Abstract TMP81: Artificial Intelligence Beats Conventional Regression Analysis in Predicting Short and Long Term Risk of Stroke in Patients Undergoing Percutaneous Coronary Interventions

Abstract

Introduction: Ischemic stroke (IS) causes substantial morbidity and mortality in patients undergoing percutaneous coronary intervention (PCI) with a 5 yr incidence ~ 3%. We sought the test the accuracy of Machine learning (ML) algorithms in predicting IS in patients undergoing PCI. Methods: Mayo Clinic CathPCI registry data were retrospectively analyzed from Jan 2003 - June 2018 including 21,872 patients who underwent PCI. The cohort was randomly divided into a training sample (75%, n=16404) and a unique test sample (25%, n=5468) prior to model generation. The risk prediction model was generated utilizing a random forest algorithm (RF model) on 188 unique variables to predict the risk of IS at 6-month, 1, 2, and 5-year post PCI. Conventional risk factors for stroke were used for logistic regression. The receiver operating characteristic (ROC) curve and area under the curve for the RF and logistic regression models were compared for the test cohort. Results: The mean age was 66.9 ± 12.4 years, and 71% were male. Patient demographics and outcomes are shown in Table 1 . The ROC area under the curve for the RF model was superior compared to the logistic regression model in predicting IS at 6 months, 1,2 and 5 yrs for the test cohort ( Figure 1 .) Conclusions: The RF model accurately predicts short and long term risk of IS and outperforms logistic regression analysis in patients undergoing PCI.