Risk stratification models for cardiac surgery

Abstract

A wide variety of risk stratification systems have been developed to quantify the risk of cardiac surgery. Generally, the focus has been on mortality; however, more recently models have been developed that allow the preoperative prediction of the incidence of morbidity, including renal failure, infection, prolonged ventilation, and neurologic deficit. Many of these risk stratification models are developed from large databases of cardiac surgical patients. Patient and surgical factors that are present preoperatively are assessed for their predictive value for postoperative complications. Risk factors that are found to be significant are assigned a specific weight in the overall summation of risk. These models have been used as tools to compare surgeon's results, institutional outcomes, individual patient risk, and within quality improvement programs. This article will focus on the European System for Cardiac Operative Risk Evaluation, the Society of Thoracic Surgeons score, the Parsonnet score, Cleveland Clinic Model, the Bayes model, and the Northern New England Score.