Jansen N Seheult1, Vincent P Anto2, Nadim Farhat3, Michelle N Stram1, Philip C Spinella4, Louis Alarcon5,6, Jason Sperry5,6, Darrell J Triulzi1,7, Mark H Yazer1,7. 1. Department of Pathology, University of Pittsburgh, Pittsburgh, Pennsylvania. 2. School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania. 3. Department of Bioengineering, University of Pittsburgh, Pittsburgh, Pennsylvania. 4. Department of Pediatrics, Division of Critical Care Medicine, Washington University in St. Louis, St Louis, Missouri. 5. Department of Surgery, University of Pittsburgh, Pittsburgh, Pennsylvania. 6. Department of Critical Care Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania. 7. The Institute for Transfusion Medicine, Pittsburgh, Pennsylvania.
Abstract
BACKGROUND: A supervised machine learning algorithm was used to generate decision trees for the prediction of massive transfusion at a Level 1 trauma center. METHODS: Trauma patients who received at least one unit of RBCs and/or low-titer group O whole blood between January 1, 2015, and December 31, 2017, were included. Massive transfusion was defined as the transfusion of 10 or more units of RBCs and/or low-titer group O whole blood in the first 24 hours of admission. A recursive partitioning algorithm was used to generate two decision trees for prediction of massive transfusion using a training data set (n = 550): the first, MTPitt, was based on demographic and clinical parameters, and the second, MTPitt+Labs, also included laboratory data. Decision tree performance was compared with the Assessment of Blood Consumption score and the Trauma Associated Severe Hemorrhage score. RESULTS: The incidence of massive transfusion in the validation data set (n = 199) was 7.5%. The MTPitt decision tree had a higher balanced accuracy (81.4%) and sensitivity (86.7%) compared to an Assessment of Blood Consumption Score of 2 or higher (77.9% and 66.7%, respectively) and a Trauma Associated Severe Hemorrhage score of 9 or higher (75.0% and 73.3%, respectively), although the 95% confidence intervals overlapped. Addition of laboratory data to the MTPitt decision tree (MTPitt+Labs) resulted in a higher specificity and balanced accuracy compared to MTPitt without an increase in sensitivity. CONCLUSIONS: The MTPitt decisions trees are highly sensitive tools for identifying patients who received a massive transfusion and do not require computational resources to be implemented in the trauma setting.
BACKGROUND: A supervised machine learning algorithm was used to generate decision trees for the prediction of massive transfusion at a Level 1 trauma center. METHODS:Traumapatients who received at least one unit of RBCs and/or low-titer group O whole blood between January 1, 2015, and December 31, 2017, were included. Massive transfusion was defined as the transfusion of 10 or more units of RBCs and/or low-titer group O whole blood in the first 24 hours of admission. A recursive partitioning algorithm was used to generate two decision trees for prediction of massive transfusion using a training data set (n = 550): the first, MTPitt, was based on demographic and clinical parameters, and the second, MTPitt+Labs, also included laboratory data. Decision tree performance was compared with the Assessment of Blood Consumption score and the Trauma Associated Severe Hemorrhage score. RESULTS: The incidence of massive transfusion in the validation data set (n = 199) was 7.5%. The MTPitt decision tree had a higher balanced accuracy (81.4%) and sensitivity (86.7%) compared to an Assessment of Blood Consumption Score of 2 or higher (77.9% and 66.7%, respectively) and a Trauma Associated Severe Hemorrhage score of 9 or higher (75.0% and 73.3%, respectively), although the 95% confidence intervals overlapped. Addition of laboratory data to the MTPitt decision tree (MTPitt+Labs) resulted in a higher specificity and balanced accuracy compared to MTPitt without an increase in sensitivity. CONCLUSIONS: The MTPitt decisions trees are highly sensitive tools for identifying patients who received a massive transfusion and do not require computational resources to be implemented in the trauma setting.
Authors: Marc Moss; S David White; Heather Warner; Daniel Dvorkin; Daniel Fink; Stephanie Gomez-Taborda; Carrie Higgins; Gintas P Krisciunas; Joseph E Levitt; Jeffrey McKeehan; Edel McNally; Alix Rubio; Rebecca Scheel; Jonathan M Siner; Rosemary Vojnik; Susan E Langmore Journal: Chest Date: 2020-07-25 Impact factor: 9.410