Estimating Surgical Blood Loss Volume Using Continuously Monitored Vital Signs

Background: There are currently no effective and accurate blood loss volume (BLV) estimation methods that can be implemented in operating rooms. To improve the accuracy and reliability of BLV estimation and facilitate clinical implementation, we propose a novel estimation method using continuously monitored photoplethysmography (PPG) and invasive arterial blood pressure (ABP). Methods: Forty anesthetized York Pigs (31.82 ± 3.52 kg) underwent a controlled hemorrhage at 20 mL/min until shock development was included. Machine-learning-based BLV estimation models were proposed and tested on normalized features derived by vital signs. Results: The results showed that the mean ± standard deviation (SD) for estimating BLV against the reference BLV of our proposed random-forest-derived BLV estimation models using PPG and ABP features, as well as the combination of ABP and PPG features, were 11.9 ± 156.2, 6.5 ± 161.5, and 7.0 ± 139.4 mL, respectively. Compared with traditional hematocrit computation formulas (estimation error: 102.1 ± 313.5 mL), our proposed models outperformed by nearly 200 mL in SD. Conclusion: This is the first attempt at predicting quantitative BLV from noninvasive measurements. Normalized PPG features are superior to ABP in accurately estimating early-stage BLV, and normalized invasive ABP features could enhance model performance in the event of a massive BLV.

[1]  L. Nilsson Respiration Signals from Photoplethysmography , 2013, Anesthesia and analgesia.

[2]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[3]  A. Vilaseca,et al.  Agreement of surgical blood loss estimation methods , 2018, Transfusion.

[4]  A. López-Picado,et al.  Determination of Perioperative Blood Loss: Accuracy or Approximation? , 2017, Anesthesia and analgesia.

[5]  A. Bracey,et al.  Patient Blood Management as Standard of Care. , 2016, Anesthesia and analgesia.

[6]  J. Benumof,et al.  A COMPUTER NOMOGRAM FOR BLOOD LOSS REPLACEMENT , 1980 .

[7]  J. Popp,et al.  Sample size planning for classification models. , 2012, Analytica chimica acta.

[8]  A. Holder,et al.  Inhaled Carbon Monoxide Protects against the Development of Shock and Mitochondrial Injury following Hemorrhage and Resuscitation , 2015, PloS one.

[9]  T. Richards,et al.  Patient blood management to reduce surgical risk , 2015, The British journal of surgery.

[10]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[11]  G. Clermont,et al.  Development of hemorrhage identification model using non-invasive vital signs , 2020, Physiological measurement.

[12]  Maxime Cannesson,et al.  Respiratory variations in pulse oximetry plethysmographic waveform amplitude to predict fluid responsiveness in the operating room. , 2007, Anesthesiology.

[13]  R. Winfield,et al.  The research agenda for trauma critical care , 2017, Intensive Care Medicine.

[14]  G. Clermont,et al.  Parsimony of Hemodynamic Monitoring Data Sufficient for the Detection of Hemorrhage , 2020, Anesthesia and analgesia.

[15]  S N Hunyor,et al.  Quantitative photoplethysmography: Lambert-Beer law or inverse function incorporating light scatter. , 1993, Journal of biomedical engineering.

[16]  G. Clermont,et al.  Increasing Cardiovascular Data Sampling Frequency and Referencing It to Baseline Improve Hemorrhage Detection , 2019, Critical care explorations.

[17]  L. Goodnough,et al.  Patient Blood Management , 2012, Anesthesiology.

[18]  J. Lipman,et al.  Estimation of blood loss is inaccurate and unreliable. , 2016, Surgery.

[19]  H. Gombotz,et al.  Patient Blood Management , 2013, Der Anaesthesist.

[20]  John Allen Photoplethysmography and its application in clinical physiological measurement , 2007, Physiological measurement.

[21]  Bo Wen,et al.  Multi-Sensor Fusion Approach for Cuff-Less Blood Pressure Measurement , 2020, IEEE Journal of Biomedical and Health Informatics.

[22]  H. A. Tetteh Physiologic responses to severe hemorrhagic shock and the genesis of cardiovascular collapse: can irreversibility be anticipated? , 2013, The Journal of surgical research.

[23]  K. Chon,et al.  Using Time-Frequency Analysis of the Photoplethysmographic Waveform to Detect the Withdrawal of 900 mL of Blood , 2012, Anesthesia and analgesia.

[24]  D. Bourke,et al.  Estimating allowable hemodilution. , 1974, Anesthesiology.

[25]  R. Pizov,et al.  Pulse oximetry plethysmographic waveform during changes in blood volume. , 1999, British journal of anaesthesia.

[26]  D. Stein,et al.  ICU Management of Trauma Patients , 2018, Critical care medicine.

[27]  Kirk H. Shelley,et al.  Early detection of spontaneous blood loss using amplitude modulation of Photoplethysmogram , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[28]  Ye Li,et al.  A Novel Continuous Blood Pressure Estimation Approach Based on Data Mining Techniques , 2017, IEEE Journal of Biomedical and Health Informatics.