Objectives: This workshop introduces participants to statistical methods for meta-analysis of the accuracy of a specific prediction model and of the added value of a specific predictor to an existing model. We discuss opportunities/challenges of the statistical methods and of common software packages.

Description: Prediction models are commonly developed and validated for predicting the presence (diagnostic) or future occurrence (prognostic) of a particular outcome. Prediction models have become abundant in the literature. Many models have been validated in numerous different studies/publications. Also, numerous studies investigate the added value of a certain predictor/biomarker to a specific existing prediction model. In both situations, aggregating such evidence is important for making inferences on the predictive accuracy of a specific model or predictor/marker. Meta-analytical approaches for both situations have recently been developed.

In this workshop we illustrate these statistical approaches and how to combine - quantitatively - results from published studies on the predictive accuracy of a specific model or added predictive accuracy of a specific predictor. We illustrate this with various empirical examples.