A tool for analysis and classification of sleep stages

Abstract

Scoring sleep stages is a critical process in assessing several sleep studies and slumber disorders. Sleep is classified in two major states: non-rapid-eye-movement (non-REM) sleep and REM sleep. Non-REM sleep comprises stages N1, N2 and N3. We develop a tool for automatic scoring the stages of sleep following the rules of 2007 AASM (American Academy of Sleep Medicine). The study propose the algorithm to classify based on some different characteristics of each stage, due to using a device of polysomnography (PSG) in order to collect the signals of Electroencephalography (EEG), Electro-oculography (EOG) and Electromyography (EMG). Methods of analysis are Fast Fourier Transform (FFT), Candidate of REM (CREM) and Digital Signal Filters (High pass, Low pass, Notch Filter). PSG signals were recorded continuously overnight in 5 healthy volunteer students (19 – 25 years old, 4 males and 1 female). PSG data are analyzed in 30 second epochs (data windows) in offline mode. The main result of analysis and classification is a hypnogram which were compared with those obtained by an experienced human scorer.