Validation of Contact-Free Sleep Monitoring Device with Comparison to Polysomnography.

STUDY OBJECTIVES: To validate a contact-free system designed to achieve maximal comfort during long-term sleep monitoring, together with high monitoring accuracy. METHODS: We used a contact-free monitoring system (EarlySense, Ltd., Israel), comprising an under-the-mattress piezoelectric sensor and a smartphone application, to collect vital signs and analyze sleep. Heart rate (HR), respiratory rate (RR), body movement, and calculated sleep-related parameters from the EarlySense (ES) sensor were compared to data simultaneously generated by the gold standard, polysomnography (PSG). Subjects in the sleep laboratory underwent overnight technician-attended full PSG, whereas subjects at home were recorded for 1 to 3 nights with portable partial PSG devices. Data were compared epoch by epoch. RESULTS: A total of 63 subjects (85 nights) were recorded under a variety of sleep conditions. Compared to PSG, the contact-free system showed similar values for average total sleep time (TST), % wake, % rapid eye movement, and % non-rapid eye movement sleep, with 96.1% and 93.3% accuracy of continuous measurement of HR and RR, respectively. We found a linear correlation between TST measured by the sensor and TST determined by PSG, with a coefficient of 0.98 (R = 0.87). Epoch-by-epoch comparison with PSG in the sleep laboratory setting revealed that the system showed sleep detection sensitivity, specificity, and accuracy of 92.5%, 80.4%, and 90.5%, respectively. CONCLUSIONS: TST estimates with the contact-free sleep monitoring system were closely correlated with the gold-standard reference. This system shows good sleep staging capability with improved performance over accelerometer-based apps, and collects additional physiological information on heart rate and respiratory rate.

Early recognition of acutely deteriorating patients in non-intensive care units: assessment of an innovative monitoring technology.

BACKGROUND: Continuous vital sign monitoring has the potential to detect early clinical deterioration. While commonly employed in the intensive care unit (ICU), accurate and noninvasive monitoring technology suitable for floor patients has yet to be used reliably. OBJECTIVE: To establish the accuracy of the Earlysense continuous monitoring system in predicting clinical deterioration. DESIGN: Noninterventional prospective study with retrospective data analysis. SETTING: Two medical wards in 2 academic medical centers. PATIENTS: Patients admitted to a medical ward with a diagnosis of an acute respiratory condition. INTERVENTION: Enrolled patients were monitored for heart rate (HR) and respiration rate (RR) by the Earlysense monitor with the alerts turned off. MEASUREMENTS: Retrospective analysis of vital sign data was performed on a derivation cohort to identify optimal cutoffs for threshold and 24-hour trend alerts. This was internally validated through correlation with clinical events recognized through chart review. RESULTS: Of 113 patients included in the study, 9 suffered major clinical deterioration. Alerts were found to be infrequent (2.7 and 0.2 alerts per patient-day for threshold and trend alert, respectively). For the threshold alerts, sensitivity and specificity in predicting deterioration was found to be 82% and 67%, respectively, for HR and 64% and 81%, respectively, for RR. For trend alerts, sensitivity and specificity were 78% and 90% for HR, and 100% and 64% for RR, respectively. CONCLUSIONS: The Earlysense monitor was able to continuously measure RR and HR, providing low alert frequency. The current study provides data supporting the ability of this system to accurately predict patient deterioration.

Using continuous motion monitoring technology to determine patient's risk for development of pressure ulcers.

OBJECTIVES: To perform initial validation of a continuous motion monitoring technology that can potentially be used as a risk assessment tool to determine risk for developing pressure ulcers (PUs). METHODS: We have used the EverOn system (Earlysense LTD, Ramat Gan, Israel) as a bed movement and activity monitor. The EverOn is a contactless continuous measurement system based on a piezoelectric sensor that is placed under the patient's mattress. The study was a noninterventional study performed in 2 medical departments in 2 medical centers. Recorded movement data from enrolled patients were retrospectively analyzed, and patients were assigned a motion level score. Motion scores for the first night of hospitalization were correlated with the Norton scale as calculated per patient on admission. RESULTS: Overall, 116 patients were included in the study from the 2 sites. Motion score was significantly different between the PU risk groups as determined by the Norton scale (10.7 ± 6.2 for low, 5.4 ± 4.9 for intermediate, and 1.6 ± 3.2 for high risk; P < 0.001). Using the Norton scale as a gold standard to define high risk for developing PU (≤14), the sensitivity of the motion score was 85%, and the specificity was 93%. With regard to individual risk components, we found that activity, mobility, physical condition, and incontinence correlated highly with motion level. CONCLUSIONS: The high correlation between the EverOn motion score and the calculated Norton scale indicates the potential of this technology to serve as a risk assessment tool for the development of PUs.

Validation of ECG-derived sleep architecture and ventilation in sleep apnea and chronic fatigue syndrome.

PURPOSE: Newly developed algorithms putatively derive measures of sleep, wakefulness, and respiratory disturbance index (RDI) through detailed analysis of heart rate variability (HRV). Here, we establish levels of agreement for one such algorithm through comparative analysis of HRV-derived values of sleep-wake architecture and RDI with those calculated from manually scored polysomnographic (PSG) recordings. METHODS: Archived PSG data collected from 234 subjects who participated in a 3-day, 2-night study characterizing polysomnographic traits of chronic fatigue syndrome were scored manually. The electrocardiogram and pulse oximetry channels were scored separately with a novel scoring algorithm to derive values for wakefulness, sleep architecture, and RDI. RESULTS: Four hundred fifty-four whole-night PSG recordings were acquired, of which, 410 were technically acceptable. Comparative analyses demonstrated no difference for total minutes of sleep, wake, NREM, REM, nor sleep efficiency generated through manual scoring with those derived through HRV analyses. When NREM sleep was further partitioned into slow-wave sleep (stages 3-4) and light sleep (stages 1-2), values calculated through manual scoring differed significantly from those derived through HRV analyses. Levels of agreement between RDIs derived through the two methods revealed an R = 0.89. The Bland-Altman approach for determining levels of agreement between RDIs generated through manual scoring with those derived through HRV analysis revealed a mean difference of -0.7 +/- 8.8 (mean +/- two standard deviations). CONCLUSION: We found no difference between values of wakefulness, sleep, NREM, REM sleep, and RDI calculated from manually scored PSG recordings with those derived through analyses of HRV.