Sleep and Wakefulness State Detection in Nocturnal Actigraphy Based on Movement Information

Wrist actigraphy (ACT) is a low-cost and well-established technique for long-term monitoring of human activity. It has a special relevance in sleep studies, where its noninvasive nature makes it a valuable tool for behavioral characterization and for the detection and diagnosis of some sleep disorde...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on biomedical engineering 2014-02, Vol.61 (2), p.426-434
Main Authors: Domingues, Alexandre, Paiva, Teresa, Sanches, J. Miguel
Format: Article
Language:English
Subjects:
Accuracy
Actigraphy (ACT)
Actigraphy - methods
Adult
Algorithms
Diagnosis
Discriminant Analysis
Error detection
Feature extraction
Female
hidden Markov model (HMM)
Hidden Markov models
Histograms
Humans
linear discriminant classifier (LDC)
Male
Markov Chains
Middle Aged
Movement
Movement - physiology
movement detection
Sensitivity
Signal Processing, Computer-Assisted
Sleep
Sleep - physiology
sleep/wake estimation
State estimation
Syntax
Wakefulness
Wakefulness - physiology
Citations: Items that this one cites
Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Wrist actigraphy (ACT) is a low-cost and well-established technique for long-term monitoring of human activity. It has a special relevance in sleep studies, where its noninvasive nature makes it a valuable tool for behavioral characterization and for the detection and diagnosis of some sleep disorders. The traditional sleep/ wakefulness state estimation algorithms from the nocturnal ACT data are unbalanced from a sensitivity and specificity points of view since they tend to overestimate sleep state, with severe consequences from a diagnosis point of view. They usually maximize the overall accuracy that does not take into account the highly unbalanced state distribution. In this paper, a method is proposed to appropriately deal with this unbalanced problem, achieving similar sensitivity and specificity scores in the state estimation process. The proposed method combines two linear discriminant classifiers, trained with two different criteria involving movement detection to generate a first state estimate. This result is then refined by a Hidden Markov Model-based algorithm. The global accuracy, the sensitivity, and the specificity of the method are 77.8 %, 75.6 %, and 81.6 %, respectively, performing better than the tested algorithms. If the performance is assessed only for movement periods, this improvement is even higher.
ISSN:0018-9294
1558-2531
DOI:10.1109/TBME.2013.2280538