Pediatric pulse oximetry-based OSA screening at different thresholds of the apnea-hypopnea index with an expression of uncertainty for inconclusive classifications

Ainara Garde* (Corresponding Author), Xenia Hoppenbrouwer, Parastoo Dehkordi, Guohai Zhou, Aryannah Umedaly Rollinson, David Wensley, Guy A. Dumont, J. Mark Ansermino

*Corresponding author for this work

    Research output: Contribution to journalArticleAcademicpeer-review

    Abstract

    Background: Assessments of pediatric obstructive sleep apnea (OSA) are underutilized across Canada due to a lack of resources. Polysomnography (PSG) measures OSA severity through the average number of apnea/hypopnea events per hour (AHI), but is resource intensive and requires a specialized sleep laboratory, which results in long waitlists and delays in OSA detection. Prompt diagnosis and treatment of OSA are crucial for children, as untreated OSA is linked to behavioral deficits, growth failure, and negative cardiovascular consequences. We aim to assess the performance of a portable pediatric OSA screening tool at different AHI cut-offs using overnight smartphone-based pulse oximetry. Material and methods: Following ethics approval and informed consent, children referred to British Columbia Children's Hospital for overnight PSG were recruited for two studies including 160 and 75 children, respectively. An additional smartphone-based pulse oximeter sensor was used in both studies to record overnight pulse oximetry [SpO2 and photoplethysmogram (PPG)] alongside the PSG. Features characterizing SpO2 dynamics and heart rate variability from pulse peak intervals of the PPG signal were derived from pulse oximetry recordings. Three multivariate logistic regression screening models, targeted at three different levels of OSA severity (AHI ≥ 1, 5, and 10), were developed using stepwise-selection of features using the Bayesian information criterion (BIC). The “Gray Zone” approach was also implemented for different tolerance values to allow for more precise detection of children with inconclusive classification results. Results: The optimal diagnostic tolerance values defining the “Gray Zone” borders (15, 10, and 5, respectively) were selected to develop the final models to screen for children at AHI cut-offs of 1, 5, and 10. The final models evaluated through cross-validation showed good accuracy (75%, 82% and 89%), sensitivity (80%, 85% and 82%) and specificity (65%, 79% and 91%) values for detecting children with AHI ≥ 1, AHI ≥ 5 and AHI ≥ 10. The percentage of children classified as inconclusive was 28%, 38% and 16% for models detecting AHI ≥ 1, AHI ≥ 5, and AHI ≥ 10, respectively. Conclusions: The proposed pulse oximetry-based OSA screening tool at different AHI cut-offs may assist clinicians in identifying children at different OSA severity levels. Using this tool at home prior to PSG can help with optimizing the limited resources for PSG screening. Further validation with larger and more heterogeneous datasets is required before introducing in clinical practice.

    Original languageEnglish
    JournalSleep Medicine
    DOIs
    Publication statusAccepted/In press - 1 Jan 2018

    Fingerprint

    Oximetry
    Obstructive Sleep Apnea
    Apnea
    Uncertainty
    Pediatrics
    Polysomnography
    Pulse
    British Columbia
    Informed Consent
    Ethics
    Canada
    Sleep
    Heart Rate
    Logistic Models

    Keywords

    • Mobile health solutions
    • Oxygen saturation dynamics
    • Pediatric sleep apnea
    • Pulse oximetry
    • Pulse rate variability
    • Signal analysis

    Cite this

    @article{4d943f8f339e44a6a8f3a027f094f6ea,
    title = "Pediatric pulse oximetry-based OSA screening at different thresholds of the apnea-hypopnea index with an expression of uncertainty for inconclusive classifications",
    abstract = "Background: Assessments of pediatric obstructive sleep apnea (OSA) are underutilized across Canada due to a lack of resources. Polysomnography (PSG) measures OSA severity through the average number of apnea/hypopnea events per hour (AHI), but is resource intensive and requires a specialized sleep laboratory, which results in long waitlists and delays in OSA detection. Prompt diagnosis and treatment of OSA are crucial for children, as untreated OSA is linked to behavioral deficits, growth failure, and negative cardiovascular consequences. We aim to assess the performance of a portable pediatric OSA screening tool at different AHI cut-offs using overnight smartphone-based pulse oximetry. Material and methods: Following ethics approval and informed consent, children referred to British Columbia Children's Hospital for overnight PSG were recruited for two studies including 160 and 75 children, respectively. An additional smartphone-based pulse oximeter sensor was used in both studies to record overnight pulse oximetry [SpO2 and photoplethysmogram (PPG)] alongside the PSG. Features characterizing SpO2 dynamics and heart rate variability from pulse peak intervals of the PPG signal were derived from pulse oximetry recordings. Three multivariate logistic regression screening models, targeted at three different levels of OSA severity (AHI ≥ 1, 5, and 10), were developed using stepwise-selection of features using the Bayesian information criterion (BIC). The “Gray Zone” approach was also implemented for different tolerance values to allow for more precise detection of children with inconclusive classification results. Results: The optimal diagnostic tolerance values defining the “Gray Zone” borders (15, 10, and 5, respectively) were selected to develop the final models to screen for children at AHI cut-offs of 1, 5, and 10. The final models evaluated through cross-validation showed good accuracy (75{\%}, 82{\%} and 89{\%}), sensitivity (80{\%}, 85{\%} and 82{\%}) and specificity (65{\%}, 79{\%} and 91{\%}) values for detecting children with AHI ≥ 1, AHI ≥ 5 and AHI ≥ 10. The percentage of children classified as inconclusive was 28{\%}, 38{\%} and 16{\%} for models detecting AHI ≥ 1, AHI ≥ 5, and AHI ≥ 10, respectively. Conclusions: The proposed pulse oximetry-based OSA screening tool at different AHI cut-offs may assist clinicians in identifying children at different OSA severity levels. Using this tool at home prior to PSG can help with optimizing the limited resources for PSG screening. Further validation with larger and more heterogeneous datasets is required before introducing in clinical practice.",
    keywords = "Mobile health solutions, Oxygen saturation dynamics, Pediatric sleep apnea, Pulse oximetry, Pulse rate variability, Signal analysis",
    author = "Ainara Garde and Xenia Hoppenbrouwer and Parastoo Dehkordi and Guohai Zhou and Rollinson, {Aryannah Umedaly} and David Wensley and Dumont, {Guy A.} and Ansermino, {J. Mark}",
    year = "2018",
    month = "1",
    day = "1",
    doi = "10.1016/j.sleep.2018.08.027",
    language = "English",
    journal = "Sleep Medicine",
    issn = "1389-9457",
    publisher = "Elsevier",

    }

    Pediatric pulse oximetry-based OSA screening at different thresholds of the apnea-hypopnea index with an expression of uncertainty for inconclusive classifications. / Garde, Ainara (Corresponding Author); Hoppenbrouwer, Xenia; Dehkordi, Parastoo; Zhou, Guohai; Rollinson, Aryannah Umedaly; Wensley, David; Dumont, Guy A.; Ansermino, J. Mark.

    In: Sleep Medicine, 01.01.2018.

    Research output: Contribution to journalArticleAcademicpeer-review

    TY - JOUR

    T1 - Pediatric pulse oximetry-based OSA screening at different thresholds of the apnea-hypopnea index with an expression of uncertainty for inconclusive classifications

    AU - Garde, Ainara

    AU - Hoppenbrouwer, Xenia

    AU - Dehkordi, Parastoo

    AU - Zhou, Guohai

    AU - Rollinson, Aryannah Umedaly

    AU - Wensley, David

    AU - Dumont, Guy A.

    AU - Ansermino, J. Mark

    PY - 2018/1/1

    Y1 - 2018/1/1

    N2 - Background: Assessments of pediatric obstructive sleep apnea (OSA) are underutilized across Canada due to a lack of resources. Polysomnography (PSG) measures OSA severity through the average number of apnea/hypopnea events per hour (AHI), but is resource intensive and requires a specialized sleep laboratory, which results in long waitlists and delays in OSA detection. Prompt diagnosis and treatment of OSA are crucial for children, as untreated OSA is linked to behavioral deficits, growth failure, and negative cardiovascular consequences. We aim to assess the performance of a portable pediatric OSA screening tool at different AHI cut-offs using overnight smartphone-based pulse oximetry. Material and methods: Following ethics approval and informed consent, children referred to British Columbia Children's Hospital for overnight PSG were recruited for two studies including 160 and 75 children, respectively. An additional smartphone-based pulse oximeter sensor was used in both studies to record overnight pulse oximetry [SpO2 and photoplethysmogram (PPG)] alongside the PSG. Features characterizing SpO2 dynamics and heart rate variability from pulse peak intervals of the PPG signal were derived from pulse oximetry recordings. Three multivariate logistic regression screening models, targeted at three different levels of OSA severity (AHI ≥ 1, 5, and 10), were developed using stepwise-selection of features using the Bayesian information criterion (BIC). The “Gray Zone” approach was also implemented for different tolerance values to allow for more precise detection of children with inconclusive classification results. Results: The optimal diagnostic tolerance values defining the “Gray Zone” borders (15, 10, and 5, respectively) were selected to develop the final models to screen for children at AHI cut-offs of 1, 5, and 10. The final models evaluated through cross-validation showed good accuracy (75%, 82% and 89%), sensitivity (80%, 85% and 82%) and specificity (65%, 79% and 91%) values for detecting children with AHI ≥ 1, AHI ≥ 5 and AHI ≥ 10. The percentage of children classified as inconclusive was 28%, 38% and 16% for models detecting AHI ≥ 1, AHI ≥ 5, and AHI ≥ 10, respectively. Conclusions: The proposed pulse oximetry-based OSA screening tool at different AHI cut-offs may assist clinicians in identifying children at different OSA severity levels. Using this tool at home prior to PSG can help with optimizing the limited resources for PSG screening. Further validation with larger and more heterogeneous datasets is required before introducing in clinical practice.

    AB - Background: Assessments of pediatric obstructive sleep apnea (OSA) are underutilized across Canada due to a lack of resources. Polysomnography (PSG) measures OSA severity through the average number of apnea/hypopnea events per hour (AHI), but is resource intensive and requires a specialized sleep laboratory, which results in long waitlists and delays in OSA detection. Prompt diagnosis and treatment of OSA are crucial for children, as untreated OSA is linked to behavioral deficits, growth failure, and negative cardiovascular consequences. We aim to assess the performance of a portable pediatric OSA screening tool at different AHI cut-offs using overnight smartphone-based pulse oximetry. Material and methods: Following ethics approval and informed consent, children referred to British Columbia Children's Hospital for overnight PSG were recruited for two studies including 160 and 75 children, respectively. An additional smartphone-based pulse oximeter sensor was used in both studies to record overnight pulse oximetry [SpO2 and photoplethysmogram (PPG)] alongside the PSG. Features characterizing SpO2 dynamics and heart rate variability from pulse peak intervals of the PPG signal were derived from pulse oximetry recordings. Three multivariate logistic regression screening models, targeted at three different levels of OSA severity (AHI ≥ 1, 5, and 10), were developed using stepwise-selection of features using the Bayesian information criterion (BIC). The “Gray Zone” approach was also implemented for different tolerance values to allow for more precise detection of children with inconclusive classification results. Results: The optimal diagnostic tolerance values defining the “Gray Zone” borders (15, 10, and 5, respectively) were selected to develop the final models to screen for children at AHI cut-offs of 1, 5, and 10. The final models evaluated through cross-validation showed good accuracy (75%, 82% and 89%), sensitivity (80%, 85% and 82%) and specificity (65%, 79% and 91%) values for detecting children with AHI ≥ 1, AHI ≥ 5 and AHI ≥ 10. The percentage of children classified as inconclusive was 28%, 38% and 16% for models detecting AHI ≥ 1, AHI ≥ 5, and AHI ≥ 10, respectively. Conclusions: The proposed pulse oximetry-based OSA screening tool at different AHI cut-offs may assist clinicians in identifying children at different OSA severity levels. Using this tool at home prior to PSG can help with optimizing the limited resources for PSG screening. Further validation with larger and more heterogeneous datasets is required before introducing in clinical practice.

    KW - Mobile health solutions

    KW - Oxygen saturation dynamics

    KW - Pediatric sleep apnea

    KW - Pulse oximetry

    KW - Pulse rate variability

    KW - Signal analysis

    UR - http://www.scopus.com/inward/record.url?scp=85055411189&partnerID=8YFLogxK

    U2 - 10.1016/j.sleep.2018.08.027

    DO - 10.1016/j.sleep.2018.08.027

    M3 - Article

    AN - SCOPUS:85055411189

    JO - Sleep Medicine

    JF - Sleep Medicine

    SN - 1389-9457

    ER -