Study of sleep-wakefulness states by computer graphics and cluster analysis before and after lesions of the pontine tegmentum in the cat.

A computerized method of quantification, graphic representation and classification of sleep-wakefulness data in the cat before and after pontine tegmental lesions has been presented. Electrophysiological signal features including average EEG amplitude, average EMG amplitude and PGO spike rate which are particularly important for the definition of sleep-wakefulness states have been quantified for each 1 min epoch in the day. The data were presented in a projected 3-dimensional data display, in which they formed clusters that are considered to be analogous to sleep-wakefulness states. A cluster analysis algorithm was employed for the automatic classification of these data, and this automatic classification was compared graphically and with contingency table analyses to traditional visual assessment of state from polygraphic records. Although there were systematic differences in the locations of state boundaries, total percent agreement between cluster analysis classification and traditional human classification was comparable to the percent agreement between any two human classifiers (about 90%). After pontine tegmental lesions involving both the gigantocellular and lateral tegmental fields, paradoxical sleep was eliminated, and the characteristics of slow wave sleep and wakefulness were altered. The elimination of the state of paradoxical sleep was evident in the computer display by the absence of the paradoxical sleep cluster, and alterations of the other states were indicated in the display by shifts in the positions of their respective clusters. Automatic classification of slow wave sleep and wakefulness after such lesions compared well with traditional classification, attesting to the validity of this approach.