Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study
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 mor...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Korean Society of Traumatology
2024-09-01
|
| Series: | Journal of Trauma and Injury |
| Subjects: | |
| Online Access: | http://jtraumainj.org/upload/pdf/jti-2024-0024.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841527001214615552 |
|---|---|
| author | Jonghee Han Su Young Yoon Junepill Seok Jin Young Lee Jin Suk Lee Jin Bong Ye Younghoon Sul Se Heon Kim Hong Rye Kim |
| author_facet | Jonghee Han Su Young Yoon Junepill Seok Jin Young Lee Jin Suk Lee Jin Bong Ye Younghoon Sul Se Heon Kim Hong Rye Kim |
| author_sort | Jonghee Han |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-0d734e6bc31f46738f4d081602ad5c50 |
| institution | Kabale University |
| issn | 2799-4317 2287-1683 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Korean Society of Traumatology |
| record_format | Article |
| series | Journal of Trauma and Injury |
| spelling | doaj-art-0d734e6bc31f46738f4d081602ad5c502025-01-16T06:10:27ZengKorean Society of TraumatologyJournal of Trauma and Injury2799-43172287-16832024-09-0137320120810.20408/jti.2024.00241317Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective studyJonghee Han0Su Young Yoon1Junepill Seok2Jin Young Lee3Jin Suk Lee4Jin Bong Ye5Younghoon Sul6Se Heon Kim7Hong Rye Kim8 Department of Cardiovascular and Thoracic Surgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea Department of Cardiovascular and Thoracic Surgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea Department of Cardiovascular and Thoracic Surgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea Department of Trauma Surgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea Department of Trauma Surgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea Department of Trauma Surgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea Department of Trauma Surgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea Department of Trauma Surgery, Trauma Center, Chungbuk National University Hospital, Cheongju, Korea Department of Neurosurgery, Trauma Center, Chungbuk National University Hospital, Cheongju, KoreaPurpose 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.http://jtraumainj.org/upload/pdf/jti-2024-0024.pdfwounds and injuriesagedmortalityprediction modelmachine learning |
| spellingShingle | Jonghee Han Su Young Yoon Junepill Seok Jin Young Lee Jin Suk Lee Jin Bong Ye Younghoon Sul Se Heon Kim Hong Rye Kim Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study Journal of Trauma and Injury wounds and injuries aged mortality prediction model machine learning |
| title | Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study |
| title_full | Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study |
| title_fullStr | Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study |
| title_full_unstemmed | Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study |
| title_short | Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study |
| title_sort | predicting 30 day mortality in severely injured elderly patients with trauma in korea using machine learning algorithms a retrospective study |
| topic | wounds and injuries aged mortality prediction model machine learning |
| url | http://jtraumainj.org/upload/pdf/jti-2024-0024.pdf |
| work_keys_str_mv | AT jongheehan predicting30daymortalityinseverelyinjuredelderlypatientswithtraumainkoreausingmachinelearningalgorithmsaretrospectivestudy AT suyoungyoon predicting30daymortalityinseverelyinjuredelderlypatientswithtraumainkoreausingmachinelearningalgorithmsaretrospectivestudy AT junepillseok predicting30daymortalityinseverelyinjuredelderlypatientswithtraumainkoreausingmachinelearningalgorithmsaretrospectivestudy AT jinyounglee predicting30daymortalityinseverelyinjuredelderlypatientswithtraumainkoreausingmachinelearningalgorithmsaretrospectivestudy AT jinsuklee predicting30daymortalityinseverelyinjuredelderlypatientswithtraumainkoreausingmachinelearningalgorithmsaretrospectivestudy AT jinbongye predicting30daymortalityinseverelyinjuredelderlypatientswithtraumainkoreausingmachinelearningalgorithmsaretrospectivestudy AT younghoonsul predicting30daymortalityinseverelyinjuredelderlypatientswithtraumainkoreausingmachinelearningalgorithmsaretrospectivestudy AT seheonkim predicting30daymortalityinseverelyinjuredelderlypatientswithtraumainkoreausingmachinelearningalgorithmsaretrospectivestudy AT hongryekim predicting30daymortalityinseverelyinjuredelderlypatientswithtraumainkoreausingmachinelearningalgorithmsaretrospectivestudy |