A novel artificial neural network based sleep-disordered breathing screening tool

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Study Objectives: This study evaluated a novel artificial neural network (ANN) based sleep-disordered breathing (SDB) screening tool incorporating nocturnal pulse oximetry with demographic, anatomic, and clinical data. The tool was compatible with 6 categories of apnea-hypopnea index (AHI) with 4% oxyhemoglobin desaturation threshold, = 5, 10, 15, 20, 25, and 30 events/h. Methods: Using a general population dataset, the training set included 2,280 subjects, whereas the test set included 470 subjects. The input of this tool was a set of 22 variables. The tool had six neural network models for each AHI threshold. Several metrics were explored to evaluate the performance of the tool: area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, and 95% confidence interval (CI). Results: The AUC was 0.904, 0.912, 0.913, 0.926, 0.930, and 0.954, respectively, with models of AHI = 5, 10, 15, 20, 25, and 30 events/h thresholds. The sensitivities of all neural network models were higher than 95%. The AHI = 30 events/h model had the maximum sensitivity: 98.31% (95% CI: 95.01%-100%). Conclusions: The results of this study suggested that the ANN based SDB screening tool can be used to identify the presence or absence of SDB. Future validation should be performed in other populations to determine the practicability of this screening tool in sleep clinics and other at-risk populations.

Original languageEnglish (US)
Pages (from-to)1063-1069
Number of pages7
JournalJournal of Clinical Sleep Medicine
Volume14
Issue number6
DOIs
StatePublished - Jun 15 2018

Fingerprint

Sleep Apnea Syndromes
Apnea
Neural Networks (Computer)
Area Under Curve
Confidence Intervals
Oxyhemoglobins
Oximetry
ROC Curve
Population
Sleep
Demography
Sensitivity and Specificity

Keywords

  • Artificial neural network
  • General population
  • Screening
  • Sleep-disordered breathing

ASJC Scopus subject areas

  • Pulmonary and Respiratory Medicine
  • Neurology
  • Clinical Neurology

Cite this

@article{37067f12a3dd4a1b9283e573fbdfd2e9,
title = "A novel artificial neural network based sleep-disordered breathing screening tool",
abstract = "Study Objectives: This study evaluated a novel artificial neural network (ANN) based sleep-disordered breathing (SDB) screening tool incorporating nocturnal pulse oximetry with demographic, anatomic, and clinical data. The tool was compatible with 6 categories of apnea-hypopnea index (AHI) with 4{\%} oxyhemoglobin desaturation threshold, = 5, 10, 15, 20, 25, and 30 events/h. Methods: Using a general population dataset, the training set included 2,280 subjects, whereas the test set included 470 subjects. The input of this tool was a set of 22 variables. The tool had six neural network models for each AHI threshold. Several metrics were explored to evaluate the performance of the tool: area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, and 95{\%} confidence interval (CI). Results: The AUC was 0.904, 0.912, 0.913, 0.926, 0.930, and 0.954, respectively, with models of AHI = 5, 10, 15, 20, 25, and 30 events/h thresholds. The sensitivities of all neural network models were higher than 95{\%}. The AHI = 30 events/h model had the maximum sensitivity: 98.31{\%} (95{\%} CI: 95.01{\%}-100{\%}). Conclusions: The results of this study suggested that the ANN based SDB screening tool can be used to identify the presence or absence of SDB. Future validation should be performed in other populations to determine the practicability of this screening tool in sleep clinics and other at-risk populations.",
keywords = "Artificial neural network, General population, Screening, Sleep-disordered breathing",
author = "Ao Li and Quan, {Stuart F} and {Silva Torres}, {Graciela Emilia} and Perfect, {Michelle M} and Meiling Wang",
year = "2018",
month = "6",
day = "15",
doi = "10.5664/jcsm.7182",
language = "English (US)",
volume = "14",
pages = "1063--1069",
journal = "Journal of Clinical Sleep Medicine",
issn = "1550-9389",
publisher = "American Academy of Sleep Medicine",
number = "6",

}

TY - JOUR

T1 - A novel artificial neural network based sleep-disordered breathing screening tool

AU - Li, Ao

AU - Quan, Stuart F

AU - Silva Torres, Graciela Emilia

AU - Perfect, Michelle M

AU - Wang, Meiling

PY - 2018/6/15

Y1 - 2018/6/15

N2 - Study Objectives: This study evaluated a novel artificial neural network (ANN) based sleep-disordered breathing (SDB) screening tool incorporating nocturnal pulse oximetry with demographic, anatomic, and clinical data. The tool was compatible with 6 categories of apnea-hypopnea index (AHI) with 4% oxyhemoglobin desaturation threshold, = 5, 10, 15, 20, 25, and 30 events/h. Methods: Using a general population dataset, the training set included 2,280 subjects, whereas the test set included 470 subjects. The input of this tool was a set of 22 variables. The tool had six neural network models for each AHI threshold. Several metrics were explored to evaluate the performance of the tool: area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, and 95% confidence interval (CI). Results: The AUC was 0.904, 0.912, 0.913, 0.926, 0.930, and 0.954, respectively, with models of AHI = 5, 10, 15, 20, 25, and 30 events/h thresholds. The sensitivities of all neural network models were higher than 95%. The AHI = 30 events/h model had the maximum sensitivity: 98.31% (95% CI: 95.01%-100%). Conclusions: The results of this study suggested that the ANN based SDB screening tool can be used to identify the presence or absence of SDB. Future validation should be performed in other populations to determine the practicability of this screening tool in sleep clinics and other at-risk populations.

AB - Study Objectives: This study evaluated a novel artificial neural network (ANN) based sleep-disordered breathing (SDB) screening tool incorporating nocturnal pulse oximetry with demographic, anatomic, and clinical data. The tool was compatible with 6 categories of apnea-hypopnea index (AHI) with 4% oxyhemoglobin desaturation threshold, = 5, 10, 15, 20, 25, and 30 events/h. Methods: Using a general population dataset, the training set included 2,280 subjects, whereas the test set included 470 subjects. The input of this tool was a set of 22 variables. The tool had six neural network models for each AHI threshold. Several metrics were explored to evaluate the performance of the tool: area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, and 95% confidence interval (CI). Results: The AUC was 0.904, 0.912, 0.913, 0.926, 0.930, and 0.954, respectively, with models of AHI = 5, 10, 15, 20, 25, and 30 events/h thresholds. The sensitivities of all neural network models were higher than 95%. The AHI = 30 events/h model had the maximum sensitivity: 98.31% (95% CI: 95.01%-100%). Conclusions: The results of this study suggested that the ANN based SDB screening tool can be used to identify the presence or absence of SDB. Future validation should be performed in other populations to determine the practicability of this screening tool in sleep clinics and other at-risk populations.

KW - Artificial neural network

KW - General population

KW - Screening

KW - Sleep-disordered breathing

UR - http://www.scopus.com/inward/record.url?scp=85048620352&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048620352&partnerID=8YFLogxK

U2 - 10.5664/jcsm.7182

DO - 10.5664/jcsm.7182

M3 - Article

C2 - 29852901

AN - SCOPUS:85048620352

VL - 14

SP - 1063

EP - 1069

JO - Journal of Clinical Sleep Medicine

JF - Journal of Clinical Sleep Medicine

SN - 1550-9389

IS - 6

ER -