Skip Navigation
Skip to contents

J Trauma Inj : Journal of Trauma and Injury

OPEN ACCESS
SEARCH
Search

Search

Page Path
HOME > Search
2 "Younghoon Sul"
Filter
Filter
Article category
Keywords
Publication year
Authors
Original Articles
Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study
Jonghee Han, Su Young Yoon, Junepill Seok, Jin Young Lee, Jin Suk Lee, Jin Bong Ye, Younghoon Sul, Se Heon Kim, Hong Rye Kim
J Trauma Inj. 2024;37(3):201-208.   Published online August 8, 2024
DOI: https://doi.org/10.20408/jti.2024.0024
  • 1,068 View
  • 39 Download
AbstractAbstract PDF
Purpose
The number of elderly patients with trauma is increasing; therefore, precise models are necessary to estimate the mortality risk of elderly patients with trauma for informed clinical decision-making. This study aimed to develop machine learning based predictive models that predict 30-day mortality in severely injured elderly patients with trauma and to compare the predictive performance of various machine learning models. Methods: This study targeted patients aged ≥65 years with an Injury Severity Score of ≥15 who visited the regional trauma center at Chungbuk National University Hospital between 2016 and 2022. Four machine learning models—logistic regression, decision tree, random forest, and eXtreme Gradient Boosting (XGBoost)—were developed to predict 30-day mortality. The models’ performance was compared using metrics such as area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, specificity, F1 score, as well as Shapley Additive Explanations (SHAP) values and learning curves. Results: The performance evaluation of the machine learning models for predicting mortality in severely injured elderly patients with trauma showed AUC values for logistic regression, decision tree, random forest, and XGBoost of 0.938, 0.863, 0.919, and 0.934, respectively. Among the four models, XGBoost demonstrated superior accuracy, precision, recall, specificity, and F1 score of 0.91, 0.72, 0.86, 0.92, and 0.78, respectively. Analysis of important features of XGBoost using SHAP revealed associations such as a high Glasgow Coma Scale negatively impacting mortality probability, while higher counts of transfused red blood cells were positively correlated with mortality probability. The learning curves indicated increased generalization and robustness as training examples increased. Conclusions: We showed that machine learning models, especially XGBoost, can be used to predict 30-day mortality in severely injured elderly patients with trauma. Prognostic tools utilizing these models are helpful for physicians to evaluate the risk of mortality in elderly patients with severe trauma.
Summary
Clinical characteristics and mortality risk factors among trauma patients by age groups at a single center in Korea over 7 years: a retrospective study
Jonghee Han, Su Young Yoon, Junepill Seok, Jin Young Lee, Jin Suk Lee, Jin Bong Ye, Younghoon Sul, Seheon Kim, Hong Rye Kim
J Trauma Inj. 2023;36(4):329-336.   Published online November 7, 2023
DOI: https://doi.org/10.20408/jti.2023.0035
  • 1,785 View
  • 77 Download
AbstractAbstract PDF
Purpose
In this study, we aimed to compare the characteristics of patients with trauma by age group in a single center in Korea to identify the clinical characteristics and analyze the risk factors affecting mortality.
Methods
Patients aged ≥18 years who visited the Chungbuk National University Hospital Regional Trauma Center between January 2016 and December 2022 were included. The accident mechanism, severity of the injury, and outcomes were compared by classifying the patients into group A (18–64 years), group B (65–79 years), and group C (≥80 years). In addition, logistic regression analysis was performed to identify factors affecting death.
Results
The most common injury mechanism was traffic accidents in group A (40.9%) and slipping in group B (37.0%) and group C (56.2%). Although group A had the highest intensive care unit admission rate (38.0%), group C had the highest mortality rate (9.5%). In the regression analysis, 3 to 8 points on the Glasgow Coma Scale had the highest odds ratio for mortality, and red blood cell transfusion within 24 hours, intensive care unit admission, age, and Injury Severity Score were the predictors of death.
Conclusions
For patients with trauma, the mechanism, injured body region, and severity of injury differed among the age groups. The high mortality rate of elderly patients suggests the need for different treatment approaches for trauma patients according to age. Identifying factors affecting clinical patterns and mortality according to age groups can help improve the prognosis of trauma patients in the future.
Summary

J Trauma Inj : Journal of Trauma and Injury
TOP