Phenotype-Based and Self-Learning Inter-Individual Sleep Apnea Screening With a Level IV-Like Monitoring System
Purpose: We propose a phenotype-based artificial intelligence system that can self-learn and is accurate for screening purposes and test it on a Level IV-like monitoring system.Methods: Based on the physiological knowledge, we hypothesize that the phenotype information will allow us to find subjects...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2018-07-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fphys.2018.00723/full |
| _version_ | 1818515217176330240 |
|---|---|
| author | Hau-Tieng Wu Hau-Tieng Wu Hau-Tieng Wu Jhao-Cheng Wu Po-Chiun Huang Ting-Yu Lin Tsai-Yu Wang Yuan-Hao Huang Yu-Lun Lo |
| author_facet | Hau-Tieng Wu Hau-Tieng Wu Hau-Tieng Wu Jhao-Cheng Wu Po-Chiun Huang Ting-Yu Lin Tsai-Yu Wang Yuan-Hao Huang Yu-Lun Lo |
| author_sort | Hau-Tieng Wu |
| collection | DOAJ |
| description | Purpose: We propose a phenotype-based artificial intelligence system that can self-learn and is accurate for screening purposes and test it on a Level IV-like monitoring system.Methods: Based on the physiological knowledge, we hypothesize that the phenotype information will allow us to find subjects from a well-annotated database that share similar sleep apnea patterns. Therefore, for a new-arriving subject, we can establish a prediction model from the existing database that is adaptive to the subject. We test the proposed algorithm on a database consisting of 62 subjects with the signals recorded from a Level IV-like wearable device measuring the thoracic and abdominal movements and the SpO2.Results: With the leave-one-subject-out cross validation, the accuracy of the proposed algorithm to screen subjects with an apnea-hypopnea index greater or equal to 15 is 93.6%, the positive likelihood ratio is 6.8, and the negative likelihood ratio is 0.03.Conclusion: The results confirm the hypothesis and show that the proposed algorithm has potential to screen patients with SAS. |
| first_indexed | 2024-12-11T00:26:11Z |
| format | Article |
| id | doaj.art-653b457511254157939730d522b847fd |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-12-11T00:26:11Z |
| publishDate | 2018-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-653b457511254157939730d522b847fd2022-12-22T01:27:32ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2018-07-01910.3389/fphys.2018.00723373195Phenotype-Based and Self-Learning Inter-Individual Sleep Apnea Screening With a Level IV-Like Monitoring SystemHau-Tieng Wu0Hau-Tieng Wu1Hau-Tieng Wu2Jhao-Cheng Wu3Po-Chiun Huang4Ting-Yu Lin5Tsai-Yu Wang6Yuan-Hao Huang7Yu-Lun Lo8Department of Mathematics, Duke University, Durham, NC, United StatesDepartment of Statistical Science, Duke University, Durham, NC, United StatesMathematics Division, National Center for Theoretical Sciences, Taipei, TaiwanDepartment of Electrical Engineering, National Tsing Hua University, Hsinchu, TaiwanDepartment of Electrical Engineering, National Tsing Hua University, Hsinchu, TaiwanDepartment of Thoracic Medicine, Chang Gung Memorial Hospital, School of Medicine, Chang Gung University, Taipei, TaiwanDepartment of Thoracic Medicine, Chang Gung Memorial Hospital, School of Medicine, Chang Gung University, Taipei, TaiwanDepartment of Electrical Engineering, Institute of Communications Engineering, National Tsing Hua University, Hsinchu, TaiwanDepartment of Thoracic Medicine, Chang Gung Memorial Hospital, School of Medicine, Chang Gung University, Taipei, TaiwanPurpose: We propose a phenotype-based artificial intelligence system that can self-learn and is accurate for screening purposes and test it on a Level IV-like monitoring system.Methods: Based on the physiological knowledge, we hypothesize that the phenotype information will allow us to find subjects from a well-annotated database that share similar sleep apnea patterns. Therefore, for a new-arriving subject, we can establish a prediction model from the existing database that is adaptive to the subject. We test the proposed algorithm on a database consisting of 62 subjects with the signals recorded from a Level IV-like wearable device measuring the thoracic and abdominal movements and the SpO2.Results: With the leave-one-subject-out cross validation, the accuracy of the proposed algorithm to screen subjects with an apnea-hypopnea index greater or equal to 15 is 93.6%, the positive likelihood ratio is 6.8, and the negative likelihood ratio is 0.03.Conclusion: The results confirm the hypothesis and show that the proposed algorithm has potential to screen patients with SAS.https://www.frontiersin.org/article/10.3389/fphys.2018.00723/fullsleep apnea screeningLevel IV-like monitoringself-learning AI systemphenotype metricinter-individual prediction |
| spellingShingle | Hau-Tieng Wu Hau-Tieng Wu Hau-Tieng Wu Jhao-Cheng Wu Po-Chiun Huang Ting-Yu Lin Tsai-Yu Wang Yuan-Hao Huang Yu-Lun Lo Phenotype-Based and Self-Learning Inter-Individual Sleep Apnea Screening With a Level IV-Like Monitoring System Frontiers in Physiology sleep apnea screening Level IV-like monitoring self-learning AI system phenotype metric inter-individual prediction |
| title | Phenotype-Based and Self-Learning Inter-Individual Sleep Apnea Screening With a Level IV-Like Monitoring System |
| title_full | Phenotype-Based and Self-Learning Inter-Individual Sleep Apnea Screening With a Level IV-Like Monitoring System |
| title_fullStr | Phenotype-Based and Self-Learning Inter-Individual Sleep Apnea Screening With a Level IV-Like Monitoring System |
| title_full_unstemmed | Phenotype-Based and Self-Learning Inter-Individual Sleep Apnea Screening With a Level IV-Like Monitoring System |
| title_short | Phenotype-Based and Self-Learning Inter-Individual Sleep Apnea Screening With a Level IV-Like Monitoring System |
| title_sort | phenotype based and self learning inter individual sleep apnea screening with a level iv like monitoring system |
| topic | sleep apnea screening Level IV-like monitoring self-learning AI system phenotype metric inter-individual prediction |
| url | https://www.frontiersin.org/article/10.3389/fphys.2018.00723/full |
| work_keys_str_mv | AT hautiengwu phenotypebasedandselflearninginterindividualsleepapneascreeningwithalevelivlikemonitoringsystem AT hautiengwu phenotypebasedandselflearninginterindividualsleepapneascreeningwithalevelivlikemonitoringsystem AT hautiengwu phenotypebasedandselflearninginterindividualsleepapneascreeningwithalevelivlikemonitoringsystem AT jhaochengwu phenotypebasedandselflearninginterindividualsleepapneascreeningwithalevelivlikemonitoringsystem AT pochiunhuang phenotypebasedandselflearninginterindividualsleepapneascreeningwithalevelivlikemonitoringsystem AT tingyulin phenotypebasedandselflearninginterindividualsleepapneascreeningwithalevelivlikemonitoringsystem AT tsaiyuwang phenotypebasedandselflearninginterindividualsleepapneascreeningwithalevelivlikemonitoringsystem AT yuanhaohuang phenotypebasedandselflearninginterindividualsleepapneascreeningwithalevelivlikemonitoringsystem AT yulunlo phenotypebasedandselflearninginterindividualsleepapneascreeningwithalevelivlikemonitoringsystem |