{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T12:55:58Z","timestamp":1789908958733,"version":"4.0.1"},"reference-count":40,"publisher":"IOP Publishing","issue":"12","license":[{"start":{"date-parts":[[2018,12,21]],"date-time":"2018-12-21T00:00:00Z","timestamp":1545350400000},"content-version":"vor","delay-in-days":20,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2018,12,21]],"date-time":"2018-12-21T00:00:00Z","timestamp":1545350400000},"content-version":"tdm","delay-in-days":20,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"crossref","award":["01IS17056"],"award-info":[{"award-number":["01IS17056"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Physiol. Meas."],"published-print":{"date-parts":[[2018,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    : Physiological networks (PN) model couplings between organs in a high-dimensional parameter space. Machine learning methods, in particular artifical neural networks (ANNs), are powerful on high-dimensional classification tasks. However, lack of interpretability of the resulting models has been a drawback in research. We assess relevant PN topology changes in obstructive sleep apnea (OSA) by novel ANN interpretation techniques.\n                    <jats:italic>Approach<\/jats:italic>\n                    : ANNs are trained to classify OSA based on the PNs of 48 patients and 48 age and gender matched healthy controls. The PNs consisting of 2812 links are derived from overnight biosignal recordings. The interpretation technique DeepLift is applied to the resulting ANN models, enabling the determination of the relevant features for classification decisions on individual subjects. The mean relevance scores of the features are compared to other machine learning methods (decision tree and random forests) and statistical tests on group differences.\n                    <jats:italic>Main results<\/jats:italic>\n                    : The ANN interpretation results show good agreement with the compared methods and 87% of the samples could be correctly classified. OSA patients show a significantly higher coupling (p\n                    <jats:inline-formula\/>\n                    0.001) in light sleep (N2) between breathing rate and EEG\n                    <jats:inline-formula\/>\n                    power in all electrode locations and to chin and leg muscular tone. In deep sleep (N3), OSA leads to significantly lower coupling (p\n                    <jats:inline-formula\/>\n                    0.01) in lateral connections of EEG\n                    <jats:inline-formula\/>\n                    and\n                    <jats:inline-formula\/>\n                    power in central and frontal positions. Misclassified OSA patients had all mild\/moderate AHIs and did not show PN topology changes. Both nights of these patients have been consistently misclassified as healthy. This may indicate, that the impact of respiratory events differs in subjects, thus forming different phenotypes.\n                    <jats:italic>Significance<\/jats:italic>\n                    : The proposed PN analysis provides a powerful and robust method to quantify a broad range of physiological interactions. Interpretability of the ANN make them a promising tool to identify new diagnostic markers in data-driven approaches.\n                  <\/jats:p>","DOI":"10.1088\/1361-6579\/aaf0c9","type":"journal-article","created":{"date-parts":[[2018,11,14]],"date-time":"2018-11-14T17:15:29Z","timestamp":1542215729000},"page":"124003","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Feature relevance in physiological networks for classification of obstructive sleep apnea"],"prefix":"10.1088","volume":"39","author":[{"given":"Christoph","family":"Jansen","sequence":"first","affiliation":[{"name":"HTW Berlin\u2014University of Applied Sciences Berlin"},{"name":"Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephan","family":"Hodel","sequence":"additional","affiliation":[{"name":"HTW Berlin\u2014University of Applied Sciences Berlin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4304-0112","authenticated-orcid":false,"given":"Thomas","family":"Penzel","sequence":"additional","affiliation":[{"name":"Charit\u00e9\u2014Universit\u00e4tsmedizin Berlin"},{"name":"St. Anne\u2019s University Hospital Brno"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Spott","sequence":"additional","affiliation":[{"name":"HTW Berlin\u2014University of Applied Sciences Berlin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7238-5339","authenticated-orcid":false,"given":"Dagmar","family":"Krefting","sequence":"additional","affiliation":[{"name":"HTW Berlin\u2014University of Applied Sciences Berlin"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2018,12,21]]},"reference":[{"key":"pmeaaaf0c9bib001","doi-asserted-by":"publisher","first-page":"2947","DOI":"10.1109\/TBME.2010.2060197","type":"journal-article","article-title":"Interhemispheric asynchrony correlates with severity of respiratory disturbance index in patients with sleep apnea","volume":"57","author":"Abeyratne","year":"2010","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmeaaaf0c9bib002","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s10916-010-9453-8","type":"journal-article","article-title":"Artificial apnea classification with quantitative sleep EEG synchronization","volume":"36","author":"Aksahin","year":"2012","journal-title":"J. Med. Syst."},{"key":"pmeaaaf0c9bib003","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0130140","type":"journal-article","article-title":"On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation","volume":"10","author":"Bach","year":"2015","journal-title":"PLoS One"},{"key":"pmeaaaf0c9bib004","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1093\/sleep\/26.6.717","type":"journal-article","article-title":"Change in periodic limb movement index during treatment of obstructive sleep apnea with continuous positive airway pressure","volume":"26","author":"Baran","year":"2003","journal-title":"Sleep"},{"key":"pmeaaaf0c9bib005","doi-asserted-by":"publisher","first-page":"e0142143","DOI":"10.1371\/journal.pone.0142143","type":"journal-article","article-title":"Network physiology: how organ systems dynamically interact","volume":"10","author":"Bartsch","year":"2015","journal-title":"PLoS One"},{"key":"pmeaaaf0c9bib006","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1038\/ncomms1705","type":"journal-article","article-title":"Network physiology reveals relations between network topology and physiological function","volume":"3","author":"Bashan","year":"2012","journal-title":"Nat. Commun."},{"key":"pmeaaaf0c9bib007","article-title":"The AASM manual for the scoring of sleep and associated events: rules, terminology and technical specifications. Version 2.4","author":"Berry","year":"2017","type":"report"},{"key":"pmeaaaf0c9bib008","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","type":"journal-article","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"pmeaaaf0c9bib009","doi-asserted-by":"publisher","first-page":"20170387","DOI":"10.1098\/rsif.2017.0387","type":"journal-article","article-title":"Opportunities and obstacles for deep learning in biology and medicine","volume":"15","author":"Ching","year":"2018","journal-title":"J. R. Soc. Interface"},{"key":"pmeaaaf0c9bib010","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1111\/j.1439-054X.2004.00038.x","type":"journal-article","article-title":"Percentile reference charts for selected sleep parameters for 20 to 80 year-old healthy subjects from the SIESTA database","volume":"9","author":"Danker-Hopfe","year":"2005","journal-title":"Somnologie\u2014Schlafforschung Schlafmedizin"},{"key":"pmeaaaf0c9bib011","doi-asserted-by":"publisher","first-page":"20150177","DOI":"10.1098\/rsta.2015.0177","type":"journal-article","article-title":"Predictability decomposition detects the impairment of brain\u2013heart dynamical networks during sleep disorders and their recovery with treatment","volume":"374","author":"Faes","year":"2016","journal-title":"Phil. Trans. R. Soc. A"},{"key":"pmeaaaf0c9bib012","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","type":"journal-article","article-title":"Measuring nominal scale agreement among many raters","volume":"76","author":"Fleiss","year":"1971","journal-title":"Psychol. Bull."},{"key":"pmeaaaf0c9bib013","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jneumeth.2012.02.025","type":"journal-article","article-title":"Connectivity measures applied to human brain electrophysiological data","volume":"207","author":"Greenblatt","year":"2012","journal-title":"J. Neurosci. Methods"},{"key":"pmeaaaf0c9bib014","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1016\/j.jsmc.2006.10.001","type":"journal-article","article-title":"Cyclic alternating pattern (CAP), sleep disordered breathing, and automatic analysis","volume":"1","author":"Guilleminault","year":"2006","journal-title":"Sleep Med. Clinics"},{"key":"pmeaaaf0c9bib015","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1016\/S2213-2600(15)00043-0","type":"journal-article","article-title":"Prevalence of sleep-disordered breathing in the general population: the HypnoLaus study","volume":"3","author":"Heinzer","year":"2015","journal-title":"Lancet Respiratory Med."},{"key":"pmeaaaf0c9bib016","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.resp.2018.06.006","type":"journal-article","article-title":"The correlations between electroencephalogram frequency components and restoration of stable breathing from respiratory events in sleep apnea hypopnea syndrome","volume":"2018","author":"Huang","year":"2018","journal-title":"Respiratory Physiol. Neurobiol."},{"key":"pmeaaaf0c9bib017","article-title":"The AASM manual for the scoring of sleep and associated events: rules, terminology and technical specifications 1st edn","author":"Iber","year":"2007","type":"report"},{"key":"pmeaaaf0c9bib018","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/18\/10\/100201","type":"journal-article","article-title":"Focus on the emerging new fields of network physiology and network medicine","volume":"18","author":"Ivanov","year":"2016","journal-title":"New J. Phys."},{"key":"pmeaaaf0c9bib019","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/978-1-4614-7138-7","type":"book","article-title":"Tree-based methods","author":"James","year":"2013"},{"key":"pmeaaaf0c9bib020","doi-asserted-by":"publisher","first-page":"399","DOI":"10.5665\/sleep.3424","type":"journal-article","article-title":"Regional reductions in sleep electroencephalography power in obstructive sleep apnea: a high-density EEG study","volume":"37","author":"Jones","year":"2014","journal-title":"Sleep"},{"key":"pmeaaaf0c9bib021","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0010602","type":"journal-article","article-title":"Cardiorespiratory phase-coupling is reduced in patients with obstructive sleep apnea","volume":"5","author":"Kabir","year":"2010","journal-title":"PLoS One"},{"key":"pmeaaaf0c9bib022","article-title":"Investigating the influence of noise and distractors on the interpretation of neural networks","author":"Kindermans","year":"2016","type":"preprint"},{"key":"pmeaaaf0c9bib023","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/51.932725","type":"journal-article","article-title":"The SIESTA project polygraphic and clinical database","volume":"20","author":"Kl\u00f6sch","year":"2001","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"pmeaaaf0c9bib024","doi-asserted-by":"publisher","DOI":"10.1063\/1.4999352","type":"journal-article","article-title":"On the difference of cardiorespiratory synchronisation and coordination","volume":"27","author":"Krause","year":"2017","journal-title":"Chaos"},{"key":"pmeaaaf0c9bib025","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1088\/1361-6579\/aa614e","type":"journal-article","article-title":"Age and gender dependency of physiological networks in sleep","volume":"38","author":"Krefting","year":"2017","journal-title":"Physiol. Meas."},{"key":"pmeaaaf0c9bib026","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1109\/IEMBS.2010.5627443","type":"journal-article","article-title":"Employment of a healthgrid for evaluation and development of polysomnographic biosignal processing methods","volume":"1","author":"Krefting","year":"2010","journal-title":"Conf. Proc. IEEE Eng. Med. Biol. Soc."},{"key":"pmeaaaf0c9bib027","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1016\/0013-4694(78)90145-1","type":"journal-article","article-title":"EMG activity of cricothyroid and chin muscles during wakefulness and sleeping in the sleep apnea syndrome","volume":"45","author":"Kurtz","year":"1978","journal-title":"Electroencephalogr. Clin. Neurophysiol."},{"key":"pmeaaaf0c9bib028","doi-asserted-by":"publisher","first-page":"15015","DOI":"10.1038\/nrdp.2015.15","type":"journal-article","article-title":"Obstructive sleep apnoea syndrome","volume":"1","author":"L\u00e9vy","year":"2015","journal-title":"Nat. Rev. Dis. Primers"},{"key":"pmeaaaf0c9bib029","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1093\/aje\/kws342","type":"journal-article","article-title":"Increased prevalence of sleep-disordered breathing in adults","volume":"177","author":"Peppard","year":"2013","journal-title":"Am. J. Epidemiology"},{"key":"pmeaaaf0c9bib030","doi-asserted-by":"publisher","first-page":"210","DOI":"10.7326\/M12-3187","type":"journal-article","article-title":"Diagnosis of obstructive sleep apnea in adults: a clinical practice guideline from the American College of Physicians","volume":"161","author":"Qaseem","year":"2014","journal-title":"Ann. Intern. Med."},{"key":"pmeaaaf0c9bib031","doi-asserted-by":"publisher","DOI":"10.1016\/0013-4694(69)90021-2)","type":"book","volume":"vol 204","author":"Rechtschaffen","year":"1968"},{"key":"pmeaaaf0c9bib032","doi-asserted-by":"publisher","first-page":"R232","DOI":"10.1152\/ajpregu.00302.2011","type":"journal-article","article-title":"Asymmetric sleep in apneic human patients","volume":"304","author":"Rial","year":"2013","journal-title":"Am. J. Physiol. Regulatory Integr. Comparative Physiol."},{"key":"pmeaaaf0c9bib033","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0093866","type":"journal-article","article-title":"Cardio-respiratory coordination increases during sleep apnea","volume":"9","author":"Riedl","year":"2014","journal-title":"PLoS One"},{"key":"pmeaaaf0c9bib034","doi-asserted-by":"publisher","first-page":"3254","DOI":"10.1109\/IEMBS.2004.1403915","type":"other","article-title":"libRASCH\u2014a programming framework for transparent access to physiological signals","volume":"vol 2","author":"Schneider","year":"2004"},{"key":"pmeaaaf0c9bib035","first-page":"3145","type":"other","article-title":"Learning important features through propagating activation differences","author":"Shrikumar","year":"2017"},{"key":"pmeaaaf0c9bib036","first-page":"1929","type":"journal-article","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"pmeaaaf0c9bib037","article-title":"The use of neural networks in the analysis of sleep stages and the diagnosis of narcolepsy","author":"Stephansen","year":"2017","type":"preprint"},{"key":"pmeaaaf0c9bib038","doi-asserted-by":"publisher","first-page":"1998","DOI":"10.1109\/TNSRE.2017.2721116","type":"journal-article","article-title":"DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG","volume":"25","author":"Supratak","year":"2017","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"pmeaaaf0c9bib039","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1111\/j.1365-2869.1995.tb00160.x","type":"journal-article","article-title":"Multi-centre comparison of five eye movement detection algorithms","volume":"4","author":"V\u00e4rri","year":"1995","journal-title":"J. Sleep Res."},{"key":"pmeaaaf0c9bib040","doi-asserted-by":"crossref","first-page":"16","DOI":"10.3760\/cma.j.issn.0366-6999.20112211","type":"journal-article","article-title":"Evaluation of neuromuscular activity in patients with obstructive sleep apnea using chin surface electromyography of polysomnography","volume":"126","author":"Yin","year":"2013","journal-title":"Chin. Med. J."}],"container-title":["Physiological Measurement"],"original-title":[],"link":[{"URL":"http:\/\/stacks.iop.org\/0967-3334\/39\/i=12\/a=124003?key=crossref.d4cd6fde16e6c93a92009b8bfd389879","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aaf0c9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"http:\/\/stacks.iop.org\/0967-3334\/39\/i=12\/a=124003\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aaf0c9","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aaf0c9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aaf0c9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aaf0c9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aaf0c9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aaf0c9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"http:\/\/stacks.iop.org\/0967-3334\/39\/i=12\/a=124003\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/stacks.iop.org\/0967-3334\/39\/i=12\/a=124003?key=crossref.d4cd6fde16e6c93a92009b8bfd389879","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aaf0c9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T12:02:55Z","timestamp":1783166575000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aaf0c9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,1]]},"references-count":40,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2018,12,21]]},"published-print":{"date-parts":[[2018,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6579\/aaf0c9","relation":{},"ISSN":["0967-3334","1361-6579"],"issn-type":[{"value":"0967-3334","type":"print"},{"value":"1361-6579","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,1]]},"assertion":[{"value":"Feature relevance in physiological networks for classification of obstructive sleep apnea","name":"article_title","label":"Article Title"},{"value":"Physiological Measurement","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2018 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2018-08-01","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2018-11-14","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2018-12-21","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}