Comparison of manual sleep staging with automated neural network-based analysis in clinical practice

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 (kappa) 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 kappa = 0.305) and only a little better (kappa = 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 (kappa = 0.331 for {wake light-sleep / deep-sleep REM} and kappa = 0.505 for {wake / sleep}), whereas inter-scorer reliability was higher (kappa = -0.641 for {wake / light-sleep / deep-sleep / REM} and kappa = 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.

Comparison of Manual Scoring With Auto Generated Polysomnographic Scoring in Obstructive Sleep Apnoea (Osa) Patients

“…are analyzed by the Physician. 11 50 Manual is accurate scoring method Nigro et al 12 96 Manual is accurate scoring method OZ turko et al 13 30 Manual is accurate scoring method J.caffarel et al 14 114 Manual is accurate scoring method B. Barreiro et al 15 28 Manual is accurate scoring method Carrasco O et al 16 36 Manual is accurate scoring method N Schaltenbrand et al 17 60 Manual is accurate scoring method St.Kubicki et al 18 34 Manual is accurate scoring method A Malhotra et al 19 70 Auto with manual editing Stephen D et al 20 31 Auto with manual editing Present study 100 Manual is accurate scoring method …”

“…6 The abnormal craniofacial characteristics include retrognathia, micrognathia, inferior positioning of hyoid bone, long and large soft palate, large tongue etc. 7,8 Patients with OSA have increased adipose tissue deposition lateral to pharynx. 9 OSA is a heterogenous disease process.…”

A Comparative Study in Cervical Muscle Activities during Various Resting Postures Using Electromyography

“…They reported that patients who lay on mattresses with normal stiffness experience less pain in their back than the ones with high stiffness mattress. Drinnan et al [17] characterized the various rest postures and separated them by a difference in parameters determined with electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG) amplitudes. Hansson et al [6] investigated the root mean square (RMS) of EMG data to present the distribution of various activity levels of neck muscles while at rest.…”

Detecting slow wave sleep using a single EEG signal channel

“…In addition to the cost and complexity of measuring and processing multiple signal channels, manual sleep staging is also tedious, time consuming, and errorprone. In response to these challenges, many automatic sleep staging methods using statistical learning or artificial intelligence techniques have been developed (Park et al, 2000, Agarwal and Gotman, 2001, Caffarel et al, 2006, Porée et al, 2006, Tagluk et al, 2010and Pan et al, 2012. The complexity of the sleep staging problems can be furthered alleviated by extracting features from fewer signal channels (Agarwal et al, 2005, Berthomier et al, 2007, Virkkala et al, 2007a, Virkkala et al, 2007b, Malinowska et al, 2009, Güneşa et al, 2010, Levendowski et al, 2012and Stepnowsky et al, 2013.…”