Sleep stage scoring using the neural network model: comparison between visual and automatic analysis in normal subjects and patients

Abstract

In this paper, we compare and analyze the results from automatic analysis and visual scoring of nocturnal sleep recordings. The validation is based on a sleep recording set of 60 subjects (33 males and 27 females), consisting of three groups: 20 normal controls subjects, 20 depressed patients and 20 insomniac patients treated with a benzodiazepine. The inter-expert variability estimated from these 60 recordings (61,949 epochs) indicated an average agreement rate of 87.5% between two experts on the basis of 30-second epochs. The automatic scoring system, compared in the same way with one expert, achieved an average agreement rate of 82.3%, without expert supervision. By adding expert supervision for ambiguous and unknown epochs, detected by computation of an uncertainty index and unknown rejection, the automatic/expert agreement grew from 82.3% to 90%, with supervision over only 20% of the night. Bearing in mind the composition and the size of the test sample, the automated sleep staging system achieved a satisfactory performance level and may be considered a useful alternative to visual sleep stage scoring for large-scale investigations of human sleep.