Sleep/wake detection based on cardiorespiratory signals and actigraphy

We investigated the potential of adding cardiac and respiratory activity information to actigraphy for sleep-wake staging. A dataset of 35 recordings with full polysomnography and actigraphy was used to assess the performance of an automated sleep/wake Bayesian classifier using electrocardiogram, inductance plethysmogram estimate of respiratory effort and actigraphy. The best performance was achieved with the linear discriminant model that provided an agreement of Cohen's kappa=0.62 for one of the configurations of the classifier, corresponding to an accuracy of 86.8%, a sensitivity of 66.9% and a specificity of 93.1%. It shows that combining different vital signs for a home sleep-wake staging system could be a promising approach.