Utility of clinical risk predictors for preoperative cardiovascular risk prediction

Abstract

Cardiovascular risk prediction using clinical risk factors is integral to both the European and the American algorithms for preoperative cardiac risk assessment and perioperative management for non-cardiac surgery. We have reviewed these risk factors and their ability to guide clinical decision making. We examine their limitations and attempt to identify factors which may improve their performance when used for clinical risk stratification. To improve the performance of the clinical risk factors, it is necessary to create uniformity in the definitions of both cardiovascular outcomes and the clinical risk factors. The risk factors selected should reflect the degree of organ dysfunction rather than a historical diagnosis. Parsimonious model design should be applied, making use of a minimal number of continuous variables rather than creating overfitted models. The inclusion of age in the model may assist partly in controlling for the duration of risk factor exposure. Risk assignment should occur throughout the perioperative period and the risk factors chosen for model inclusion should vary depending on when the assignment occurs (before operation, intraoperatively, or after operation).