Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals using Feature Engineering and a Bidirectional LSTM Network. Rad, A. B., Zabihi, M., Zhao, Z., Gabbouj, M., Katsaggelos, A. K., & Särkkä, S. arXiv e-prints, sep, 2019. Paper abstract bibtex Objective: The aim of this study is to develop an automated classification algorithm for polysomnography (PSG) recordings to detect non-apneic and non-hypopneic arousals. Our particular focus is on detecting the respiratory effort-related arousals (RERAs) which are very subtle respiratory events that do not meet the criteria for apnea or hypopnea, and are more challenging to detect. Methods: The proposed algorithm is based on a bidirectional long short-term memory (BiLSTM) classifier and 465 multi-domain features, extracted from multimodal clinical time series. The features consist of a set of physiology-inspired features (n = 75), obtained by multiple steps of feature selection and expert analysis, and a set of physiology-agnostic features (n = 390), derived from scattering transform. Results: The proposed algorithm is validated on the 2018 PhysioNet challenge dataset. The overall performance in terms of the area under the precision-recall curve (AUPRC) is 0.50 on the hidden test dataset. This result is tied for the second-best score during the follow-up and official phases of the 2018 PhysioNet challenge. Conclusions: The results demonstrate that it is possible to automatically detect subtle non-apneic/non-hypopneic arousal events from PSG recordings. Significance: Automatic detection of subtle respiratory events such as RERAs together with other non-apneic/non-hypopneic arousals will allow detailed annotations of large PSG databases. This contributes to a better retrospective analysis of sleep data, which may also improve the quality of treatment.
@article{AliBahrami2019,
abstract = {Objective: The aim of this study is to develop an automated classification algorithm for polysomnography (PSG) recordings to detect non-apneic and non-hypopneic arousals. Our particular focus is on detecting the respiratory effort-related arousals (RERAs) which are very subtle respiratory events that do not meet the criteria for apnea or hypopnea, and are more challenging to detect. Methods: The proposed algorithm is based on a bidirectional long short-term memory (BiLSTM) classifier and 465 multi-domain features, extracted from multimodal clinical time series. The features consist of a set of physiology-inspired features (n = 75), obtained by multiple steps of feature selection and expert analysis, and a set of physiology-agnostic features (n = 390), derived from scattering transform. Results: The proposed algorithm is validated on the 2018 PhysioNet challenge dataset. The overall performance in terms of the area under the precision-recall curve (AUPRC) is 0.50 on the hidden test dataset. This result is tied for the second-best score during the follow-up and official phases of the 2018 PhysioNet challenge. Conclusions: The results demonstrate that it is possible to automatically detect subtle non-apneic/non-hypopneic arousal events from PSG recordings. Significance: Automatic detection of subtle respiratory events such as RERAs together with other non-apneic/non-hypopneic arousals will allow detailed annotations of large PSG databases. This contributes to a better retrospective analysis of sleep data, which may also improve the quality of treatment.},
archivePrefix = {arXiv},
arxivId = {1909.02971},
author = {Rad, Ali Bahrami and Zabihi, Morteza and Zhao, Zheng and Gabbouj, Moncef and Katsaggelos, Aggelos K. and S{\"{a}}rkk{\"{a}}, Simo},
eprint = {1909.02971},
journal = {arXiv e-prints},
month = {sep},
pages = {arXiv----1909},
title = {{Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals using Feature Engineering and a Bidirectional LSTM Network}},
url = {http://arxiv.org/abs/1909.02971},
year = {2019}
}
Downloads: 0
{"_id":"9vjmhvdNTEZEsm8vc","bibbaseid":"rad-zabihi-zhao-gabbouj-katsaggelos-srkk-automatedpolysomnographyanalysisfordetectionofnonapneicandnonhypopneicarousalsusingfeatureengineeringandabidirectionallstmnetwork-2019","author_short":["Rad, A. B.","Zabihi, M.","Zhao, Z.","Gabbouj, M.","Katsaggelos, A. K.","Särkkä, S."],"bibdata":{"bibtype":"article","type":"article","abstract":"Objective: The aim of this study is to develop an automated classification algorithm for polysomnography (PSG) recordings to detect non-apneic and non-hypopneic arousals. Our particular focus is on detecting the respiratory effort-related arousals (RERAs) which are very subtle respiratory events that do not meet the criteria for apnea or hypopnea, and are more challenging to detect. Methods: The proposed algorithm is based on a bidirectional long short-term memory (BiLSTM) classifier and 465 multi-domain features, extracted from multimodal clinical time series. The features consist of a set of physiology-inspired features (n = 75), obtained by multiple steps of feature selection and expert analysis, and a set of physiology-agnostic features (n = 390), derived from scattering transform. Results: The proposed algorithm is validated on the 2018 PhysioNet challenge dataset. The overall performance in terms of the area under the precision-recall curve (AUPRC) is 0.50 on the hidden test dataset. This result is tied for the second-best score during the follow-up and official phases of the 2018 PhysioNet challenge. Conclusions: The results demonstrate that it is possible to automatically detect subtle non-apneic/non-hypopneic arousal events from PSG recordings. Significance: Automatic detection of subtle respiratory events such as RERAs together with other non-apneic/non-hypopneic arousals will allow detailed annotations of large PSG databases. This contributes to a better retrospective analysis of sleep data, which may also improve the quality of treatment.","archiveprefix":"arXiv","arxivid":"1909.02971","author":[{"propositions":[],"lastnames":["Rad"],"firstnames":["Ali","Bahrami"],"suffixes":[]},{"propositions":[],"lastnames":["Zabihi"],"firstnames":["Morteza"],"suffixes":[]},{"propositions":[],"lastnames":["Zhao"],"firstnames":["Zheng"],"suffixes":[]},{"propositions":[],"lastnames":["Gabbouj"],"firstnames":["Moncef"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]},{"propositions":[],"lastnames":["Särkkä"],"firstnames":["Simo"],"suffixes":[]}],"eprint":"1909.02971","journal":"arXiv e-prints","month":"sep","pages":"arXiv—-1909","title":"Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals using Feature Engineering and a Bidirectional LSTM Network","url":"http://arxiv.org/abs/1909.02971","year":"2019","bibtex":"@article{AliBahrami2019,\nabstract = {Objective: The aim of this study is to develop an automated classification algorithm for polysomnography (PSG) recordings to detect non-apneic and non-hypopneic arousals. Our particular focus is on detecting the respiratory effort-related arousals (RERAs) which are very subtle respiratory events that do not meet the criteria for apnea or hypopnea, and are more challenging to detect. Methods: The proposed algorithm is based on a bidirectional long short-term memory (BiLSTM) classifier and 465 multi-domain features, extracted from multimodal clinical time series. The features consist of a set of physiology-inspired features (n = 75), obtained by multiple steps of feature selection and expert analysis, and a set of physiology-agnostic features (n = 390), derived from scattering transform. Results: The proposed algorithm is validated on the 2018 PhysioNet challenge dataset. The overall performance in terms of the area under the precision-recall curve (AUPRC) is 0.50 on the hidden test dataset. This result is tied for the second-best score during the follow-up and official phases of the 2018 PhysioNet challenge. Conclusions: The results demonstrate that it is possible to automatically detect subtle non-apneic/non-hypopneic arousal events from PSG recordings. Significance: Automatic detection of subtle respiratory events such as RERAs together with other non-apneic/non-hypopneic arousals will allow detailed annotations of large PSG databases. This contributes to a better retrospective analysis of sleep data, which may also improve the quality of treatment.},\narchivePrefix = {arXiv},\narxivId = {1909.02971},\nauthor = {Rad, Ali Bahrami and Zabihi, Morteza and Zhao, Zheng and Gabbouj, Moncef and Katsaggelos, Aggelos K. and S{\\\"{a}}rkk{\\\"{a}}, Simo},\neprint = {1909.02971},\njournal = {arXiv e-prints},\nmonth = {sep},\npages = {arXiv----1909},\ntitle = {{Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals using Feature Engineering and a Bidirectional LSTM Network}},\nurl = {http://arxiv.org/abs/1909.02971},\nyear = {2019}\n}\n","author_short":["Rad, A. B.","Zabihi, M.","Zhao, Z.","Gabbouj, M.","Katsaggelos, A. K.","Särkkä, S."],"key":"AliBahrami2019","id":"AliBahrami2019","bibbaseid":"rad-zabihi-zhao-gabbouj-katsaggelos-srkk-automatedpolysomnographyanalysisfordetectionofnonapneicandnonhypopneicarousalsusingfeatureengineeringandabidirectionallstmnetwork-2019","role":"author","urls":{"Paper":"http://arxiv.org/abs/1909.02971"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","ya2CyA73rpZseyrZ8","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":[],"search_terms":["automated","polysomnography","analysis","detection","non","apneic","non","hypopneic","arousals","using","feature","engineering","bidirectional","lstm","network","rad","zabihi","zhao","gabbouj","katsaggelos","särkkä"],"title":"Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals using Feature Engineering and a Bidirectional LSTM Network","year":2019}