These findings suggest that machine classification is highly consistent with human sleep staging and that error in the algorithm's assignments is rather a problem of lack of well-defined criteria for human experts to judge certain polysomnogram epochs than an insufficiency of computational procedures.

In healthy subjects, sleep has a typical structure of three to five cyclic transitions between different sleep states. In major depression, this regular pattern is often destroyed but can be reestablished during successful treatment. The differences between healthy and abnormal sleep are generally assessed in a time-consuming process, which consists of determining the nightly variations of the sleep states (the hypnogram) based on visual inspection of the electroencephalogram (EEG), electrooculogram, and electromyogram. In this study, three different methods of sleep EEG analysis (spectrum, outlier, and recurrence analysis) have been examined with regard to their ability to extract information about treatment effects in patients with major depression. Our data suggest that improved sleep patterns during treatment with antidepressant medication can be identified with an appropriate analysis of the EEG. By comparing different methods, we have found that many treatment effects identified by spectrum analysis can be reproduced by the much simpler technique of outlier analysis. Finally, the cyclic structure of sleep and its modification by antidepressant treatment is best illustrated by a non-linear approach, the so-called recurrence method.