An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring
Abstract In-home automated scoring systems are in high demand; however, the current systems are not widely adopted in clinical settings. Problems with electrode contact and restriction on measurable signals often result in unstable and inaccurate scoring for clinical use. To address these issues, we...
Saved in:
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-09-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-024-72612-8 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832585703354007552 |
---|---|
author | Kazumasa Horie Ryusuke Miyamoto Leo Ota Takashi Abe Yoko Suzuki Fusae Kawana Toshio Kokubo Masashi Yanagisawa Hiroyuki Kitagawa |
author_facet | Kazumasa Horie Ryusuke Miyamoto Leo Ota Takashi Abe Yoko Suzuki Fusae Kawana Toshio Kokubo Masashi Yanagisawa Hiroyuki Kitagawa |
author_sort | Kazumasa Horie |
collection | DOAJ |
description | Abstract In-home automated scoring systems are in high demand; however, the current systems are not widely adopted in clinical settings. Problems with electrode contact and restriction on measurable signals often result in unstable and inaccurate scoring for clinical use. To address these issues, we propose a method based on ensemble of small sleep stage scoring models with different input signal sets. By excluding models that employ problematic signals from the voting process, our method can mitigate the effects of electrode contact failure. Comparative experiments demonstrated that our method could reduce the impact of contact problems and improve scoring accuracy for epochs with problematic signals by 8.3 points, while also decreasing the deterioration in scoring accuracy from 7.9 to 0.3 points compared to typical methods. Additionally, we confirmed that assigning different input sets to small models did not diminish the advantages of the ensemble but instead increased its efficacy. The proposed model can improve overall scoring accuracy and minimize the effect of problematic signals simultaneously, making in-home sleep stage scoring systems more suitable for clinical practice. |
format | Article |
id | doaj-art-4d704f5fd4414b9b9683961c20910e50 |
institution | Kabale University |
issn | 2045-2322 |
language | English |
publishDate | 2024-09-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj-art-4d704f5fd4414b9b9683961c20910e502025-01-26T12:35:13ZengNature PortfolioScientific Reports2045-23222024-09-0114111210.1038/s41598-024-72612-8An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoringKazumasa Horie0Ryusuke Miyamoto1Leo Ota2Takashi Abe3Yoko Suzuki4Fusae Kawana5Toshio Kokubo6Masashi Yanagisawa7Hiroyuki Kitagawa8Center for Computational Sciences, University of TsukubaDepartment of Marine Biosciences, Tokyo University of Marine Science and TechnologyCenter for Computational Sciences, University of TsukubaInternational Institute for Integrative Sleep Medicine (WPI-IIIS), University of TsukubaInternational Institute for Integrative Sleep Medicine (WPI-IIIS), University of TsukubaYumino Heart ClinicInternational Institute for Integrative Sleep Medicine (WPI-IIIS), University of TsukubaInternational Institute for Integrative Sleep Medicine (WPI-IIIS), University of TsukubaCenter for Computational Sciences, University of TsukubaAbstract In-home automated scoring systems are in high demand; however, the current systems are not widely adopted in clinical settings. Problems with electrode contact and restriction on measurable signals often result in unstable and inaccurate scoring for clinical use. To address these issues, we propose a method based on ensemble of small sleep stage scoring models with different input signal sets. By excluding models that employ problematic signals from the voting process, our method can mitigate the effects of electrode contact failure. Comparative experiments demonstrated that our method could reduce the impact of contact problems and improve scoring accuracy for epochs with problematic signals by 8.3 points, while also decreasing the deterioration in scoring accuracy from 7.9 to 0.3 points compared to typical methods. Additionally, we confirmed that assigning different input sets to small models did not diminish the advantages of the ensemble but instead increased its efficacy. The proposed model can improve overall scoring accuracy and minimize the effect of problematic signals simultaneously, making in-home sleep stage scoring systems more suitable for clinical practice.https://doi.org/10.1038/s41598-024-72612-8 |
spellingShingle | Kazumasa Horie Ryusuke Miyamoto Leo Ota Takashi Abe Yoko Suzuki Fusae Kawana Toshio Kokubo Masashi Yanagisawa Hiroyuki Kitagawa An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring Scientific Reports |
title | An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring |
title_full | An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring |
title_fullStr | An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring |
title_full_unstemmed | An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring |
title_short | An ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring |
title_sort | ensemble method for improving robustness against the electrode contact problems in automated sleep stage scoring |
url | https://doi.org/10.1038/s41598-024-72612-8 |
work_keys_str_mv | AT kazumasahorie anensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT ryusukemiyamoto anensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT leoota anensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT takashiabe anensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT yokosuzuki anensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT fusaekawana anensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT toshiokokubo anensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT masashiyanagisawa anensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT hiroyukikitagawa anensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT kazumasahorie ensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT ryusukemiyamoto ensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT leoota ensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT takashiabe ensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT yokosuzuki ensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT fusaekawana ensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT toshiokokubo ensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT masashiyanagisawa ensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring AT hiroyukikitagawa ensemblemethodforimprovingrobustnessagainsttheelectrodecontactproblemsinautomatedsleepstagescoring |