Kd. Nielsen et al., CAUSAL PROBABILISTIC NETWORK AND POWER SPECTRAL ESTIMATION USED IN SLEEP STAGE CLASSIFICATION, Methods of information in medicine, 36(4-5), 1997, pp. 345-348
Citations number
7
Categorie Soggetti
Medical Informatics","Computer Science Interdisciplinary Applications
A new method for sleep-stage classification using a causal probabilist
ic network as automatic classifier has been implemented and validated.
The system uses features from the primary sleep signals from the brai
n (EEG) and the eyes (AOG) as input. From the EEG, features are derive
d containing spectral information which is used to classify power in t
he classical spectral bands, sleep spindles and K-complexes. From AOG,
information on rapid eye movements is derived. Features are extracted
every 2 seconds. The CPN-based sleep classifier was implemented using
the HUGIN system, an application tool to handle causal probabilistic
networks. The results obtained using different training approaches sho
w agreements ranging from 68.7 to 70.7% between the system and the two
experts when a pooled agreement is computed over the six subjects. As
a comparison, the interrater agreement between the two experts was fo
und to be 71.4%, measured also over the six subjects.