Machine learning approaches for predicting sleep arousal response based on heart rate variability, oxygen saturation, and body profiles
Objective Obstructive sleep apnea is a global health concern, and several tools have been developed to screen its severity. However, most tools focus on respiratory events instead of sleep arousal, which can also affect sleep efficiency. This study employed easy-to-measure parameters—namely heart ra...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-10-01
|
| Series: | Digital Health |
| Online Access: | https://doi.org/10.1177/20552076231205744 |
| _version_ | 1797660058810580992 |
|---|---|
| author | Chih-Fan Kuo Cheng-Yu Tsai Wun-Hao Cheng Wen-Hua Hs Arnab Majumdar Marc Stettler Kang-Yun Lee Yi-Chun Kuan Po-Hao Feng Chien-Hua Tseng Kuan-Yuan Chen Jiunn-Horng Kang Hsin-Chien Lee Cheng-Jung Wu Wen-Te Liu |
| author_facet | Chih-Fan Kuo Cheng-Yu Tsai Wun-Hao Cheng Wen-Hua Hs Arnab Majumdar Marc Stettler Kang-Yun Lee Yi-Chun Kuan Po-Hao Feng Chien-Hua Tseng Kuan-Yuan Chen Jiunn-Horng Kang Hsin-Chien Lee Cheng-Jung Wu Wen-Te Liu |
| author_sort | Chih-Fan Kuo |
| collection | DOAJ |
| description | Objective Obstructive sleep apnea is a global health concern, and several tools have been developed to screen its severity. However, most tools focus on respiratory events instead of sleep arousal, which can also affect sleep efficiency. This study employed easy-to-measure parameters—namely heart rate variability, oxygen saturation, and body profiles—to predict arousal occurrence. Methods Body profiles and polysomnography recordings were collected from 659 patients. Continuous heart rate variability and oximetry measurements were performed and then labeled based on the presence of sleep arousal. The dataset, comprising five body profiles, mean heart rate, six heart rate variability, and five oximetry variables, was then split into 80% training/validation and 20% testing datasets. Eight machine learning approaches were employed. The model with the highest accuracy, area under the receiver operating characteristic curve, and area under the precision recall curve values in the training/validation dataset was applied to the testing dataset and to determine feature importance. Results InceptionTime, which exhibited superior performance in predicting sleep arousal in the training dataset, was used to classify the testing dataset and explore feature importance. In the testing dataset, InceptionTime achieved an accuracy of 76.21%, an area under the receiver operating characteristic curve of 84.33%, and an area under the precision recall curve of 86.28%. The standard deviations of time intervals between successive normal heartbeats and the square roots of the means of the squares of successive differences between normal heartbeats were predominant predictors of arousal occurrence. Conclusions The established models can be considered for screening sleep arousal occurrence or integrated in wearable devices for home-based sleep examination. |
| first_indexed | 2024-03-11T18:24:17Z |
| format | Article |
| id | doaj.art-a682ec5dcf464393b5dbb9cd3057f9d4 |
| institution | Directory Open Access Journal |
| issn | 2055-2076 |
| language | English |
| last_indexed | 2024-03-11T18:24:17Z |
| publishDate | 2023-10-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Digital Health |
| spelling | doaj.art-a682ec5dcf464393b5dbb9cd3057f9d42023-10-14T09:04:02ZengSAGE PublishingDigital Health2055-20762023-10-01910.1177/20552076231205744Machine learning approaches for predicting sleep arousal response based on heart rate variability, oxygen saturation, and body profilesChih-Fan Kuo0Cheng-Yu Tsai1Wun-Hao Cheng2Wen-Hua Hs3Arnab Majumdar4Marc Stettler5Kang-Yun Lee6Yi-Chun Kuan7Po-Hao Feng8Chien-Hua Tseng9Kuan-Yuan Chen10 Jiunn-Horng Kang11Hsin-Chien Lee12Cheng-Jung Wu13Wen-Te Liu14 Department of Medical Education, Chung Shan Medical University Hospital, Taichung, Taiwan Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, , New Taipei City, Taiwan Respiratory Therapy, Division of Pulmonary Medicine, Department of Internal Medicine, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan School of Respiratory Therapy, College of Medicine, , Taipei, Taiwan Department of Civil and Environmental Engineering, , London, UK Department of Civil and Environmental Engineering, , London, UK Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, , Taipei City, Taiwan Taipei Neuroscience Institute, , Taipei, Taiwan Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, , Taipei City, Taiwan Division of Pulmonary Medicine, Department of Internal Medicine, School of Medicine, College of Medicine, , Taipei City, Taiwan Division of Pulmonary Medicine, Department of Internal Medicine, Shuang Ho Hospital, , New Taipei City, Taiwan Graduate Institute of Nanomedicine and Medical Engineering, College of Biomedical Engineering, , Taipei, Taiwan Department of Psychiatry, , Taipei, Taiwan Department of Otolaryngology, Taipei Medical University-Shuang Ho Hospital, New Taipei City, Taiwan Research Center of Artificial Intelligence in Medicine, , Taipei, TaiwanObjective Obstructive sleep apnea is a global health concern, and several tools have been developed to screen its severity. However, most tools focus on respiratory events instead of sleep arousal, which can also affect sleep efficiency. This study employed easy-to-measure parameters—namely heart rate variability, oxygen saturation, and body profiles—to predict arousal occurrence. Methods Body profiles and polysomnography recordings were collected from 659 patients. Continuous heart rate variability and oximetry measurements were performed and then labeled based on the presence of sleep arousal. The dataset, comprising five body profiles, mean heart rate, six heart rate variability, and five oximetry variables, was then split into 80% training/validation and 20% testing datasets. Eight machine learning approaches were employed. The model with the highest accuracy, area under the receiver operating characteristic curve, and area under the precision recall curve values in the training/validation dataset was applied to the testing dataset and to determine feature importance. Results InceptionTime, which exhibited superior performance in predicting sleep arousal in the training dataset, was used to classify the testing dataset and explore feature importance. In the testing dataset, InceptionTime achieved an accuracy of 76.21%, an area under the receiver operating characteristic curve of 84.33%, and an area under the precision recall curve of 86.28%. The standard deviations of time intervals between successive normal heartbeats and the square roots of the means of the squares of successive differences between normal heartbeats were predominant predictors of arousal occurrence. Conclusions The established models can be considered for screening sleep arousal occurrence or integrated in wearable devices for home-based sleep examination.https://doi.org/10.1177/20552076231205744 |
| spellingShingle | Chih-Fan Kuo Cheng-Yu Tsai Wun-Hao Cheng Wen-Hua Hs Arnab Majumdar Marc Stettler Kang-Yun Lee Yi-Chun Kuan Po-Hao Feng Chien-Hua Tseng Kuan-Yuan Chen Jiunn-Horng Kang Hsin-Chien Lee Cheng-Jung Wu Wen-Te Liu Machine learning approaches for predicting sleep arousal response based on heart rate variability, oxygen saturation, and body profiles Digital Health |
| title | Machine learning approaches for predicting sleep arousal response based on heart rate variability, oxygen saturation, and body profiles |
| title_full | Machine learning approaches for predicting sleep arousal response based on heart rate variability, oxygen saturation, and body profiles |
| title_fullStr | Machine learning approaches for predicting sleep arousal response based on heart rate variability, oxygen saturation, and body profiles |
| title_full_unstemmed | Machine learning approaches for predicting sleep arousal response based on heart rate variability, oxygen saturation, and body profiles |
| title_short | Machine learning approaches for predicting sleep arousal response based on heart rate variability, oxygen saturation, and body profiles |
| title_sort | machine learning approaches for predicting sleep arousal response based on heart rate variability oxygen saturation and body profiles |
| url | https://doi.org/10.1177/20552076231205744 |
| work_keys_str_mv | AT chihfankuo machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT chengyutsai machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT wunhaocheng machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT wenhuahs machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT arnabmajumdar machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT marcstettler machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT kangyunlee machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT yichunkuan machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT pohaofeng machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT chienhuatseng machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT kuanyuanchen machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT jiunnhorngkang machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT hsinchienlee machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT chengjungwu machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles AT wenteliu machinelearningapproachesforpredictingsleeparousalresponsebasedonheartratevariabilityoxygensaturationandbodyprofiles |