Polysomnography (PSG) is the gold standard for the analysis of sleep architecture but is not always available in routine practice, as it is time consuming and cumbersome for patients. Bispectral index (BIS), developed to quantify the deepness of general anesthesia, may be used as a simplified tool to evaluate natural sleep depth. We objectively recorded sleep architecture in young patients using the latest BIS Vista monitor and correlated BIS values with PSG sleep stages in order to determine BIS thresholds. Patients, referred for the screening of sleep apnea/hypopnea syndrome or differential diagnosis of hypersomnia were recruited. Overnight PSG and BIS were performed simultaneously. BIS values were averaged for each sleep stage. Pre-sleep wakefulness (W) and wake after sleep onset (WASO) were also differentiated. BIS values were discarded for a signal quality index <90 %. ROC curves were plotted to discriminate sleep stages from each other. Twelve patients (5.7-29.3 years old) were included. Mean BIS values were 83 ± 8, 76 ± 12, 77 ± 11, 70 ± 10, 43 ± 10, and 75 ± 10 for W, WASO, N1, N2, N3 and R (REM) stages, respectively. BIS failed to distinguish W, WASO, N1 and R stages. BIS threshold that identified stage N2 was <73 (AUC = 0.784, p < 0.001) with low sensitivity (75 %) and poor specificity (64 %). BIS threshold that identified stage N3 was <55 (AUC = 0.964, p < 0.001) with an 87 %-sensitivity and a 93 %-specificity. BIS identified stage N3 with satisfactory sensitivity and specificity but is limited by its inability to distinguish REM sleep from wake. Further studies combining BIS with chin electromyogram and/or electrooculogram could be of interest.
Keywords: Bispectral index; Natural sleep; Polysomnography; Sleep architecture; Sleep disorders.