Michelle Scerbo1, Hari Radhakrishnan1, Bryan Cotton1, Anahita Dua1, Deborah Del Junco1, Charles Wade1, John B Holcomb2. 1. Division of Acute Care Surgery, Department of Surgery, Center for Translational Injury Research (CeTIR), University of Texas-Houston, Houston, Texas. 2. Division of Acute Care Surgery, Department of Surgery, Center for Translational Injury Research (CeTIR), University of Texas-Houston, Houston, Texas. Electronic address: john.holcomb@uth.tmc.edu.
Abstract
BACKGROUND: Overtriage not only wastes resources but also displaces the patient from their community and causes delay of treatment for the more seriously injured. This study aimed to validate the Random Forest computer model (RFM) as means of better triaging trauma patients to level 1 trauma centers. METHODS: Adult trauma patients with "medium activation" presenting via helicopter to a level 1 trauma center from May 2007 to May 2009 were included. The "medium activation" trauma patient is alert and hemodynamically stable on scene but has either subnormal vital signs or accumulation of risk factors that may indicate a potentially serious injury. Variables included in the RFM analysis were demographics, mechanism of injury, prehospital fluid, medications, vitals, and disposition. Statistical analysis was performed via the Random Forest algorithm to compare our institutional triage rate to rates determined by the RFM. RESULTS: A total of 1653 patients were included in this study, of which 496 were used in the testing set of the RFM. In our testing set, 33.8% of patients brought to our level 1 trauma center could have been managed at a level 3 trauma center, and 88% of patients who required a level 1 trauma center were identified correctly. In the testing set, there was an overtriage rate of 66%, whereas using the RFM, we decreased the overtriage rate to 42% (P < 0.001). There was an undertriage rate of 8.3%. The RFM predicted patient disposition with a sensitivity of 89%, specificity of 42%, negative predictive value of 92%, and positive predictive value of 34%. CONCLUSIONS: Although prospective validation is required, it appears that computer modeling potentially could be used to guide triage decisions, allowing both more accurate triage and more efficient use of the trauma system.
BACKGROUND: Overtriage not only wastes resources but also displaces the patient from their community and causes delay of treatment for the more seriously injured. This study aimed to validate the Random Forest computer model (RFM) as means of better triaging traumapatients to level 1 trauma centers. METHODS: Adult traumapatients with "medium activation" presenting via helicopter to a level 1 trauma center from May 2007 to May 2009 were included. The "medium activation" traumapatient is alert and hemodynamically stable on scene but has either subnormal vital signs or accumulation of risk factors that may indicate a potentially serious injury. Variables included in the RFM analysis were demographics, mechanism of injury, prehospital fluid, medications, vitals, and disposition. Statistical analysis was performed via the Random Forest algorithm to compare our institutional triage rate to rates determined by the RFM. RESULTS: A total of 1653 patients were included in this study, of which 496 were used in the testing set of the RFM. In our testing set, 33.8% of patients brought to our level 1 trauma center could have been managed at a level 3 trauma center, and 88% of patients who required a level 1 trauma center were identified correctly. In the testing set, there was an overtriage rate of 66%, whereas using the RFM, we decreased the overtriage rate to 42% (P < 0.001). There was an undertriage rate of 8.3%. The RFM predicted patient disposition with a sensitivity of 89%, specificity of 42%, negative predictive value of 92%, and positive predictive value of 34%. CONCLUSIONS: Although prospective validation is required, it appears that computer modeling potentially could be used to guide triage decisions, allowing both more accurate triage and more efficient use of the trauma system.
Authors: Ellen J MacKenzie; Frederick P Rivara; Gregory J Jurkovich; Avery B Nathens; Katherine P Frey; Brian L Egleston; David S Salkever; Daniel O Scharfstein Journal: N Engl J Med Date: 2006-01-26 Impact factor: 91.245
Authors: Edward L Hannan; Louise Szypulski Farrell; Arthur Cooper; Mark Henry; Bruce Simon; Ronald Simon Journal: J Am Coll Surg Date: 2005-04 Impact factor: 6.113
Authors: Ryan K Lehmann; Zachary M Arthurs; Daniel G Cuadrado; Linda E Casey; Alec C Beekley; Matthew J Martin Journal: Am J Surg Date: 2007-05 Impact factor: 2.565