EarlySense (Israel)

IntroductionContinuous physiological monitoring devices are often not available for monitoring high-risk neonates in low-resource settings. Easy-to-use, non-invasive, multiparameter, continuous physiological monitoring devices could be instrumental in providing appropriate care and improving outcomes for high-risk neonates in these low-resource settings.Methods and analysisThe purpose of this prospective, observational, facility-based evaluation is to provide evidence to establish whether two existing non-invasive, multiparameter, continuous physiological monitoring devices developed by device developers, EarlySense and Sibel, can accurately and reliably measure vital signs in neonates (when compared with verified reference devices). We will also assess the feasibility, usability and acceptability of these devices for use in neonates in low-resource settings in Africa. Up to 500 neonates are enrolled in two phases: (1) a verification and accuracy evaluation phase at Aga Khan University—Nairobi and (2) a clinical feasibility evaluation phase at Pumwani Maternity Hospital in Nairobi, Kenya. Both quantitative and qualitative data are collected and analysed. Agreement between the investigational and reference devices is determined using a priori-defined accuracy thresholds.Ethics and disseminationThis trial was approved by the Aga Khan University Nairobi Research Ethics Committee and the Western Institutional Review Board. We plan to disseminate research results in peer-reviewed journals and international conferences.Trial registration numberNCT03920761.

To validate a contact-free system designed to achieve maximal comfort during long-term sleep monitoring, together with high monitoring accuracy. 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. 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. 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.

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. To establish the accuracy of the Earlysense continuous monitoring system in predicting clinical deterioration. Noninterventional prospective study with retrospective data analysis. Two medical wards in 2 academic medical centers. Patients admitted to a medical ward with a diagnosis of an acute respiratory condition. Enrolled patients were monitored for heart rate (HR) and respiration rate (RR) by the Earlysense monitor with the alerts turned off. 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. 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. 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.