Abstract

Obstructive sleep apnea (OSA) is a relatively common disease in the general population. Patients with OSA have a high risk of various comorbid medical diseases. Polysomnography (PSG) is the current gold standard for diagnosing OSA but is time consuming and expensive. This study aims to identify a sensitive screening parameter that can be used by clinicians to determine the time of referral for PSG examination in Taiwan. Eighty-seven patients, including 67 males and 20 females, were included in this study. We divided the patients into two groups: training data (n = 58) and testing group (n = 29). Pearson χ2 test was used to perform bivariate analysis, and a decision tree was used to build a model. The decision model selected the frequency of desaturation > 4% per hour (DI4) as the indicator of OSA influence. The testing data accuracy of the C4.5 decision tree was 82.80%. External data were also used to validate the model reliability. The accuracy of the external data was 95.96%. Approximately one-third of patients with DI4 between 11 and 33 suffered from OSA. This population requires further diagnosis. Oximetry is an important and widely available screening method in Taiwan. This study proposes the need for PSG referral if DI4 is between 11 and 33.

Original languageEnglish
JournalJournal of Medical Systems
Volume39
Issue number3
DOIs
Publication statusPublished - 2015

Fingerprint

Oximetry
Obstructive Sleep Apnea
Taiwan
Screening
Polysomnography
Decision Trees
Decision trees
Referral and Consultation
Testing
Population
Sleep

Keywords

  • Decision tree
  • Obstructive sleep apnea
  • Oximetry
  • Polysomnography

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Health Informatics
  • Health Information Management
  • Information Systems

Cite this

Use of Oximetry as a Screening Tool for Obstructive Sleep Apnea : a Case Study in Taiwan. / Huang, Shou-Hung; Teng, Nai Chia; Wang, Kung Jeng; Chen, Kun Huang; Lee, Hsin Chien; Wang, Pa Chun.

In: Journal of Medical Systems, Vol. 39, No. 3, 2015.

Research output: Contribution to journalArticle

@article{e9913a31c3f8489788cb9b3143b36abc,
title = "Use of Oximetry as a Screening Tool for Obstructive Sleep Apnea: a Case Study in Taiwan",
abstract = "Obstructive sleep apnea (OSA) is a relatively common disease in the general population. Patients with OSA have a high risk of various comorbid medical diseases. Polysomnography (PSG) is the current gold standard for diagnosing OSA but is time consuming and expensive. This study aims to identify a sensitive screening parameter that can be used by clinicians to determine the time of referral for PSG examination in Taiwan. Eighty-seven patients, including 67 males and 20 females, were included in this study. We divided the patients into two groups: training data (n = 58) and testing group (n = 29). Pearson χ2 test was used to perform bivariate analysis, and a decision tree was used to build a model. The decision model selected the frequency of desaturation > 4{\%} per hour (DI4) as the indicator of OSA influence. The testing data accuracy of the C4.5 decision tree was 82.80{\%}. External data were also used to validate the model reliability. The accuracy of the external data was 95.96{\%}. Approximately one-third of patients with DI4 between 11 and 33 suffered from OSA. This population requires further diagnosis. Oximetry is an important and widely available screening method in Taiwan. This study proposes the need for PSG referral if DI4 is between 11 and 33.",
keywords = "Decision tree, Obstructive sleep apnea, Oximetry, Polysomnography",
author = "Shou-Hung Huang and Teng, {Nai Chia} and Wang, {Kung Jeng} and Chen, {Kun Huang} and Lee, {Hsin Chien} and Wang, {Pa Chun}",
year = "2015",
doi = "10.1007/s10916-015-0195-5",
language = "English",
volume = "39",
journal = "Journal of Medical Systems",
issn = "0148-5598",
publisher = "Springer New York",
number = "3",

}

TY - JOUR

T1 - Use of Oximetry as a Screening Tool for Obstructive Sleep Apnea

T2 - a Case Study in Taiwan

AU - Huang, Shou-Hung

AU - Teng, Nai Chia

AU - Wang, Kung Jeng

AU - Chen, Kun Huang

AU - Lee, Hsin Chien

AU - Wang, Pa Chun

PY - 2015

Y1 - 2015

N2 - Obstructive sleep apnea (OSA) is a relatively common disease in the general population. Patients with OSA have a high risk of various comorbid medical diseases. Polysomnography (PSG) is the current gold standard for diagnosing OSA but is time consuming and expensive. This study aims to identify a sensitive screening parameter that can be used by clinicians to determine the time of referral for PSG examination in Taiwan. Eighty-seven patients, including 67 males and 20 females, were included in this study. We divided the patients into two groups: training data (n = 58) and testing group (n = 29). Pearson χ2 test was used to perform bivariate analysis, and a decision tree was used to build a model. The decision model selected the frequency of desaturation > 4% per hour (DI4) as the indicator of OSA influence. The testing data accuracy of the C4.5 decision tree was 82.80%. External data were also used to validate the model reliability. The accuracy of the external data was 95.96%. Approximately one-third of patients with DI4 between 11 and 33 suffered from OSA. This population requires further diagnosis. Oximetry is an important and widely available screening method in Taiwan. This study proposes the need for PSG referral if DI4 is between 11 and 33.

AB - Obstructive sleep apnea (OSA) is a relatively common disease in the general population. Patients with OSA have a high risk of various comorbid medical diseases. Polysomnography (PSG) is the current gold standard for diagnosing OSA but is time consuming and expensive. This study aims to identify a sensitive screening parameter that can be used by clinicians to determine the time of referral for PSG examination in Taiwan. Eighty-seven patients, including 67 males and 20 females, were included in this study. We divided the patients into two groups: training data (n = 58) and testing group (n = 29). Pearson χ2 test was used to perform bivariate analysis, and a decision tree was used to build a model. The decision model selected the frequency of desaturation > 4% per hour (DI4) as the indicator of OSA influence. The testing data accuracy of the C4.5 decision tree was 82.80%. External data were also used to validate the model reliability. The accuracy of the external data was 95.96%. Approximately one-third of patients with DI4 between 11 and 33 suffered from OSA. This population requires further diagnosis. Oximetry is an important and widely available screening method in Taiwan. This study proposes the need for PSG referral if DI4 is between 11 and 33.

KW - Decision tree

KW - Obstructive sleep apnea

KW - Oximetry

KW - Polysomnography

UR - http://www.scopus.com/inward/record.url?scp=84922689699&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922689699&partnerID=8YFLogxK

U2 - 10.1007/s10916-015-0195-5

DO - 10.1007/s10916-015-0195-5

M3 - Article

C2 - 25677955

AN - SCOPUS:84922689699

VL - 39

JO - Journal of Medical Systems

JF - Journal of Medical Systems

SN - 0148-5598

IS - 3

ER -