Títol:
|
Characterization of Daytime Sleepiness by Time–Frequency Measures of EEG Signals
|
Autor/a:
|
Melia, Umberto; Guaita, Marc; Vallverdú, Montserrat; Clarià Sancho, Francisco; Montserrat i Capdevila, Josep; Vilaseca, Isabel; Salamero, Manel; Gaig, Carles; Caminal Magrans, Pere; Santamaria, Joan
|
Notes:
|
Excessive daytime sleepiness (EDS) is one of
the main symptoms of several sleep-related disorders with
a great impact on patient lives. While many studies have
been carried out in order to assess daytime sleepiness,
automatic EDS detection still remains an open problem. In
this work, a detection approach based on the time–frequency
analysis of electroencephalography (EEG) signals
is proposed. Multichannel EEG signals were recorded
during five maintenance of wakefulness (MWT) and multiple
sleep latency tests alternated throughout the day from
patients suffering from sleep-disordered breathing. A group
of 20 patients with EDS was compared with a group of 20
patients without daytime sleepiness (WDS) by analyzing
60-s EEG windows in the waking state. Measures obtained
from the Choi–Williams distribution (CWD) and the crossCWD
were calculated in the EEG frequency bands d
(0.1–4 Hz), h (4–8 Hz), a (8–12 Hz), b (12–30 Hz), and
total band (TB, 0.1–45 Hz). Statistical differences between
EDS and WDS groups were found in the d and h bands
during MWT events (p\0.0001). The results show that
the EDS group presented more power in the h band, while
the WDS group presented higher spectral and cross-spectral
entropy in the frontal zone in the d band. In general,
CWD and cross-CWD measures yielded sensitivities and
specificities of above 80 %. The area under the receiver
operating characteristic curve was above 0.85 for classifying
EDS and WDS patients.
This work was supported within the framework of CICYT Grant TEC2010-20886, FIS PI07/0318 to MS (co-financed by FEDER), and Research Fellowship Grant FPU AP2009-0858 from the Spanish Government. CIBER of Bioengineering, Biomaterials and Nanomedicine is an initiative of ISCIII. |
Matèries:
|
-Biomedical signal processing -Time– frequency representation -Electroencephalography -Excessive daytime sleepiness |
Drets:
|
(c) Springer, 2015
info:eu-repo/semantics/restrictedAccess |
Tipus de document:
|
article publishedVersion |
Publicat per:
|
Springer Verlag
|
Compartir:
|
|