Diagnosis of Sleep Apnoea Using a Mandibular Monitor and Machine Learning Analysis: One-Night Agreement Compared to in-Home Polysomnography

Julia L Kelly, Raoua Ben Messaoud, Marie Joyeux-Faure, Robin Terrail, Renaud Tamisier, Jean-Benoît Martinot, Nhat-Nam Le-Dong, Mary J Morrell, Jean-Louis Pépin, Julia L Kelly, Raoua Ben Messaoud, Marie Joyeux-Faure, Robin Terrail, Renaud Tamisier, Jean-Benoît Martinot, Nhat-Nam Le-Dong, Mary J Morrell, Jean-Louis Pépin

Abstract

Background: The capacity to diagnose obstructive sleep apnoea (OSA) must be expanded to meet an estimated disease burden of nearly one billion people worldwide. Validated alternatives to the gold standard polysomnography (PSG) will improve access to testing and treatment. This study aimed to evaluate the diagnosis of OSA, using measurements of mandibular movement (MM) combined with automated machine learning analysis, compared to in-home PSG.

Methods: 40 suspected OSA patients underwent single overnight in-home sleep testing with PSG (Nox A1, ResMed, Australia) and simultaneous MM monitoring (Sunrise, Sunrise SA, Belgium). PSG recordings were manually analysed by two expert sleep centres (Grenoble and London); MM analysis was automated. The Obstructive Respiratory Disturbance Index calculated from the MM monitoring (MM-ORDI) was compared to the PSG (PSG-ORDI) using intraclass correlation coefficient and Bland-Altman analysis. Receiver operating characteristic curves (ROC) were constructed to optimise the diagnostic performance of the MM monitor at different PSG-ORDI thresholds (5, 15, and 30 events/hour).

Results: 31 patients were included in the analysis (58% men; mean (SD) age: 48 (15) years; BMI: 30.4 (7.6) kg/m2). Good agreement was observed between MM-ORDI and PSG-ORDI (median bias 0.00; 95% CI -23.25 to + 9.73 events/hour). However, for 15 patients with no or mild OSA, MM monitoring overestimated disease severity (PSG-ORDI < 5: MM-ORDI mean overestimation + 5.58 (95% CI + 2.03 to + 7.46) events/hour; PSG-ORDI > 5-15: MM-ORDI overestimation + 3.70 (95% CI -0.53 to + 18.32) events/hour). In 16 patients with moderate-severe OSA (n = 9 with PSG-ORDI 15-30 events/h and n = 7 with a PSG-ORD > 30 events/h), there was an underestimation (PSG-ORDI > 15: MM-ORDI underestimation -8.70 (95% CI -28.46 to + 4.01) events/hour). ROC optimal cut-off values for PSG-ORDI thresholds of 5, 15, 30 events/hour were: 9.53, 12.65 and 24.81 events/hour, respectively. These cut-off values yielded a sensitivity of 88, 100 and 79%, and a specificity of 100, 75, 96%. The positive predictive values were: 100, 80, 95% and the negative predictive values 89, 100, 82%, respectively.

Conclusion: The diagnosis of OSA, using MM with machine learning analysis, is comparable to manually scored in-home PSG. Therefore, this novel monitor could be a convenient diagnostic tool that can easily be used in the patients' own home.

Clinical trial registration: https://ichgcp.net/clinical-trials-registry/NCT04262557" title="See in ClinicalTrials.gov">NCT04262557.

Keywords: automated machine learning analysis; in-home diagnosis; mandibular monitor; one-night agreement; performance; polysomnography; sleep apnoea.

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Copyright © 2022 Kelly, Ben Messaoud, Joyeux-Faure, Terrail, Tamisier, Martinot, Le-Dong, Morrell and Pépin.

Figures

FIGURE 1
FIGURE 1
Bland-Altman analysis for MM-ORDI versus average PSG-ORDI. Bland-Altman plot shows the disagreement between average PSG-ORDI and MM-ORDI (y axis) as a function of the average PSG ORDI (x axis), with individual cases stratified into three clinical groups. Bidimensional kernel density estimation plots are superimposed to show the joint distribution of measurement bias within each subgroup. The blue horizontal lines indicate the median, lower and upper bound (5th and 95th centiles) of the measurement bias in the whole sample. The distribution of the disagreement between the two methods, stratified by group, is shown on the right, with three horizontal lines indicating the median bias within each group. MM: mandibular movement; ORDI: obstructive respiratory disturbance index; PSG: polysomnography.
FIGURE 2
FIGURE 2
Bland-Altman analysis for London PSG-ORDI versus Grenoble PSG-ORDI. Bland-Altman plot shows the disagreement between average PSG-ORDI (London) and PSG-ORDI (Grenoble) (y axis) as a function of Grenoble PSG-ORDI (x axis), with individual cases stratified into three clinical groups. Bidimensional kernel density estimation plots are superimposed to show the joint distribution of measurement bias within each subgroup. The blue horizontal lines indicate the median, lower and upper bound (5th and 95th centiles) of the measurement bias in the whole sample. The distribution of the disagreement between the 2 methods, stratified by group, is shown on the right, with 3 horizontal lines indicating the median bias within each group. PSG: polysomnography; ORDI: obstructive respiratory disturbance index.
FIGURE 3
FIGURE 3
ROC curve analysis for MM-ORDI versus average PSG-ORDI. Cut-off calibration and ROC curves evaluating the global performance of 3 binary classification rules to detect patients with OSA with polysomnography-derived respiratory disturbance index (PSG-ORDI) of at least 5, 15 or 30 events/hour, using MM-ORDI. The 95% CIs of the area under the curve (AUC) were obtained by bootstrapping. The diagonal dotted line serves as a reference and shows the performance if OSA detection was made randomly. ROC: receiver operator characteristic; MM: mandibular movements; ORDI: obstructive respiratory disturbance index; OSA: obstructive sleep apnoea; 95% CIs: 95% confidence intervals; AUC: area under the curve.

References

    1. Benjafield A. V., Ayas N. T., Eastwood P. R., Heinzer R., Ip M. S. M., Morrell M. J., et al. (2019). Estimation of the global prevalence and burden of obstructive sleep apnoea: a literature-based analysis. Lancet Respir. Med. 7 687–698. 10.1016/S2213-2600(19)30198-5
    1. Berry R. B., Brooks R., Gamaldo C., Harding S. M., Lloyd R. M., Quan S. F., et al. (2017). AASM Scoring Manual Updates for 2017 (Version 2.4). J. Clin. Sleep Med. 13 665–666. 10.5664/jcsm.6576
    1. Berry R. B., Budhiraja R., Gottlieb D. J., Gozal D., Iber C., Kapur V. K., et al. (2012). Rules for scoring respiratory events in sleep: update of the 2007 AASM Manual for the Scoring of Sleep and Associated Events. Deliberations of the Sleep Apnea Definitions Task Force of the American Academy of Sleep Medicine. J. Clin. Sleep Med. 8 597–619. 10.5664/jcsm.2172
    1. Bianchi M. T., Goparaju B. (2017). Potential Underestimation of Sleep Apnea Severity by At-Home Kits: rescoring In-Laboratory Polysomnography Without Sleep Staging. J. Clin. Sleep Med. 13 551–555. 10.5664/jcsm.6540
    1. Bruyneel M., Ninane V. (2014). Unattended home-based polysomnography for sleep disordered breathing: current concepts and perspectives. Sleep Med. Rev. 18 341–347. 10.1016/j.smrv.2013.12.002
    1. Collop N. A., Anderson W. M., Boehlecke B., Claman D., Goldberg R., Gottlieb D. J., et al. (2007). Clinical guidelines for the use of unattended portable monitors in the diagnosis of obstructive sleep apnea in adult patients. Portable Monitoring Task Force of the American Academy of Sleep Medicine. J. Clin. Sleep Med. 3 737–747. 10.5664/jcsm.27032
    1. Corral J., Sánchez-Quiroga M., Carmona-Bernal C., Sánchez-Armengol Á, de la Torre A. S., Durán-Cantolla J., et al. (2017). Conventional Polysomnography Is Not Necessary for the Management of Most Patients with Suspected Obstructive Sleep Apnea. Noninferiority, Randomized Controlled Trial. Am. J. Respir. Crit. Care Med. 196 1181–1190. 10.1164/rccm.201612-2497OC
    1. Escourrou P., Grote L., Penzel T., Mcnicholas W. T., Verbraecken J., Tkacova R., et al. (2015). The diagnostic method has a strong influence on classification of obstructive sleep apnea. J. Sleep Res. 24 730–738. 10.1111/jsr.12318
    1. Fiorillo L., Puiatti A., Papandrea M., Ratti P. L., Favaro P., Roth C., et al. (2019). Automated sleep scoring: a review of the latest approaches. Sleep Med. Rev. 48:101204. 10.1016/j.smrv.2019.07.007
    1. Grote L. (2019). The global burden of sleep apnoea. Lancet Respir. Med. 7 645–647. 10.1016/s2213-2600(19)30226-7
    1. Grote L., McNicholas W. T., Hedner J. ESADA collaborators (2020). Sleep apnoea management in Europe during the COVID-19 pandemic: data from the European Sleep Apnoea Database (ESADA). Eur. Respir. J. 55:2001323. 10.1183/13993003.01323-2020
    1. Knauert M., Naik S., Gillespie M. B., Kryger M. (2015). Clinical consequences and economic costs of untreated obstructive sleep apnea syndrome. World J. Otorhinolaryngol. Head Neck Surg. 1 17–27. 10.1016/j.wjorl.2015.08.001
    1. Levy P., Kohler M., McNicholas W. T., Barbe F., McEvoy R. D., Somers V. K., et al. (2015). Obstructive sleep apnoea syndrome. Nat. Rev. Dis. Primers 1:15015.
    1. Linz D., McEvoy R. D., Cowie M. R., Somers V. K., Nattel S., Lévy P., et al. (2018). Associations of Obstructive Sleep Apnea With Atrial Fibrillation and Continuous Positive Airway Pressure Treatment: a Review. JAMA Cardiol. 3 532–540. 10.1001/jamacardio.2018.0095
    1. Lyons M. M., Bhatt N. Y., Pack A. I., Magalang U. J. (2020). Global burden of sleep-disordered breathing and its implications. Respirology 25 690–702. 10.1111/resp.13838
    1. Magalang U. J., Chen N. H., Cistulli P. A., Fedson A. C., Gíslason T., Hillman D., et al. (2013). Agreement in the scoring of respiratory events and sleep among international sleep centers. Sleep 36 591–596.
    1. Martinot J. B., Le-Dong N. N., Cuthbert V., Denison S., Silkoff P. E., Guénard H., et al. (2017b). Mandibular Movements As Accurate Reporters of Respiratory Effort during Sleep: validation against Diaphragmatic Electromyography. Front. Neurol. 8:353. 10.3389/fneur.2017.00353
    1. Martinot J. B., Borel J. C., Cuthbert V., Guénard H. J., Denison S., Silkoff P. E., et al. (2017a). Mandibular position and movements: suitability for diagnosis of sleep apnoea. Respirology 22 567–574. 10.1111/resp.12929
    1. Martinot J. B., Le-Dong N. N., Cuthbert V., Denison S., Silkoff P., Borel J. C., et al. (2020). The key role of the mandible in modulating airflow amplitude during sleep. Respir. Physiol. Neurobiol. 279:103447. 10.1016/j.resp.2020.103447
    1. Martinot J. B., Senny F., Denison S., Cuthbert V., Gueulette E., Guénard H., et al. (2015). Mandibular movements identify respiratory effort in pediatric obstructive sleep apnea. J. Clin. Sleep Med. 11 567–574. 10.5664/jcsm.4706
    1. Masa J. F., Duran-Cantolla J., Capote F., Cabello M., Abad J., Garcia-Rio F., et al. (2014). Effectiveness of home single-channel nasal pressure for sleep apnea diagnosis. Sleep 37 1953–1961. 10.5665/sleep.4248
    1. Maury G., Cambron L., Jamart J., Marchand E., Senny F., Poirrier R. (2013). Added value of a mandible movement automated analysis in the screening of obstructive sleep apnea. J. Sleep Res. 22 96–103. 10.1111/j.1365-2869.2012.01035.x
    1. Maury G., Senny F., Cambron L., Albert A., Seidel L., Poirrier R. (2014). Mandible behaviour interpretation during wakefulness, sleep and sleep-disordered breathing. J. Sleep Res. 23 709–716. 10.1111/jsr.12180
    1. McDaid C., Griffin S., Weatherly H., Duree K., van der Burgt M., van Hout S., et al. (2009). Continuous positive airway pressure devices for the treatment of obstructive sleep apnoea-hypopnoea syndrome: a systematic review and economic analysis. Health Technol. Assess. 13 143–274. 10.3310/hta13040
    1. Medicines and Healthcare products Regulatory Agency [MHRA] (2021). Managing medical devices. Guidance for health and social care organisations. South Colonnade: Medicines and Healthcare products Regulatory Agency.
    1. Mendonça F., Mostafa S. S., Ravelo-García A. G., Morgado-Dias F., Penzel T. (2018). Devices for home detection of obstructive sleep apnea: a review. Sleep Med. Rev. 41 149–160. 10.1016/j.smrv.2018.02.004
    1. Natsky A. N., Vakulin A., Coetzer C. L. C., McEvoy R. D., Adams R. J., Kaambwa B. (2021). Economic evaluation of diagnostic sleep studies for obstructive sleep apnoea: a systematic review protocol. Syst. Rev. 10:104. 10.1186/s13643-021-01651-3
    1. Nordigarden A., Zetterblad J., Trinks C., Green H., Eliasson P., Druid P., et al. (2011). Irreversible pan-ERBB inhibitor canertinib elicits anti-leukaemic effects and induces the regression of FLT3-ITD transformed cells in mice. Br. J. Haematol. 155 198–208. 10.1111/j.1365-2141.2011.08819.x
    1. Patel S. R., Donovan L. M. (2020). The COVID-19 Pandemic Presents an Opportunity to Reassess the Value of Polysomnography. Am. J. Respir. Crit. Care Med. 202 309–310. 10.1164/rccm.202005-1546ED
    1. Pépin J. L., Letesson C., Le-Dong N. N., Dedave A., Denison S., Cuthbert V., et al. (2020). Assessment of Mandibular Movement Monitoring With Machine Learning Analysis for the Diagnosis of Obstructive Sleep Apnea. JAMA Netw. Open 3:e1919657. 10.1001/jamanetworkopen.2019.19657
    1. Randerath W., Bassetti C. L., Bonsignore M. R., Farre R., Ferini-Strambi L., Grote L., et al. (2018). Challenges and perspectives in obstructive sleep apnoea: report by an ad hoc working group of the Sleep Disordered Breathing Group of the European Respiratory Society and the European Sleep Research Society. Eur. Respir. J. 52:1702616. 10.1183/13993003.02616-2017
    1. Reutrakul S., Mokhlesi B. (2017). Obstructive Sleep Apnea and Diabetes: a State of the Art Review. Chest 152 1070–1086. 10.1016/j.chest.2017.05.009
    1. Roeder M., Bradicich M., Schwarz E. I., Thiel S., Gaisl T., Held U., et al. (2020). Night-to-night variability of respiratory events in obstructive sleep apnoea: a systematic review and meta-analysis. Thorax 75 1095–1102. 10.1136/thoraxjnl-2020-214544
    1. Roeder M., Sievi N. A., Bradicich M., Grewe F. A., Siegfried S., Gaisl T., et al. (2021). The Accuracy of Repeated Sleep Studies in OSA: a Longitudinal Observational Study With 14 Nights of Oxygen Saturation Monitoring. Chest 159 1222–1231. 10.1016/j.chest.2020.09.098
    1. Rosenberg R. S., Van Hout S. (2013). The American Academy of Sleep Medicine inter-scorer reliability program: sleep stage scoring. J. Clin. Sleep Med. 9 81–87. 10.5664/jcsm.2350
    1. Sateia M. J. (2014). International classification of sleep disorders-third edition: highlights and modifications. Chest 146 1387–1394. 10.1378/chest.14-0970
    1. Schiza S., Simonds A., Randerath W., Fanfulla F., Testelmans D., Grote L., et al. (2021). Sleep laboratories reopening and COVID-19: a European perspective. Eur. Respir. J. 57:2002722. 10.1183/13993003.02722-2020
    1. Senny F., Destiné J., Poirrier R. (2008). Midsagittal jaw movement analysis for the scoring of sleep apneas and hypopneas. IEEE Trans. Biomed. Eng. 55 87–95. 10.1109/TBME.2007.899351
    1. Senny F., Destiné J., Poirrier R. (2009). Midsagittal jaw movements as a sleep/wake marker. IEEE Trans. Biomed. Eng. 56 303–309. 10.1109/TBME.2008.2003264
    1. Senny F., Maury G., Cambron L., Leroux A., Destiné J., Poirrier R. (2012). The sleep/wake state scoring from mandible movement signal. Sleep Breath. 16 535–542. 10.1007/s11325-011-0539-4
    1. Wimms A. J., Kelly J. L., Turnbull C. D., McMillan A., Craig S. E., O’Reilly J. F., et al. (2020). Continuous positive airway pressure versus standard care for the treatment of people with mild obstructive sleep apnoea (MERGE): a multicentre, randomised controlled trial. Lancet Respir. Med. 8 349–358. 10.1016/S2213-2600(19)30402-3
    1. Younes M., Raneri J., Hanly P. (2016). Staging Sleep in Polysomnograms: analysis of Inter-Scorer Variability. J. Clin. Sleep Med. 12 885–894. 10.5664/jcsm.5894

Source: PubMed

スポンサーと協力者

医学的状態

薬物療法

3
購読する