EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Artificial intelligence models for predicting pulmonary complications in patients with chest trauma: a retrospective study

Junepill Seok, Jinseok Lee, Wu Seong Kang

Journal of Trauma and Injury · 30.09.2025 · 38 (3) · 237-247

DOI: 10.20408/jti.2025.0100 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Trauma and Injury, erschienen am 30.09.2025. Verfasst von Junepill Seok und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Thoracic and Cardiovascular Surgery, Chungbuk National University Hospital, Chungbuk National University College of Medicine, Cheongju,…. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Korean Association for Research, Procedures on Education on Trauma.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Pulmonary complications, including pneumonia and respiratory failure, continue to be major contributors to morbidity and mortality in patients with chest trauma. Although several artificial intelligence (AI) models have been developed to predict trauma mortality, there remains a lack of AI-based prediction models specifically targeting pulmonary complications in chest trauma. To address this gap, we developed and validated an explainable AI model for predicting pulmonary complications.

Methods

This retrospective analysis included 1,040 patients with blunt chest trauma who were treated at a single regional trauma center between January 2019 and March 2023. Pulmonary complications were defined as pneumonia, prolonged mechanical ventilation (>48 hours), or other major thoracic complications necessitating surgical intervention. Machine learning algorithms, including extreme gradient boosting (XGBoost), random forest, adaptive boosting (AdaBoost), light gradient boosting machine (LightGBM), and a deep neural network, were trained using hyperparameter tuning and threefold cross-validation. Model performance was evaluated by sensitivity, specificity, accuracy, balanced accuracy, F1 score, and the area under the receiver operating characteristic curve (AUC). Model interpretability was assessed using Shapley Additive Explanations (SHAP) values.

Results

Among the total cohort, 188 patients (18.1%) developed pulmonary complications. In the independent testing dataset (n=208), XGBoost achieved the highest AUC (0.856), while AdaBoost demonstrated the highest balanced accuracy (0.779). All machine learning models outperformed conventional scoring systems. SHAP analysis identified key predictors of pulmonary complications, including age, Injury Severity Score, Glasgow Coma Scale score, Abbreviated Injury Scale of the extremity or head, initial PaO2 to fraction of inspired oxygen ratio, location of the primary rib fracture, and presence of flail motion.

Conclusions

The developed AI model accurately predicts pulmonary complications in patients with chest trauma and outperforms traditional prognostic tools. The model's explainability offers actionable clinical insights, supporting early risk stratification and evidence-based decision-making in trauma care.

Schlagwörter

Stichwörter der Autor:innen

Explainable artificial intelligenceMachine learningRib fracturesThoracic injuries

Autor:innen und Institutionen

  • Department of Thoracic and Cardiovascular Surgery, Chungbuk National University Hospital, Chungbuk National University College of Medicine, Cheongju, Korea.
  • Department of Biomedical Engineering, College of Electronics and Information, Kyung Hee University, Yongin, Korea.
  • Department of Trauma Surgery, Jeju Regional Trauma Center, Cheju Halla General Hospital, Jeju, Korea.
  • Now with Department of Trauma Surgery, Gachon University Gil Medical Center, Incheon, Korea.

Förderung

  • Korean Association for Research, Procedures on Education on Trauma

Zitieren

APA

Seok, J., Lee, J., & Kang, W. S. (2025). Artificial intelligence models for predicting pulmonary complications in patients with chest trauma: a retrospective study. Journal of Trauma and Injury, 38(3), 237-247. https://doi.org/10.20408/jti.2025.0100

Vancouver

Seok J, Lee J, Kang WS. Artificial intelligence models for predicting pulmonary complications in patients with chest trauma: a retrospective study. Journal of Trauma and Injury. 2025;38(3):237-247. doi:10.20408/jti.2025.0100

BibTeX
@article{Seok2025,
  author = {Seok, Junepill and Lee, Jinseok and Kang, Wu Seong},
  title = {Artificial intelligence models for predicting pulmonary complications in patients with chest trauma: a retrospective study},
  journal = {Journal of Trauma and Injury},
  year = {2025},
  volume = {38},
  number = {3},
  pages = {237--247},
  doi = {10.20408/jti.2025.0100}
}
Kostenlos starten →