Comparative Performance of Logistic Regression, XGBoost, and Multilayer Perceptron for Mortality and Treatment Strategy Prediction in Blunt Thoracic Aortic Injury
Open Access
- 1 January 2026
- journal article
- Published by The Pacific Northwest Journal of Surgery in The Pacific Northwest Journal of Surgery
- Vol. 3 (1) , 4-12
Abstract
Introduction: Blunt thoracic aortic injury (BTAI) is a rare but lethal trauma mechanism. Mortality prediction has traditionally relied on logistic regression (LR), yet machine learning (ML) methods may better capture complex nonlinear relationships. Methods: Using the Aortic Trauma Foundation registry, we compared LR, extreme gradient boosting (XGB), and multilayer perceptron (MLP) for two tasks: (1) in-hospital mortality prediction and (2) classification of management strategy, open surgical repair (OSR), thoracic endovascular aortic repair (TEVAR), or medical management alone (MMA). Explanatory LR models identified independent predictors; predictive models targeted ~80% sensitivity in test sets. Performance metrics included area under the receiver operating characteristic curve (AUC), average precision, accuracy, F1 score, precision, recall, and Brier score. Results: Explanatory LR for mortality achieved excellent discrimination (AUC = 0.961), with higher Injury Severity Score, age, and ICU length of stay predicting increased mortality, and conversely, higher Glasgow Coma Scale, pH, and hospital stay protective. Predictive LR and XGB performed similarly (AUCs = 0.849 and 0.855; Brier = 0.083 and 0.101), both outperforming MLP (AUC = 0.757). For management strategy, explanatory LR identified limited predictors (e.g., ISS for OSR; age, heart rate, platelet count, and ISS for TEVAR). Predictive performance was modest: XGB (accuracy = 0.690; macro-AUC = 0.648) slightly outperformed MLP (accuracy = 0.667; macro-AUC = 0.565). Conclusions: Well-specified LR matched XGB for mortality prediction in BTAI, offering interpretability with high accuracy. Management strategy prediction remained limited across models, likely reflecting unmeasured institutional and procedural factors. Enriching datasets with imaging and practice-pattern variables may improve operative decision modeling.Keywords
This publication has 12 references indexed in Scilit:
- Using machine learning to predict outcomes of patients with blunt traumatic aortic injuriesJournal of Trauma and Acute Care Surgery, 2024
- Blunt Traumatic Aortic Injury Management, a French TraumaBase Analytic CohortEuropean Journal of Vascular and Endovascular Surgery, 2022
- An Artificial Neural Networks Model for Early Predicting In‐Hospital Mortality in Acute Pancreatitis in MIMIC‐IIIBioMed Research International, 2021
- Grade four blunt traumatic aortic injury with massive haemothorax: Resuscitation considerations during the primary surveyTrauma & Case Reports, 2020
- Delayed endovascular aortic repair is associated with reduced in-hospital mortality in patients with blunt thoracic aortic injuryJournal of Vascular Surgery, 2018
- Associated injuries, management, and outcomes of blunt abdominal aortic injuryJournal of Vascular Surgery, 2012
- Vancouver simplified grading system with computed tomographic angiography for blunt aortic injuryThe Journal of Thoracic and Cardiovascular Surgery, 2012
- Endovascular repair of traumatic thoracic aortic injury: Clinical practice guidelines of the Society for Vascular SurgeryJournal of Vascular Surgery, 2011
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974
- THE INJURY SEVERITY SCORE1974