Statistical Primer: Developing and Validating a Risk Prediction Model

Risk-prediction models are well-known in cardiac surgery—the EuroSCORE and STS models being some of the most recognized. They are used for risk stratification, decision-making, and benchmarking. However, development of these models can be complex and once a model is developed, it is important to validate it. This article by Grant and colleagues discusses various issues in developing and validating risk-prediction models to aid clinicians in gaining a basic understanding of the advantages and limitations of such models.