Validation of non-invasive monitoring device to evaluate sleep quality.

This paper presents the validation of a noninvasive sleep monitoring device and sleep quality evaluation. The system is based on an array of pressure sensors positioned on the bed that can measure relevant parameters to estimate sleep quality. This device can measure time in bed (TB), body movements (BM), the thorax expansion, periods out of bed (POB) and apnea events. We compare the results of the unobtrusive pressure sensor array with traditional polysomnography (PSG). The algorithms developed for the device provide a very good detection of all the parameters required to estimate sleep quality as compared to the gold-standard data for a study of 30 patients. For the periods out of bed it presents a sensibility (Se) and specificity (Sp) of 100%. To grade the severity of sleep apnea we compare the number of events per hour or apnea-hypopnea index (AHI) obtained by the device and the PSG; obtaining a Se of 94% and a Sp of 61%. These results validate the use of the device for screening of sleep apnea disease.

Contact pressure monitoring device for sleep studies.

This project implements a non-invasive sleep monitoring system using a bed pressure sensor array. The system detects changes in the contact pressure between a subject and the bed and is able to automatically select the sensor with the best respiratory signal, determine the respiratory rate (RR), count number of sleep apneas and count body position changes through the night. The respiratory signal is validated with an airflow sensor using Pearson's correlation coefficient. To determine the performance of body position and apnea detection algorithms, the sensibility and positive predictivity is computed on preliminary data and known records from a Physionet database. Real data is obtained from 5 subjects totaling 39 hours measured at home during a full night sleep, in a non-invasive way. The data is used to calculate relevant parameters to estimate a sleep quality. Cumulative frequency of sleep interval duration is proposed as a novel metric for sleep assessment.