Using Machine Learning to Predict Outcomes Following Carotid Artery Stenting

Carotid artery stenting (CAS) carries important perioperative risks. Outcome prediction tools may help guide clinical decision-making but remain limited. We developed machine learning (ML) algorithms that predict 30-day outcomes following transfemoral CAS. The National Surgical Quality Improvement Program (NSQIP) targeted vascular database was used to identify patients who underwent transfemoral CAS between 2011-2021. Input features included 36 preoperative demographic/clinical variables. The primary outcome was 30-day major adverse cardiovascular event (composite of stroke, myocardial infarction [MI], or death). The secondary outcomes were 30-day stroke, MI, death, carotid-related morbidity, other morbidity, non-home discharge, and unplanned readmission. Our data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, we trained six ML models using pre-operative features (Extreme Gradient Boosting [XGBoost], random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Model robustness was evaluated with calibration plot and Brier score. Variable importance scores were calculated to determine the top 10 predictive features. Performance was assessed on subgroups based on age, sex, race, ethnicity, symptom status, stent type, and urgency. Overall, 2,093 patients underwent transfemoral CAS during the study period. Thirty-day MACE occurred in 130 (6.2%) patients. The best performing prediction model for 30-day MACE was XGBoost, achieving an AUROC (95% CI) of 0.93 (0.92-0.94) (Fig 1). In comparison, logistic regression had an AUROC (95% CI) of 0.67 (0.65-0.68) and existing tools in the literature demonstrate AUROCs ranging from 0.58-0.74. For secondary outcomes, XGBoost achieved AUROCs between 0.86-0.97. The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.02 (Fig 2). The top three predictive features in our algorithm were: (1) symptomatic carotid stenosis, (2) age, and (3) American Society of Anesthesiologists classification. Model performance remained robust across demographic and clinical subpopulations. Our ML models accurately predict 30-day outcomes following transfemoral CAS using preoperative data, performing better than logistic regression and existing tools. They have potential for important utility in guiding risk mitigation strategies for patients being considered for transfemoral CAS to improve outcomes.Fig 2Calibration plot with Brier score for predicting 30-day major adverse cardiovascular events following carotid artery stenting using Extreme Gradient Boosting (XGBoost) model.View Large Image Figure ViewerDownload Hi-res image Download (PPT)