAP therapy in obstructive sleep apnea. / McDonald, Anthony D.; Lee, John D.; Aksan, Nazan S.; Dawson, Jeffrey D.; Tippin, Jon; Rizzo, Matthew.

Proceedings of the Human Factors and Ergonomics Society Annual Meeting, HFES 2013. 2013. p. 1859-1863 (Proceedings of the Human Factors and Ergonomics Society).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

McDonald, AD, Lee, JD, Aksan, NS, Dawson, JD, Tippin, J & Rizzo, M 2013, Highway healthcare: How naturalistic driving data index adherence to CPAP therapy in obstructive sleep apnea. in Proceedings of the Human Factors and Ergonomics Society Annual Meeting, HFES 2013. Proceedings of the Human Factors and Ergonomics Society, pp. 1859-1863, 57th Human Factors and Ergonomics Society Annual Meeting - 2013, HFES 2013, San Diego, CA, United States, 9/30/13. https://doi.org/10.1177/1541931213571415
McDonald AD, Lee JD, Aksan NS, Dawson JD, Tippin J, Rizzo M. Highway healthcare: How naturalistic driving data index adherence to CPAP therapy in obstructive sleep apnea. In Proceedings of the Human Factors and Ergonomics Society Annual Meeting, HFES 2013. 2013. p. 1859-1863. (Proceedings of the Human Factors and Ergonomics Society). https://doi.org/10.1177/1541931213571415
McDonald, Anthony D. ; Lee, John D. ; Aksan, Nazan S. ; Dawson, Jeffrey D. ; Tippin, Jon ; Rizzo, Matthew. / Highway healthcare : How naturalistic driving data index adherence to CPAP therapy in obstructive sleep apnea. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, HFES 2013. 2013. pp. 1859-1863 (Proceedings of the Human Factors and Ergonomics Society).
@inproceedings{0a5725ce77bb4573a28b533780a62513,
title = "Highway healthcare: How naturalistic driving data index adherence to CPAP therapy in obstructive sleep apnea",
abstract = "Drowsy driving is a major factor in many vehicle crashes around the world. Sleep disorders, such as obstructive sleep apnea (OSA), underpin many of these crashes. Continuous positive airway pressure (CPAP) therapy is an effective treatment for sleep apnea but it requires consistent use and is often rejected by OSA patients. Rejection of CPAP treatment creates a dangerous on-road environment for both OSA sufferers and the general public. Algorithms capable of detecting CPAP use and its effects on driving are integral to identifying and mitigating this danger. This work uses naturalistic kinematic driving data to develop an algorithm which can detect nightly CPAP abstinence and adequate CPAP use. Speed and lateral acceleration data were collected using a data recorder in participant's primary vehicle and CPAP data were collected by downloading adherence data from participant CPAP machines. The speed and acceleration data were reduced to a set of symbols using Symbolic Aggregate approximation (SAX) time-series analysis. The symbols were converted into a sequence frequency dataset using sliding windows of size 1 to 10 s with a 1 Hz sampling rate. A Random Forest classifier was trained on the data to create a classification algorithm. On a held aside testing set, the Random Forest algorithm correctly identified 71{\%} of the instances and had an area under the receiver operating characteristic curve of 0.76. The variable importance of the algorithm suggested that kinematic patterns associated with common drowsy driver crash types were key features in the algorithm's prediction performance.",
author = "McDonald, {Anthony D.} and Lee, {John D.} and Aksan, {Nazan S.} and Dawson, {Jeffrey D.} and Jon Tippin and Matthew Rizzo",
year = "2013",
month = "12",
day = "13",
doi = "10.1177/1541931213571415",
language = "English (US)",
isbn = "9780945289432",
series = "Proceedings of the Human Factors and Ergonomics Society",
pages = "1859--1863",
booktitle = "Proceedings of the Human Factors and Ergonomics Society Annual Meeting, HFES 2013",

}

TY - GEN

T1 - Highway healthcare

T2 - How naturalistic driving data index adherence to CPAP therapy in obstructive sleep apnea

AU - McDonald, Anthony D.

AU - Lee, John D.

AU - Aksan, Nazan S.

AU - Dawson, Jeffrey D.

AU - Tippin, Jon

AU - Rizzo, Matthew

PY - 2013/12/13

Y1 - 2013/12/13

N2 - Drowsy driving is a major factor in many vehicle crashes around the world. Sleep disorders, such as obstructive sleep apnea (OSA), underpin many of these crashes. Continuous positive airway pressure (CPAP) therapy is an effective treatment for sleep apnea but it requires consistent use and is often rejected by OSA patients. Rejection of CPAP treatment creates a dangerous on-road environment for both OSA sufferers and the general public. Algorithms capable of detecting CPAP use and its effects on driving are integral to identifying and mitigating this danger. This work uses naturalistic kinematic driving data to develop an algorithm which can detect nightly CPAP abstinence and adequate CPAP use. Speed and lateral acceleration data were collected using a data recorder in participant's primary vehicle and CPAP data were collected by downloading adherence data from participant CPAP machines. The speed and acceleration data were reduced to a set of symbols using Symbolic Aggregate approximation (SAX) time-series analysis. The symbols were converted into a sequence frequency dataset using sliding windows of size 1 to 10 s with a 1 Hz sampling rate. A Random Forest classifier was trained on the data to create a classification algorithm. On a held aside testing set, the Random Forest algorithm correctly identified 71% of the instances and had an area under the receiver operating characteristic curve of 0.76. The variable importance of the algorithm suggested that kinematic patterns associated with common drowsy driver crash types were key features in the algorithm's prediction performance.

AB - Drowsy driving is a major factor in many vehicle crashes around the world. Sleep disorders, such as obstructive sleep apnea (OSA), underpin many of these crashes. Continuous positive airway pressure (CPAP) therapy is an effective treatment for sleep apnea but it requires consistent use and is often rejected by OSA patients. Rejection of CPAP treatment creates a dangerous on-road environment for both OSA sufferers and the general public. Algorithms capable of detecting CPAP use and its effects on driving are integral to identifying and mitigating this danger. This work uses naturalistic kinematic driving data to develop an algorithm which can detect nightly CPAP abstinence and adequate CPAP use. Speed and lateral acceleration data were collected using a data recorder in participant's primary vehicle and CPAP data were collected by downloading adherence data from participant CPAP machines. The speed and acceleration data were reduced to a set of symbols using Symbolic Aggregate approximation (SAX) time-series analysis. The symbols were converted into a sequence frequency dataset using sliding windows of size 1 to 10 s with a 1 Hz sampling rate. A Random Forest classifier was trained on the data to create a classification algorithm. On a held aside testing set, the Random Forest algorithm correctly identified 71% of the instances and had an area under the receiver operating characteristic curve of 0.76. The variable importance of the algorithm suggested that kinematic patterns associated with common drowsy driver crash types were key features in the algorithm's prediction performance.

UR - http://www.scopus.com/inward/record.url?scp=84889782109&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889782109&partnerID=8YFLogxK

U2 - 10.1177/1541931213571415

DO - 10.1177/1541931213571415

M3 - Conference contribution

C2 - 26500422

AN - SCOPUS:84889782109

SN - 9780945289432

T3 - Proceedings of the Human Factors and Ergonomics Society

SP - 1859

EP - 1863

BT - Proceedings of the Human Factors and Ergonomics Society Annual Meeting, HFES 2013

ER -