Trauma patients with "compensated" internal hemorrhage may not be identified with standard medical monitors until signs of shock appear, at which point it may be difficult or too late to pursue life-saving interventions. We tested the hypothesis that a novel machine-learning model called the compensatory reserve index (CRI) could differentiate tolerance to acute volume loss of individuals well in advance of changes in stroke volume (SV) or standard vital signs. Two hundred one healthy humans underwent progressive lower body negative pressure (LBNP) until the onset of hemodynamic instability (decompensation). Continuously measured photoplethysmogram signals were used to estimate SV and develop a model for estimating CRI. Validation of the CRI was tested on 101 subjects who were classified into two groups: low tolerance (LT; n = 33) and high tolerance (HT; n = 68) to LBNP (mean LBNP time: LT = 16.23 min vs. HT = 25.86 min). On an arbitrary scale of 1 to 0, the LT group CRI reached 0.6 at an average time of 5.27 ± 1.18 (95% confidence interval) min followed by 0.3 at 11.39 ± 1.14 min. In comparison, the HT group reached CRI of 0.6 at 7.62 ± 0.94 min followed by 0.3 at 15.35 ± 1.03 min. Changes in heart rate, blood pressure, and SV did not differentiate HT from LT groups. Machine modeling of the photoplethysmogram response to reduced central blood volume can accurately trend individual-specific progression to hemodynamic decompensation. These findings foretell early identification of blood loss, anticipating hemodynamic instability, and timely application of life-saving interventions.

Current monitoring technologies are unable to detect early, compensatory changes that are associated with significant blood loss. We previously introduced a novel algorithm to calculate the Compensatory Reserve Index (CRI) based on the analysis of arterial waveform features obtained from photoplethysmogram recordings. In the present study, we hypothesized that the CRI would provide greater sensitivity and specificity to detect blood loss compared with traditional vital signs and other hemodynamic measures. Continuous noninvasive vital sign waveform data, including CRI, photoplethysmogram, heart rate, blood pressures, SpO2, cardiac output, and stroke volume, were analyzed from 20 subjects before, during, and after an average controlled voluntary hemorrhage of ∼1.2 L of blood. Compensatory Reserve Index decreased by 33% in a linear fashion across progressive blood volume loss, with no clinically significant alterations in vital signs. The receiver operating characteristic area under the curve for the CRI was 0.90, with a sensitivity of 0.80 and specificity of 0.76. In comparison, blood pressures, heart rate, SpO2, cardiac output, and stroke volume had significantly lower receiver operating characteristic area under the curve values and specificities for detecting the same volume of blood loss. Consistent with our hypothesis, CRI detected blood loss and restoration with significantly greater specificity than did other traditional physiologic measures. Single measurement of CRI may enable more accurate triage, whereas CRI monitoring may allow for earlier detection of casualty deterioration.

Machine modeling can quickly and accurately detect and trend central blood volume reduction in real time during the compensatory phase of hemorrhage as well as estimate when an individual is "running on empty" and will decompensate (CRI, 0), well in advance of meaningful changes in traditional vital signs.