Using machine learning to predict outcomes of patients with blunt traumatic aortic injuries
Authors:
- 29 March 2024
- journal article
- research article
- Published by Wolters Kluwer Health in Journal of Trauma and Acute Care Surgery
- Vol. 97 (2) , 258-265
Abstract
Introduction The optimal management of blunt thoracic aortic injury (BTAI) remains controversial, with experienced centers offering therapy ranging from medical management to TEVAR. We investigated the utility of a machine learning (ML) algorithm to develop a prognostic model of risk factors on mortality in patients with BTAI. Methods The Aortic Trauma Foundation registry was utilized to examine demographics, injury characteristics, management and outcomes of patients with BTAI. A STREAMLINE (A Simple, Transparent, End-To-End Automated Machine Learning Pipeline Facilitating Data Analysis and Algorithm Comparison) model as well as logistic regression (LR) analysis with imputation using chained equations was developed and compared. Results From a total of 1018 patients in the registry, 702 patients were included in the final analysis. Of the 258 (37%) patients who were medically managed, 44 (17%) died during admission, 14 (5.4%) of which were aortic related deaths. 444 (63%) patients underwent TEVAR and 343 of which underwent TEVAR within 24 hours of admission. Amongst TEVAR patients, 39 (8.8%) patients died and 7 (1.6%) had aortic related deaths. (Table 1) Comparison of the STREAMLINE and LR model showed no significant difference in ROC curves and high AUCs of 0.869 (95% CI, 0.813 – 0.925) and 0.840 (95% CI, 0.779 – 0.900) respectively in predicting in-hospital mortality. Unexpectedly, however, the variables prioritized in each model differed between models (Figure 1A-B). The top three variables identified from the LR model were similar to that from existing literature. The STREAMLINE model, however, prioritized location of the injury along the lesser curve, age and aortic injury grade (Figure 1A). Conclusions Machine learning provides insight on prioritization of variables not typically identified in standard multivariable logistic regression. Further investigation and validation in other aortic injury cohorts are needed to delineate the utility of ML models. Level of Evidence Level III Study Type Original research (prognostic/epidemiological)Keywords
This publication has 39 references indexed in Scilit:
- High-performance pediatric surgical risk calculator: A novel algorithm based on machine learning and pediatric NSQIP dataThe American Journal of Surgery, 2023
- Management of Moderate Blunt Thoracic Aortic Injuries in Patients with Intracranial HemorrhageAnnals of Vascular Surgery, 2021
- Prehospital triage of acute aortic syndrome using a machine learning algorithmBritish Journal of Surgery, 2020
- Applied Machine Learning for the Prediction of Growth of Abdominal Aortic Aneurysm in HumansEJVES Short Reports, 2018
- Association of Hospital Participation in a Quality Reporting Program With Surgical Outcomes and Expenditures for Medicare BeneficiariesJAMA, 2015
- Early Aortic Repair Worsens Concurrent Traumatic Brain InjuryThe Annals of Thoracic Surgery, 2014
- Differences in aortic arch radius of curvature, neck size, and taper in patients with traumatic and aortic diseaseJournal of Surgical Research, 2013
- Evolution of the Incidence, Management, and Mortality of Blunt Thoracic Aortic Injury: A Population-Based AnalysisJournal of the American College of Surgeons, 2013
- Delayed Management of Blunt Traumatic Aortic Injury: Open Surgical Versus Endovascular RepairThe Annals of Thoracic Surgery, 2013
- Functional and survival outcomes in traumatic blunt thoracic aortic injuries: An analysis of the National Trauma DatabankJournal of Vascular Surgery, 2009