A Model for Predicting the Risk of Carotid Artery Disease

Objective: To develop a model for the identification of individuals at risk for carotid stenosis (CS) that could be useful in a clinical setting when trying to decide whether screening is worthwhile. Background: Evidence that aggressive medical therapy and life style changes reduce the risk of stroke in individuals with CS is increasing and has led to a renewed interest in screening for CS. Methods: Data on demographics and risk factors were obtained from 2,885,257 individuals who had carotid Duplex scans by Life Line Screening between 2003 and 2008. Multivariable logistic regression analysis was used to identify independent risk factors for CS (>50% stenosis). A scoring system was developed where risk factors were assigned a weighted score. Predictive ability was assessed by calculating C statistics and r(2). Results: In the screened cohort, 71,004 patients (2.4%) had CS. Independent risk factors include advanced age, smoking, peripheral arterial disease, high blood pressure, coronary artery disease, diabetes, cholesterol, and abdominal aortic aneurysm. African Americans, Asians, and Hispanics had reduced risk than whites. Exercise and consumption of fruit, vegetables, and nuts had a modest protective effect. A predictive scoring system was created that identifies individuals with CS more efficiently (C statistic = 0.753) than previously published models. Conclusions: We provide a model that enables identification of individuals who have a high probability of having CS. This model can be helpful in designing targeted screening programs that are cost-effective.