Trauma survival prediction in Asian population: a modification of TRISS to improve accuracy

Validation of the Conventional Trauma and Injury Severity Score and a Newly Developed Survival Predictive Model in Pediatric Patients with Blunt Trauma: A Nationwide Observation Study

To date, there is no clinically useful prediction model that is suitable for Japanese pediatric trauma patients. Herein, this study aimed to developed a model for predicting the survival of Japanese pediatric patients with blunt trauma and compare its validity with that of the conventional TRISS model. Patients registered in the Japan Trauma Data Bank were grouped into a derivation cohort (2009-2013) and validation cohort (2014-2018). Logistic regression analysis was performed using the derivation dataset to establish prediction models using age, injury severity, and physiology. The validity of the modified model was evaluated by the area under the receiver operating characteristic curve (AUC). Among 11 predictor models, Model 1 and Model 11 had the best performance (AUC = 0.980). The AUC of all models was lower in patients with survival probability Ps < 0.5 than in patients with Ps ≥ 0.5. The AUC of all models was lower in neonates/infants than in other age categories. Model 11 also had the best performance (AUC = 0.762 and 0.909, respectively) in patients with Ps < 0.5 and neonates/infants. The predictive ability of the newly modified models was not superior to that of the current TRISS model. Our results may be useful to develop a highly accurate prediction model based on the new predictive variables and cutoff values associated with the survival mortality of injured Japanese pediatric patients who are younger and more severely injured by using a nationwide dataset with fewer missing data and added valuables, which can be used to evaluate the age-related physiological and anatomical severity of injured patients.

Algorithm to Improve Resuscitation Outcomes in Patients With Traumatic Out-of-Hospital Cardiac Arrest

Background: This study proposed an algorithm to improve resuscitation outcomes in the emergency department (ED) for patients with traumatic out-of-hospital cardiac arrest (TOHCA). We also performed a retrospective chart review of patient outcomes before and after implementing the algorithm and sought to define factors that might influence patient outcomes.

Methods: In September 2018, we implemented an algorithm for patients with TOHCA. This algorithm rapidly identifies possible causes of TOHCA and recommends appropriate interventions. We retrospectively reviewed the outcomes of all patients with TOHCA during a five-year period (comprising periods before and after the algorithm) and compared the results before and after the implementation of the algorithm.

Results: After this algorithm was implemented, the use of the ED interventions of blood transfusion, placement of a large-bore central venous catheter, and thoracostomy increased significantly. The rate of return of spontaneous circulation (ROSC) also increased (before vs. after: ROSC: 23.6% vs. 41.5%, P = 0.035). Regarding hospital admission and survival to hospital discharge, we observed the trend of increment (hospital admission: 18.2% vs. 24.6%, P = 0.394; survival to hospital discharge: 0.0% vs. 4.6%, P = 0.107). Admitted patients exhibited a higher end-tidal CO₂ level during resuscitation than nonadmitted patients [admitted vs. nonadmitted: 41.5 (33.3-52.0) vs. 12.0 (7.5-18.8), P = 0.001].

Conclusion: Our algorithm prioritizes the three major treatable causes of TOHCA: impedance of venous return, hypovolemia, and hypoxia. We found that rate of ROSC increased with the increasing implementation of the ED interventions recommended by the algorithm.

Validation of the Trauma and Injury Severity Score for Prediction of Mortality in a Greek Trauma Population

BACKGROUND

Although the Trauma and Injury Severity Score (TRISS) has been extensively used for mortality risk adjustment in trauma, its applicability in contemporary trauma populations is increasingly questioned.

OBJECTIVE

The study aimed to evaluate the predictive performance of the TRISS in its original and revised version and compare these with a recalibrated version, including current data from a Greek trauma population.

METHODS

This is a retrospective cohort study of admitted trauma patients conducted in two tertiary Greek hospitals from January 2016 to December 2018. The model algorithm was calculated based on the Major Trauma Outcome Study coefficients (TRISSMTOS), the National Trauma Data Bank coefficients (TRISSNTDB), and reweighted coefficients of logistic regression obtained from a Greek trauma dataset (TRISSGrTD). The primary endpoint was inhospital mortality. Models' prediction was performed using discrimination and calibration statistics.

RESULTS

A total of 8,988 trauma patients were included, of whom 854 died (9.5%). The TRISSMTOS displayed excellent discrimination with an area under the curve (AUC) of 0.912 (95% CI 0.902-0.923) and comparable with TRISSNTDB (AUC = 0.908, 95% CI 0.897-0.919, p = .1195). Calibration of both models was poor (Hosmer-Lemeshow test p < .001), tending to underestimate the probability of mortality across almost all risk groups. The TRISSGrTD resulted in statistically significant improvement in discrimination (AUC = 0.927, 95% CI 0.918-0.936, p < .0001) and acceptable calibration (Hosmer-Lemeshow test p = .113).

CONCLUSION

In this cohort of Greek trauma patients, the performance of the original TRISS was suboptimal, and there was no evidence that it has benefited from its latest revision. By contrast, a strong case exists for supporting a locally recalibrated version to render the TRISS applicable for mortality prediction and performance benchmarking.

RISC II is superior to TRISS in predicting 30-day mortality in blunt major trauma patients in Hong Kong

PURPOSE

Hong Kong (HK) trauma registries have been using the Trauma and Injury Severity Score (TRISS) for audit and benchmarking since their introduction in 2000. We compare the mortality prediction model using TRISS and Revised Injury Severity Classification, version II (RISC II) for trauma centre patients in HK.

METHODS

This was a retrospective cohort study with all five trauma centres in HK. Adult trauma patients with Injury Severity Score (ISS) > 15 suffering from blunt injuries from January 2013 to December 2015 were included. TRISS models using the US and local coefficients were compared with the RISC II model. The primary outcome was 30-day mortality and the area under the receiver operating characteristic curve (AUC) for tested models.

RESULTS

1840 patients were included, of whom 1236/1840 (67%) were male. Median age was 59 years and median ISS was 25. Low falls were the most common mechanism of injury. The 30-day mortality was 23%. RISC II yielded a superior AUC of 0.896, compared with the TRISS models (MTOS: 0.848; PATOS: 0.839; HK: 0.858). Prespecified subgroup analyses showed that all the models performed worse for age ≥ 70, ASA ≥ III, and low falls. RISC II had a higher AUC compared with the TRISS models in all subgroups, although not statistically significant.

CONCLUSION

RISC II was superior to TRISS in predicting the 30-day mortality for Hong Kong adult blunt major trauma patients. RISC II may be useful when performing future audit or benchmarking exercises for trauma in Hong Kong.

Validation of age-specific survival prediction in pediatric patients with blunt trauma using trauma and injury severity score methodology: a ten-year Nationwide observational study

BACKGROUND

In-hospital mortality in trauma patients has decreased recently owing to improved trauma injury prevention systems. However, no study has evaluated the validity of the Trauma and Injury Severity Score (TRISS) in pediatric patients by a detailed classification of patients' age and injury severity in Japan. This retrospective nationwide study evaluated the validity of TRISS in predicting survival in Japanese pediatric patients with blunt trauma by age and injury severity.

METHODS

Data were obtained from the Japan Trauma Data Bank during 2009-2018. The outcomes were as follows: (1) patients' characteristics and mortality by age groups (neonates/infants aged 0 years, preschool children aged 1-5 years, schoolchildren aged 6-11 years, and adolescents aged 12-18 years), (2) validity of survival probability (Ps) assessed using the TRISS methodology by the four age groups and six Ps-interval groups (0.00-0.25, 0.26-0.50, 0.51-0.75, 0.76-0.90, 0.91-0.95, and 0.96-1.00), and (3) the observed/expected survivor ratio by age- and Ps-interval groups. The validity of TRISS was evaluated by the predictive ability of the TRISS method using the receiver operating characteristic (ROC) curves that present the sensitivity, specificity, positive predictive value, negative predictive value, accuracy, area under the receiver operator characteristic curve (AUC) of TRISS.

RESULTS

In all the age categories considered, the AUC for TRISS demonstrated high performance (0.935, 0.981, 0.979, and 0.977). The AUC for TRISS was 0.865, 0.585, 0.614, 0.585, 0.591, and 0.600 in Ps-interval groups (0.96-1.00), (0.91-0.95), (0.76. - 0.90), (0.51-0.75), (0.26-0.50), and (0.00-0.25), respectively. In all the age categories considered, the observed survivors among patients with Ps interval (0.00-0.25) were 1.5 times or more than the expected survivors calculated using the TRISS method.

CONCLUSIONS

The TRISS methodology appears to predict survival accurately in Japanese pediatric patients with blunt trauma; however, there were several problems in adopting the TRISS methodology for younger blunt trauma patients with higher injury severity. In the next step, it may be necessary to develop a simple, high-quality prediction model that is more suitable for pediatric trauma patients than the current TRISS model.

Machine Learning Models of Survival Prediction in Trauma Patients

BACKGROUND

We aimed to build a model using machine learning for the prediction of survival in trauma patients and compared these model predictions to those predicted by the most commonly used algorithm, the Trauma and Injury Severity Score (TRISS).

METHODS

Enrolled hospitalized trauma patients from 2009 to 2016 were divided into a training dataset (70% of the original data set) for generation of a plausible model under supervised classification, and a test dataset (30% of the original data set) to test the performance of the model. The training and test datasets comprised 13,208 (12,871 survival and 337 mortality) and 5603 (5473 survival and 130 mortality) patients, respectively. With the provision of additional information such as pre-existing comorbidity status or laboratory data, logistic regression (LR), support vector machine (SVM), and neural network (NN) (with the Stuttgart Neural Network Simulator (RSNNS)) were used to build models of survival prediction and compared to the predictive performance of TRISS. Predictive performance was evaluated by accuracy, sensitivity, and specificity, as well as by area under the curve (AUC) measures of receiver operating characteristic curves.

RESULTS

In the validation dataset, NN and the TRISS presented the highest score (82.0%) for balanced accuracy, followed by SVM (75.2%) and LR (71.8%) models. In the test dataset, NN had the highest balanced accuracy (75.1%), followed by the TRISS (70.2%), SVM (70.6%), and LR (68.9%) models. All four models (LR, SVM, NN, and TRISS) exhibited a high accuracy of more than 97.5% and a sensitivity of more than 98.6%. However, NN exhibited the highest specificity (51.5%), followed by the TRISS (41.5%), SVM (40.8%), and LR (38.5%) models.

CONCLUSIONS

These four models (LR, SVM, NN, and TRISS) exhibited a similar high accuracy and sensitivity in predicting the survival of the trauma patients. In the test dataset, the NN model had the highest balanced accuracy and predictive specificity.

Trauma and Injury Severity Score modification for predicting survival of trauma in one regional emergency medical center in Korea: Construction of Trauma and Injury Severity Score coefficient model

Background:

The problem that is central to trauma research is the prediction of survival rate after trauma. Trauma and Injury Severity Score is being used for predicting survival rate after trauma. Many countries have conducted a study on the classification, characteristics of variables, and the validity of the Trauma and Injury Severity Score model. However, few investigations have been made on the characteristics of coefficients or variables related to Trauma and Injury Severity Score in Korea. Objectives: There is a need for coefficient analysis of Trauma and Injury Severity Score which was created based on the United States database to be optimized for the situation in Korea.

Methods:

This study examined how the currently used Trauma and Injury Severity Score coefficients were developed and created for trauma patients visiting the emergency department in a hospital in Korea using the analytical method. A total of 34,340 trauma patients who were hospitalized into an emergency center from January 2012 to December 2014 for 3 years were analyzed with trauma registry established on August 2006.

Results:

Trauma and Injury Severity Score coefficients were transformed with the methods that were used to make the existing Trauma and Injury Severity Score coefficients using the trauma patients’ data. Regression coefficients (B) were drawn by building up a logistic regression analysis model that used variables such as Injury Severity Score, Revised Trauma Score, and age depending on survival with Trauma and Injury Severity Score.

Conclusion:

With regard to Trauma and Injury Severity Score established in the United States differing from Korea in injury types, it seems possible to realize significant survival rate by deriving coefficients with data in Korea and reanalyzing them.

Mortality prediction models in the general trauma population: A systematic review

BACKGROUND

Trauma is the leading cause of death in individuals younger than 40 years. There are many different models for predicting patient outcome following trauma. To our knowledge, no comprehensive review has been performed on prognostic models for the general trauma population. Therefore, this review aimed to describe (1) existing mortality prediction models for the general trauma population, (2) the methodological quality and (3) which variables are most relevant for the model prediction of mortality in the general trauma population.

METHODS

An online search was conducted in June 2015 using Embase, Medline, Web of Science, Cinahl, Cochrane, Google Scholar and PubMed. Relevant English peer-reviewed articles that developed, validated or updated mortality prediction models in a general trauma population were included.

RESULTS

A total of 90 articles were included. The cohort sizes ranged from 100 to 1,115,389 patients, with overall mortality rates that ranged from 0.6% to 35%. The Trauma and Injury Severity Score (TRISS) was the most commonly used model. A total of 258 models were described in the articles, of which only 103 models (40%) were externally validated. Cases with missing values were often excluded and discrimination of the different prediction models ranged widely (AUROC between 0.59 and 0.98). The predictors were often included as dichotomized or categorical variables, while continuous variables showed better performance.

CONCLUSION

Researchers are still searching for a better mortality prediction model in the general trauma population. Models should 1) be developed and/or validated using an adequate sample size with sufficient events per predictor variable, 2) use multiple imputation models to address missing values, 3) use the continuous variant of the predictor if available and 4) incorporate all different types of readily available predictors (i.e., physiological variables, anatomical variables, injury cause/mechanism, and demographic variables). Furthermore, while mortality rates are decreasing, it is important to develop models that predict physical, cognitive status, or quality of life to measure quality of care.

A survival prediction logistic regression models for blunt trauma victims in Japan

Aim

This research aimed to propose a logistic regression model for Japanese blunt trauma victims.

Methods

We tested whether the logistic regression model previously created from data registered in the Japan Trauma Data Bank between 2005 and 2008 is still valid for the data from the same data bank between 2009 and 2013. Additionally, we analyzed whether the model would be highly accurate even when its coefficients were rounded off to two decimal places.

Results

The model was proved to be highly accurate (94.56%) in the recent data (2009–2013). We also showed that the model remains valid without respiratory rate data and the simplified model would maintain high accuracy.

Conclusion

We propose the equation of survival prediction of blunt trauma victims in Japan to be Ps = 1/(1+e^−b), where b = −0.76 + 1.03 × Revised Trauma Score − 0.07 × Injury Severity Score − 0.04 × age.

The Applicability of Trauma and Injury Severity Score for a Blunt Trauma Population in Korea and a Proposal of New Models Using Score Predictors

PURPOSE

The purpose of this study was to verify the utility of existing Trauma and Injury Severity Score (TRISS) coefficients and to propose a new prediction model with a new set of TRISS coefficients or predictors.

MATERIALS AND METHODS

Of the blunt adult trauma patients who were admitted to our hospital in 2014, those eligible for Korea Trauma Data Bank entry were selected to collect the TRISS predictors. The study data were input into the TRISS formula to obtain "probability of survival" values, which were examined for consistency with actual patient survival status. For TRISS coefficients, Major Trauma Outcome Study-derived values revised in 1995 and National Trauma Data Bank-derived and National Sample Project-derived coefficients revised in 2009 were used. Additionally, using a logistic regression method, a new set of coefficients was derived from our medical center's database. Areas under the receiver operating characteristic (ROC) curve (AUC) for each prediction ability were obtained, and a pairwise comparison of ROC curves was performed.

RESULTS

In the statistical analysis, the AUCs (0.879-0.899) for predicting outcomes were lower than those of other countries. However, by adjusting the TRISS score using a continuous variable rather than a code for age, we were able to achieve higher AUCs [0.913 (95% confidence interval, 0.899 to 0.926)].

CONCLUSION

These results support further studies that will allow a more accurate prediction of prognosis for trauma patients. Furthermore, Korean TRISS coefficients or a new prediction model suited for Korea needs to be developed using a sufficiently sized sample.