Objectives:
To introduce participants to statistical methods for meta-analysis of risk prediction models. We will discuss opportunities and challenges of combining previously published prediction models for the same targeted outcome or populations. We will introduce the statistical methodology and software packages. Derivation of a meta-analytical risk prediction model using real data will be illustrated.

Description:
Risk prediction models are developed and validated for predicting the future occurrence of a particular outcome (prognostic) but also to predict the presence of a certain disease (diagnostic). Prediction models aim to provide absolute probabilities of a certain outcome or disease in an individual. Prediction models are abundant in the literature and numerous prediction models have been developed for the same outcome or target population. The question is whether and how previously published prediction models can be combined in a meta-analytical manner. Innovative methods have been developed to meta-analyse (combine) previously published prediction models.

We will discuss why and how meta-analysis of risk prediction research is opportune and will describe how previously published prediction models can be combined. We will demonstrate how to accommodate for heterogeneity across study populations and illustrate how to interpret the meta-analytical model performance and provide strategies to improve generalizability and applicability.