Diagnosis of Sleep Apnoea Using a Mandibular Monitor and Machine Learning Analysis: One-Night Agreement Compared to in-Home Polysomnography
BackgroundThe 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...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-03-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.726880/full |
| _version_ | 1818140684091129856 |
|---|---|
| author | Julia L. Kelly Raoua Ben Messaoud Marie Joyeux-Faure Marie Joyeux-Faure Robin Terrail Robin Terrail Renaud Tamisier Renaud Tamisier Jean-Benoît Martinot Jean-Benoît Martinot Nhat-Nam Le-Dong Mary J. Morrell Jean-Louis Pépin Jean-Louis Pépin |
| author_facet | Julia L. Kelly Raoua Ben Messaoud Marie Joyeux-Faure Marie Joyeux-Faure Robin Terrail Robin Terrail Renaud Tamisier Renaud Tamisier Jean-Benoît Martinot Jean-Benoît Martinot Nhat-Nam Le-Dong Mary J. Morrell Jean-Louis Pépin Jean-Louis Pépin |
| author_sort | Julia L. Kelly |
| collection | DOAJ |
| description | BackgroundThe 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.Methods40 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).Results31 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.ConclusionThe 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 Registrationhttps://clinicaltrials.gov, identifier NCT04262557 |
| first_indexed | 2024-12-11T10:47:54Z |
| format | Article |
| id | doaj.art-0854ebe4051245f8b171623ff8005dbf |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-11T10:47:54Z |
| publishDate | 2022-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-0854ebe4051245f8b171623ff8005dbf2022-12-22T01:10:25ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-03-011610.3389/fnins.2022.726880726880Diagnosis of Sleep Apnoea Using a Mandibular Monitor and Machine Learning Analysis: One-Night Agreement Compared to in-Home PolysomnographyJulia L. Kelly0Raoua Ben Messaoud1Marie Joyeux-Faure2Marie Joyeux-Faure3Robin Terrail4Robin Terrail5Renaud Tamisier6Renaud Tamisier7Jean-Benoît Martinot8Jean-Benoît Martinot9Nhat-Nam Le-Dong10Mary J. Morrell11Jean-Louis Pépin12Jean-Louis Pépin13National Heart and Lung Institute, Imperial College London, Royal Brompton Hospital, London, United KingdomHP2 Laboratory, Inserm U1300, Grenoble Alpes University, Grenoble, FranceHP2 Laboratory, Inserm U1300, Grenoble Alpes University, Grenoble, FranceEFCR Laboratory, Thorax and Vessels division, Grenoble Alpes University Hospital, Grenoble, FranceHP2 Laboratory, Inserm U1300, Grenoble Alpes University, Grenoble, FranceEFCR Laboratory, Thorax and Vessels division, Grenoble Alpes University Hospital, Grenoble, FranceHP2 Laboratory, Inserm U1300, Grenoble Alpes University, Grenoble, FranceEFCR Laboratory, Thorax and Vessels division, Grenoble Alpes University Hospital, Grenoble, FranceSleep Laboratory, CHU Université catholique de Louvain (UCL) Namur Site Sainte-Elisabeth, Namur, BelgiumInstitute of Experimental and Clinical Research, UCL Bruxelles Woluwe, Brussels, BelgiumSunrise, Namur, BelgiumNational Heart and Lung Institute, Imperial College London, Royal Brompton Hospital, London, United KingdomHP2 Laboratory, Inserm U1300, Grenoble Alpes University, Grenoble, FranceEFCR Laboratory, Thorax and Vessels division, Grenoble Alpes University Hospital, Grenoble, FranceBackgroundThe 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.Methods40 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).Results31 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.ConclusionThe 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 Registrationhttps://clinicaltrials.gov, identifier NCT04262557https://www.frontiersin.org/articles/10.3389/fnins.2022.726880/fullsleep apnoeapolysomnographymandibular monitorin-home diagnosisone-night agreementperformance |
| spellingShingle | Julia L. Kelly Raoua Ben Messaoud Marie Joyeux-Faure Marie Joyeux-Faure Robin Terrail Robin Terrail Renaud Tamisier Renaud Tamisier Jean-Benoît Martinot Jean-Benoît Martinot Nhat-Nam Le-Dong Mary J. Morrell Jean-Louis Pépin Jean-Louis Pépin Diagnosis of Sleep Apnoea Using a Mandibular Monitor and Machine Learning Analysis: One-Night Agreement Compared to in-Home Polysomnography Frontiers in Neuroscience sleep apnoea polysomnography mandibular monitor in-home diagnosis one-night agreement performance |
| title | Diagnosis of Sleep Apnoea Using a Mandibular Monitor and Machine Learning Analysis: One-Night Agreement Compared to in-Home Polysomnography |
| title_full | Diagnosis of Sleep Apnoea Using a Mandibular Monitor and Machine Learning Analysis: One-Night Agreement Compared to in-Home Polysomnography |
| title_fullStr | Diagnosis of Sleep Apnoea Using a Mandibular Monitor and Machine Learning Analysis: One-Night Agreement Compared to in-Home Polysomnography |
| title_full_unstemmed | Diagnosis of Sleep Apnoea Using a Mandibular Monitor and Machine Learning Analysis: One-Night Agreement Compared to in-Home Polysomnography |
| title_short | Diagnosis of Sleep Apnoea Using a Mandibular Monitor and Machine Learning Analysis: One-Night Agreement Compared to in-Home Polysomnography |
| title_sort | diagnosis of sleep apnoea using a mandibular monitor and machine learning analysis one night agreement compared to in home polysomnography |
| topic | sleep apnoea polysomnography mandibular monitor in-home diagnosis one-night agreement performance |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2022.726880/full |
| work_keys_str_mv | AT julialkelly diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT raouabenmessaoud diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT mariejoyeuxfaure diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT mariejoyeuxfaure diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT robinterrail diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT robinterrail diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT renaudtamisier diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT renaudtamisier diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT jeanbenoitmartinot diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT jeanbenoitmartinot diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT nhatnamledong diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT maryjmorrell diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT jeanlouispepin diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography AT jeanlouispepin diagnosisofsleepapnoeausingamandibularmonitorandmachinelearninganalysisonenightagreementcomparedtoinhomepolysomnography |