Sleep stage classification by combination of actigraphic and heart rate signals

This paper presents the performance of sleep stage classification by combination of actigraphic and heart rate signals. We studied 40,643 epochs (length 3 min) of polysomnographic data in 289 subjects. Body movement indices derived from actigraphic data and autonomic functional indices from heart rate variability were useful for discriminating between non-REM sleep and waking/REM sleep at 76.9% sensitivity and 74.5% specificity and between REM sleep and waking at 77.2% sensitivity and 72.3% specificity.