Automatic stage scoring of single-channel sleep EEG by using multiscale entropy and autoregressive models

Sheng Fu Liang, Chin En Kuo, Yu Han Hu, Yu Hsiang Pan, Yung Hung Wang

Research output: Contribution to journalArticlepeer-review

188 Citations (Scopus)

Abstract

In this paper, we propose an automatic sleep-scoring method combining multiscale entropy (MSE) and autoregressive (AR) models for single-channel EEG and to assess the performance of the method comparatively with manual scoring based on full polysomnograms. This is the first time that MSE has ever been applied to sleep scoring. All-night polysomnograms from 20 healthy individuals were scored using the Rechtschaffen and Kales rules. The developed method analyzed the EEG signals of C3-A2 for sleep staging. The results of automatic and manual scorings were compared on an epoch-by-epoch basis. A total of 8480 30-s sleep EEG epochs were measured and used for performance evaluation. The epoch-by-epoch comparison was made by classifying the EEG epochs into five states (Wake/REM/S1/S2/SWS) by the proposed method and manual scoring. The overall sensitivity and kappa coefficient of MSE alone are 76.9% and 0.65, respectively. Moreover, the overall sensitivity and kappa coefficient of our proposed method of integrating MSE, AR models, and a smoothing process can reach the sensitivity level of 88.1% and 0.81, respectively. Our results show that MSE is a useful and representative feature for sleep staging. It has high accuracy and good home-care applicability because a single EEG channel is used for sleep staging.

Original languageEnglish
Article number6165354
Pages (from-to)1649-1657
Number of pages9
JournalIEEE Transactions on Instrumentation and Measurement
Volume61
Issue number6
DOIs
Publication statusPublished - 2012

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Automatic stage scoring of single-channel sleep EEG by using multiscale entropy and autoregressive models'. Together they form a unique fingerprint.

Cite this