The sleep/wake state scoring from mandible movement signal.

PURPOSE: Estimating the total sleep time in home recording devices is necessary to avoid underestimation of the indices reflecting sleep apnea and hypopnea syndrome severity, e.g., the apnea-hypopnea index (AHI). A new method to distinguish sleep from wake using jaw movement signal processing is assessed. METHODS: In this prospective study, jaw movement signal was recorded using the Somnolter (SMN) portable monitoring device synchronously with polysomnography (PSG) in consecutive patients complaining about a lack of recovery sleep. The automated sleep/wake scoring method is based on frequency and complexity analysis of the jaw movement signal. This computed scoring was compared with the PSG hypnogram, the two total sleep times (TST(PSG) and TST(SMN)) as well. RESULTS: The mean and standard deviation (in minutes) of TST(PSG) on the whole dataset (n = 124) were 407 ± 95.6, while these statistics were 394.2 ± 99.3 for TST(SMN). The Bland and Altman analysis of the difference between the two TST was 12.8 ± 57.3 min. The sensitivity and specificity (in percent) were 85.3 and 65.5 globally. The efficiency decreased slightly when AHI lies between 15 and 30, but remained similar for lower or greater AHI. In the 24 patients with insomnia/depression diagnosis, a mean difference in TST of -3.3 min, a standard deviation of 58.2 min, a sensitivity of 86.3%, and a specificity of 66.2% were found. CONCLUSIONS: Mandible movement recording and its dedicated signal processing for sleep/wake recognition improve sleep disorder index accuracy by assessing the total sleep time. Such a feature is welcome in home screening methods.

Midsagittal jaw movements as a sleep/wake marker.

The seriousness of the Obstructive Sleep Apnea/Hypopnea Syndrome is measured by the apnea-hypopnea index (AHI), the number of sleep apneas and hypopneas over the total sleep time (TST). Cardiorespiratory signals are used to detect respiratory events while the TST is usually assessed by the analysis of electroencephalogram traces in polysomnography (PSG) or wrist actigraphy trace in portable monitoring. This paper presents a sleep/wake automatic detector that relies on a wavelet-based complexity measure of the midsagittal jaw movement signal and multilayer perceptrons. In all, 63 recordings were used to train and test the method, while 38 recordings constituted an independent evaluation set for which the sensitivity, the specificity, and the global agreement of sleep recognition, respectively, reached 85.1%, 76.4%, and 82.9%, compared with the PSG data. The AHI computed automatically and only from the jaw movement analysis was significantly improved (p < 0.0001) when considering this sleep/wake detector. Moreover, a sensitivity of 88.6% and a specificity of 83.6% were found for the diagnosis of the sleep apnea syndrome according to a threshold of 15. Thus, the jaw movement signal is reasonably accurate in separating sleep from wake, and, in addition to its ability to score respiratory events, is a valuable signal for portable monitoring.

Midsagittal jaw movement analysis for the scoring of sleep apneas and hypopneas.

Given the importance of the detection and classification of sleep apneas and hypopneas (SAHs) in the diagnosis and the characterization of the SAH syndrome, there is a need for a reliable noninvasive technique measuring respiratory effort. This paper proposes a new method for the scoring of SAHs based on the recording of the midsagittal jaw motion (MJM, mouth opening) and on a dedicated automatic analysis of this signal. Continuous wavelet transform is used to quantize respiratory effort from the jaw motion, to detect salient mandibular movements related to SAHs and to delineate events which are likely to contain the respiratory events. The classification of the delimited events is performed using multilayer perceptrons which were trained and tested on sleep data from 34 recordings. Compared with SAHs scored manually by an expert, the sensitivity and specificity of the detection were 86.1% and 87.4%, respectively. Moreover, the overall classification agreement in the recognition of obstructive, central, and mixed respiratory events between the manual and automatic scorings was 73.1%. The MJM signal is hence a reliable marker of respiratory effort and allows an accurate detection and classification of SAHs.