Literature DB >> 32964831

Large-scale assessment of consistency in sleep stage scoring rules among multiple sleep centers using an interpretable machine learning algorithm.

Gi-Ren Liu1, Ting-Yu Lin2, Hau-Tieng Wu3, Yuan-Chung Sheu4,5, Ching-Lung Liu6, Wen-Te Liu7, Mei-Chen Yang8, Yung-Lun Ni9, Kun-Ta Chou10, Chao-Hsien Chen6, Dean Wu7, Chou-Chin Lan8, Kuo-Liang Chiu9,11, Hwa-Yen Chiu10, Yu-Lun Lo2.   

Abstract

STUDY
OBJECTIVES: Polysomnography is the gold standard in identifying sleep stages; however, there are discrepancies in how technicians use the standards. Because organizing meetings to evaluate this discrepancy and/or reach a consensus among multiple sleep centers is time-consuming, we developed an artificial intelligence system to efficiently evaluate the reliability and consistency of sleep scoring and hence the sleep center quality.
METHODS: An interpretable machine learning algorithm was used to evaluate the interrater reliability (IRR) of sleep stage annotation among sleep centers. The artificial intelligence system was trained to learn raters from 1 hospital and was applied to patients from the same or other hospitals. The results were compared with the experts' annotation to determine IRR. Intracenter and intercenter assessments were conducted on 679 patients without sleep apnea from 6 sleep centers in Taiwan. Centers with potential quality issues were identified by the estimated IRR.
RESULTS: In the intracenter assessment, the median accuracy ranged from 80.3%-83.3%, with the exception of 1 hospital, which had an accuracy of 72.3%. In the intercenter assessment, the median accuracy ranged from 75.7%-83.3% when the 1 hospital was excluded from testing and training. The performance of the proposed method was higher for the N2, awake, and REM sleep stages than for the N1 and N3 stages. The significant IRR discrepancy of the 1 hospital suggested a quality issue. This quality issue was confirmed by the physicians in charge of the 1 hospital.
CONCLUSIONS: The proposed artificial intelligence system proved effective in assessing IRR and hence the sleep center quality.
© 2021 American Academy of Sleep Medicine.

Entities:  

Keywords:  intercenter assessments; interrater reliability; intracenter assessments; machine learning; sleep stage scoring

Mesh:

Year:  2021        PMID: 32964831      PMCID: PMC7853209          DOI: 10.5664/jcsm.8820

Source DB:  PubMed          Journal:  J Clin Sleep Med        ISSN: 1550-9389            Impact factor:   4.062


  19 in total

1.  Interobserver agreement among sleep scorers from different centers in a large dataset.

Authors:  R G Norman; I Pal; C Stewart; J A Walsleben; D M Rapoport
Journal:  Sleep       Date:  2000-11-01       Impact factor: 5.849

2.  Canonical correlation analysis: an overview with application to learning methods.

Authors:  David R Hardoon; Sandor Szedmak; John Shawe-Taylor
Journal:  Neural Comput       Date:  2004-12       Impact factor: 2.026

3.  Computer-Assisted Automated Scoring of Polysomnograms Using the Somnolyzer System.

Authors:  Naresh M Punjabi; Naima Shifa; Georg Dorffner; Susheel Patil; Grace Pien; Rashmi N Aurora
Journal:  Sleep       Date:  2015-10-01       Impact factor: 5.849

4.  DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG.

Authors:  Akara Supratak; Hao Dong; Chao Wu; Yike Guo
Journal:  IEEE Trans Neural Syst Rehabil Eng       Date:  2017-06-28       Impact factor: 3.802

5.  A Novel Multi-Class EEG-Based Sleep Stage Classification System.

Authors:  Pejman Memar; Farhad Faradji
Journal:  IEEE Trans Neural Syst Rehabil Eng       Date:  2018-01       Impact factor: 3.802

6.  Three drowsiness categories assessment by electroencephalogram in driving simulator environment.

Authors:  Izzat A Akbar; Arthur M Rumagit; Mitaku Utsunomiya; Takamasa Morie; Tomohiko Igasaki
Journal:  Conf Proc IEEE Eng Med Biol Soc       Date:  2017-07

7.  Computer-assisted sleep classification according to the standard of the American Academy of Sleep Medicine: validation study of the AASM version of the Somnolyzer 24 × 7.

Authors:  Peter Anderer; Arnaud Moreau; Michael Woertz; Marco Ross; Georg Gruber; Silvia Parapatics; Erna Loretz; Esther Heller; Andrea Schmidt; Marion Boeck; Doris Moser; Gerhard Kloesch; Bernd Saletu; Gerda M Saletu-Zyhlarz; Heidi Danker-Hopfe; Josef Zeitlhofer; Georg Dorffner
Journal:  Neuropsychobiology       Date:  2010-09-09       Impact factor: 2.328

8.  Process and outcome for international reliability in sleep scoring.

Authors:  Xiaozhe Zhang; Xiaosong Dong; Jan W Kantelhardt; Jing Li; Long Zhao; Carmen Garcia; Martin Glos; Thomas Penzel; Fang Han
Journal:  Sleep Breath       Date:  2014-05-07       Impact factor: 2.816

9.  Interrater reliability for sleep scoring according to the Rechtschaffen & Kales and the new AASM standard.

Authors:  Heidi Danker-Hopfe; Peter Anderer; Josef Zeitlhofer; Marion Boeck; Hans Dorn; Georg Gruber; Esther Heller; Erna Loretz; Doris Moser; Silvia Parapatics; Bernd Saletu; Andrea Schmidt; Georg Dorffner
Journal:  J Sleep Res       Date:  2009-03       Impact factor: 3.981

10.  A transition-constrained discrete hidden Markov model for automatic sleep staging.

Authors:  Shing-Tai Pan; Chih-En Kuo; Jian-Hong Zeng; Sheng-Fu Liang
Journal:  Biomed Eng Online       Date:  2012-08-21       Impact factor: 2.819

View more
  1 in total

1.  Intelligent automatic sleep staging model based on CNN and LSTM.

Authors:  Lan Zhuang; Minhui Dai; Yi Zhou; Lingyu Sun
Journal:  Front Public Health       Date:  2022-07-27
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.