Format

Send to

Choose Destination
J Neurosci Methods. 2015 Jul 30;250:94-105. doi: 10.1016/j.jneumeth.2015.01.022. Epub 2015 Jan 25.

Learning machines and sleeping brains: Automatic sleep stage classification using decision-tree multi-class support vector machines.

Author information

1
Sfax National Engineering School (ENIS), LETI Lab, University of Sfax, Sfax, Tunisia.
2
DYCOG Lab, Lyon Neuroscience Research Center, INSERM U1028, UMR 5292, University Lyon I, Lyon, France.
3
Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA.
4
Sfax National Engineering School (ENIS), LETI Lab, University of Sfax, Sfax, Tunisia; Higher Institute of Industrial Systems of Gabes (ISSIG), University of Gabes, Gabes, Tunisia.
5
DYCOG Lab, Lyon Neuroscience Research Center, INSERM U1028, UMR 5292, University Lyon I, Lyon, France; Psychology Department, University of Montreal, QC, Canada. Electronic address: karim.jerbi@umontreal.ca.

Abstract

BACKGROUND:

Sleep staging is a critical step in a range of electrophysiological signal processing pipelines used in clinical routine as well as in sleep research. Although the results currently achievable with automatic sleep staging methods are promising, there is need for improvement, especially given the time-consuming and tedious nature of visual sleep scoring.

NEW METHOD:

Here we propose a sleep staging framework that consists of a multi-class support vector machine (SVM) classification based on a decision tree approach. The performance of the method was evaluated using polysomnographic data from 15 subjects (electroencephalogram (EEG), electrooculogram (EOG) and electromyogram (EMG) recordings). The decision tree, or dendrogram, was obtained using a hierarchical clustering technique and a wide range of time and frequency-domain features were extracted. Feature selection was carried out using forward sequential selection and classification was evaluated using k-fold cross-validation.

RESULTS:

The dendrogram-based SVM (DSVM) achieved mean specificity, sensitivity and overall accuracy of 0.92, 0.74 and 0.88 respectively, compared to expert visual scoring. Restricting DSVM classification to data where both experts' scoring was consistent (76.73% of the data) led to a mean specificity, sensitivity and overall accuracy of 0.94, 0.82 and 0.92 respectively.

COMPARISON WITH EXISTING METHODS:

The DSVM framework outperforms classification with more standard multi-class "one-against-all" SVM and linear-discriminant analysis.

CONCLUSION:

The promising results of the proposed methodology suggest that it may be a valuable alternative to existing automatic methods and that it could accelerate visual scoring by providing a robust starting hypnogram that can be further fine-tuned by expert inspection.

KEYWORDS:

Decision-tree; Dendrogram; Electroencephalography (EEG); Hierarchical clustering; Linear Discriminant Analysis (LDA); Machine learning; Oscillations; Polysomnography; Sleep scoring; Support vector machine (SVM)

PMID:
25629798
DOI:
10.1016/j.jneumeth.2015.01.022
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center