Wearable Sensors Incorporating Compensatory Reserve Measurement for Advancing Physiological Monitoring in Critically Injured Trauma Patients

Abstract

Vital signs historically served as the primary method to triage patients and resources for trauma and emergency care, but have failed to provide clinically-meaningful predictive information about patient clinical status. In this review, a framework is presented that focuses on potential wearable sensor technologies that can harness necessary electronic physiological signal integration with a current state-of-the-art predictive machine-learning algorithm that provides early clinical assessment of hypovolemia status to impact patient outcome. The ability to study the physiology of hemorrhage using a human model of progressive central hypovolemia led to the development of a novel machine-learning algorithm known as the compensatory reserve measurement (CRM). Greater sensitivity, specificity, and diagnostic accuracy to detect hemorrhage and onset of decompensated shock has been demonstrated by the CRM when compared to all standard vital signs and hemodynamic variables. The development of CRM revealed that continuous measurements of changes in arterial waveform features represented the most integrated signal of physiological compensation for conditions of reduced systemic oxygen delivery. In this review, detailed analysis of sensor technologies that include photoplethysmography, tonometry, ultrasound-based blood pressure, and cardiogenic vibration are identified as potential candidates for harnessing arterial waveform analog features required for real-time calculation of CRM. The integration of wearable sensors with the CRM algorithm provides a potentially powerful medical monitoring advancement to save civilian and military lives in emergency medical settings.

Efficacy of the compensatory reserve measurement in an emergency department trauma population

“…We initially enrolled 165 subjects, on whom we collected clinical data, yet only 90 had usable data for algorithm analysis and development. The missing and/or corrupt files affecting 75 patients without usable waveform data underscore the need for sensor technology development with optimized signal‐to‐noise capabilities 32 . Such improvements in monitoring technology would be beneficial in emergency care medical settings where the most critically injured patients are moved around the most, thus creating substantial background noise.…”

Compensatory reserve detects subclinical shock with more expeditious prediction for need of life‐saving interventions compared to systolic blood pressure and blood lactate

“…Recent studies have shown these contributing factors can have significant effects on the reliability of current field assessment strategies. The specificity of a machine‐learning approach allows the CRM to overcome many of these monitoring limitations because the algorithm is based on a database of more than 650,000 waveforms that includes a wide demographic of age (18–55 years), sex, fitness, and body mass (BMI range = 17.3–39.4 kg/m 2 ) in a population of greater than 250 healthy humans 11, 12, 24, 26 . The capability of the algorithm to “learn” to recognize the physiology of progression to decompensated shock in healthy humans has provided a basis for the algorithm to consistently recognize the compensatory status of trauma patients with pathophysiology 12, 19‐22, 27 …”

“…First, SI displays relatively low sensitivity that can fail to distinguish trauma patients with hemorrhage from those without 22 . Second, poor sensitivity may also reflect that clinically significant elevations in SI occur late during the early compensatory phases of progressive central hypovolemia compared to CRM 6, 11, 17, 39 . Third, and perhaps most clinically important, is the evidence that SI displays relatively low specificity for the progression of stages of shock that can lead to misleading assessment of patient status.…”

“…The CRM device consisting of a standard pulse oximeter sensor (PureLight model 8000AA, Nonin Medical Inc., Plymouth, MN) was placed on the finger and remained in place until discharge or transfer to the operating room or inpatient unit. The CRM was derived using a proprietary machine‐learning algorithm capable of analyzing continuous real‐time changes in specific features of the photoplehtysmogram that calculates a quantified scale from 100% (complete reserve) to 0% (depleted reserve) of the proportion of the sum total capacity of an individual patient to compensate for blood loss 6, 11, 12 . The CRM device was developed for investigational use only.…”

“…As such, identification of compensated shock during the early subclinical phase could potentially facilitate improved clinical decision making and accelerate the provision of life-saving interventions (LSIs). In this regard, the compensatory reserve measurement (CRM) has been consistently shown to reflect early stages of physiological compensation with greater sensitivity and specificity than standard vital signs in conditions of experimentally induced central hypovolemia, [11][12][13][14][15] controlled human blood loss, [16][17][18] and trauma patients with hemorrhage. [19][20][21][22] In the present clinical investigation, we captured for the first time CRM of trauma patients at progressive stages from a state of subclinical shock to overt hemorrhagic shock.…”