Predicting 30-day Mortality in Severely Injured Elderly Patients with Trauma in Korea Using Machine Learning Algorithms - a Retrospective Study

Aug 3, 2026

Upload by Levi

Accurate mortality prediction is needed as the number of elderly trauma patients continues to rise, enabling better clinical decision-making. This retrospective study developed and compared machine learning predictive models for 30-day mortality in severely injured patients aged 65 years or older (ISS ≥15) treated at a regional trauma center from 2016–2022. Four models were evaluated with discrimination and classification metrics and interpreted using SHAP, while learning curves assessed generalization and robustness.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Purpose

Methods

Study population

Machine learning models and evaluation

Results

Model performance

Feature interpretation (SHAP)

Learning curves

Conclusions

Keywords

Original Article J Trauma Inj 2024;37(3):201-208 [https://doi.org/10.20408/jti.2024.0024](https://doi.org/10.20408/jti.2024.0024) pISSN 2799-4317 • eISSN 2287-1683 Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study Jonghee Han, MD1 , Su Young Yoon, MD1 , Junepill Seok, MD2 , Jin Young Lee, MD2 , Jin Suk Lee, MD2 , Jin Bong Ye, MD2 , Younghoon Sul, MD2,3 , Se Heon Kim, MD2 , Hong Rye Kim, MD4 1Department of Cardiovascular and Thoracic Surgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea 2 Department of Trauma Surgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea 3 Department of Trauma Surgery, Chungbuk National University College of Medicine, Cheongju, Korea 4 Department of Neurosurgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea Received: April 22, 2024 Revised: May 23, 2024 Accepted: May 29, 2024 Correspondence to Jonghee Han, MD Department of Cardiovascular and Thoracic Surgery, Trauma Center, Chungbuk National University Hospital, 776 1sunhwan-ro, Seowon-gu, Cheongju 28644, Korea Tel: +82-43-269-7849 [Email: medihan7@naver.com](Email: medihan7@naver.com) 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. Keywords: Wounds and injuries; Aged; Mortality; Prediction model; Machine learning © 2024 The Korean Society of Traumatology This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ([https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited. [https://doi.org/10.20408/jti.2024.0024](https://doi.org/10.20408/jti.2024.0024) [www.jtr

FAQs

What was the aim of the study on elderly trauma patients in Korea?

To develop machine learning–based models that predict 30-day mortality in severely injured elderly trauma patients and to compare the predictive performance of different algorithms.

What patient group and time period were included in the retrospective analysis?

Patients aged 65 years or older with an Injury Severity Score of at least 15 who visited a regional trauma center at Chungbuk National University Hospital between 2016 and 2022.

Which machine learning model performed best for predicting 30-day mortality?

XGBoost showed the superior overall classification performance among the four models, with the highest accuracy, precision, recall, specificity, and F1 score reported in the results.

Aug 3, 2026

Upload by Levi