Automated analysis of overnight oximetry recordings by means of support vector machines to assist in the diagnosis of paediatric sleep apnoea. Sedano A.C., Gonzalez D.A., Kheirandish-Gozal L., Gutierrez-Tobal G.C., Sanchez R.H., Gozal D., & Del Campo Matias F. 2016. ![Automated analysis of overnight oximetry recordings by means of support vector machines to assist in the diagnosis of paediatric sleep apnoea [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Background. Paediatric obstructive sleep apnoea-hypopnoea syndrome (OSAHS) has emerged as a frequent and concerning medical condition in the past 2-3 decades. In-laboratory overnight polysomnography (PSG) is the gold standard diagnostic technique but is complex and relatively inaccessible. Objectives. Blood oxygen saturation (SpO2) from nocturnal oximetry could provide essential information in order to simplify the diagnostic process. The goal of this study was to design and assess an automated classifier aimed at detecting OSAHS. Methods. The population under study was composed of 176 children referred to the Sleep Unit due to suspected OSAHS. All children underwent complete in-laboratory PSG as gold standard. An apnoeahypopnoea index (AHI) greater than or equal to 5 e/h were considered OSAHScondpositive. The population was randomly divided into training set (60%) and test set (40%). SpO2recordings from PSG were processed offline. Three nonlinear measures were derived from nocturnal SpO2recordings and used to design a support vector machine (SVM) classifier. Conventional oxygen desaturation index of 3% (ODI3) was used for comparison purposes. Results. The SVM classifier reached 85.7% sensitivity, 81.0% specificity, 4.50 LR+, 0.18 LR-, and 82.9% accuracy in the test set. On the contrary, ODI3 achieved 89.3% sensitivity, 69.1% specificity, 2.89 LR+, 0.16 LR-, and 77.1% accuracy in the same test set. Conclusions. The proposed SVM classifier outperforms the conventional desaturation index ODI3. Therefore, SVMs and nonlinear measures could provide useful tools to assist in the diagnosis of paediatric OSAHS.
@misc{sedano_a.c._automated_2016,
title = {Automated analysis of overnight oximetry recordings by means of support vector machines to assist in the diagnosis of paediatric sleep apnoea},
url = {http://erj.ersjournals.com/content/48/suppl_60/OA4556},
abstract = {Background. Paediatric obstructive sleep apnoea-hypopnoea syndrome (OSAHS) has emerged as a frequent and concerning medical condition in the past 2-3 decades. In-laboratory overnight polysomnography (PSG) is the gold standard diagnostic technique but is complex and relatively inaccessible. Objectives. Blood oxygen saturation (SpO2) from nocturnal oximetry could provide essential information in order to simplify the diagnostic process. The goal of this study was to design and assess an automated classifier aimed at detecting OSAHS. Methods. The population under study was composed of 176 children referred to the Sleep Unit due to suspected OSAHS. All children underwent complete in-laboratory PSG as gold standard. An apnoeahypopnoea index (AHI) greater than or equal to 5 e/h were considered OSAHScondpositive. The population was randomly divided into training set (60\%) and test set (40\%). SpO2recordings from PSG were processed offline. Three nonlinear measures were derived from nocturnal SpO2recordings and used to design a support vector machine (SVM) classifier. Conventional oxygen desaturation index of 3\% (ODI3) was used for comparison purposes. Results. The SVM classifier reached 85.7\% sensitivity, 81.0\% specificity, 4.50 LR+, 0.18 LR-, and 82.9\% accuracy in the test set. On the contrary, ODI3 achieved 89.3\% sensitivity, 69.1\% specificity, 2.89 LR+, 0.16 LR-, and 77.1\% accuracy in the same test set. Conclusions. The proposed SVM classifier outperforms the conventional desaturation index ODI3. Therefore, SVMs and nonlinear measures could provide useful tools to assist in the diagnosis of paediatric OSAHS.},
urldate = {0048-01-02},
journal = {European Respiratory Journal},
author = {{Sedano A.C.} and {Gonzalez D.A.} and {Kheirandish-Gozal L.} and {Gutierrez-Tobal G.C.} and {Sanchez R.H.} and {Gozal D.} and {Del Campo Matias F.}},
year = {2016},
keywords = {*oximetry, *sleep disordered breathing, *support vector machine, Child, apnea monitoring, controlled clinical trial, controlled study, diagnosis, endogenous compound, gold standard, human, major clinical study, oxygen desaturation, polysomnography, randomized controlled trial, transcription factor Sp2, transcription factor Sp4}
}
Downloads: 0
{"_id":"63CvfM7t2p5k9A7wJ","bibbaseid":"sedanoac-gonzalezda-kheirandishgozall-gutierreztobalgc-sanchezrh-gozald-delcampomatiasf-automatedanalysisofovernightoximetryrecordingsbymeansofsupportvectormachinestoassistinthediagnosisofpaediatricsleepapnoea-2016","downloads":0,"creationDate":"2017-05-12T20:20:58.249Z","title":"Automated analysis of overnight oximetry recordings by means of support vector machines to assist in the diagnosis of paediatric sleep apnoea","author_short":["Sedano A.C.","Gonzalez D.A.","Kheirandish-Gozal L.","Gutierrez-Tobal G.C.","Sanchez R.H.","Gozal D.","Del Campo Matias F."],"year":2016,"bibtype":"misc","biburl":"http://bibbase.org/zotero/gxu917","bibdata":{"bibtype":"misc","type":"misc","title":"Automated analysis of overnight oximetry recordings by means of support vector machines to assist in the diagnosis of paediatric sleep apnoea","url":"http://erj.ersjournals.com/content/48/suppl_60/OA4556","abstract":"Background. Paediatric obstructive sleep apnoea-hypopnoea syndrome (OSAHS) has emerged as a frequent and concerning medical condition in the past 2-3 decades. In-laboratory overnight polysomnography (PSG) is the gold standard diagnostic technique but is complex and relatively inaccessible. Objectives. Blood oxygen saturation (SpO2) from nocturnal oximetry could provide essential information in order to simplify the diagnostic process. The goal of this study was to design and assess an automated classifier aimed at detecting OSAHS. Methods. The population under study was composed of 176 children referred to the Sleep Unit due to suspected OSAHS. All children underwent complete in-laboratory PSG as gold standard. An apnoeahypopnoea index (AHI) greater than or equal to 5 e/h were considered OSAHScondpositive. The population was randomly divided into training set (60%) and test set (40%). SpO2recordings from PSG were processed offline. Three nonlinear measures were derived from nocturnal SpO2recordings and used to design a support vector machine (SVM) classifier. Conventional oxygen desaturation index of 3% (ODI3) was used for comparison purposes. Results. The SVM classifier reached 85.7% sensitivity, 81.0% specificity, 4.50 LR+, 0.18 LR-, and 82.9% accuracy in the test set. On the contrary, ODI3 achieved 89.3% sensitivity, 69.1% specificity, 2.89 LR+, 0.16 LR-, and 77.1% accuracy in the same test set. Conclusions. The proposed SVM classifier outperforms the conventional desaturation index ODI3. Therefore, SVMs and nonlinear measures could provide useful tools to assist in the diagnosis of paediatric OSAHS.","urldate":"0048-01-02","journal":"European Respiratory Journal","author":[{"firstnames":[],"propositions":[],"lastnames":["Sedano A.C."],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Gonzalez D.A."],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Kheirandish-Gozal L."],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Gutierrez-Tobal G.C."],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Sanchez R.H."],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Gozal D."],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Del Campo Matias F."],"suffixes":[]}],"year":"2016","keywords":"*oximetry, *sleep disordered breathing, *support vector machine, Child, apnea monitoring, controlled clinical trial, controlled study, diagnosis, endogenous compound, gold standard, human, major clinical study, oxygen desaturation, polysomnography, randomized controlled trial, transcription factor Sp2, transcription factor Sp4","bibtex":"@misc{sedano_a.c._automated_2016,\n\ttitle = {Automated analysis of overnight oximetry recordings by means of support vector machines to assist in the diagnosis of paediatric sleep apnoea},\n\turl = {http://erj.ersjournals.com/content/48/suppl_60/OA4556},\n\tabstract = {Background. Paediatric obstructive sleep apnoea-hypopnoea syndrome (OSAHS) has emerged as a frequent and concerning medical condition in the past 2-3 decades. In-laboratory overnight polysomnography (PSG) is the gold standard diagnostic technique but is complex and relatively inaccessible. Objectives. Blood oxygen saturation (SpO2) from nocturnal oximetry could provide essential information in order to simplify the diagnostic process. The goal of this study was to design and assess an automated classifier aimed at detecting OSAHS. Methods. The population under study was composed of 176 children referred to the Sleep Unit due to suspected OSAHS. All children underwent complete in-laboratory PSG as gold standard. An apnoeahypopnoea index (AHI) greater than or equal to 5 e/h were considered OSAHScondpositive. The population was randomly divided into training set (60\\%) and test set (40\\%). SpO2recordings from PSG were processed offline. Three nonlinear measures were derived from nocturnal SpO2recordings and used to design a support vector machine (SVM) classifier. Conventional oxygen desaturation index of 3\\% (ODI3) was used for comparison purposes. Results. The SVM classifier reached 85.7\\% sensitivity, 81.0\\% specificity, 4.50 LR+, 0.18 LR-, and 82.9\\% accuracy in the test set. On the contrary, ODI3 achieved 89.3\\% sensitivity, 69.1\\% specificity, 2.89 LR+, 0.16 LR-, and 77.1\\% accuracy in the same test set. Conclusions. The proposed SVM classifier outperforms the conventional desaturation index ODI3. Therefore, SVMs and nonlinear measures could provide useful tools to assist in the diagnosis of paediatric OSAHS.},\n\turldate = {0048-01-02},\n\tjournal = {European Respiratory Journal},\n\tauthor = {{Sedano A.C.} and {Gonzalez D.A.} and {Kheirandish-Gozal L.} and {Gutierrez-Tobal G.C.} and {Sanchez R.H.} and {Gozal D.} and {Del Campo Matias F.}},\n\tyear = {2016},\n\tkeywords = {*oximetry, *sleep disordered breathing, *support vector machine, Child, apnea monitoring, controlled clinical trial, controlled study, diagnosis, endogenous compound, gold standard, human, major clinical study, oxygen desaturation, polysomnography, randomized controlled trial, transcription factor Sp2, transcription factor Sp4}\n}\n\n","author_short":["Sedano A.C.","Gonzalez D.A.","Kheirandish-Gozal L.","Gutierrez-Tobal G.C.","Sanchez R.H.","Gozal D.","Del Campo Matias F."],"key":"sedano_a.c._automated_2016","id":"sedano_a.c._automated_2016","bibbaseid":"sedanoac-gonzalezda-kheirandishgozall-gutierreztobalgc-sanchezrh-gozald-delcampomatiasf-automatedanalysisofovernightoximetryrecordingsbymeansofsupportvectormachinestoassistinthediagnosisofpaediatricsleepapnoea-2016","role":"author","urls":{"Paper":"http://erj.ersjournals.com/content/48/suppl_60/OA4556"},"keyword":["*oximetry","*sleep disordered breathing","*support vector machine","Child","apnea monitoring","controlled clinical trial","controlled study","diagnosis","endogenous compound","gold standard","human","major clinical study","oxygen desaturation","polysomnography","randomized controlled trial","transcription factor Sp2","transcription factor Sp4"],"downloads":0,"html":""},"search_terms":["automated","analysis","overnight","oximetry","recordings","means","support","vector","machines","assist","diagnosis","paediatric","sleep","apnoea","sedano a.c.","gonzalez d.a.","kheirandish-gozal l.","gutierrez-tobal g.c.","sanchez r.h.","gozal d.","del campo matias f."],"keywords":["*oximetry","*sleep disordered breathing","*support vector machine","child","apnea monitoring","controlled clinical trial","controlled study","diagnosis","endogenous compound","gold standard","human","major clinical study","oxygen desaturation","polysomnography","randomized controlled trial","transcription factor sp2","transcription factor sp4"],"authorIDs":[],"dataSources":["9LqPNaySNpNxYBFzj"]}