Secondary Logo

Institutional members access full text with Ovid®

Use of Advanced Machine-Learning Techniques for Noninvasive Monitoring of Hemorrhage

Convertino, Victor A. PhD; Moulton, Steven L. MD; Grudic, Gregory Z. PhD; Rickards, Caroline A. PhD; Hinojosa-Laborde, Carmen PhD; Gerhardt, Robert T. MD; Blackbourne, Lorne H. MD; Ryan, Kathy L. PhD

The Journal of Trauma: Injury, Infection, and Critical Care: July 2011 - Volume 71 - Issue 1 - p S25-S32
doi: 10.1097/TA.0b013e3182211601
Review Article
Buy

Background: Hemorrhagic shock is a leading cause of death in both civilian and battlefield trauma. Currently available medical monitors provide measures of standard vital signs that are insensitive and nonspecific. More important, hypotension and other signs and symptoms of shock can appear when it may be too late to apply effective life-saving interventions. The resulting challenge is that early diagnosis is difficult because hemorrhagic shock is first recognized by late-responding vital signs and symptoms. The purpose of these experiments was to test the hypothesis that state-of-the-art machine-learning techniques, when integrated with novel non-invasive monitoring technologies, could detect early indicators of blood volume loss and impending circulatory failure in conscious, healthy humans who experience reduced central blood volume.

Methods: Humans were exposed to progressive reductions in central blood volume using lower body negative pressure as a model of hemorrhage until the onset of hemodynamic decompensation. Continuous, noninvasively measured hemodynamic signals were used for the development of machine-learning algorithms. Accuracy estimates were obtained by building models using signals from all but one subject and testing on that subject. This process was repeated, each time using a different subject.

Results: The model was 96.5% accurate in predicting the estimated amount of reduced central blood volume, and the correlation between predicted and actual lower body negative pressure level for hemodynamic decompensation was 0.89.

Conclusions: Machine modeling can accurately identify reduced central blood volume and predict impending hemodynamic decompensation (shock onset) in individuals. Such a capability can provide decision support for earlier intervention.

From the US Army Institute of Surgical Research (V.A.C., C.H.-L., R.T.G., K.L.R., L.H.B.), Tactical Combat Casualty Care (TCCC) Research Program, Fort Sam Houston, Texas; Department of Surgery (S.L.M.), University of Colorado, School of Medicine, Aurora, Colorado; Flashback Technologies (G.Z.G.), LLC, Boulder, Colorado; University of Texas at San Antonio (C.A.R.), San Antonio, Texas.

Submitted for publication March 9, 2011.

Accepted for publication April 22, 2011.

Supported by funding from the United States Army Medical Research and Materiel Command Combat Casualty Care Research Program and the Small Business Innovative Research program.

This study was conducted under a protocol reviewed and approved by the Brooke Army Medical Center Institutional Review Board and in accordance with the approved protocol.

The opinions or assertions contained herein are the private views of the authors and are not to be construed as official or as reflecting the views of the Department of the Army or the Department of Defense.

Address for reprints: Victor A. Convertino, PhD, US Army Institute of Surgical Research, 3698 Chambers Pass, Fort Sam Houston, TX 78234; email: victor.convertino@amedd.army.mil.

© 2011 Lippincott Williams & Wilkins, Inc.