Oxygen Saturation and RR Intervals Feature Selection for Sleep Apnea Detection
A diagnostic system for sleep apnea based on oxygen saturation and RR intervals obtained from the EKG (electrocardiogram) is proposed with the goal to detect and quantify minute long segments of sleep with breathing pauses. We measured the discriminative capacity of combinations of features obtained...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2015-05-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1099-4300/17/5/2932 |
| _version_ | 1818013237113782272 |
|---|---|
| author | Antonio G. Ravelo-García Jan F. Kraemer Juan L. Navarro-Mesa Eduardo Hernández-Pérez Javier Navarro-Esteva Gabriel Juliá-Serdá Thomas Penzel Niels Wessel |
| author_facet | Antonio G. Ravelo-García Jan F. Kraemer Juan L. Navarro-Mesa Eduardo Hernández-Pérez Javier Navarro-Esteva Gabriel Juliá-Serdá Thomas Penzel Niels Wessel |
| author_sort | Antonio G. Ravelo-García |
| collection | DOAJ |
| description | A diagnostic system for sleep apnea based on oxygen saturation and RR intervals obtained from the EKG (electrocardiogram) is proposed with the goal to detect and quantify minute long segments of sleep with breathing pauses. We measured the discriminative capacity of combinations of features obtained from RR series and oximetry to evaluate improvements of the performance compared to oximetry-based features alone. Time and frequency domain variables derived from oxygen saturation (SpO2) as well as linear and non-linear variables describing the RR series have been explored in recordings from 70 patients with suspected sleep apnea. We applied forward feature selection in order to select a minimal set of variables that are able to locate patterns indicating respiratory pauses. Linear discriminant analysis (LDA) was used to classify the presence of apnea during specific segments. The system will finally provide a global score indicating the presence of clinically significant apnea integrating the segment based apnea detection. LDA results in an accuracy of 87%; sensitivity of 76% and specificity of 91% (AUC = 0.90) with a global classification of 97% when only oxygen saturation is used. In case of additionally including features from the RR series; the system performance improves to an accuracy of 87%; sensitivity of 73% and specificity of 92% (AUC = 0.92), with a global classification rate of 100%. |
| first_indexed | 2024-04-14T06:30:39Z |
| format | Article |
| id | doaj.art-56ffe26db63541a3ba9ef0d7de31dba0 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-14T06:30:39Z |
| publishDate | 2015-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-56ffe26db63541a3ba9ef0d7de31dba02022-12-22T02:07:37ZengMDPI AGEntropy1099-43002015-05-011752932295710.3390/e17052932e17052932Oxygen Saturation and RR Intervals Feature Selection for Sleep Apnea DetectionAntonio G. Ravelo-García0Jan F. Kraemer1Juan L. Navarro-Mesa2Eduardo Hernández-Pérez3Javier Navarro-Esteva4Gabriel Juliá-Serdá5Thomas Penzel6Niels Wessel7Institute for Technological Development and Innovation in Communications, Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria 35017, SpainDepartment of Physics, Humboldt-Universitat zu Berlin, Berlin 10115, GermanyInstitute for Technological Development and Innovation in Communications, Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria 35017, SpainInstitute for Technological Development and Innovation in Communications, Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria 35017, SpainPulmonary Medicine Department, Hospital Universitario de Gran Canaria Dr. Negrın, Las Palmas de Gran Canaria 35010, SpainPulmonary Medicine Department, Hospital Universitario de Gran Canaria Dr. Negrın, Las Palmas de Gran Canaria 35010, SpainSleep Center, Charité Universitatsmedizin, Berlin 10117, GermanyDepartment of Physics, Humboldt-Universitat zu Berlin, Berlin 10115, GermanyA diagnostic system for sleep apnea based on oxygen saturation and RR intervals obtained from the EKG (electrocardiogram) is proposed with the goal to detect and quantify minute long segments of sleep with breathing pauses. We measured the discriminative capacity of combinations of features obtained from RR series and oximetry to evaluate improvements of the performance compared to oximetry-based features alone. Time and frequency domain variables derived from oxygen saturation (SpO2) as well as linear and non-linear variables describing the RR series have been explored in recordings from 70 patients with suspected sleep apnea. We applied forward feature selection in order to select a minimal set of variables that are able to locate patterns indicating respiratory pauses. Linear discriminant analysis (LDA) was used to classify the presence of apnea during specific segments. The system will finally provide a global score indicating the presence of clinically significant apnea integrating the segment based apnea detection. LDA results in an accuracy of 87%; sensitivity of 76% and specificity of 91% (AUC = 0.90) with a global classification of 97% when only oxygen saturation is used. In case of additionally including features from the RR series; the system performance improves to an accuracy of 87%; sensitivity of 73% and specificity of 92% (AUC = 0.92), with a global classification rate of 100%.http://www.mdpi.com/1099-4300/17/5/2932sleep apneaRR intervalsoxygen saturationfeature selection |
| spellingShingle | Antonio G. Ravelo-García Jan F. Kraemer Juan L. Navarro-Mesa Eduardo Hernández-Pérez Javier Navarro-Esteva Gabriel Juliá-Serdá Thomas Penzel Niels Wessel Oxygen Saturation and RR Intervals Feature Selection for Sleep Apnea Detection Entropy sleep apnea RR intervals oxygen saturation feature selection |
| title | Oxygen Saturation and RR Intervals Feature Selection for Sleep Apnea Detection |
| title_full | Oxygen Saturation and RR Intervals Feature Selection for Sleep Apnea Detection |
| title_fullStr | Oxygen Saturation and RR Intervals Feature Selection for Sleep Apnea Detection |
| title_full_unstemmed | Oxygen Saturation and RR Intervals Feature Selection for Sleep Apnea Detection |
| title_short | Oxygen Saturation and RR Intervals Feature Selection for Sleep Apnea Detection |
| title_sort | oxygen saturation and rr intervals feature selection for sleep apnea detection |
| topic | sleep apnea RR intervals oxygen saturation feature selection |
| url | http://www.mdpi.com/1099-4300/17/5/2932 |
| work_keys_str_mv | AT antoniogravelogarcia oxygensaturationandrrintervalsfeatureselectionforsleepapneadetection AT janfkraemer oxygensaturationandrrintervalsfeatureselectionforsleepapneadetection AT juanlnavarromesa oxygensaturationandrrintervalsfeatureselectionforsleepapneadetection AT eduardohernandezperez oxygensaturationandrrintervalsfeatureselectionforsleepapneadetection AT javiernavarroesteva oxygensaturationandrrintervalsfeatureselectionforsleepapneadetection AT gabrieljuliaserda oxygensaturationandrrintervalsfeatureselectionforsleepapneadetection AT thomaspenzel oxygensaturationandrrintervalsfeatureselectionforsleepapneadetection AT nielswessel oxygensaturationandrrintervalsfeatureselectionforsleepapneadetection |