Michael Joseph Mina1, Anne M Winkler, Christopher J Dente. 1. From the Departments of Surgery (M.J.M., C.J.D.), and Pathology and Laboratory Medicine (A.M.W.), School of Medicine, Grady Memorial Hospital, and the Rollins School of Public Health (M.J.M.), Emory University; and the Emory Medical Scientist Training Program (M.J.M), Atlanta, Georgia.
Abstract
BACKGROUND: The use of massive transfusion protocols (MTPs) is now common in civilian trauma settings, and early activation of MTP has been shown to increase survival of MTP recipients. Numerous MTP prediction tools have been developed; however, they are often cumbersome to use efficiently or have traded predictive power for ease of use. We hypothesized that a highly accurate predictor of massive transfusion could be created and incorporated into a smartphone application that would provide an additional tool for clinicians to use in directing the resuscitation of critically injured patients. METHODS: Data from all trauma admissions since the inception of MTP were put in place at Grady Memorial Hospital in Atlanta, Georgia, were collected. A predictive model was developed using the least absolute shrinkage and selection operator (LASSO) and 10-fold cross validation. Data were resampled over 500 iterations, each using a unique and random subset of 80% of the data for model training and 20% for validation. RESULTS: The trauma registry contained 13,961 cases between 2007 and November 2011, of which 10,900 were complete and 394 received MTP. Of 44 input terms, only the mechanism of injury, heart rate, systolic blood pressure, and base deficit were found to be important predictors of massive transfusion. Our model has an area under the receiver operating curve of 0.96 (against data not used during model training) and accurately predicted MTP status for 97% of all patients. The model accurately discriminated full MTPs from MTP activations that did not meet criteria for massive transfusion. While complex to calculate by hand, our model has been packaged into a mobile application, allowing for efficient use while minimizing potential for user error. CONCLUSION: We have developed a highly accurate model for the prediction of massive transfusion that has potential to be easily accessed and used within a simple and efficient mobile application for smartphones. LEVEL OF EVIDENCE: Prognostic/epidemiologic study, level III.
BACKGROUND: The use of massive transfusion protocols (MTPs) is now common in civilian trauma settings, and early activation of MTP has been shown to increase survival of MTP recipients. Numerous MTP prediction tools have been developed; however, they are often cumbersome to use efficiently or have traded predictive power for ease of use. We hypothesized that a highly accurate predictor of massive transfusion could be created and incorporated into a smartphone application that would provide an additional tool for clinicians to use in directing the resuscitation of critically injured patients. METHODS: Data from all trauma admissions since the inception of MTP were put in place at Grady Memorial Hospital in Atlanta, Georgia, were collected. A predictive model was developed using the least absolute shrinkage and selection operator (LASSO) and 10-fold cross validation. Data were resampled over 500 iterations, each using a unique and random subset of 80% of the data for model training and 20% for validation. RESULTS: The trauma registry contained 13,961 cases between 2007 and November 2011, of which 10,900 were complete and 394 received MTP. Of 44 input terms, only the mechanism of injury, heart rate, systolic blood pressure, and base deficit were found to be important predictors of massive transfusion. Our model has an area under the receiver operating curve of 0.96 (against data not used during model training) and accurately predicted MTP status for 97% of all patients. The model accurately discriminated full MTPs from MTP activations that did not meet criteria for massive transfusion. While complex to calculate by hand, our model has been packaged into a mobile application, allowing for efficient use while minimizing potential for user error. CONCLUSION: We have developed a highly accurate model for the prediction of massive transfusion that has potential to be easily accessed and used within a simple and efficient mobile application for smartphones. LEVEL OF EVIDENCE: Prognostic/epidemiologic study, level III.
Authors: John B Holcomb; Don Jenkins; Peter Rhee; Jay Johannigman; Peter Mahoney; Sumeru Mehta; E Darrin Cox; Michael J Gehrke; Greg J Beilman; Martin Schreiber; Stephen F Flaherty; Kurt W Grathwohl; Phillip C Spinella; Jeremy G Perkins; Alec C Beekley; Neil R McMullin; Myung S Park; Ernest A Gonzalez; Charles E Wade; Michael A Dubick; C William Schwab; Fred A Moore; Howard R Champion; David B Hoyt; John R Hess Journal: J Trauma Date: 2007-02
Authors: Erica I Hodgman; Bryan C Morse; Christopher J Dente; Michael J Mina; Beth H Shaz; Jeffrey M Nicholas; Amy D Wyrzykowski; Jeffrey P Salomone; Grace S Rozycki; David V Feliciano Journal: J Trauma Acute Care Surg Date: 2012-04 Impact factor: 3.313
Authors: Marc Maegele; Thomas Brockamp; Ulrike Nienaber; Christian Probst; Herbert Schoechl; Klaus Görlinger; Philip Spinella Journal: Transfus Med Hemother Date: 2012-03-08 Impact factor: 3.747
Authors: E I Hodgman; M W Cripps; M J Mina; E M Bulger; M A Schreiber; K J Brasel; M J Cohen; P Muskat; J G Myers; L H Alarcon; M H Rahbar; J B Holcomb; B A Cotton; E E Fox; D J Del Junco; C E Wade; H A Phelan Journal: J Trauma Acute Care Surg Date: 2018-02 Impact factor: 3.313
Authors: Hunter B Moore; Ernest E Moore; Michael P Chapman; Benjamin R Huebner; Peter M Einersen; Solimon Oushy; Christopher C Silliman; Anirban Banerjee; Angela Sauaia Journal: J Am Coll Surg Date: 2017-05-15 Impact factor: 6.113