Misclassification of OSA Severity With Automated Scoring of Home Sleep Recordings

Aurora, R. Nisha; Swartz, Rachel; Punjabi, Naresh M.

doi:10.1378/chest.14-0929

Cited by 52 publications

(29 citation statements)

References 30 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 10 21 Our results show that RDI MAN agreed slightly better than RDI RAW with the laboratory AHI but, again, the differences were small compared with the confidence limits. Our Bland-Altman plots did not show the large differences between the manually scored and the computer-scored RDI for the ApneaLink Plus that were reported in a recent paper by Aurora et al 22 Unlike the 2014 paper from Masa et al , 23 we did not see much difference between the receiver–operator characteristic curves for mild, moderate and severe sleep apnoea when comparing the laboratory polysomnography with home testing performed on a different night. However, they had studied a much larger group of participants than we did and they used the ApneaLink, which records only nasal airflow, rather than the four-channel ApneaLink Plus.…”

Section: Discussioncontrasting

confidence: 83%

Type III home sleep testing versus pulse oximetry: is the respiratory disturbance index better than the oxygen desaturation index to predict the apnoea-hypopnoea index measured during laboratory polysomnography?

et al. 2015

View full text Add to dashboard Cite

ObjectivesIn its guidelines on the use of portable monitors to diagnose obstructive sleep apnoea, the American Academy of Sleep Medicine endorses home polygraphy with type III devices recording at a minimum airflow the respiratory effort and pulse oximetry, but advises against simple pulse oximetry. However, oximetry is widely available and simple to use in the home. This study was designed to compare the ability of the oxygen desaturation index (ODI) based on oximetry alone with a stand-alone pulse oximeter (SPO) and from the oximetry channel of the ApneaLink Plus (ALP), with the respiratory disturbance index (RDI) based on four channels from the ALP to predict the apnoea–hypopnoea index (AHI) from laboratory polysomnography.DesignCross-sectional diagnostic accuracy study.SettingSleep medicine practice of a multispecialty clinic.ParticipantsPatients referred for laboratory polysomnography with suspected sleep apnoea. We enrolled 135 participants with 123 attempting the home sleep testing and 73 having at least 4 hours of satisfactory data from SPO and ALP.InterventionsParticipants had home testing performed simultaneously with both a SPO and an ALP. The 2 oximeter probes were worn on different fingers of the same hand. The ODI for the SPO was calculated using Profox software (ODISOX). For the ALP, RDI and ODI were calculated using both technician scoring (RDIMAN and ODIMAN) and the ALP computer scoring (RDIRAW and ODIRAW).ResultsThe receiver–operator characteristic areas under the curve for AHI ≥5 were RDIMAN 0.88 (95% confidence limits 0.81–0.96), RDIRAW 0.86 (0.76–0.94), ODIMAN 0.86 (0.77–0.95), ODIRAW 0.84 (0.75–0.93) and ODISOX 0.83 (0.73–0.93).ConclusionsWe conclude that the RDI and the ODI, measured at home on the same night, give similar predictions of the laboratory AHI, measured on a different night. The differences between the two methods are small compared with the reported night-to-night variation of the AHI.

show abstract

Section: Discussioncontrasting

confidence: 83%

Type III home sleep testing versus pulse oximetry: is the respiratory disturbance index better than the oxygen desaturation index to predict the apnoea-hypopnoea index measured during laboratory polysomnography?

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Two prior studies examined the agreement between automatic and manual scoring of respiratory events in HSTs. 9,24 The two studies suggest that the agreement between automatic and manual agreement is modest and that automatic agreement consistently underestimated the AHI derived from manual scoring of HSTs. None of these prior publications reported the agreement when different scoring software is used on the same studies, which is a strength of our current study given that this would be the real-world situation in collaborative research involving international sleep centers.…”

mentioning

confidence: 99%

Agreement in the Scoring of Respiratory Events Among International Sleep Centers for Home Sleep Testing

Magalang

Arnardóttir

Chen

et al. 2016

Journal of Clinical Sleep Medicine

View full text Add to dashboard Cite

Study Objectives: Home sleep testing (HST) is used worldwide to confirm the presence of obstructive sleep apnea (OSA). We sought to determine the agreement of HST scoring among international sleep centers. Methods: Fifteen HSTs, previously recorded using a type 3 monitor, were deidentified and saved in European Data Format. The studies were scored by nine technologists from the sleep centers of the Sleep Apnea Global Interdisciplinary Consortium (SAGIC) using the locally available software. Each study was scored separately using one of three different airflow signals: nasal pressure (NP), transformed (square root) nasal pressure signal (transformed NP), and uncalibrated respiratory inductive plethysmography (RIP) flow. Only one of the three airflow signals was visible to the scorer at each scoring session. The scoring procedure was repeated to determine the intrarater reliability. Conclusion:There is a strong agreement in the scoring of the respiratory events for HST among international sleep centers. Our results suggest that centralized scoring of HSTs may not be necessary in future research collaboration among international sites.

show abstract

“…From the patient standpoint, new non-contact sensing technologies such as pressure-sensitive LCs have the potential to make sleep testing more comfortable and seamless. On the other hand, automated scoring algorithms embedded in the diagnostic device have allowed fast diagnosis of OSA [5]. In this section we provide a brief review of research works that relate to the system and methods we present in this paper.…”

Section: Related Workmentioning

confidence: 99%

In-Home Sleep Apnea Severity Classification using Contact-free Load Cells and an AdaBoosted Decision Tree Algorithm

Mosquera-Lopez

Leitschuh

Condon

et al. 2018

2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

We present a method for automated diagnosis and classification of severity of sleep apnea using an array of non-contact pressure-sensitive sensors placed underneath a mattress as an alternative to conventional obtrusive sensors. Our algorithm comprises two stages: i) A decision tree classifier that identifies patients with sleep apnea, and ii) a subsequent linear regression model that estimates the Apnea-Hypopnea Index (AHI), which is used to determine the severity of sleep disordered breathing. We tested our algorithm on a cohort of 14 patients who underwent overnight home sleep apnea test. The machine learning algorithm was trained and performance was evaluated using leave-one-patient-out cross-validation. The accuracy of the proposed approach in detecting sleep apnea is 86.96%, with sensitivity and specificity of 81.82% and 91.67%, respectively. Moreover, classification of severity of the sleep disorder was correctly assigned in 11 out of 14 cases, and the mean absolute error in the AHI estimation was calculated to be 3.83 events/hr.

show abstract

Misclassification of OSA Severity With Automated Scoring of Home Sleep Recordings

Cited by 52 publications

References 30 publications

Type III home sleep testing versus pulse oximetry: is the respiratory disturbance index better than the oxygen desaturation index to predict the apnoea-hypopnoea index measured during laboratory polysomnography?

Type III home sleep testing versus pulse oximetry: is the respiratory disturbance index better than the oxygen desaturation index to predict the apnoea-hypopnoea index measured during laboratory polysomnography?

Agreement in the Scoring of Respiratory Events Among International Sleep Centers for Home Sleep Testing

In-Home Sleep Apnea Severity Classification using Contact-free Load Cells and an AdaBoosted Decision Tree Algorithm

Contact Info

Product

Resources

About