Comparison of manual sleep staging with automated neural network-based analysis in clinical practice
- 26 January 2006
- journal article
- research article
- Published by Springer Science and Business Media LLC in Medical & Biological Engineering & Computing
- Vol. 44 (1-2), 105-110
- https://doi.org/10.1007/s11517-005-0002-4
Abstract
We have compared sleep staging by an automated neural network (ANN) system, BioSleep™ (Oxford BioSignals) and a human scorer using the Rechtschaffen and Kales scoring system. Sleep study recordings from 114 patients with suspected obstructed sleep apnoea syndrome (OSA) were analysed by ANN and by a blinded human scorer. We also examined human scorer reliability by calculating the agreement between the index scorer and a second independent blinded scorer for 28 of the 114 studies. For each study, we built contingency tables on an epoch-by-epoch (30 s epochs) comparison basis. From these, we derived kappa (κ) coefficients for different combinations of sleep stages. The overall agreement of automatic and manual scoring for the 114 studies for the classification {wake | light-sleep | deep-sleep | REM} was poor (median κ=0.305) and only a little better (κ=0.449) for the crude {wake | sleep} distinction. For the subgroup of 28 randomly selected studies, the overall agreement of automatic and manual scoring was again relatively low (κ=0.331 for {wake | light-sleep | deep-sleep | REM} and κ=0.505 for {wake | sleep}), whereas inter-scorer reliability was higher (κ=0.641 for {wake | light-sleep | deep-sleep | REM} and κ=0.737 for {wake | sleep}). We conclude that such an ANN-based analysis system is not sufficiently accurate for sleep study analyses using the R&K classification system.Keywords
This publication has 13 references indexed in Scilit:
- BioSleep: a comprehensive sleep analysis systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Unconstrained detection of respiration rhythm and pulse rate with one under-pillow sensor during sleepMedical & Biological Engineering & Computing, 2005
- Systematic comparison of different algorithms for apnoea detection based on electrocardiogram recordingsMedical & Biological Engineering & Computing, 2002
- Proposed supplements and amendments to ‘A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects’, the Rechtschaffen & Kales (1968) standardPsychiatry and Clinical Neurosciences, 2001
- Untersuchungen zum vollautomatischen Schlaf-EEG-Analysesystem QUISI®1Pneumologie, 2000
- The study of micro-arousals using neural network analysis of the EEGPublished by Institution of Engineering and Technology (IET) ,1999
- Validation of automated sleep analysis in normal children.European Respiratory Journal, 1998
- A new approach to the analysis of the human sleep/wakefulness continuumJournal of Sleep Research, 1996
- Automated Sleep EEg Analysis using an RBF NetworkPublished by Springer Science and Business Media LLC ,1995
- New method of automated sleep quantificationMedical & Biological Engineering & Computing, 1992