Combining Heart Rate Variability and Oximetry to Improve Apneic Event Screening in Non-Desaturating Patients
In this paper, we thoroughly analyze the detection of sleep apnea events in the context of Obstructive Sleep Apnea (OSA), which is considered a public health problem because of its high prevalence and serious health implications. We especially evaluate patients who do not always show desaturations d...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/9/4267 |
| _version_ | 1797601736170405888 |
|---|---|
| author | Sofía Martín-González Antonio G. Ravelo-García Juan L. Navarro-Mesa Eduardo Hernández-Pérez |
| author_facet | Sofía Martín-González Antonio G. Ravelo-García Juan L. Navarro-Mesa Eduardo Hernández-Pérez |
| author_sort | Sofía Martín-González |
| collection | DOAJ |
| description | In this paper, we thoroughly analyze the detection of sleep apnea events in the context of Obstructive Sleep Apnea (OSA), which is considered a public health problem because of its high prevalence and serious health implications. We especially evaluate patients who do not always show desaturations during apneic episodes (non-desaturating patients). For this purpose, we use a database (HuGCDN2014-OXI) that includes desaturating and non-desaturating patients, and we use the widely used Physionet Apnea Dataset for a meaningful comparison with prior work. Our system combines features extracted from the Heart-Rate Variability (HRV) and SpO<sub>2</sub>, and it explores their potential to characterize desaturating and non-desaturating events. The HRV-based features include spectral, cepstral, and nonlinear information (Detrended Fluctuation Analysis (DFA) and Recurrence Quantification Analysis (RQA)). SpO<sub>2</sub>-based features include temporal (variance) and spectral information. The features feed a Linear Discriminant Analysis (LDA) classifier. The goal is to evaluate the effect of using these features either individually or in combination, especially in non-desaturating patients. The main results for the detection of apneic events are: (a) Physionet success rate of 96.19%, sensitivity of 95.74% and specificity of 95.25% (Area Under Curve (AUC): 0.99); (b) HuGCDN2014-OXI of 87.32%, 83.81% and 88.55% (AUC: 0.934), respectively. The best results for the global diagnosis of OSA patients (HuGCDN2014-OXI) are: success rate of 95.74%, sensitivity of 100%, and specificity of 89.47%. We conclude that combining both features is the most accurate option, especially when there are non-desaturating patterns among the recordings under study. |
| first_indexed | 2024-03-11T04:06:47Z |
| format | Article |
| id | doaj.art-564f8d4b10f749269b4a89a43c52650b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T04:06:47Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-564f8d4b10f749269b4a89a43c52650b2023-11-17T23:42:01ZengMDPI AGSensors1424-82202023-04-01239426710.3390/s23094267Combining Heart Rate Variability and Oximetry to Improve Apneic Event Screening in Non-Desaturating PatientsSofía Martín-González0Antonio G. Ravelo-García1Juan L. Navarro-Mesa2Eduardo Hernández-Pérez3Institute for Technological Development and Innovation in Communications, Universidad de Las Palmas de Gran Canaria, 35017 Las Palmas de Gran Canaria, SpainInstitute for Technological Development and Innovation in Communications, Universidad de Las Palmas de Gran Canaria, 35017 Las Palmas de Gran Canaria, SpainInstitute for Technological Development and Innovation in Communications, Universidad de Las Palmas de Gran Canaria, 35017 Las Palmas de Gran Canaria, SpainInstitute for Technological Development and Innovation in Communications, Universidad de Las Palmas de Gran Canaria, 35017 Las Palmas de Gran Canaria, SpainIn this paper, we thoroughly analyze the detection of sleep apnea events in the context of Obstructive Sleep Apnea (OSA), which is considered a public health problem because of its high prevalence and serious health implications. We especially evaluate patients who do not always show desaturations during apneic episodes (non-desaturating patients). For this purpose, we use a database (HuGCDN2014-OXI) that includes desaturating and non-desaturating patients, and we use the widely used Physionet Apnea Dataset for a meaningful comparison with prior work. Our system combines features extracted from the Heart-Rate Variability (HRV) and SpO<sub>2</sub>, and it explores their potential to characterize desaturating and non-desaturating events. The HRV-based features include spectral, cepstral, and nonlinear information (Detrended Fluctuation Analysis (DFA) and Recurrence Quantification Analysis (RQA)). SpO<sub>2</sub>-based features include temporal (variance) and spectral information. The features feed a Linear Discriminant Analysis (LDA) classifier. The goal is to evaluate the effect of using these features either individually or in combination, especially in non-desaturating patients. The main results for the detection of apneic events are: (a) Physionet success rate of 96.19%, sensitivity of 95.74% and specificity of 95.25% (Area Under Curve (AUC): 0.99); (b) HuGCDN2014-OXI of 87.32%, 83.81% and 88.55% (AUC: 0.934), respectively. The best results for the global diagnosis of OSA patients (HuGCDN2014-OXI) are: success rate of 95.74%, sensitivity of 100%, and specificity of 89.47%. We conclude that combining both features is the most accurate option, especially when there are non-desaturating patterns among the recordings under study.https://www.mdpi.com/1424-8220/23/9/4267apnea detectioncepstrum coefficientsdetrended fluctuation analysisheart rate variabilitylinear and nonlinear analysisnon-desaturating patients |
| spellingShingle | Sofía Martín-González Antonio G. Ravelo-García Juan L. Navarro-Mesa Eduardo Hernández-Pérez Combining Heart Rate Variability and Oximetry to Improve Apneic Event Screening in Non-Desaturating Patients Sensors apnea detection cepstrum coefficients detrended fluctuation analysis heart rate variability linear and nonlinear analysis non-desaturating patients |
| title | Combining Heart Rate Variability and Oximetry to Improve Apneic Event Screening in Non-Desaturating Patients |
| title_full | Combining Heart Rate Variability and Oximetry to Improve Apneic Event Screening in Non-Desaturating Patients |
| title_fullStr | Combining Heart Rate Variability and Oximetry to Improve Apneic Event Screening in Non-Desaturating Patients |
| title_full_unstemmed | Combining Heart Rate Variability and Oximetry to Improve Apneic Event Screening in Non-Desaturating Patients |
| title_short | Combining Heart Rate Variability and Oximetry to Improve Apneic Event Screening in Non-Desaturating Patients |
| title_sort | combining heart rate variability and oximetry to improve apneic event screening in non desaturating patients |
| topic | apnea detection cepstrum coefficients detrended fluctuation analysis heart rate variability linear and nonlinear analysis non-desaturating patients |
| url | https://www.mdpi.com/1424-8220/23/9/4267 |
| work_keys_str_mv | AT sofiamartingonzalez combiningheartratevariabilityandoximetrytoimproveapneiceventscreeninginnondesaturatingpatients AT antoniogravelogarcia combiningheartratevariabilityandoximetrytoimproveapneiceventscreeninginnondesaturatingpatients AT juanlnavarromesa combiningheartratevariabilityandoximetrytoimproveapneiceventscreeninginnondesaturatingpatients AT eduardohernandezperez combiningheartratevariabilityandoximetrytoimproveapneiceventscreeninginnondesaturatingpatients |