{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:44:36Z","timestamp":1791996276515,"version":"4.4.0"},"reference-count":32,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Study Objectives<\/jats:title>\n                    <jats:p>Current multimodal approaches for automated sleep apnea detection usually assume continuous signal availability, although sensor dropout is common in clinical practice. We evaluated probability-level late fusion across signal configurations and missing-data conditions to determine whether performance depends more on signal complementarity or modality count.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>We trained random forest base classifiers on electroencephalography (EEG), electrocardiography (ECG), pulse oximetry (SpO\u2082), and abdominal effort features from 148 patients. Each classifier generated three-class posterior probabilities, which were concatenated and input to a meta-classifier for final epoch-level prediction. Unreliable SpO\u2082 epochs were excluded only from SpO\u2082 base-model fitting but retained during meta-classifier training and testing using uniform placeholder probabilities [0.333, 0.333, and 0.333] plus the isBad quality flag. Selected unimodal and multimodal configurations were evaluated in 37 held-out patients using macro-F1 as the primary metric. Bootstrap confidence intervals stratified by SpO\u2082 quality assessed robustness under dropout.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Abdominal effort alone achieved macro-F1\u2009=\u20090.996. SpO\u2082\u2009+\u2009abdominal effort achieved the highest macro-F1\u2009=\u20090.997, only marginally above abdominal effort alone. ECG\u2009+\u2009EEG outperformed SpO\u2082\u2009+\u2009ECG and SpO\u2082\u2009+\u2009EEG despite lacking direct respiratory or oxygenation information. SpO\u2082\u2009+\u2009EEG showed degraded performance (macro-F1\u2009=\u20090.739; hypopnea precision\u2009=\u20090.203). Adding SpO\u2082 to ECG\u2009+\u2009EEG reduced performance (0.872 vs 0.899). Performance remained stable despite 30.7% SpO\u2082 dropout.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Within probability-level late fusion, performance depended more on signal complementarity than modality count. Quality-aware probability integration enabled robust classification under realistic SpO\u2082 dropout without retraining, but fixed-epoch late fusion limited exploitation of temporally misaligned oximetry information.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/sleep\/zsag247","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T13:11:36Z","timestamp":1789737096000},"source":"Crossref","is-referenced-by-count":0,"title":["Multimodal respiratory event detection leveraging signal complementarity under intermittent SpO\u2082 loss"],"prefix":"10.1093","author":[{"given":"Linh T D","family":"Tran","sequence":"first","affiliation":[{"name":"Center for Family Doctors, School of Medicine, University of Medicine and Pharmacy at Ho Chi Minh City , Ho Chi Minh City 70000 ,","place":["Vietnam"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trang H","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Faculty of Applied Sciences, University of Li\u00e8ge , Li\u00e8ge 4000 ,","place":["Belgium"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vu Q","family":"Do","sequence":"additional","affiliation":[{"name":"Department of Science and Technology, University of Medicine and Pharmacy at Ho Chi Minh City , Ho Chi Minh City 70000 ,","place":["Vietnam"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Loan T H","family":"Bui","sequence":"additional","affiliation":[{"name":"General Planning Department, University Medical Center Ho Chi Minh City , Ho Chi Minh City 70000 ,","place":["Vietnam"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vinh N","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Center for Family Doctors, School of Medicine, University of Medicine and Pharmacy at Ho Chi Minh City , Ho Chi Minh City 70000 ,","place":["Vietnam"]},{"name":"Department of Respiratory Functional Exploration, University Medical Center , Ho Chi Minh City 70000 ,","place":["Vietnam"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tran Ngoc","family":"Dang","sequence":"additional","affiliation":[{"name":"Department of Science and Technology, University of Medicine and Pharmacy at Ho Chi Minh City , Ho Chi Minh City 70000 ,","place":["Vietnam"]},{"name":"Department of Environmental Health, Faculty of Public Health, University of Medicine and Pharmacy at Ho Chi Minh City , Ho Chi Minh City 70000 ,","place":["Vietnam"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"issue":"9","key":"2026101411471984800_ref1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15091088","article-title":"The global burden of obstructive sleep apnea","volume":"15","author":"Iannella","year":"2025","journal-title":"Diagnostics (Basel)"},{"issue":"3","key":"2026101411471984800_ref2","doi-asserted-by":"publisher","first-page":"e56","DOI":"10.1161\/CIR.0000000000000988","article-title":"Obstructive sleep apnea and cardiovascular disease: a scientific statement from the American Heart Association","volume":"144","author":"Yeghiazarians","year":"2021","journal-title":"Circulation."},{"issue":"3","key":"2026101411471984800_ref3","doi-asserted-by":"publisher","first-page":"479","DOI":"10.5664\/jcsm.6506","article-title":"Clinical practice guideline for diagnostic testing for adult obstructive sleep apnea: an American Academy of Sleep Medicine clinical practice guideline","volume":"13","author":"Kapur","year":"2017","journal-title":"J Clin Sleep Med"},{"issue":"1","key":"2026101411471984800_ref4","first-page":"60","article-title":"Home sleep apnea testing for obstructive sleep apnea","volume":"121","author":"Hussein","year":"2024","journal-title":"Mo Med"},{"issue":"1","key":"2026101411471984800_ref5","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1038\/s41597-025-05583-8","article-title":"A multimodal dataset for training deep learning models aimed at detecting and analyzing sleep apnea","volume":"12","author":"Tao","year":"2025","journal-title":"Sci Data"},{"issue":"4","key":"2026101411471984800_ref6","doi-asserted-by":"publisher","first-page":"823","DOI":"10.5664\/jcsm.10420","article-title":"Distinguishing central from obstructive hypopneas on a clinical polysomnogram","volume":"19","author":"Javaheri","year":"2023","journal-title":"J Clin Sleep Med"},{"issue":"7","key":"2026101411471984800_ref7","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1164\/rccm.200907-1146OC","article-title":"Automated prediction of apnea and hypopnea, using a LAMSTAR artificial neural network","volume":"181","author":"Waxman","year":"2010","journal-title":"Am J Respir Crit Care Med"},{"key":"2026101411471984800_ref8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/embc58623.2025.11252834","article-title":"Continuous SpO2 monitoring using reflectance pulse oximetry at the wrist and upper arm during overnight sleep apnea recordings","volume":"2025","author":"Adam","year":"2025","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"2026101411471984800_ref9","volume-title":"The AASM Manual for the Scoring of Sleep and Associated Events, Version 3","author":"Troester","year":"2023"},{"key":"2026101411471984800_ref10","volume-title":"Proc 9th Mach Learn Healthcare Conf","author":"Fayyaz"},{"issue":"3","key":"2026101411471984800_ref11","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1007\/s11325-021-02465-2","article-title":"Sleep apnea and respiratory anomaly detection from a wearable band and oxygen saturation","volume":"26","author":"Ganglberger","year":"2022","journal-title":"Sleep Breath"},{"key":"2026101411471984800_ref12","doi-asserted-by":"publisher","first-page":"100549","DOI":"10.1016\/j.array.2025.100549","article-title":"Volatility-aware multimodal sleep modeling with latent state inference and pareto-optimized sensor fusion","volume":"28","author":"Sirpal","year":"2025","journal-title":"Array."},{"key":"2026101411471984800_ref13","doi-asserted-by":"publisher","first-page":"e1554","DOI":"10.7717\/peerj-cs.1554","article-title":"Sleep disorder and apnea events detection framework with high performance using two-tier learning model design","volume":"9","author":"Arslan","year":"2023","journal-title":"PeerJ Comput Sci"},{"issue":"2","key":"2026101411471984800_ref14","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Netw"},{"key":"2026101411471984800_ref15","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1186\/1471-2105-7-91","article-title":"Bias in error estimation when using cross-validation for model selection","volume":"7","author":"Varma","year":"2006","journal-title":"BMC Bioinformatics"},{"issue":"6","key":"2026101411471984800_ref16","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","article-title":"Multimodal fusion for multimedia analysis: a survey","volume":"16","author":"Atrey","year":"2010","journal-title":"Multimedia Syst"},{"issue":"4","key":"2026101411471984800_ref17","doi-asserted-by":"publisher","DOI":"10.1183\/23120541.01051-2023","article-title":"Prolonged lung-to-finger circulation time indicates an increased risk of intermittent hypoxaemia in sleep apnoea patients","volume":"10","author":"Pahari","year":"2024","journal-title":"ERJ Open Res"},{"issue":"4","key":"2026101411471984800_ref18","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1093\/sleep\/21.4.386","article-title":"Importance of the pulse oximeter averaging time when measuring oxygen desaturation in sleep apnea","volume":"21","author":"Farr\u00e9","year":"1998","journal-title":"Sleep."},{"issue":"2","key":"2026101411471984800_ref19","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab569","article-title":"Multimodal deep learning for biomedical data fusion: a review","volume":"23","author":"Stahlschmidt","year":"2022","journal-title":"Brief Bioinform"},{"key":"2026101411471984800_ref20","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: a survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"14","key":"2026101411471984800_ref21","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.1093\/eurheartj\/ehy624","article-title":"The hypoxic burden of sleep apnoea predicts cardiovascular disease-related mortality: the Osteoporotic Fractures in Men Study and the Sleep Heart Health Study","volume":"40","author":"Azarbarzin","year":"2019","journal-title":"Eur Heart J"},{"issue":"10","key":"2026101411471984800_ref22","doi-asserted-by":"publisher","DOI":"10.1093\/sleep\/zsab145","article-title":"Characteristics and reproducibility of novel sleep EEG biomarkers and their variation with sleep apnea and insomnia in a large community-based cohort","volume":"44","author":"Younes","year":"2021","journal-title":"Sleep."},{"issue":"12","key":"2026101411471984800_ref23","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.5664\/jcsm.7540","article-title":"Clinical use of a home sleep apnea test: an updated American Academy of Sleep Medicine position statement","volume":"14","author":"Rosen","year":"2018","journal-title":"J Clin Sleep Med"},{"issue":"7","key":"2026101411471984800_ref24","doi-asserted-by":"publisher","first-page":"737","DOI":"10.5664\/jcsm.27032","article-title":"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","volume":"3","author":"Collop","year":"2007","journal-title":"J Clin Sleep Med"},{"issue":"10","key":"2026101411471984800_ref25","doi-asserted-by":"publisher","first-page":"4977","DOI":"10.1109\/JBHI.2023.3253728","article-title":"MaskSleepNet: a cross-modality adaptation neural network for heterogeneous signals processing in sleep staging","volume":"27","author":"Zhu","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"key":"2026101411471984800_ref26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2147\/nss.S492806","article-title":"Deep learning for obstructive sleep apnea detection and severity assessment: a multimodal signals fusion multiscale transformer model","volume":"17","author":"Zhang","year":"2025","journal-title":"Nat Sci Sleep"},{"issue":"1","key":"2026101411471984800_ref27","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/s40747-024-01648-0","article-title":"Multimodal heterogeneous graph fusion for automated obstructive sleep apnea-hypopnea syndrome diagnosis","volume":"11","author":"Wang","year":"2024","journal-title":"Complex Intell Syst"},{"key":"2026101411471984800_ref28","doi-asserted-by":"publisher","first-page":"102808","DOI":"10.1016\/j.artmed.2024.102808","article-title":"A bimodal feature fusion convolutional neural network for detecting obstructive sleep apnea\/hypopnea from nasal airflow and oximetry signals","volume":"150","author":"Peng","year":"2024","journal-title":"Artif Intell Med"},{"key":"2026101411471984800_ref29","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1613\/jair.594","article-title":"Issues in stacked generalization","volume":"10","author":"Ting","year":"1999","journal-title":"J Artif Intell Res"},{"issue":"1","key":"2026101411471984800_ref30","doi-asserted-by":"publisher","first-page":"13200","DOI":"10.1038\/s41598-019-49330-7","article-title":"Artificial neural network analysis of the oxygen saturation signal enables accurate diagnostics of sleep apnea","volume":"9","author":"Nikkonen","year":"2019","journal-title":"Sci Rep"},{"key":"2026101411471984800_ref31","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1007\/978-3-031-47715-7_38","volume-title":"Intelligent Systems and Applications","author":"Juraev","year":"2024"},{"issue":"6","key":"2026101411471984800_ref32","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","article-title":"Deep multimodal learning: a survey on recent advances and trends","volume":"34","author":"Ramachandram","year":"2017","journal-title":"IEEE Signal Process Mag"}],"container-title":["SLEEP"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/sleep\/advance-article-pdf\/doi\/10.1093\/sleep\/zsag247\/71225129\/zsag247.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/sleep\/advance-article-pdf\/doi\/10.1093\/sleep\/zsag247\/71225129\/zsag247.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/sleep\/advance-article-pdf\/doi\/10.1093\/sleep\/zsag247\/71225129\/zsag247.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T15:47:32Z","timestamp":1791992852000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/sleep\/advance-article\/doi\/10.1093\/sleep\/zsag247\/8817199"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1093\/sleep\/zsag247","relation":{},"ISSN":["0161-8105","1550-9109"],"issn-type":[{"value":"0161-8105","type":"print"},{"value":"1550-9109","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]},"article-number":"zsag247"}}