Predicting The Outcome Of Limb Revascularization In Patients With Lower-extremity Arterial Trauma: Development And External Validation Of A Supervised Machine-learning Algorithm To Support Surgical Decisions.
*Zane B Perkins1, *Barbaros Yet1, *Anna Sharrock2, *Rory Rickard2, *William Marsh1, Todd E Rasmussen3, *Nigel R.m. Tai2
1Queen Mary, University of London, London, United Kingdom2Royal Centre for Defence Medicine, Birmingham, United Kingdom3Uniformed Services University of Health Sciences, Bethesda, MD
Objective(s): Estimating the likely success of limb revascularization in patients with lower-extremity arterial trauma is central to decisions between attempting limb salvage and amputation. However, the projected outcome is often unclear at the time surgical decisions need to be made, making decisions difficult and threatening sound judgement. The objective of this study was to develop and validate a prediction model that can quantify an individual patient’s risk of failed revascularization.
Methods: A Bayesian Network (BN) prognostic model was developed using domain knowledge and data from the U.S. Joint Trauma System (US-JTS). Performance (discrimination, calibration, and accuracy) was tested using ten-fold cross validation and externally validated on data from the U.K. Joint Theatre Trauma Registry (UK-JTTR). BN performance was compared to the Mangled Extremity Severity Score (MESS).
Results: Rates of amputation performed because of non-viable limb tissue were 12.2% and 19.6% in the US-JTS (n=508) and UK-JTTR (n=51) populations respectively. A 10-predictor BN accurately predicted failed revascularization: AUROC 0.95, calibration slope (CS) 1.96, brier score (BS) 0.05, and brier skill score (BSS) 0.50. The model maintained excellent performance in an external validation population: AUROC 0.99, CS 7.44, BS 0.08, BSS 0.58, and had significantly better performance than MESS at predicting the need for amputation (AUROC 0.95 (0.92–0.98) versus 0.74 (0.67–0.80); P<0.0001).
Conclusions: A BN (https://www.traumamodels.com) can accurately predict the outcome of limb revascularization at the time of initial wound evaluation. This information may complement clinical judgement, support rational and shared treatment decisions, and establish sensible treatment expectations.
Back to 2020 Abstracts