Comparison between the results of an automatic and a visual scoring of sleep EEG recordings

In this paper, results from the visual scoring of nocturnal polygraphic recordings, carried out by nine different groups of readers from different Italian sleep laboratories, are analyzed; inter-and intragroup variability is shown and statistically discussed. Data are then compared with the results of an automatic scoring of the same recordings, carried out by the Medilog Sleep Stager. The validity of this automatic method of scoring is discussed. Finally, an epoch by epoch analysis is described, with the aim of achieving a more detailed evaluation of the intergroup variability.