Design and Development of an Objective Evaluation System for a Web-Based Simulator for Trauma Management.

BACKGROUND: Trauma injuries are one of the main leading causes of death in the world. Training with guidelines and protocols is adequate to provide a fast and efficient treatment to patients that suffer a trauma injury. OBJECTIVES: This study aimed to evaluate deviations from a set protocol, a new set of metrics has been proposed and tested in a pilot study. METHODS: The participants were final-year students from the Universidad Autónoma de Madrid and first-year medical residents from the Hospital Universitario La Paz. They were asked to train four trauma scenarios with a web-based simulator for 2 weeks. A test was performed pre-training and another one post-training to evaluate the evolution of the treatment to those four trauma scenarios considering a predefined trauma protocol and based on the new set of metrics. The scenarios were pelvic and lower limb traumas in a hospital and in a prehospital setting, which allow them to learn and assess different trauma protocols. RESULTS: The results show that, in general, there is an improvement of the new metrics after training with the simulator. CONCLUSION: These new metrics provide comprehensive information for both trainers and trainees. For trainers, the evaluation of the simulation is automated and contains all relevant information to assess the performance of the trainee. And for trainees, it provides valuable real-time information that could support the trauma management learning process.

Could machine learning algorithms help us predict massive bleeding at prehospital level?

OBJECTIVE: Comparison of the predictive ability of various machine learning algorithms (MLA) versus traditional prediction scales (TPS) for massive hemorrhage (MH) in patients with severe traumatic injury (STI). DESIGN: On a database of a retrospective cohort with prehospital clinical variables and MH outcome, a treatment of the database was performed to be able to apply the different AML, obtaining a total set of 473 patients (80% training, 20% validation). For modeling, proportional imputation and cross validation were performed. The predictive power was evaluated with the ROC metric and the importance of the variables using the Shapley values. SETTING: Out-of-hospital care of patients with STI. PARTICIPANTS: Patients with STI treated out-of-hospital by a out-of-hospital medical service from January 2010 to December 2015 and transferred to a trauma center in Madrid. INTERVENTIONS: None. MAIN VARIABLES OF INTEREST: Obtaining and comparing the "Receiver Operating Characteristic curve" (ROC curve) metric of four MLAs: "random forest" (RF), "vector support machine" (SVM), "gradient boosting machine" (GBM) and "neural network" (NN) with the results obtained with TPS. RESULTS: The different AML reached ROC values higher than 0.85, having medians close to 0.98. We found no significant differences between AMLs. Each AML offers a different set of more important variables with a predominance of hemodynamic, resuscitation variables and neurological impairment. CONCLUSIONS: MLA may be helpful in patients with HM by outperforming TPS.

Modified Needleman-Wunsch algorithm for trauma management performance evaluation.

BACKGROUND: Trauma injuries are one of the leading causes of death in the world, representing approximately 8 % of all deaths. Therefore, trauma management training is of great importance and new training courses have arisen during the last decades. However, actual training courses do not typically analyze compliance with the protocols and guidelines available in the literature. Considering general trauma management guidelines such as the Advanced Trauma Life Support (ATLS) manual and the expertise of trauma specialists, a trauma management automated evaluation system has been designed in this paper. METHODS: A modification to the Needleman-Wunsch (NW) algorithm is developed, including all relevant aspects of trauma management to automatically evaluate how a trauma intervention has been implemented according to trauma protocols. This allows to consider more information with respect to the order of the actions taken and the type of actions performed than current evaluation methods, such as checklists or videos recorded in simulation. A web-based trauma simulator is used so that it can be used at any setting with internet connection. Final-year medical students and first- and second-year residents performed an experimental test, where a trauma score is obtained with the modified NW algorithm. This automatic score relates to how similar the actions are to trauma protocols. RESULTS: The results show the best combination of the scores used for the modified NW variables. This combination has an error, for the different case scenarios created, below 0.07 which verifies the values obtained. Additionally, trauma experts verified the results obtained showing a median difference of 0 between the protocol adherence evaluation using the algorithm and the one provided by the trauma experts. CONCLUSIONS: The best set of score values to apply to the modified NW algorithm show that the modified NW algorithm provides a successful objective measurement with respect to the protocol compliance.

Prognostic value of metabolic parameters measured by first responders attending patients with severe trauma: associations with the New Injury Severity Score and mortality. / Valor pronóstico de los parámetros metabólicos medidos en la asistencia inicial a pacientes con trauma grave: asociación con la puntuación de la escala NISS y la mortalidad.

OBJECTIVES: Patients with severe or potentially severe trauma must be identified early, a challenge in prehospital settings. This study aimed to analyze the possible diagnostic and prognostic usefulness of analytical markers recorded in the early moments of care. MATERIAL AND METHODS: Observational study of information extracted from the prospective multicenter Code Trauma database for 2016-2019, excluding data for isolated head injuries. Using the New Injury Severity Score (NISS), we classified cases into 4 levels of severity. NISS and mortality were considered the dependent variables in inferential analyses. We calculated the areas under receiver operating characteristic curves, identified optimal cutoff points (Youden index), and calculated positive (PPV) and negative predictive values.. RESULTS: Of the 1039 trauma patients in the registry, 709 were included in the study. Their mean (SD) age was 40.4 (17.3) years, and 77.3% were men. Motorcycle accidents were the most common causes of trauma (in 21%), and mortality was 12.1%. Lactate concentration, pH, PCO2, hemoglobin concentration, hematocrit, and blood sugar were significantly associated with severity and mortality. The PPVs corresponding to pH for the 4 NISS score groups (34-41, 42-49, 50-59, and $ 60) and mortality, respectively, were 61.2, 64.1, 70.7, 62.2, and 66.6. The PPVs of traditionally used clinical variables were lower. CONCLUSION: Patients with more severe trauma had lower pH values and higher PCO2, lactate, and base excess values. PCO2, pH, and blood sugar findings were the best predictors of severity. Metabolic variables are better predictors than traditionally recorded hemodynamic variables.

OBJETIVO: En entornos de emergencia prehospitalarios, la detección temprana de un paciente con trauma grave o potencialmente crítico es un desafío. El objetivo es analizar las posibilidades diagnósticas y pronóstico de los parámetros analíticos obtenidos en los primeros momentos de la asistencia inicial. METODO: Estudio observacional multicéntrico de la base de datos prospectiva "Código Trauma" de 2016-2019 excluyendo el trauma craneoencefálico aislado. La evaluación de las lesiones se realizó utilizando el New Injury Severity Score (NISS). Los pacientes fueron clasificados en 4 grupos según nivel de gravedad. Para el análisis inferencial, las puntuaciones NISS y el resultado de mortalidad se consideraron variables dependientes. Se realizó el análisis de la curva ROC, puntos de corte óptimos mediante el índice de Youden y se calcularon los valores predictivos positivo (VPP) y negativo. RESULTADOS: De los 1.039 pacientes traumatizados del registro, 709 fueron incluidos en el estudio, con una edad media de 40,4 años (DE 17,3), 77,3% eran varones, el mecanismo lesional principal accidentes de moto (21%) y la mortalidad del 12,1%. El pH, lactato, pCO2, hemoglobina, hematocrito y glucemia influyeron significativamente en gravedad y mortalidad. El VPP de mortalidad para pH fue 61,2, 64,1, 70,7, 62,2 y 66,6 para los grupos de NISS 34- 41, 42-49, 50-59 y $ 60 puntos la mortalidad, respectivamente. Las variables clínicas clásicas obtuvieron valores más bajos. CONCLUSIONES: Los pacientes con mayor gravedad presentaron menor pH y concentraciones más altas de pCO2, lactato y exceso de bases. El pH, la pCO2 y la glucemia tuvieron la mayor capacidad predictiva de gravedad. La capacidad predictiva de los valores metabólicos es superior a la de los valores hemodinámicos clásicos.

Valor pronóstico de los parámetros metabólicos medidos en la asistencia inicial a pacientes con trauma grave: asociación con la puntuación de la escala NISS y la mortalidad / Prognostic value of metabolic parameters measured by first responders attending patients with severe trauma: associations with the New Injury Severity Score and mortality

Objetivos. En entornos de emergencia prehospitalarios, la detección temprana de un paciente con trauma grave o potencialmente crítico es un desafío. El objetivo es analizar las posibilidades diagnósticas y pronóstico de los parámetros analíticos obtenidos en los primeros momentos de la asistencia inicial. Métodos. Estudio observacional multicéntrico de la base de datos prospectiva “Código Trauma” de 2016-2019 excluyendo el trauma craneoencefálico aislado. La evaluación de las lesiones se realizó utilizando el New Injury Severity Score (NISS). Los pacientes fueron clasificados en 4 grupos según nivel de gravedad. Para el análisis inferencial, las puntuaciones NISS y el resultado de mortalidad se consideraron variables dependientes. Se realizó el análisis de la curva ROC, puntos de corte óptimos mediante el índice de Youden y se calcularon los valores predictivos positivo (VPP) y negativo. Resultados. De los 1.039 pacientes traumatizados del registro, 709 fueron incluidos en el estudio, con una edad media de 40,4 años (DE 17,3), 77,3% eran varones, el mecanismo lesional principal accidentes de moto (21%) y la mortalidad del 12,1%. El pH, lactato, pCO2, hemoglobina, hematocrito y glucemia influyeron significativamente en gravedad y mortalidad. El VPP de mortalidad para pH fue 61,2, 64,1, 70,7, 62,2 y 66,6 para los grupos de NISS 34-41, 42-49, 50-59 y $ 60 puntos la mortalidad, respectivamente. Las variables clínicas clásicas obtuvieron valores más bajos. Conclusiones. Los pacientes con mayor gravedad presentaron menor pH y concentraciones más altas de pCO2, lactato y exceso de bases. El pH, la pCO2 y la glucemia tuvieron la mayor capacidad predictiva de gravedad. La capacidad predictiva de los valores metabólicos es superior a la de los valores hemodinámicos clásicos. (AU)

Background and objective: Patients with severe or potentially severe trauma must be identified early, a challenge in prehospital settings. This study aimed to analyze the possible diagnostic and prognostic usefulness of analytical markers recorded in the early moments of care. Methods: Observational study of information extracted from the prospective multicenter Code Trauma database for 2016-2019, excluding data for isolated head injuries. Using the New Injury Severity Score (NISS), we classified cases into 4 levels of severity. NISS and mortality were considered the dependent variables in inferential analyses. We calculated the areas under receiver operating characteristic curves, identified optimal cutoff points (Youden index), and calculated positive (PPV) and negative predictive values. Results: Of the 1039 trauma patients in the registry, 709 were included in the study. Their mean (SD) age was 40.4 (17.3) years, and 77.3% were men. Motorcycle accidents were the most common causes of trauma (in 21%), and mortality was 12.1%. Lactate concentration, pH, PCO2, hemoglobin concentration, hematocrit, and blood sugar were significantly associated with severity and mortality. The PPVs corresponding to pH for the 4 NISS score groups (34-41, 42-49, 50-59, and $ 60) and mortality, respectively, were 61.2, 64.1, 70.7, 62.2, and 66.6. The PPVs of traditionally used clinical variables were lower. Conclusions: Patients with more severe trauma had lower pH values and higher PCO2, lactate, and base excess values. PCO2, pH, and blood sugar findings were the best predictors of severity. Metabolic variables are better predictors than traditionally recorded hemodynamic variables. (AU)