A Machine-Learning-Based Tool for Stroke Risk Prediction in Blunt Cerebrovascular Injury: Development and Preliminary Evaluation

Authors

• Victoria Wagner
• Joshua D Preston
• Alejandro De Leon Castro
• William F Mueller
• Jonathan Nguyen
• Manuel Garcia-Toca
• Elizabeth R Benjamin
• S Rob Todd
• Jason D Sciarretta

Language

English

Publication Date

4-10-2026

Journal

European Journal of Trauma and Emergency Surgery

DOI

10.1007/s00068-026-03172-x

PMID

41961261

PMCID

PMC13068730

PubMedCentral® Posted Date

4-10-2026

PubMedCentral® Full Text Version

Post-print

Abstract

Purpose: Stroke risk correlates with the Biffl grading system in blunt cerebrovascular injury (BCVI). Although anti-thrombotic therapy is the mainstay of stroke prevention, no point-of-care clinical decision-support tool exists to guide timing for therapy. We sought to develop an interactive online calculator that incorporates patient-specific demographic and injury characteristics to estimate stroke risk and risk reduction with anti-thrombotic (AT) administration.

Methods: Data from BCVI patients (n = 1,197) at a Level I Trauma Center were retrospectively collected. Six machine learning methods were employed to predict stroke risk with and without AT therapy. Class imbalance was addressed using downsampling and/or class weighting. Model performance was assessed using 10-fold cross-validation. The model was implemented as an R-based Shiny online application.

Results: Stroke rate among the population was 4%, and the strongest predictors for stroke were the greatest Biffl grade of carotid (aOR [95%CI] = 2.02 [1.62-2.53]) and vertebral injuries (1.44 [1.18-1.77]). The least absolute shrinkage and selection operator (LASSO) model outperformed all others, achieving 66% [33%-100%] sensitivity and 74% [62%-82%] specificity for stroke prediction, with an area under the receiver operating characteristic curve of 0.79 [0.57-0.95]. This model was integrated into an interactive online tool ( https://grady-bcvi-calc.shinyapps.io/calculator/ ), where patient demographic and injury characteristics can be used to compute baseline stroke risk and estimate stroke risk with AT.

Conclusion: We developed and evaluated a preliminary predictive model for personalized stroke risk assessment in patients with BCVI using key risk factors. The integration of patient-specific risk-benefit assessments into clinical decision-making could optimize and reduce variability in AT therapy. External validation is warranted to prepare this tool for broad clinical applicability.

Keywords

Humans, Machine Learning, Male, Female, Stroke, Retrospective Studies, Middle Aged, Risk Assessment, Adult, Cerebrovascular Trauma, Wounds, Nonpenetrating, Risk Factors, Aged, Trauma Centers, Trauma decision support, Predictive modeling, Machine learning, Point-of-care, Risk stratification, Vascular trauma

Published Open-Access

yes

Recommended Citation

Wagner, Victoria; Preston, Joshua D; De Leon Castro, Alejandro; et al., "A Machine-Learning-Based Tool for Stroke Risk Prediction in Blunt Cerebrovascular Injury: Development and Preliminary Evaluation" (2026). Faculty, Staff and Student Publications. 4522.
https://digitalcommons.library.tmc.edu/uthmed_docs/4522