Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts 02120, USA.
J Hosp Med. 2012 Oct;7(8):628-33. doi: 10.1002/jhm.1963. Epub 2012 Aug 3.
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.
连续生命体征监测有可能及早发现临床恶化。虽然在重症监护病房（ICU）中普遍应用，但尚未可靠地使用适合于病房患者的准确、非侵入性监测技术。
确定 Earlysense 连续监测系统在预测临床恶化方面的准确性。
非干预性前瞻性研究，回顾性数据分析。
2 家学术医疗中心的 2 个内科病房。
内科病房收治的急性呼吸状况诊断患者。
接受监测的患者通过 Earlysense 监测器监测心率（HR）和呼吸频率（RR），关闭警报。
对衍生队列的生命体征数据进行回顾性分析，以确定用于阈值和 24 小时趋势警报的最佳截止值。通过与通过图表审查识别的临床事件进行相关性内部验证。
在纳入的 113 例患者中，有 9 例发生重大临床恶化。发现警报很少（阈值和趋势警报的每个患者日分别为 2.7 和 0.2 次警报）。对于阈值警报，HR 和 RR 的预测恶化的敏感性和特异性分别为 82%和 67%，64%和 81%。对于趋势警报，HR 的敏感性和特异性分别为 78%和 90%，RR 的敏感性和特异性分别为 100%和 64%。
Earlysense 监测器能够连续测量 RR 和 HR，警报频率低。本研究提供了支持该系统准确预测患者恶化能力的数据。
