Real-Time Detection of Sleep Apnea Based on Breathing Sounds and Prediction Reinforcement Using Home Noises: Algorithm Development and Validation
BackgroundMultinight monitoring can be helpful for the diagnosis and management of obstructive sleep apnea (OSA). For this purpose, it is necessary to be able to detect OSA in real time in a noisy home environment. Sound-based OSA assessment holds great potential since it can...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2023-02-01
|
| Series: | Journal of Medical Internet Research |
| Online Access: | https://www.jmir.org/2023/1/e44818 |
| _version_ | 1797734331001602048 |
|---|---|
| author | Vu Linh Le Daewoo Kim Eunsung Cho Hyeryung Jang Roben Delos Reyes Hyunggug Kim Dongheon Lee In-Young Yoon Joonki Hong Jeong-Whun Kim |
| author_facet | Vu Linh Le Daewoo Kim Eunsung Cho Hyeryung Jang Roben Delos Reyes Hyunggug Kim Dongheon Lee In-Young Yoon Joonki Hong Jeong-Whun Kim |
| author_sort | Vu Linh Le |
| collection | DOAJ |
| description |
BackgroundMultinight monitoring can be helpful for the diagnosis and management of obstructive sleep apnea (OSA). For this purpose, it is necessary to be able to detect OSA in real time in a noisy home environment. Sound-based OSA assessment holds great potential since it can be integrated with smartphones to provide full noncontact monitoring of OSA at home.
ObjectiveThe purpose of this study is to develop a predictive model that can detect OSA in real time, even in a home environment where various noises exist.
MethodsThis study included 1018 polysomnography (PSG) audio data sets, 297 smartphone audio data sets synced with PSG, and a home noise data set containing 22,500 noises to train the model to predict breathing events, such as apneas and hypopneas, based on breathing sounds that occur during sleep. The whole breathing sound of each night was divided into 30-second epochs and labeled as “apnea,” “hypopnea,” or “no-event,” and the home noises were used to make the model robust to a noisy home environment. The performance of the prediction model was assessed using epoch-by-epoch prediction accuracy and OSA severity classification based on the apnea-hypopnea index (AHI).
ResultsEpoch-by-epoch OSA event detection showed an accuracy of 86% and a macro F1-score of 0.75 for the 3-class OSA event detection task. The model had an accuracy of 92% for “no-event,” 84% for “apnea,” and 51% for “hypopnea.” Most misclassifications were made for “hypopnea,” with 15% and 34% of “hypopnea” being wrongly predicted as “apnea” and “no-event,” respectively. The sensitivity and specificity of the OSA severity classification (AHI≥15) were 0.85 and 0.84, respectively.
ConclusionsOur study presents a real-time epoch-by-epoch OSA detector that works in a variety of noisy home environments. Based on this, additional research is needed to verify the usefulness of various multinight monitoring and real-time diagnostic technologies in the home environment. |
| first_indexed | 2024-03-12T12:42:43Z |
| format | Article |
| id | doaj.art-c4d56f55ccb44cc1a5e589c09c9158cf |
| institution | Directory Open Access Journal |
| issn | 1438-8871 |
| language | English |
| last_indexed | 2024-03-12T12:42:43Z |
| publishDate | 2023-02-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | Journal of Medical Internet Research |
| spelling | doaj.art-c4d56f55ccb44cc1a5e589c09c9158cf2023-08-28T23:46:37ZengJMIR PublicationsJournal of Medical Internet Research1438-88712023-02-0125e4481810.2196/44818Real-Time Detection of Sleep Apnea Based on Breathing Sounds and Prediction Reinforcement Using Home Noises: Algorithm Development and ValidationVu Linh Lehttps://orcid.org/0000-0001-6589-9895Daewoo Kimhttps://orcid.org/0000-0003-2475-6956Eunsung Chohttps://orcid.org/0000-0002-6230-5972Hyeryung Janghttps://orcid.org/0000-0002-7314-0739Roben Delos Reyeshttps://orcid.org/0000-0003-1368-6817Hyunggug Kimhttps://orcid.org/0000-0002-6579-5313Dongheon Leehttps://orcid.org/0000-0003-4660-6174In-Young Yoonhttps://orcid.org/0000-0002-3995-8238Joonki Honghttps://orcid.org/0000-0002-8378-3332Jeong-Whun Kimhttps://orcid.org/0000-0003-4858-3316 BackgroundMultinight monitoring can be helpful for the diagnosis and management of obstructive sleep apnea (OSA). For this purpose, it is necessary to be able to detect OSA in real time in a noisy home environment. Sound-based OSA assessment holds great potential since it can be integrated with smartphones to provide full noncontact monitoring of OSA at home. ObjectiveThe purpose of this study is to develop a predictive model that can detect OSA in real time, even in a home environment where various noises exist. MethodsThis study included 1018 polysomnography (PSG) audio data sets, 297 smartphone audio data sets synced with PSG, and a home noise data set containing 22,500 noises to train the model to predict breathing events, such as apneas and hypopneas, based on breathing sounds that occur during sleep. The whole breathing sound of each night was divided into 30-second epochs and labeled as “apnea,” “hypopnea,” or “no-event,” and the home noises were used to make the model robust to a noisy home environment. The performance of the prediction model was assessed using epoch-by-epoch prediction accuracy and OSA severity classification based on the apnea-hypopnea index (AHI). ResultsEpoch-by-epoch OSA event detection showed an accuracy of 86% and a macro F1-score of 0.75 for the 3-class OSA event detection task. The model had an accuracy of 92% for “no-event,” 84% for “apnea,” and 51% for “hypopnea.” Most misclassifications were made for “hypopnea,” with 15% and 34% of “hypopnea” being wrongly predicted as “apnea” and “no-event,” respectively. The sensitivity and specificity of the OSA severity classification (AHI≥15) were 0.85 and 0.84, respectively. ConclusionsOur study presents a real-time epoch-by-epoch OSA detector that works in a variety of noisy home environments. Based on this, additional research is needed to verify the usefulness of various multinight monitoring and real-time diagnostic technologies in the home environment.https://www.jmir.org/2023/1/e44818 |
| spellingShingle | Vu Linh Le Daewoo Kim Eunsung Cho Hyeryung Jang Roben Delos Reyes Hyunggug Kim Dongheon Lee In-Young Yoon Joonki Hong Jeong-Whun Kim Real-Time Detection of Sleep Apnea Based on Breathing Sounds and Prediction Reinforcement Using Home Noises: Algorithm Development and Validation Journal of Medical Internet Research |
| title | Real-Time Detection of Sleep Apnea Based on Breathing Sounds and Prediction Reinforcement Using Home Noises: Algorithm Development and Validation |
| title_full | Real-Time Detection of Sleep Apnea Based on Breathing Sounds and Prediction Reinforcement Using Home Noises: Algorithm Development and Validation |
| title_fullStr | Real-Time Detection of Sleep Apnea Based on Breathing Sounds and Prediction Reinforcement Using Home Noises: Algorithm Development and Validation |
| title_full_unstemmed | Real-Time Detection of Sleep Apnea Based on Breathing Sounds and Prediction Reinforcement Using Home Noises: Algorithm Development and Validation |
| title_short | Real-Time Detection of Sleep Apnea Based on Breathing Sounds and Prediction Reinforcement Using Home Noises: Algorithm Development and Validation |
| title_sort | real time detection of sleep apnea based on breathing sounds and prediction reinforcement using home noises algorithm development and validation |
| url | https://www.jmir.org/2023/1/e44818 |
| work_keys_str_mv | AT vulinhle realtimedetectionofsleepapneabasedonbreathingsoundsandpredictionreinforcementusinghomenoisesalgorithmdevelopmentandvalidation AT daewookim realtimedetectionofsleepapneabasedonbreathingsoundsandpredictionreinforcementusinghomenoisesalgorithmdevelopmentandvalidation AT eunsungcho realtimedetectionofsleepapneabasedonbreathingsoundsandpredictionreinforcementusinghomenoisesalgorithmdevelopmentandvalidation AT hyeryungjang realtimedetectionofsleepapneabasedonbreathingsoundsandpredictionreinforcementusinghomenoisesalgorithmdevelopmentandvalidation AT robendelosreyes realtimedetectionofsleepapneabasedonbreathingsoundsandpredictionreinforcementusinghomenoisesalgorithmdevelopmentandvalidation AT hyunggugkim realtimedetectionofsleepapneabasedonbreathingsoundsandpredictionreinforcementusinghomenoisesalgorithmdevelopmentandvalidation AT dongheonlee realtimedetectionofsleepapneabasedonbreathingsoundsandpredictionreinforcementusinghomenoisesalgorithmdevelopmentandvalidation AT inyoungyoon realtimedetectionofsleepapneabasedonbreathingsoundsandpredictionreinforcementusinghomenoisesalgorithmdevelopmentandvalidation AT joonkihong realtimedetectionofsleepapneabasedonbreathingsoundsandpredictionreinforcementusinghomenoisesalgorithmdevelopmentandvalidation AT jeongwhunkim realtimedetectionofsleepapneabasedonbreathingsoundsandpredictionreinforcementusinghomenoisesalgorithmdevelopmentandvalidation |